Hassan Rivaz

Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz et al.

Segmentation of anatomical structures and pathological regions in medical images is essential for modern clinical diagnosis, disease research, and treatment planning. While significant advancements have been made in deep learning-based segmentation techniques, many of these methods still suffer from limitations in data efficiency, generalizability, and interactivity. As a result, developing precise segmentation methods that require fewer labeled datasets remains a critical challenge in medical image analysis. Recently, the introduction of foundation models like CLIP and Segment-Anything-Model (SAM), with robust cross-domain representations, has paved the way for interactive and universal image segmentation. However, further exploration of these models for data-efficient segmentation in medical imaging is still needed and highly relevant. In this paper, we introduce MedCLIP-SAMv2, a novel framework that integrates the CLIP and SAM models to perform segmentation on clinical scans using text prompts, in both zero-shot and weakly supervised settings. Our approach includes fine-tuning the BiomedCLIP model with a new Decoupled Hard Negative Noise Contrastive Estimation (DHN-NCE) loss, and leveraging the Multi-modal Information Bottleneck (M2IB) to create visual prompts for generating segmentation masks from SAM in the zero-shot setting. We also investigate using zero-shot segmentation labels within a weakly supervised paradigm to enhance segmentation quality further. Extensive testing across four diverse segmentation tasks and medical imaging modalities (breast tumor ultrasound, brain tumor MRI, lung X-ray, and lung CT) demonstrates the high accuracy of our proposed framework. Our code is available at https://github.com/HealthX-Lab/MedCLIP-SAMv2.

Mostafa Sharifzadeh, Habib Benali, Hassan Rivaz

Phase aberration is one of the primary sources of image quality degradation in ultrasound, which is induced by spatial variations in sound speed across the heterogeneous medium. This effect disrupts transmitted waves and prevents coherent summation of echo signals, resulting in suboptimal image quality. In real experiments, obtaining non-aberrated ground truths can be extremely challenging, if not infeasible. It hinders the performance of deep learning-based phase aberration correction techniques due to sole reliance on simulated data and the presence of domain shift between simulated and experimental data. Here, for the first time, we propose a deep learning-based method that does not require reference data to compensate for the phase aberration effect. We train a network wherein both input and target output are randomly aberrated radio frequency (RF) data. Moreover, we demonstrate that a conventional loss function such as mean square error is inadequate for training the network to achieve optimal performance. Instead, we propose an adaptive mixed loss function that employs both B-mode and RF data, resulting in more efficient convergence and enhanced performance. Source code is available at \url{http://code.sonography.ai}.

Taha Koleilat, Hassan Rivaz, Yiming Xiao

Parameter-efficient adaptation of vision-language foundation models is crucial for precise multimodal understanding of biomedical images, yet existing methods remain deterministic and often struggle under domain shift or ambiguous image-text alignment. This limitation is particularly critical in the clinic, where models should remain robust in low-data regimes and domain shifts. We present Evi-Steer, an evidential cross-modal low-dimensional steering framework for BiomedCLIP that enables uncertainty-aware parameter-efficient fine-tuning while updating only 0.11% of total model parameters. Our approach performs lightweight low-dimensional token updates in both vision and text encoders while simultaneously estimating epistemic uncertainty. These uncertainty estimates update gate residuals, allowing the model to adapt conservatively when evidence is weak. Furthermore, we introduce cross-modal confidence fusion based on Dempster-Shafer theory, enabling visual adaptation to be conditioned on textual confidence and suppressing conflicting or uncertain cross-modal updates. We conduct a comprehensive evaluation on 15 biomedical imaging datasets spanning 8 organs and 8 imaging modalities under few-shot learning and domain generalization settings. Evi-Steer consistently outperforms state-of-the-art methods under few-shot learning and domain shift settings, demonstrating a practical and robust pathway for deploying vision-language models in real-world clinical settings. Code is available at https://github.com/HealthX-Lab/Evi-Steer.

Bahareh Behboodi, Francois-Xavier Carton, Matthieu Chabanas et al.

Purpose: Registration and segmentation of magnetic resonance (MR) and ultrasound (US) images play an essential role in surgical planning and resection of brain tumors. However, validating these techniques is challenging due to the scarcity of publicly accessible sources with high-quality ground truth information. To this end, we propose a unique annotation dataset of tumor tissues and resection cavities from the previously published RESECT dataset (Xiao et al. 2017) to encourage a more rigorous assessments of image processing techniques. Acquisition and validation methods: The RESECT database consists of MR and intraoperative US (iUS) images of 23 patients who underwent resection surgeries. The proposed dataset contains tumor tissues and resection cavity annotations of the iUS images. The quality of annotations were validated by two highly experienced neurosurgeons through several assessment criteria. Data format and availability: Annotations of tumor tissues and resection cavities are provided in 3D NIFTI formats. Both sets of annotations are accessible online in the \url{https://osf.io/6y4db}. Discussion and potential applications: The proposed database includes tumor tissue and resection cavity annotations from real-world clinical ultrasound brain images to evaluate segmentation and registration methods. These labels could also be used to train deep learning approaches. Eventually, this dataset should further improve the quality of image guidance in neurosurgery.

Ali K. Z. Tehrani, Md Ashikuzzaman, Hassan Rivaz

Convolutional Neural Networks (CNN) have shown promising results for displacement estimation in UltraSound Elastography (USE). Many modifications have been proposed to improve the displacement estimation of CNNs for USE in the axial direction. However, the lateral strain, which is essential in several downstream tasks such as the inverse problem of elasticity imaging, remains a challenge. The lateral strain estimation is complicated since the motion and the sampling frequency in this direction are substantially lower than the axial one, and a lack of carrier signal in this direction. In computer vision applications, the axial and the lateral motions are independent. In contrast, the tissue motion pattern in USE is governed by laws of physics which link the axial and lateral displacements. In this paper, inspired by Hooke's law, we first propose Physically Inspired ConsTraint for Unsupervised Regularized Elastography (PICTURE), where we impose a constraint on the Effective Poisson's ratio (EPR) to improve the lateral strain estimation. In the next step, we propose self-supervised PICTURE (sPICTURE) to further enhance the strain image estimation. Extensive experiments on simulation, experimental phantom and in vivo data demonstrate that the proposed methods estimate accurate axial and lateral strain maps.

Zirui Qiu, Hassan Rivaz, Yiming Xiao

While deep learning techniques have provided the state-of-the-art performance in various clinical tasks, explainability regarding their decision-making process can greatly enhance the credence of these methods for safer and quicker clinical adoption. With high flexibility, Gradient-weighted Class Activation Mapping (Grad-CAM) has been widely adopted to offer intuitive visual interpretation of various deep learning models' reasoning processes in computer-assisted diagnosis. However, despite the popularity of the technique, there is still a lack of systematic study on Grad-CAM's performance on different deep learning architectures. In this study, we investigate its robustness and effectiveness across different popular deep learning models, with a focus on the impact of the networks' depths and architecture types, by using a case study of automatic pneumothorax diagnosis in X-ray scans. Our results show that deeper neural networks do not necessarily contribute to a strong improvement of pneumothorax diagnosis accuracy, and the effectiveness of GradCAM also varies among different network architectures.

Hojat Asgariandehkordi, Sobhan Goudarzi, Adrian Basarab et al.

Ultrasound images are widespread in medical diagnosis for musculoskeletal, cardiac, and obstetrical imaging due to the efficiency and non-invasiveness of the acquisition methodology. However, the acquired images are degraded by acoustic (e.g. reverberation and clutter) and electronic sources of noise. To improve the Peak Signal to Noise Ratio (PSNR) of the images, previous denoising methods often remove the speckles, which could be informative for radiologists and also for quantitative ultrasound. Herein, a method based on the recent Denoising Diffusion Probabilistic Models (DDPM) is proposed. It iteratively enhances the image quality by eliminating the noise while preserving the speckle texture. It is worth noting that the proposed method is trained in a completely unsupervised manner, and no annotated data is required. The experimental blind test results show that our method outperforms the previous nonlocal means denoising methods in terms of PSNR and Generalized Contrast to Noise Ratio (GCNR) while preserving speckles.

Soorena Salari, Amirhossein Rasoulian, Hassan Rivaz et al.

Homologous anatomical landmarks between medical scans are instrumental in quantitative assessment of image registration quality in various clinical applications, such as MRI-ultrasound registration for tissue shift correction in ultrasound-guided brain tumor resection. While manually identified landmark pairs between MRI and ultrasound (US) have greatly facilitated the validation of different registration algorithms for the task, the procedure requires significant expertise, labor, and time, and can be prone to inter- and intra-rater inconsistency. So far, many traditional and machine learning approaches have been presented for anatomical landmark detection, but they primarily focus on mono-modal applications. Unfortunately, despite the clinical needs, inter-modal/contrast landmark detection has very rarely been attempted. Therefore, we propose a novel contrastive learning framework to detect corresponding landmarks between MRI and intra-operative US scans in neurosurgery. Specifically, two convolutional neural networks were trained jointly to encode image features in MRI and US scans to help match the US image patch that contain the corresponding landmarks in the MRI. We developed and validated the technique using the public RESECT database. With a mean landmark detection accuracy of 5.88+-4.79 mm against 18.78+-4.77 mm with SIFT features, the proposed method offers promising results for MRI-US landmark detection in neurosurgical applications for the first time.

Soorena Salari, Amirhossein Rasoulian, Hassan Rivaz et al.

In brain tumor resection, accurate removal of cancerous tissues while preserving eloquent regions is crucial to the safety and outcomes of the treatment. However, intra-operative tissue deformation (called brain shift) can move the surgical target and render the pre-surgical plan invalid. Intra-operative ultrasound (iUS) has been adopted to provide real-time images to track brain shift, and inter-modal (i.e., MRI-iUS) registration is often required to update the pre-surgical plan. Quality control for the registration results during surgery is important to avoid adverse outcomes, but manual verification faces great challenges due to difficult 3D visualization and the low contrast of iUS. Automatic algorithms are urgently needed to address this issue, but the problem was rarely attempted. Therefore, we propose a novel deep learning technique based on 3D focal modulation in conjunction with uncertainty estimation to accurately assess MRI-iUS registration errors for brain tumor surgery. Developed and validated with the public RESECT clinical database, the resulting algorithm can achieve an estimation error of 0.59+-0.57 mm.

Sepideh K. Gharamaleki, Brandon Helfield, Hassan Rivaz

Ultrasound Localization Microscopy (ULM) is an emerging technique that employs the localization of echogenic microbubbles (MBs) to finely sample and image the microcirculation beyond the diffraction limit of ultrasound imaging. Conventional MB localization methods are mainly based on considering a specific Point Spread Function (PSF) for MBs, which leads to loss of information caused by overlapping MBs, non-stationary PSFs, and harmonic MB echoes. Therefore, it is imperative to devise methods that can accurately localize MBs while being resilient to MB nonlinearities and variations of MB concentrations that distort MB PSFs. This paper proposes a transformer-based MB localization approach to address this issue. We adopted DEtection TRansformer (DETR) arXiv:2005.12872 , which is an end-to-end object recognition method that detects a unique bounding box for each of the detected objects using set-based Hungarian loss and bipartite matching. To the authors' knowledge, this is the first time transformers have been used for MB localization. To appraise the proposed strategy, the pre-trained DETR network's performance has been tested for detecting MBs using transfer learning principles. We have fine-tuned the network on a subset of randomly selected frames of the dataset provided by the IEEE IUS Ultra-SR challenge organizers and then tested on the rest using cross-validation. For the simulation dataset, the paper supports the deployment of transformer-based solutions for MB localization at high accuracy.

Hojat Asgariandehkordi, Sobhan Goudarzi, Mostafa Sharifzadeh et al.

Ultrasound plane wave imaging is a cutting-edge technique that enables high frame-rate imaging. However, one challenge associated with high frame-rate ultrasound imaging is the high noise associated with them, hindering their wider adoption. Therefore, the development of a denoising method becomes imperative to augment the quality of plane wave images. Drawing inspiration from Denoising Diffusion Probabilistic Models (DDPMs), our proposed solution aims to enhance plane wave image quality. Specifically, the method considers the distinction between low-angle and high-angle compounding plane waves as noise and effectively eliminates it by adapting a DDPM to beamformed radiofrequency (RF) data. The method underwent training using only 400 simulated images. In addition, our approach employs natural image segmentation masks as intensity maps for the generated images, resulting in accurate denoising for various anatomy shapes. The proposed method was assessed across simulation, phantom, and in vivo images. The results of the evaluations indicate that our approach not only enhances image quality on simulated data but also demonstrates effectiveness on phantom and in vivo data in terms of image quality. Comparative analysis with other methods underscores the superiority of our proposed method across various evaluation metrics. The source code and trained model will be released along with the dataset at: http://code.sonography.ai

Ali K. Z. Tehrani, Hassan Rivaz

Displacement estimation is a critical step of virtually all Ultrasound Elastography (USE) techniques. Two main features make this task unique compared to the general optical flow problem: the high-frequency nature of ultrasound radio-frequency (RF) data and the governing laws of physics on the displacement field. Recently, the architecture of the optical flow networks has been modified to be able to use RF data. Also, semi-supervised and unsupervised techniques have been employed for USE by considering prior knowledge of displacement continuity in the form of the first- and second-derivative regularizers. Despite these attempts, no work has considered the tissue compression pattern, and displacements in axial and lateral directions have been assumed to be independent. However, tissue motion pattern is governed by laws of physics in USE, rendering the axial and the lateral displacements highly correlated. In this paper, we propose Physically Inspired ConsTraint for Unsupervised Regularized Elastography (PICTURE), where we impose constraints on the Poisson's ratio to improve lateral displacement estimates. Experiments on phantom and in vivo data show that PICTURE substantially improves the quality of the lateral displacement estimation.

Ali Nasiri-Sarvi, Mahdi S. Hosseini, Hassan Rivaz

Mamba-based models, VMamba and Vim, are a recent family of vision encoders that offer promising performance improvements in many computer vision tasks. This paper compares Mamba-based models with traditional Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) using the breast ultrasound BUSI dataset and Breast Ultrasound B dataset. Our evaluation, which includes multiple runs of experiments and statistical significance analysis, demonstrates that some of the Mamba-based architectures often outperform CNN and ViT models with statistically significant results. For example, in the B dataset, the best Mamba-based models have a 1.98\% average AUC and a 5.0\% average Accuracy improvement compared to the best non-Mamba-based model in this study. These Mamba-based models effectively capture long-range dependencies while maintaining some inductive biases, making them suitable for applications with limited data. The code is available at \url{https://github.com/anasiri/BU-Mamba}

Mumu Aktar, Hassan Rivaz, Marta Kersten-Oertel et al.

Angiography is widely used to detect, diagnose, and treat cerebrovascular diseases. While numerous techniques have been proposed to segment the vascular network from different imaging modalities, deep learning (DL) has emerged as a promising approach. However, existing DL methods often depend on proprietary datasets and extensive manual annotation. Moreover, the availability of pre-trained networks specifically for medical domains and 3D volumes is limited. To overcome these challenges, we propose a few-shot learning approach called VesselShot for cerebrovascular segmentation. VesselShot leverages knowledge from a few annotated support images and mitigates the scarcity of labeled data and the need for extensive annotation in cerebral blood vessel segmentation. We evaluated the performance of VesselShot using the publicly available TubeTK dataset for the segmentation task, achieving a mean Dice coefficient (DC) of 0.62(0.03).

Parinaz Roshanzamir, Hassan Rivaz, Joshua Ahn et al.

Recent developments in deep learning (DL) techniques have led to great performance improvement in medical image segmentation tasks, especially with the latest Transformer model and its variants. While labels from fusing multi-rater manual segmentations are often employed as ideal ground truths in DL model training, inter-rater variability due to factors such as training bias, image noise, and extreme anatomical variability can still affect the performance and uncertainty of the resulting algorithms. Knowledge regarding how inter-rater variability affects the reliability of the resulting DL algorithms, a key element in clinical deployment, can help inform better training data construction and DL models, but has not been explored extensively. In this paper, we measure aleatoric and epistemic uncertainties using test-time augmentation (TTA), test-time dropout (TTD), and deep ensemble to explore their relationship with inter-rater variability. Furthermore, we compare UNet and TransUNet to study the impacts of Transformers on model uncertainty with two label fusion strategies. We conduct a case study using multi-class paraspinal muscle segmentation from T2w MRIs. Our study reveals the interplay between inter-rater variability and uncertainties, affected by choices of label fusion strategies and DL models.

Ali K. Z. Tehrani, Ivan M. Rosado-Mendez, Hassan Rivaz

Quantitative ultrasound (QUS) allows estimating the intrinsic tissue properties. Speckle statistics are the QUS parameters that describe the first order statistics of ultrasound (US) envelope data. The parameters of Homodyned K-distribution (HK-distribution) are the speckle statistics that can model the envelope data in diverse scattering conditions. However, they require a large amount of data to be estimated reliably. Consequently, finding out the intrinsic uncertainty of the estimated parameters can help us to have a better understanding of the estimated parameters. In this paper, we propose a Bayesian Neural Network (BNN) to estimate the parameters of HK-distribution and quantify the uncertainty of the estimator.

Ali K. Z. Tehrani, Hassan Rivaz

Convolutional Neural Networks (CNN) have been employed for displacement estimation in ultrasound elastography (USE). High-quality axial strains (derivative of the axial displacement in the axial direction) can be estimated by the proposed networks. In contrast to axial strain, lateral strain, which is highly required in Poisson's ratio imaging and elasticity reconstruction, has a poor quality. The main causes include low sampling frequency, limited motion, and lack of phase information in the lateral direction. Recently, physically inspired constraint in unsupervised regularized elastography (PICTURE) has been proposed. This method took into account the range of the feasible lateral strain defined by the rules of physics of motion and employed a regularization strategy to improve the lateral strains. Despite the substantial improvement, the regularization was only applied during the training; hence it did not guarantee during the test that the lateral strain is within the feasible range. Furthermore, only the feasible range was employed, other constraints such as incompressibility were not investigated. In this paper, we address these two issues and propose kPICTURE in which two iterative algorithms were infused into the network architecture in the form of known operators to ensure the lateral strain is within the feasible range and impose incompressibility during the test phase.

Soorena Salari, Amirhossein Rasoulian, Hassan Rivaz et al.

Early surgical treatment of brain tumors is crucial in reducing patient mortality rates. However, brain tissue deformation (called brain shift) occurs during the surgery, rendering pre-operative images invalid. As a cost-effective and portable tool, intra-operative ultrasound (iUS) can track brain shift, and accurate MRI-iUS registration techniques can update pre-surgical plans and facilitate the interpretation of iUS. This can boost surgical safety and outcomes by maximizing tumor removal while avoiding eloquent regions. However, manual assessment of MRI-iUS registration results in real-time is difficult and prone to errors due to the 3D nature of the data. Automatic algorithms that can quantify the quality of inter-modal medical image registration outcomes can be highly beneficial. Therefore, we propose a novel deep-learning (DL) based framework with the Swin UNETR to automatically assess 3D-patch-wise dense error maps for MRI-iUS registration in iUS-guided brain tumor resection and show its performance with real clinical data for the first time.

Dorsa Ameri, Ali K. Z. Tehrani, Ivan M. Rosado-Mendez et al.

Homodyned K-distribution (HK-distribution) parameter estimation in quantitative ultrasound (QUS) has been recently addressed using Bayesian Neural Networks (BNNs). BNNs have been shown to significantly reduce computational time in speckle statistics-based QUS without compromising accuracy and precision. Additionally, they provide estimates of feature uncertainty, which can guide the clinician's trust in the reported feature value. The total predictive uncertainty in Bayesian modeling can be decomposed into epistemic (uncertainty over the model parameters) and aleatoric (uncertainty inherent in the data) components. By decomposing the predictive uncertainty, we can gain insights into the factors contributing to the total uncertainty. In this study, we propose a method to compute epistemic and aleatoric uncertainties for HK-distribution parameters ($α$ and $k$) estimated by a BNN, in both simulation and experimental data. In addition, we investigate the relationship between the prediction error and both uncertainties, shedding light on the interplay between these uncertainties and HK parameters errors.

Ali K. Z. Tehrani, Ivan M. Rosado-Mendez, Hassan Rivaz

Quantitative Ultrasound (QUS) provides important information about the tissue properties. QUS parametric image can be formed by dividing the envelope data into small overlapping patches and computing different speckle statistics such as parameters of the Nakagami and Homodyned K-distributions (HK-distribution). The calculated QUS parametric images can be erroneous since only a few independent samples are available inside the patches. Another challenge is that the envelope samples inside the patch are assumed to come from the same distribution, an assumption that is often violated given that the tissue is usually not homogenous. In this paper, we propose a method based on Convolutional Neural Networks (CNN) to estimate QUS parametric images without patching. We construct a large dataset sampled from the HK-distribution, having regions with random shapes and QUS parameter values. We then use a well-known network to estimate QUS parameters in a multi-task learning fashion. Our results confirm that the proposed method is able to reduce errors and improve border definition in QUS parametric images.

Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz et al.

Medical image segmentation of anatomical structures and pathology is crucial in modern clinical diagnosis, disease study, and treatment planning. To date, great progress has been made in deep learning-based segmentation techniques, but most methods still lack data efficiency, generalizability, and interactability. Consequently, the development of new, precise segmentation methods that demand fewer labeled datasets is of utmost importance in medical image analysis. Recently, the emergence of foundation models, such as CLIP and Segment-Anything-Model (SAM), with comprehensive cross-domain representation opened the door for interactive and universal image segmentation. However, exploration of these models for data-efficient medical image segmentation is still limited, but is highly necessary. In this paper, we propose a novel framework, called MedCLIP-SAM that combines CLIP and SAM models to generate segmentation of clinical scans using text prompts in both zero-shot and weakly supervised settings. To achieve this, we employed a new Decoupled Hard Negative Noise Contrastive Estimation (DHN-NCE) loss to fine-tune the BiomedCLIP model and the recent gScoreCAM to generate prompts to obtain segmentation masks from SAM in a zero-shot setting. Additionally, we explored the use of zero-shot segmentation labels in a weakly supervised paradigm to improve the segmentation quality further. By extensively testing three diverse segmentation tasks and medical image modalities (breast tumor ultrasound, brain tumor MRI, and lung X-ray), our proposed framework has demonstrated excellent accuracy. Code is available at https://github.com/HealthX-Lab/MedCLIP-SAM.

Ali Nasiri-Sarvi, Anh Tien Nguyen, Hassan Rivaz et al.

Sparse autoencoders (SAEs) decompose polysemantic neural representations, where neurons respond to multiple unrelated concepts, into monosemantic features that capture single, interpretable concepts. However, standard training objectives only weakly encourage this decomposition, and existing monosemanticity metrics require pairwise comparisons across all dataset samples, making them inefficient during training and evaluation. We study a recent MonoScore metric and derive a single-pass algorithm that computes exactly the same quantity, but with a cost that grows linearly, rather than quadratically, with the number of dataset images. On OpenImagesV7, we achieve up to a 1200x speedup wall-clock speedup in evaluation and 159x during training, while adding only ~4% per-epoch overhead. This allows us to treat MonoScore as a training signal: we introduce the Monosemanticity Loss (MonoLoss), a plug-in objective that directly rewards semantically consistent activations for learning interpretable monosemantic representations. Across SAEs trained on CLIP, SigLIP2, and pretrained ViT features, using BatchTopK, TopK, and JumpReLU SAEs, MonoLoss increases MonoScore for most latents. MonoLoss also consistently improves class purity (the fraction of a latent's activating images belonging to its dominant class) across all encoder and SAE combinations, with the largest gain raising baseline purity from 0.152 to 0.723. Used as an auxiliary regularizer during ResNet-50 and CLIP-ViT-B/32 finetuning, MonoLoss yields up to 0.6\% accuracy gains on ImageNet-1K and monosemantic activating patterns on standard benchmark datasets. The code is publicly available at https://github.com/AtlasAnalyticsLab/MonoLoss.

Ali Nasiri-Sarvi, Vincent Quoc-Huy Trinh, Hassan Rivaz et al.

Representation learning from Gigapixel Whole Slide Images (WSI) poses a significant challenge in computational pathology due to the complicated nature of tissue structures and the scarcity of labeled data. Multi-instance learning methods have addressed this challenge, leveraging image patches to classify slides utilizing pretrained models using Self-Supervised Learning (SSL) approaches. The performance of both SSL and MIL methods relies on the architecture of the feature encoder. This paper proposes leveraging the Vision Mamba (Vim) architecture, inspired by state space models, within the DINO framework for representation learning in computational pathology. We evaluate the performance of Vim against Vision Transformers (ViT) on the Camelyon16 dataset for both patch-level and slide-level classification. Our findings highlight Vim's enhanced performance compared to ViT, particularly at smaller scales, where Vim achieves an 8.21 increase in ROC AUC for models of similar size. An explainability analysis further highlights Vim's capabilities, which reveals that Vim uniquely emulates the pathologist workflow-unlike ViT. This alignment with human expert analysis highlights Vim's potential in practical diagnostic settings and contributes significantly to developing effective representation-learning algorithms in computational pathology. We release the codes and pretrained weights at \url{https://github.com/AtlasAnalyticsLab/Vim4Path}.

Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz et al.

Recent advancements in vision-language models (VLMs), such as CLIP, have demonstrated substantial success in self-supervised representation learning for vision tasks. However, effectively adapting VLMs to downstream applications remains challenging, as their accuracy often depends on time-intensive and expertise-demanding prompt engineering, while full model fine-tuning is costly. This is particularly true for biomedical images, which, unlike natural images, typically suffer from limited annotated datasets, unintuitive image contrasts, and nuanced visual features. Recent prompt learning techniques, such as Context Optimization (CoOp) intend to tackle these issues, but still fall short in generalizability. Meanwhile, explorations in prompt learning for biomedical image analysis are still highly limited. In this work, we propose BiomedCoOp, a novel prompt learning framework that enables efficient adaptation of BiomedCLIP for accurate and highly generalizable few-shot biomedical image classification. Our approach achieves effective prompt context learning by leveraging semantic consistency with average prompt ensembles from Large Language Models (LLMs) and knowledge distillation with a statistics-based prompt selection strategy. We conducted comprehensive validation of our proposed framework on 11 medical datasets across 9 modalities and 10 organs against existing state-of-the-art methods, demonstrating significant improvements in both accuracy and generalizability. The code is publicly available at https://github.com/HealthX-Lab/BiomedCoOp.

Omid Nejati Manzari, Hojat Asgariandehkordi, Taha Koleilat et al.

Large vision-language models (VLMs) excel on general benchmarks but often lack robustness in medical imaging, where heterogeneous supervision induces cross-dataset interference and sensitivity to data regime (i.e., how the supervisory signals are mixed). In realistic clinical workflows, data and tasks arrive sequentially, so naive continual training further leads to catastrophic forgetting. To address these challenges, we propose MedQwen, a parameter-efficient medical VLM that couples a spectrally routed Mixture-of-Experts (MoE) with a theoretically grounded scaling rule that aligns low-rank updates with a full-rank, fully fine-tuned MoE, without changing the base architecture. Concretely, we initialize each expert from non-overlapping singular value decomposition (SVD) segments of the pretrained weight and introduce a residual compensation and scaling scheme to enable stable expert specialization and consistent routing under distribution shift. Across 23 medical datasets covering visual question answering, report generation, radiology classification, and hallucination mitigation, MedQwen achieves strong, reliable performance: it approaches full fine-tuning on zero-shot classification with 339$\times$ fewer trainable parameters, and reduces sequential forgetting to $\sim$5\% where strong baselines degrade by $>$20-50\%.

Taha Koleilat, Hojat Asgariandehkordi, Omid Nejati Manzari et al.

Medical image segmentation remains challenging due to limited annotations for training, ambiguous anatomical features, and domain shifts. While vision-language models such as CLIP offer strong cross-modal representations, their potential for dense, text-guided medical image segmentation remains underexplored. We present MedCLIPSeg, a novel framework that adapts CLIP for robust, data-efficient, and uncertainty-aware medical image segmentation. Our approach leverages patch-level CLIP embeddings through probabilistic cross-modal attention, enabling bidirectional interaction between image and text tokens and explicit modeling of predictive uncertainty. Together with a soft patch-level contrastive loss that encourages more nuanced semantic learning across diverse textual prompts, MedCLIPSeg effectively improves data efficiency and domain generalizability. Extensive experiments across 16 datasets spanning five imaging modalities and six organs demonstrate that MedCLIPSeg outperforms prior methods in accuracy, efficiency, and robustness, while providing interpretable uncertainty maps that highlight local reliability of segmentation results. This work demonstrates the potential of probabilistic vision-language modeling for text-driven medical image segmentation.

Benoit Freiche, Anthony El-Khoury, Ali Nasiri-Sarvi et al.

Diffusion models for image generation have been a subject of increasing interest due to their ability to generate diverse, high-quality images. Image generation has immense potential in medical imaging because open-source medical images are difficult to obtain compared to natural images, especially for rare conditions. The generated images can be used later to train classification and segmentation models. In this paper, we propose simulating realistic ultrasound (US) images by successive fine-tuning of large diffusion models on different publicly available databases. To do so, we fine-tuned Stable Diffusion, a state-of-the-art latent diffusion model, on BUSI (Breast US Images) an ultrasound breast image dataset. We successfully generated high-quality US images of the breast using simple prompts that specify the organ and pathology, which appeared realistic to three experienced US scientists and a US radiologist. Additionally, we provided user control by conditioning the model with segmentations through ControlNet. We will release the source code at http://code.sonography.ai/ to allow fast US image generation to the scientific community.

Soorena Salari, Arash Harirpoush, Hassan Rivaz et al.

Anatomical landmark detection in medical images is essential for various clinical and research applications, including disease diagnosis and surgical planning. However, manual landmark annotation is time-consuming and requires significant expertise. Existing deep learning (DL) methods often require large amounts of well-annotated data, which are costly to acquire. In this paper, we introduce CABLD, a novel self-supervised DL framework for 3D brain landmark detection in unlabeled scans with varying contrasts by using only a single reference example. To achieve this, we employed an inter-subject landmark consistency loss with an image registration loss while introducing a 3D convolution-based contrast augmentation strategy to promote model generalization to new contrasts. Additionally, we utilize an adaptive mixed loss function to schedule the contributions of different sub-tasks for optimal outcomes. We demonstrate the proposed method with the intricate task of MRI-based 3D brain landmark detection. With comprehensive experiments on four diverse clinical and public datasets, including both T1w and T2w MRI scans at different MRI field strengths, we demonstrate that CABLD outperforms the state-of-the-art methods in terms of mean radial errors (MREs) and success detection rates (SDRs). Our framework provides a robust and accurate solution for anatomical landmark detection, reducing the need for extensively annotated datasets and generalizing well across different imaging contrasts. Our code is publicly available at https://github.com/HealthX-Lab/CABLD.

Pascal Spiegler, Taha Koleilat, Arash Harirpoush et al.

Pancreatic cancer carries a poor prognosis and relies on endoscopic ultrasound (EUS) for targeted biopsy and radiotherapy. However, the speckle noise, low contrast, and unintuitive appearance of EUS make segmentation of pancreatic tumors with fully supervised deep learning (DL) models both error-prone and dependent on large, expert-curated annotation datasets. To address these challenges, we present TextSAM-EUS, a novel, lightweight, text-driven adaptation of the Segment Anything Model (SAM) that requires no manual geometric prompts at inference. Our approach leverages text prompt learning (context optimization) through the BiomedCLIP text encoder in conjunction with a LoRA-based adaptation of SAM's architecture to enable automatic pancreatic tumor segmentation in EUS, tuning only 0.86% of the total parameters. On the public Endoscopic Ultrasound Database of the Pancreas, TextSAM-EUS with automatic prompts attains 82.69% Dice and 85.28% normalized surface distance (NSD), and with manual geometric prompts reaches 83.10% Dice and 85.70% NSD, outperforming both existing state-of-the-art (SOTA) supervised DL models and foundation models (e.g., SAM and its variants). As the first attempt to incorporate prompt learning in SAM-based medical image segmentation, TextSAM-EUS offers a practical option for efficient and robust automatic EUS segmentation. Code is available at https://github.com/HealthX-Lab/TextSAM-EUS .

Hamza Rasaee, Taha Koleilat, Hassan Rivaz

Accurate and generalizable object segmentation in ultrasound imaging remains a significant challenge due to anatomical variability, diverse imaging protocols, and limited annotated data. In this study, we propose a prompt-driven vision-language model (VLM) that integrates Grounding DINO with SAM2 (Segment Anything Model2) to enable object segmentation across multiple ultrasound organs. A total of 18 public ultrasound datasets, encompassing the breast, thyroid, liver, prostate, kidney, and paraspinal muscle, were utilized. These datasets were divided into 15 for fine-tuning and validation of Grounding DINO using Low Rank Adaptation (LoRA) to the ultrasound domain, and 3 were held out entirely for testing to evaluate performance in unseen distributions. Comprehensive experiments demonstrate that our approach outperforms state-of-the-art segmentation methods, including UniverSeg, MedSAM, MedCLIP-SAM, BiomedParse, and SAMUS on most seen datasets while maintaining strong performance on unseen datasets without additional fine-tuning. These results underscore the promise of VLMs in scalable and robust ultrasound image analysis, reducing dependence on large, organ-specific annotated datasets. We will publish our code on code.sonography.ai after acceptance.

Denisha Thakkar, Vincent Quoc-Huy Trinh, Sonal Varma et al.

Diffusion Generative Models (DGM) have rapidly surfaced as emerging topics in the field of computer vision, garnering significant interest across a wide array of deep learning applications. Despite their high computational demand, these models are extensively utilized for their superior sample quality and robust mode coverage. While research in diffusion generative models is advancing, exploration within the domain of computational pathology and its large-scale datasets has been comparatively gradual. Bridging the gap between the high-quality generation capabilities of Diffusion Generative Models and the intricate nature of pathology data, this paper presents an in-depth comparative analysis of diffusion methods applied to a pathology dataset. Our analysis extends to datasets with varying Fields of View (FOV), revealing that DGMs are highly effective in producing high-quality synthetic data. An ablative study is also conducted, followed by a detailed discussion on the impact of various methods on the synthesized histopathology images. One striking observation from our experiments is how the adjustment of image size during data generation can simulate varying fields of view. These findings underscore the potential of DGMs to enhance the quality and diversity of synthetic pathology data, especially when used with real data, ultimately increasing accuracy of deep learning models in histopathology. Code is available from https://github.com/AtlasAnalyticsLab/Diffusion4Path

Taha Koleilat, Hassan Rivaz, Yiming Xiao

Vision-language models (VLMs) like CLIP have shown impressive zero-shot and few-shot learning capabilities across diverse applications. However, adapting these models to new fine-grained domains remains difficult due to reliance on prompt engineering and the high cost of full model fine-tuning. Existing adaptation approaches rely on augmented components, such as prompt tokens and adapter modules, which could limit adaptation quality, destabilize the model, and compromise the rich knowledge learned during pretraining. In this work, we present CLIP-SVD, a novel multi-modal and parameter-efficient adaptation technique that leverages Singular Value Decomposition (SVD) to modify the internal parameter space of CLIP without injecting additional modules. Specifically, we fine-tune only the singular values of the CLIP parameter matrices to rescale the basis vectors for domain adaptation while retaining the pretrained model. This design enables enhanced adaptation performance using only 0.04% of the model's total parameters and better preservation of its generalization ability. CLIP-SVD achieves state-of-the-art classification results on 11 natural and 10 biomedical datasets, outperforming previous methods in both accuracy and generalization under few-shot settings. Additionally, we leverage a natural language-based approach to analyze the effectiveness and dynamics of the CLIP adaptation to allow interpretability of CLIP-SVD. The code is publicly available at https://github.com/HealthX-Lab/CLIP-SVD.

Ali Nasiri-Sarvi, Hassan Rivaz, Mahdi S. Hosseini

Understanding how different AI models encode the same high-level concepts, such as objects or attributes, remains challenging because each model typically produces its own isolated representation. Existing interpretability methods like Sparse Autoencoders (SAEs) produce latent concepts individually for each model, resulting in incompatible concept spaces and limiting cross-model interpretability. To address this, we introduce SPARC (Sparse Autoencoders for Aligned Representation of Concepts), a new framework that learns a single, unified latent space shared across diverse architectures and modalities (e.g., vision models like DINO, and multimodal models like CLIP). SPARC's alignment is enforced through two key innovations: (1) a Global TopK sparsity mechanism, ensuring all input streams activate identical latent dimensions for a given concept; and (2) a Cross-Reconstruction Loss, which explicitly encourages semantic consistency between models. On Open Images, SPARC dramatically improves concept alignment, achieving a Jaccard similarity of 0.80, more than tripling the alignment compared to previous methods. SPARC creates a shared sparse latent space where individual dimensions often correspond to similar high-level concepts across models and modalities, enabling direct comparison of how different architectures represent identical concepts without requiring manual alignment or model-specific analysis. As a consequence of this aligned representation, SPARC also enables practical applications such as text-guided spatial localization in vision-only models and cross-model/cross-modal retrieval. Code and models are available at https://github.com/AtlasAnalyticsLab/SPARC.

Sepideh KhakzadGharamaleki, Hassan Rivaz, Brandon Helfield

Conventional pulse-echo ultrasound suffers when low-cost probes deliver only narrow fractional bandwidths, elongating pulses and erasing high-frequency detail. We address this limitation by learning a data-driven mapping from band-limited to broadband spectrogram of radio-frequency (RF) lines. To this end, a variation of Tiny Vision Transform (ViT) auto-encoder is trained on simulation data using a curriculum-weighted loss. On heterogeneous speckle-cyst phantoms, the network reduces image-domain MSE by 90 percent, boosts PSNR by 6.7 dB, and raises SSIM to 0.965 compared with the narrow-band input. It also sharpens point-target rows in a completely unseen resolution phantom, demonstrating strong out-of-distribution generalisation without sacrificing frame rate or phase information. These results indicate that a purely software upgrade can endow installed narrow-band probes with broadband-like performance, potentially widening access to high-resolution ultrasound in resource-constrained settings.

Omid Nejati Manzari, Hojat Asgariandehkordi, Taha Koleilat et al.

Convolutional networks, transformers, hybrid models, and Mamba-based architectures have demonstrated strong performance across various medical image classification tasks. However, these methods were primarily designed to classify clean images using labeled data. In contrast, real-world clinical data often involve image corruptions that are unique to multi-center studies and stem from variations in imaging equipment across manufacturers. In this paper, we introduce the Medical Vision Transformer (MedViTV2), a novel architecture incorporating Kolmogorov-Arnold Network (KAN) layers into the transformer architecture for the first time, aiming for generalized medical image classification. We have developed an efficient KAN block to reduce computational load while enhancing the accuracy of the original MedViT. Additionally, to counteract the fragility of our MedViT when scaled up, we propose an enhanced Dilated Neighborhood Attention (DiNA), an adaptation of the efficient fused dot-product attention kernel capable of capturing global context and expanding receptive fields to scale the model effectively and addressing feature collapse issues. Moreover, a hierarchical hybrid strategy is introduced to stack our Local Feature Perception and Global Feature Perception blocks in an efficient manner, which balances local and global feature perceptions to boost performance. Extensive experiments on 17 medical image classification datasets and 12 corrupted medical image datasets demonstrate that MedViTV2 achieved state-of-the-art results in 27 out of 29 experiments with reduced computational complexity. MedViTV2 is 44\% more computationally efficient than the previous version and significantly enhances accuracy, achieving improvements of 4.6\% on MedMNIST, 5.8\% on NonMNIST, and 13.4\% on the MedMNIST-C benchmark.

Soorena Salari, Hassan Rivaz, Yiming Xiao

Automated detection of anatomical landmarks plays a crucial role in many diagnostic and surgical applications. Progresses in deep learning (DL) methods have resulted in significant performance enhancement in tasks related to anatomical landmark detection. While current research focuses on accurately localizing these landmarks in medical scans, the importance of inter-rater annotation variability in building DL models is often overlooked. Understanding how inter-rater variability impacts the performance and reliability of the resulting DL algorithms, which are crucial for clinical deployment, can inform the improvement of training data construction and boost DL models' outcomes. In this paper, we conducted a thorough study of different annotation-fusion strategies to preserve inter-rater variability in DL models for anatomical landmark detection, aiming to boost the performance and reliability of the resulting algorithms. Additionally, we explored the characteristics and reliability of four metrics, including a novel Weighted Coordinate Variance metric to quantify landmark detection uncertainty/inter-rater variability. Our research highlights the crucial connection between inter-rater variability, DL-models performances, and uncertainty, revealing how different approaches for multi-rater landmark annotation fusion can influence these factors.

Hojat Asgariandehkordi, Mostafa Sharifzadeh, Hassan Rivaz

Ultrasound Coherent Plane Wave Compounding (CPWC) enhances image contrast by combining echoes from multiple steered transmissions. While increasing the number of angles generally improves image quality, it drastically reduces the frame rate and can introduce blurring artifacts in fast-moving targets. Moreover, compounded images remain susceptible to noise, particularly when acquired with a limited number of transmissions. We propose a zero-shot denoising framework tailored for low-angle CPWC acquisitions, which enhances contrast without relying on a separate training dataset. The method divides the available transmission angles into two disjoint subsets, each used to form compound images that include higher noise levels. The new compounded images are then used to train a deep model via a self-supervised residual learning scheme, enabling it to suppress incoherent noise while preserving anatomical structures. Because angle-dependent artifacts vary between the subsets while the underlying tissue response is similar, this physics-informed pairing allows the network to learn to disentangle the inconsistent artifacts from the consistent tissue signal. Unlike supervised methods, our model requires no domain-specific fine-tuning or paired data, making it adaptable across anatomical regions and acquisition setups. The entire pipeline supports efficient training with low computational cost due to the use of a lightweight architecture, which comprises only two convolutional layers. Evaluations on simulation, phantom, and in vivo data demonstrate superior contrast enhancement and structure preservation compared to both classical and deep learning-based denoising methods.

Soorena Salari, Catherine Spino, Laurie-Anne Pharand et al.

Accurate tissue motion tracking is critical to ensure treatment outcome and safety in 2D-Cine MRI-guided radiotherapy. This is typically achieved by registration of sequential images, but existing methods often face challenges with large misalignments and lack of interpretability. In this paper, we introduce DINOMotion, a novel deep learning framework based on DINOv2 with Low-Rank Adaptation (LoRA) layers for robust, efficient, and interpretable motion tracking. DINOMotion automatically detects corresponding landmarks to derive optimal image registration, enhancing interpretability by providing explicit visual correspondences between sequential images. The integration of LoRA layers reduces trainable parameters, improving training efficiency, while DINOv2's powerful feature representations offer robustness against large misalignments. Unlike iterative optimization-based methods, DINOMotion directly computes image registration at test time. Our experiments on volunteer and patient datasets demonstrate its effectiveness in estimating both linear and nonlinear transformations, achieving Dice scores of 92.07% for the kidney, 90.90% for the liver, and 95.23% for the lung, with corresponding Hausdorff distances of 5.47 mm, 8.31 mm, and 6.72 mm, respectively. DINOMotion processes each scan in approximately 30ms and consistently outperforms state-of-the-art methods, particularly in handling large misalignments. These results highlight its potential as a robust and interpretable solution for real-time motion tracking in 2D-Cine MRI-guided radiotherapy.

Erin Rainville, Amirhossein Rasoulian, Hassan Rivaz et al.

Intracranial aneurysms (IAs) are abnormal dilations of cerebral blood vessels that, if ruptured, can lead to life-threatening consequences. However, their small size and soft contrast in radiological scans often make it difficult to perform accurate and efficient detection and morphological analyses, which are critical in the clinical care of the disorder. Furthermore, the lack of large public datasets with voxel-wise expert annotations pose challenges for developing deep learning algorithms to address the issues. Therefore, we proposed a novel weakly supervised 3D multi-task UNet that integrates vesselness priors to jointly perform aneurysm detection and segmentation in time-of-flight MR angiography (TOF-MRA). Specifically, to robustly guide IA detection and segmentation, we employ the popular Frangi's vesselness filter to derive soft cerebrovascular priors for both network input and an attention block to conduct segmentation from the decoder and detection from an auxiliary branch. We train our model on the Lausanne dataset with coarse ground truth segmentation, and evaluate it on the test set with refined labels from the same database. To further assess our model's generalizability, we also validate it externally on the ADAM dataset. Our results demonstrate the superior performance of the proposed technique over the SOTA techniques for aneurysm segmentation (Dice = 0.614, 95%HD =1.38mm) and detection (false positive rate = 1.47, sensitivity = 92.9%).

Sepideh K. Gharamaleki, Brandon Helfield, Hassan Rivaz

Super-resolution ultrasound imaging with ultrasound localization microscopy (ULM) offers a high-resolution view of microvascular structures. Yet, ULM image quality heavily relies on precise microbubble (MB) detection. Despite the crucial role of localization algorithms, there has been limited focus on the practical pitfalls in MB detection tasks such as setting the detection threshold. This study examines how False Positives (FPs) and False Negatives (FNs) affect ULM image quality by systematically adding controlled detection errors to simulated data. Results indicate that while both FP and FN rates impact Peak Signal-to-Noise Ratio (PSNR) similarly, increasing FP rates from 0\% to 20\% decreases Structural Similarity Index (SSIM) by 7\%, whereas same FN rates cause a greater drop of around 45\%. Moreover, dense MB regions are more resilient to detection errors, while sparse regions show high sensitivity, showcasing the need for robust MB detection frameworks to enhance super-resolution imaging.

Sepideh K. Gharamaleki, Brandon Helfield, Hassan Rivaz

Super-resolution ultrasound (SR-US) is a powerful imaging technique for capturing microvasculature and blood flow at high spatial resolution. However, accurate microbubble (MB) localization remains a key challenge, as errors in localization can propagate through subsequent stages of the super-resolution process, affecting overall performance. In this paper, we explore the potential of ensemble learning techniques to enhance MB localization by increasing detection sensitivity and reducing false positives. Our study evaluates the effectiveness of ensemble methods on both in vivo and simulated outputs of a Deformable DEtection TRansformer (Deformable DETR) network. As a result of our study, we are able to demonstrate the advantages of these ensemble approaches by showing improved precision and recall in MB detection and offering insights into their application in SR-US.

Zirui Qiu, Hassan Rivaz, Yiming Xiao

Purpose: As visual inspection is an inherent process during radiological screening, the associated eye gaze data can provide valuable insights into relevant clinical decisions. As deep learning has become the state-of-the-art for computer-assisted diagnosis, integrating human behavior, such as eye gaze data, into these systems is instrumental to help align machine predictions with clinical diagnostic criteria, thus enhancing the quality of automatic radiological diagnosis. Methods: We propose a novel deep learning framework for joint disease diagnosis and prediction of corresponding clinical visual attention maps for chest X-ray scans. Specifically, we introduce a new dual-encoder multi-task UNet, which leverages both a DenseNet201 backbone and a Residual and Squeeze-and-Excitation block-based encoder to extract diverse features for visual attention map prediction, and a multi-scale feature-fusion classifier to perform disease classification. To tackle the issue of asynchronous training schedules of individual tasks in multi-task learning, we proposed a multi-stage cooperative learning strategy, with contrastive learning for feature encoder pretraining to boost performance. Results: Our proposed method is shown to significantly outperform existing techniques for chest X-ray diagnosis (AUC=0.93) and the quality of visual attention map prediction (Correlation coefficient=0.58). Conclusion: Benefiting from the proposed multi-task multi-stage cooperative learning, our technique demonstrates the benefit of integrating clinicians' eye gaze into clinical AI systems to boost performance and potentially explainability.

Ali K. Z. Tehrani, Ivan M. Rosado-Mendez, Hassan Rivaz

Quantitative UltraSound (QUS) aims to reveal information about the tissue microstructure using backscattered echo signals from clinical scanners. Among different QUS parameters, scatterer number density is an important property that can affect estimation of other QUS parameters. Scatterer number density can be classified into high or low scatterer densities. If there are more than 10 scatterers inside the resolution cell, the envelope data is considered as Fully Developed Speckle (FDS) and otherwise, as Under Developed Speckle (UDS). In conventional methods, the envelope data is divided into small overlapping windows (a strategy here we refer to as patching), and statistical parameters such as SNR and skewness are employed to classify each patch of envelope data. However, these parameters are system dependent meaning that their distribution can change by the imaging settings and patch size. Therefore, reference phantoms which have known scatterer number density are imaged with the same imaging settings to mitigate system dependency. In this paper, we aim to segment regions of ultrasound data without any patching. A large dataset is generated which has different shapes of scatterer number density and mean scatterer amplitude using a fast simulation method. We employ a convolutional neural network (CNN) for the segmentation task and investigate the effect of domain shift when the network is tested on different datasets with different imaging settings. Nakagami parametric image is employed for the multi-task learning to improve the performance. Furthermore, inspired by the reference phantom methods in QUS, A domain adaptation stage is proposed which requires only two frames of data from FDS and UDS classes. We evaluate our method for different experimental phantoms and in vivo data.

Behnaz Gheflati, Hassan Rivaz

Medical ultrasound (US) imaging has become a prominent modality for breast cancer imaging due to its ease-of-use, low-cost and safety. In the past decade, convolutional neural networks (CNNs) have emerged as the method of choice in vision applications and have shown excellent potential in automatic classification of US images. Despite their success, their restricted local receptive field limits their ability to learn global context information. Recently, Vision Transformer (ViT) designs that are based on self-attention between image patches have shown great potential to be an alternative to CNNs. In this study, for the first time, we utilize ViT to classify breast US images using different augmentation strategies. The results are provided as classification accuracy and Area Under the Curve (AUC) metrics, and the performance is compared with the state-of-the-art CNNs. The results indicate that the ViT models have comparable efficiency with or even better than the CNNs in classification of US breast images.

Abdelrahman Zayed, Hassan Rivaz

Ultrasound Elastography aims to determine the mechanical properties of the tissue by monitoring tissue deformation due to internal or external forces. Tissue deformations are estimated from ultrasound radio frequency (RF) signals and are often referred to as time delay estimation (TDE). Given two RF frames I1 and I2, we can compute a displacement image which shows the change in the position of each sample in I1 to a new position in I2. Two important challenges in TDE include high computational complexity and the difficulty in choosing suitable RF frames. Selecting suitable frames is of high importance because many pairs of RF frames either do not have acceptable deformation for extracting informative strain images or are decorrelated and deformation cannot be reliably estimated. Herein, we introduce a method that learns 12 displacement modes in quasi-static elastography by performing Principal Component Analysis (PCA) on displacement fields of a large training database. In the inference stage, we use dynamic programming (DP) to compute an initial displacement estimate of around 1% of the samples, and then decompose this sparse displacement into a linear combination of the 12 displacement modes. Our method assumes that the displacement of the whole image could also be described by this linear combination of principal components. We then use the GLobal Ultrasound Elastography (GLUE) method to fine-tune the result yielding the exact displacement image. Our method, which we call PCA-GLUE, is more than 10 times faster than DP in calculating the initial displacement map while giving the same result. Our second contribution in this paper is determining the suitability of the frame pair I1 and I2 for strain estimation, which we achieve by using the weight vector that we calculated for PCA-GLUE as an input to a multi-layer perceptron (MLP) classifier.

Mostafa Sharifzadeh, Habib Benali, Hassan Rivaz

Convolutional neural networks (CNNs) have attracted a rapidly growing interest in a variety of different processing tasks in the medical ultrasound community. However, the performance of CNNs is highly reliant on both the amount and fidelity of the training data. Therefore, scarce data is almost always a concern, particularly in the medical field, where clinical data is not easily accessible. The utilization of synthetic data is a popular approach to address this challenge. However, but simulating a large number of images using packages such as Field II is time-consuming, and the distribution of simulated images is far from that of the real images. Herein, we introduce a novel ultra-fast ultrasound image simulation method based on the Fourier transform and evaluate its performance in a lesion segmentation task. We demonstrate that data augmentation using the images generated by the proposed method substantially outperforms Field II in terms of Dice similarity coefficient, while the simulation is almost 36000 times faster (both on CPU).

Bahareh Behboodi, Hassan Rivaz, Susan Lalondrelle et al.

On-line segmentation of the uterus can aid effective image-based guidance for precise delivery of dose to the target tissue (the uterocervix) during cervix cancer radiotherapy. 3D ultrasound (US) can be used to image the uterus, however, finding the position of uterine boundary in US images is a challenging task due to large daily positional and shape changes in the uterus, large variation in bladder filling, and the limitations of 3D US images such as low resolution in the elevational direction and imaging aberrations. Previous studies on uterus segmentation mainly focused on developing semi-automatic algorithms where require manual initialization to be done by an expert clinician. Due to limited studies on the automatic 3D uterus segmentation, the aim of the current study was to overcome the need for manual initialization in the semi-automatic algorithms using the recent deep learning-based algorithms. Therefore, we developed 2D UNet-based networks that are trained based on two scenarios. In the first scenario, we trained 3 different networks on each plane (i.e., sagittal, coronal, axial) individually. In the second scenario, our proposed network was trained using all the planes of each 3D volume. Our proposed schematic can overcome the initial manual selection of previous semi-automatic algorithm.

Hamza Rasaee, Hassan Rivaz

Ultrasound is a non-invasive imaging modality that can be conveniently used to classify suspicious breast nodules and potentially detect the onset of breast cancer. Recently, Convolutional Neural Networks (CNN) techniques have shown promising results in classifying ultrasound images of the breast into benign or malignant. However, CNN inference acts as a black-box model, and as such, its decision-making is not interpretable. Therefore, increasing effort has been dedicated to explaining this process, most notably through GRAD-CAM and other techniques that provide visual explanations into inner workings of CNNs. In addition to interpretation, these methods provide clinically important information, such as identifying the location for biopsy or treatment. In this work, we analyze how adversarial assaults that are practically undetectable may be devised to alter these importance maps dramatically. Furthermore, we will show that this change in the importance maps can come with or without altering the classification result, rendering them even harder to detect. As such, care must be taken when using these importance maps to shed light on the inner workings of deep learning. Finally, we utilize Multi-Task Learning (MTL) and propose a new network based on ResNet-50 to improve the classification accuracies. Our sensitivity and specificity is comparable to the state of the art results.

Annika Reinke, Minu D. Tizabi, Carole H. Sudre et al.

While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation. Performance metrics are particularly key for meaningful, objective, and transparent performance assessment and validation of the used automatic algorithms, but relatively little attention has been given to the practical pitfalls when using specific metrics for a given image analysis task. These are typically related to (1) the disregard of inherent metric properties, such as the behaviour in the presence of class imbalance or small target structures, (2) the disregard of inherent data set properties, such as the non-independence of the test cases, and (3) the disregard of the actual biomedical domain interest that the metrics should reflect. This living dynamically document has the purpose to illustrate important limitations of performance metrics commonly applied in the field of image analysis. In this context, it focuses on biomedical image analysis problems that can be phrased as image-level classification, semantic segmentation, instance segmentation, or object detection task. The current version is based on a Delphi process on metrics conducted by an international consortium of image analysis experts from more than 60 institutions worldwide.

Md Ashikuzzaman, Noushin Jafarpisheh, Sunil Rottoo et al.

Intraoperative tracking of surgical instruments is an inevitable task of computer-assisted surgery. An optical tracking system often fails to precisely reconstruct the dynamic location and pose of a surgical tool due to the acquisition noise and measurement variance. Embedding a Kalman Filter (KF) or any of its extensions such as extended and unscented Kalman filters with the optical tracker resolves this issue by reducing the estimation variance and regularizing the temporal behavior. However, the current rigid-body KF implementations are computationally burdensome and hence, takes long execution time which hinders real-time surgical tracking. This paper introduces a fast and computationally efficient implementation of linear KF to improve the measurement accuracy of an optical tracking system with high temporal resolution. Instead of the surgical tool as a whole, our KF framework tracks each individual fiducial mounted on it using a Newtonian model. In addition to simulated dataset, we validate our technique against real data obtained from a high frame-rate commercial optical tracking system. The proposed KF framework substantially stabilizes the tracking behavior in all of our experiments and reduces the mean-squared error (MSE) from the order of $10^{-2}$ $mm^{2}$ to $10^{-4}$ $mm^{2}$.