Tanveer Syeda-Mahmood

Ashutosh Jadhav, Satyananda Kashyap, Hakan Bulu et al. · ibm-research

Intrasaccular flow disruptors treat cerebral aneurysms by diverting the blood flow from the aneurysm sac. Residual flow into the sac after the intervention is a failure that could be due to the use of an undersized device, or to vascular anatomy and clinical condition of the patient. We report a machine learning model based on over 100 clinical and imaging features that predict the outcome of wide-neck bifurcation aneurysm treatment with an intravascular embolization device. We combine clinical features with a diverse set of common and novel imaging measurements within a random forest model. We also develop neural network segmentation algorithms in 2D and 3D to contour the sac in angiographic images and automatically calculate the imaging features. These deliver 90% overlap with manual contouring in 2D and 83% in 3D. Our predictive model classifies complete vs. partial occlusion outcomes with an accuracy of 75.31%, and weighted F1-score of 0.74.

Neha Srivathsa, Razi Mahmood, Tanveer Syeda-Mahmood · berkeley

Chest X-rays have become the focus of vigorous deep learning research in recent years due to the availability of large labeled datasets. While classification of anomalous findings is now possible, ensuring that they are correctly localized still remains challenging, as this requires recognition of anomalies within anatomical regions. Existing deep learning networks for fine-grained anomaly classification learn location-specific findings using architectures where the location and spatial contiguity information is lost during the flattening step before classification. In this paper, we present a new spatially preserving deep learning network that preserves location and shape information through auto-encoding of feature maps during flattening. The feature maps, auto-encoder and classifier are then trained in an end-to-end fashion to enable location aware classification of findings in chest X-rays. Results are shown on a large multi-hospital chest X-ray dataset indicating a significant improvement in the quality of finding classification over state-of-the-art methods.

Elisa Warner, Joonsang Lee, William Hsu et al.

Machine learning (ML) applications in medical artificial intelligence (AI) systems have shifted from traditional and statistical methods to increasing application of deep learning models. This survey navigates the current landscape of multimodal ML, focusing on its profound impact on medical image analysis and clinical decision support systems. Emphasizing challenges and innovations in addressing multimodal representation, fusion, translation, alignment, and co-learning, the paper explores the transformative potential of multimodal models for clinical predictions. It also highlights the need for principled assessments and practical implementation of such models, bringing attention to the dynamics between decision support systems and healthcare providers and personnel. Despite advancements, challenges such as data biases and the scarcity of "big data" in many biomedical domains persist. We conclude with a discussion on principled innovation and collaborative efforts to further the mission of seamless integration of multimodal ML models into biomedical practice.

Rodrigo Bonazzola, Enzo Ferrante, Nishant Ravikumar et al.

Recent genome-wide association studies (GWAS) have been successful in identifying associations between genetic variants and simple cardiac parameters derived from cardiac magnetic resonance (CMR) images. However, the emergence of big databases including genetic data linked to CMR, facilitates investigation of more nuanced patterns of shape variability. Here, we propose a new framework for gene discovery entitled Unsupervised Phenotype Ensembles (UPE). UPE builds a redundant yet highly expressive representation by pooling a set of phenotypes learned in an unsupervised manner, using deep learning models trained with different hyperparameters. These phenotypes are then analyzed via (GWAS), retaining only highly confident and stable associations across the ensemble. We apply our approach to the UK Biobank database to extract left-ventricular (LV) geometric features from image-derived three-dimensional meshes. We demonstrate that our approach greatly improves the discoverability of genes influencing LV shape, identifying 11 loci with study-wide significance and 8 with suggestive significance. We argue that our approach would enable more extensive discovery of gene associations with image-derived phenotypes for other organs or image modalities.

Niharika S. D'Souza, Hongzhi Wang, Andrea Giovannini et al.

In a complex disease such as tuberculosis, the evidence for the disease and its evolution may be present in multiple modalities such as clinical, genomic, or imaging data. Effective patient-tailored outcome prediction and therapeutic guidance will require fusing evidence from these modalities. Such multimodal fusion is difficult since the evidence for the disease may not be uniform across all modalities, not all modality features may be relevant, or not all modalities may be present for all patients. All these nuances make simple methods of early, late, or intermediate fusion of features inadequate for outcome prediction. In this paper, we present a novel fusion framework using multiplexed graphs and derive a new graph neural network for learning from such graphs. Specifically, the framework allows modalities to be represented through their targeted encodings, and models their relationship explicitly via multiplexed graphs derived from salient features in a combined latent space. We present results that show that our proposed method outperforms state-of-the-art methods of fusing modalities for multi-outcome prediction on a large Tuberculosis (TB) dataset.

Niharika S. D'Souza, Hongzhi Wang, Andrea Giovannini et al.

With the emergence of multimodal electronic health records, the evidence for an outcome may be captured across multiple modalities ranging from clinical to imaging and genomic data. Predicting outcomes effectively requires fusion frameworks capable of modeling fine-grained and multi-faceted complex interactions between modality features within and across patients. We develop an innovative fusion approach called MaxCorr MGNN that models non-linear modality correlations within and across patients through Hirschfeld-Gebelein-Renyi maximal correlation (MaxCorr) embeddings, resulting in a multi-layered graph that preserves the identities of the modalities and patients. We then design, for the first time, a generalized multi-layered graph neural network (MGNN) for task-informed reasoning in multi-layered graphs, that learns the parameters defining patient-modality graph connectivity and message passing in an end-to-end fashion. We evaluate our model an outcome prediction task on a Tuberculosis (TB) dataset consistently outperforming several state-of-the-art neural, graph-based and traditional fusion techniques.

Ken C. L. Wong, Hongzhi Wang, Tanveer Syeda-Mahmood

Due to the computational complexity of 3D medical image segmentation, training with downsampled images is a common remedy for out-of-memory errors in deep learning. Nevertheless, as standard spatial convolution is sensitive to variations in image resolution, the accuracy of a convolutional neural network trained with downsampled images can be suboptimal when applied on the original resolution. To address this limitation, we introduce FNOSeg3D, a 3D segmentation model robust to training image resolution based on the Fourier neural operator (FNO). The FNO is a deep learning framework for learning mappings between functions in partial differential equations, which has the appealing properties of zero-shot super-resolution and global receptive field. We improve the FNO by reducing its parameter requirement and enhancing its learning capability through residual connections and deep supervision, and these result in our FNOSeg3D model which is parameter efficient and resolution robust. When tested on the BraTS'19 dataset, it achieved superior robustness to training image resolution than other tested models with less than 1% of their model parameters.

Ken C. L. Wong, Hongzhi Wang, Tanveer Syeda-Mahmood

With the introduction of Transformers, different attention-based models have been proposed for image segmentation with promising results. Although self-attention allows capturing of long-range dependencies, it suffers from a quadratic complexity in the image size especially in 3D. To avoid the out-of-memory error during training, input size reduction is usually required for 3D segmentation, but the accuracy can be suboptimal when the trained models are applied on the original image size. To address this limitation, inspired by the Fourier neural operator (FNO), we introduce the HartleyMHA model which is robust to training image resolution with efficient self-attention. FNO is a deep learning framework for learning mappings between functions in partial differential equations, which has the appealing properties of zero-shot super-resolution and global receptive field. We modify the FNO by using the Hartley transform with shared parameters to reduce the model size by orders of magnitude, and this allows us to further apply self-attention in the frequency domain for more expressive high-order feature combination with improved efficiency. When tested on the BraTS'19 dataset, it achieved superior robustness to training image resolution than other tested models with less than 1% of their model parameters.

Yuan Zhou, Jing Mei, Yiqin Yu et al.

Visual Question Answering (VQA) becomes one of the most active research problems in the medical imaging domain. A well-known VQA challenge is the intrinsic diversity between the image and text modalities, and in the medical VQA task, there is another critical problem relying on the limited size of labelled image-question-answer data. In this study we propose an encoder-decoder framework that leverages the image-text joint representation learned from large-scaled medical image-caption data and adapted to the small-sized medical VQA task. The encoder embeds across the image-text dual modalities with self-attention mechanism and is independently pre-trained on the large-scaled medical image-caption dataset by multiple self-supervised learning tasks. Then the decoder is connected to the top of the encoder and fine-tuned using the small-sized medical VQA dataset. The experiment results present that our proposed method achieves better performance comparing with the baseline and SOTA methods.

Ken C. L. Wong, Levente Klein, Ademir Ferreira da Silva et al.

Soil organic carbon (SOC) sequestration is the transfer and storage of atmospheric carbon dioxide in soils, which plays an important role in climate change mitigation. SOC concentration can be improved by proper land use, thus it is beneficial if SOC can be estimated at a regional or global scale. As multispectral satellite data can provide SOC-related information such as vegetation and soil properties at a global scale, estimation of SOC through satellite data has been explored as an alternative to manual soil sampling. Although existing studies show promising results, they are mainly based on pixel-based approaches with traditional machine learning methods, and convolutional neural networks (CNNs) are uncommon. To study the use of CNNs on SOC remote sensing, here we propose the FNO-DenseNet based on the Fourier neural operator (FNO). By combining the advantages of the FNO and DenseNet, the FNO-DenseNet outperformed the FNO in our experiments with hundreds of times fewer parameters. The FNO-DenseNet also outperformed a pixel-based random forest by 18% in the mean absolute percentage error.

Granite Vision Team, Leonid Karlinsky, Assaf Arbelle et al.

We introduce Granite Vision, a lightweight large language model with vision capabilities, specifically designed to excel in enterprise use cases, particularly in visual document understanding. Our model is trained on a comprehensive instruction-following dataset, including document-related tasks, such as content extraction from tables, charts, diagrams, sketches, and infographics, as well as general image tasks. The architecture of Granite Vision is centered around visual modality alignment with a decoder-only, 2 billion parameter Granite large language model. Additionally, we introduce a dedicated safety classification approach in test-time that leverages a sparse set of attention vectors to identify potential harmful inputs. Despite its lightweight architecture, Granite Vision achieves strong results in standard benchmarks related to visual document understanding, as well as on the LiveXiv benchmark, which is designed to avoid test set contamination by using a constantly updated corpus of recently published Arxiv papers. We are releasing the model under the Apache-2 license, allowing for both research and commercial use, while offering complete visibility into the training data and other relevant details. See https://huggingface.co/ibm-granite/ for model weights.

Satyananda Kashyap, Niharika S. D'Souza, Luyao Shi et al.

Content-addressable memories such as Modern Hopfield Networks (MHN) have been studied as mathematical models of auto-association and storage/retrieval in the human declarative memory, yet their practical use for large-scale content storage faces challenges. Chief among them is the occurrence of meta-stable states, particularly when handling large amounts of high dimensional content. This paper introduces Hopfield Encoding Networks (HEN), a framework that integrates encoded neural representations into MHNs to improve pattern separability and reduce meta-stable states. We show that HEN can also be used for retrieval in the context of hetero association of images with natural language queries, thus removing the limitation of requiring access to partial content in the same domain. Experimental results demonstrate substantial reduction in meta-stable states and increased storage capacity while still enabling perfect recall of a significantly larger number of inputs advancing the practical utility of associative memory networks for real-world tasks.

Tanveer Syeda-Mahmood, Hassan M. Ahmad, Nadeem Ansari et al.

Chest X-rays are the most common diagnostic exams in emergency rooms and hospitals. There has been a surge of work on automatic interpretation of chest X-rays using deep learning approaches after the availability of large open source chest X-ray dataset from NIH. However, the labels are not sufficiently rich and descriptive for training classification tools. Further, it does not adequately address the findings seen in Chest X-rays taken in anterior-posterior (AP) view which also depict the placement of devices such as central vascular lines and tubes. In this paper, we present a new chest X-ray benchmark database of 73 rich sentence-level descriptors of findings seen in AP chest X-rays. We describe our method of obtaining these findings through a semi-automated ground truth generation process from crowdsourcing of clinician annotations. We also present results of building classifiers for these findings that show that such higher granularity labels can also be learned through the framework of deep learning classifiers.

Razi Mahmood, Pingkun Yan, Diego Machado Reyes et al. · berkeley

Several evaluation metrics have been developed recently to automatically assess the quality of generative AI reports for chest radiographs based only on textual information using lexical, semantic, or clinical named entity recognition methods. In this paper, we develop a new method of report quality evaluation by first extracting fine-grained finding patterns capturing the location, laterality, and severity of a large number of clinical findings. We then performed phrasal grounding to localize their associated anatomical regions on chest radiograph images. The textual and visual measures are then combined to rate the quality of the generated reports. We present results that compare this evaluation metric with other textual metrics on a gold standard dataset derived from the MIMIC collection and show its robustness and sensitivity to factual errors.

Emily Alsentzer, Marie-Laure Charpignon, Bill Chen et al.

The 6th Annual Conference on Health, Inference, and Learning (CHIL 2025), hosted by the Association for Health Learning and Inference (AHLI), was held in person on June 25-27, 2025, at the University of California, Berkeley, in Berkeley, California, USA. As part of this year's program, we hosted Research Roundtables to catalyze collaborative, small-group dialogue around critical, timely topics at the intersection of machine learning and healthcare. Each roundtable was moderated by a team of senior and junior chairs who fostered open exchange, intellectual curiosity, and inclusive engagement. The sessions emphasized rigorous discussion of key challenges, exploration of emerging opportunities, and collective ideation toward actionable directions in the field. In total, eight roundtables were held by 19 roundtable chairs on topics of "Explainability, Interpretability, and Transparency," "Uncertainty, Bias, and Fairness," "Causality," "Domain Adaptation," "Foundation Models," "Learning from Small Medical Data," "Multimodal Methods," and "Scalable, Translational Healthcare Solutions."

Razi Mahmood, Diego Machado-Reyes, Joy Wu et al. · berkeley

With the emergence of large-scale vision language models (VLM), it is now possible to produce realistic-looking radiology reports for chest X-ray images. However, their clinical translation has been hampered by the factual errors and hallucinations in the produced descriptions during inference. In this paper, we present a novel phrase-grounded fact-checking model (FC model) that detects errors in findings and their indicated locations in automatically generated chest radiology reports. Specifically, we simulate the errors in reports through a large synthetic dataset derived by perturbing findings and their locations in ground truth reports to form real and fake findings-location pairs with images. A new multi-label cross-modal contrastive regression network is then trained on this dataset. We present results demonstrating the robustness of our method in terms of accuracy of finding veracity prediction and localization on multiple X-ray datasets. We also show its effectiveness for error detection in reports of SOTA report generators on multiple datasets achieving a concordance correlation coefficient of 0.997 with ground truth-based verification, thus pointing to its utility during clinical inference in radiology workflows.

Ken C. L. Wong, Hongzhi Wang, Tanveer Syeda-Mahmood

In medical image segmentation, convolutional neural networks (CNNs) and transformers are dominant. For CNNs, given the local receptive fields of convolutional layers, long-range spatial correlations are captured through consecutive convolutions and pooling. However, as the computational cost and memory footprint can be prohibitively large, 3D models can only afford fewer layers than 2D models with reduced receptive fields and abstract levels. For transformers, although long-range correlations can be captured by multi-head attention, its quadratic complexity with respect to input size is computationally demanding. Therefore, either model may require input size reduction to allow more filters and layers for better segmentation. Nevertheless, given their discrete nature, models trained with patch-wise training or image downsampling may produce suboptimal results when applied on higher resolutions. To address this issue, here we propose the resolution-robust HNOSeg-XS architecture. We model image segmentation by learnable partial differential equations through the Fourier neural operator which has the zero-shot super-resolution property. By replacing the Fourier transform by the Hartley transform and reformulating the problem in the frequency domain, we created the HNOSeg-XS model, which is resolution robust, fast, memory efficient, and extremely parameter efficient. When tested on the BraTS'23, KiTS'23, and MVSeg'23 datasets with a Tesla V100 GPU, HNOSeg-XS showed its superior resolution robustness with fewer than 34.7k model parameters. It also achieved the overall best inference time (< 0.24 s) and memory efficiency (< 1.8 GiB) compared to the tested CNN and transformer models.

Ken C. L. Wong, Hongzhi Wang, Etienne E. Vos et al.

Global warming leads to the increase in frequency and intensity of climate extremes that cause tremendous loss of lives and property. Accurate long-range climate prediction allows more time for preparation and disaster risk management for such extreme events. Although machine learning approaches have shown promising results in long-range climate forecasting, the associated model uncertainties may reduce their reliability. To address this issue, we propose a late fusion approach that systematically combines the predictions from multiple models to reduce the expected errors of the fused results. We also propose a network architecture with the novel denormalization layer to gain the benefits of data normalization without actually normalizing the data. The experimental results on long-range 2m temperature forecasting show that the framework outperforms the 30-year climate normals, and the accuracy can be improved by increasing the number of models.

Vaishnavi Subramanian, Tanveer Syeda-Mahmood, Minh N. Do

The availability of multi-modality datasets provides a unique opportunity to characterize the same object of interest using multiple viewpoints more comprehensively. In this work, we investigate the use of canonical correlation analysis (CCA) and penalized variants of CCA (pCCA) for the fusion of two modalities. We study a simple graphical model for the generation of two-modality data. We analytically show that, with known model parameters, posterior mean estimators that jointly use both modalities outperform arbitrary linear mixing of single modality posterior estimators in latent variable prediction. Penalized extensions of CCA (pCCA) that incorporate domain knowledge can discover correlations with high-dimensional, low-sample data, whereas traditional CCA is inapplicable. To facilitate the generation of multi-dimensional embeddings with pCCA, we propose two matrix deflation schemes that enforce desirable properties exhibited by CCA. We propose a two-stage prediction pipeline using pCCA embeddings generated with deflation for latent variable prediction by combining all the above. On simulated data, our proposed model drastically reduces the mean-squared error in latent variable prediction. When applied to publicly available histopathology data and RNA-sequencing data from The Cancer Genome Atlas (TCGA) breast cancer patients, our model can outperform principal components analysis (PCA) embeddings of the same dimension in survival prediction.

Ken C. L. Wong, Elena S. Sinkovskaya, Alfred Z. Abuhamad et al.

Congenital heart disease (CHD) is the most common congenital abnormality associated with birth defects in the United States. Despite training efforts and substantial advancement in ultrasound technology over the past years, CHD remains an abnormality that is frequently missed during prenatal ultrasonography. Therefore, computer-aided detection of CHD can play a critical role in prenatal care by improving screening and diagnosis. Since many CHDs involve structural abnormalities, automatic segmentation of anatomical structures is an important step in the analysis of fetal echocardiograms. While existing methods mainly focus on the four-chamber view with a small number of structures, here we present a more comprehensive deep learning segmentation framework covering 14 anatomical structures in both three-vessel trachea and four-chamber views. Specifically, our framework enhances the V-Net with spatial dropout, group normalization, and deep supervision to train a segmentation model that can be applied on both views regardless of abnormalities. By identifying the pitfall of using the Dice loss when some labels are unavailable in some images, this framework integrates information from multiple views and is robust to missing structures due to anatomical anomalies, achieving an average Dice score of 79%.

Vaishnavi Subramanian, Tanveer Syeda-Mahmood, Minh N. Do

Effective understanding of a disease such as cancer requires fusing multiple sources of information captured across physical scales by multimodal data. In this work, we propose a novel feature embedding module that derives from canonical correlation analyses to account for intra-modality and inter-modality correlations. Experiments on simulated and real data demonstrate how our proposed module can learn well-correlated multi-dimensional embeddings. These embeddings perform competitively on one-year survival classification of TCGA-BRCA breast cancer patients, yielding average F1 scores up to 58.69% under 5-fold cross-validation.

Tanveer Syeda-Mahmood, Ph. D, K. C. L Wong et al.

Chest radiographs are the most common diagnostic exam in emergency rooms and intensive care units today. Recently, a number of researchers have begun working on large chest X-ray datasets to develop deep learning models for recognition of a handful of coarse finding classes such as opacities, masses and nodules. In this paper, we focus on extracting and learning fine-grained labels for chest X-ray images. Specifically we develop a new method of extracting fine-grained labels from radiology reports by combining vocabulary-driven concept extraction with phrasal grouping in dependency parse trees for association of modifiers with findings. A total of 457 fine-grained labels depicting the largest spectrum of findings to date were selected and sufficiently large datasets acquired to train a new deep learning model designed for fine-grained classification. We show results that indicate a highly accurate label extraction process and a reliable learning of fine-grained labels. The resulting network, to our knowledge, is the first to recognize fine-grained descriptions of findings in images covering over nine modifiers including laterality, location, severity, size and appearance.

Karina Kanjaria, Anup Pillai, Chaitanya Shivade et al.

Due to advances in machine learning and artificial intelligence (AI), a new role is emerging for machines as intelligent assistants to radiologists in their clinical workflows. But what systematic clinical thought processes are these machines using? Are they similar enough to those of radiologists to be trusted as assistants? A live demonstration of such a technology was conducted at the 2016 Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA). The demonstration was presented in the form of a question-answering system that took a radiology multiple choice question and a medical image as inputs. The AI system then demonstrated a cognitive workflow, involving text analysis, image analysis, and reasoning, to process the question and generate the most probable answer. A post demonstration survey was made available to the participants who experienced the demo and tested the question answering system. Of the reported 54,037 meeting registrants, 2,927 visited the demonstration booth, 1,991 experienced the demo, and 1,025 completed a post-demonstration survey. In this paper, the methodology of the survey is shown and a summary of its results are presented. The results of the survey show a very high level of receptiveness to cognitive computing technology and artificial intelligence among radiologists.

Satyananda Kashyap, Alexandros Karargyris, Joy Wu et al.

Deep learning has now become the de facto approach to the recognition of anomalies in medical imaging. Their 'black box' way of classifying medical images into anomaly labels poses problems for their acceptance, particularly with clinicians. Current explainable AI methods offer justifications through visualizations such as heat maps but cannot guarantee that the network is focusing on the relevant image region fully containing the anomaly. In this paper, we develop an approach to explainable AI in which the anomaly is assured to be overlapping the expected location when present. This is made possible by automatically extracting location-specific labels from textual reports and learning the association of expected locations to labels using a hybrid combination of Bi-Directional Long Short-Term Memory Recurrent Neural Networks (Bi-LSTM) and DenseNet-121. Use of this expected location to bias the subsequent attention-guided inference network based on ResNet101 results in the isolation of the anomaly at the expected location when present. The method is evaluated on a large chest X-ray dataset.

Tanveer Syeda-Mahmood, Ken C. L. Wong, Yaniv Gur et al.

Obtaining automated preliminary read reports for common exams such as chest X-rays will expedite clinical workflows and improve operational efficiencies in hospitals. However, the quality of reports generated by current automated approaches is not yet clinically acceptable as they cannot ensure the correct detection of a broad spectrum of radiographic findings nor describe them accurately in terms of laterality, anatomical location, severity, etc. In this work, we present a domain-aware automatic chest X-ray radiology report generation algorithm that learns fine-grained description of findings from images and uses their pattern of occurrences to retrieve and customize similar reports from a large report database. We also develop an automatic labeling algorithm for assigning such descriptors to images and build a novel deep learning network that recognizes both coarse and fine-grained descriptions of findings. The resulting report generation algorithm significantly outperforms the state of the art using established score metrics.

John Paul Francis, Hongzhi Wang, Kate White et al.

The Pancreatic beta cell is an important target in diabetes research. For scalable modeling of beta cell ultrastructure, we investigate automatic segmentation of whole cell imaging data acquired through soft X-ray tomography. During the course of the study, both complete and partial ultrastructure annotations were produced manually for different subsets of the data. To more effectively use existing annotations, we propose a method that enables the application of partially labeled data for full label segmentation. For experimental validation, we apply our method to train a convolutional neural network with a set of 12 fully annotated data and 12 partially annotated data and show promising improvement over standard training that uses fully annotated data alone.

Vaishnavi Subramanian, Minh N. Do, Tanveer Syeda-Mahmood

Lung cancer has a high rate of recurrence in early-stage patients. Predicting the post-surgical recurrence in lung cancer patients has traditionally been approached using single modality information of genomics or radiology images. We investigate the potential of multimodal fusion for this task. By combining computed tomography (CT) images and genomics, we demonstrate improved prediction of recurrence using linear Cox proportional hazards models with elastic net regularization. We work on a recent non-small cell lung cancer (NSCLC) radiogenomics dataset of 130 patients and observe an increase in concordance-index values of up to 10%. Employing non-linear methods from the neural network literature, such as multi-layer perceptrons and visual-question answering fusion modules, did not improve performance consistently. This indicates the need for larger multimodal datasets and fusion techniques better adapted to this biological setting.

Vaishnavi Subramanian, Hongzhi Wang, Joy T. Wu et al.

Central venous catheters (CVCs) are commonly used in critical care settings for monitoring body functions and administering medications. They are often described in radiology reports by referring to their presence, identity and placement. In this paper, we address the problem of automatic detection of their presence and identity through automated segmentation using deep learning networks and classification based on their intersection with previously learned shape priors from clinician annotations of CVCs. The results not only outperform existing methods of catheter detection achieving 85.2% accuracy at 91.6% precision, but also enable high precision (95.2%) classification of catheter types on a large dataset of over 10,000 chest X-rays, presenting a robust and practical solution to this problem.

Alexandros Karargyris, Ken C. L. Wong, Joy T. Wu et al.

In many screening applications, the primary goal of a radiologist or assisting artificial intelligence is to rule out certain findings. The classifiers built for such applications are often trained on large datasets that derive labels from clinical notes written for patients. While the quality of the positive findings described in these notes is often reliable, lack of the mention of a finding does not always rule out the presence of it. This happens because radiologists comment on the patient in the context of the exam, for example focusing on trauma as opposed to chronic disease at emergency rooms. However, this disease finding ambiguity can affect the performance of algorithms. Hence it is critical to model the ambiguity during training. We propose a scheme to apply reasonable class weight modifiers to our loss function for the no mention cases during training. We experiment with two different deep neural network architectures and show that the proposed method results in a large improvement in the performance of the classifiers, specially on negated findings. The baseline performance of a custom-made dilated block network proposed in this paper shows an improvement in comparison with baseline DenseNet-201, while both architectures benefit from the new proposed loss function weighting scheme. Over 200,000 chest X-ray images and three highly common diseases, along with their negated counterparts, are included in this study.

Ken C. L. Wong, Mehdi Moradi, Joy Wu et al.

Chest X-rays (CXRs) are among the most commonly used medical image modalities. They are mostly used for screening, and an indication of disease typically results in subsequent tests. As this is mostly a screening test used to rule out chest abnormalities, the requesting clinicians are often interested in whether a CXR is normal or not. A machine learning algorithm that can accurately screen out even a small proportion of the "real normal" exams out of all requested CXRs would be highly beneficial in reducing the workload for radiologists. In this work, we report a deep neural network trained for classifying CXRs with the goal of identifying a large number of normal (disease-free) images without risking the discharge of sick patients. We use an ImageNet-pretrained Inception-ResNet-v2 model to provide the image features, which are further used to train a model on CXRs labelled by expert radiologists. The probability threshold for classification is optimized for 100% precision for the normal class, ensuring no sick patients are released. At this threshold we report an average recall of 50%. This means that the proposed solution has the potential to cut in half the number of disease-free CXRs examined by radiologists, without risking the discharge of sick patients.

Alexandros Karargyris, Satyananda Kashyap, Joy T Wu et al.

Age prediction based on appearances of different anatomies in medical images has been clinically explored for many decades. In this paper, we used deep learning to predict a persons age on Chest X-Rays. Specifically, we trained a CNN in regression fashion on a large publicly available dataset. Moreover, for interpretability, we explored activation maps to identify which areas of a CXR image are important for the machine (i.e. CNN) to predict a patients age, offering insight. Overall, amongst correctly predicted CXRs, we see areas near the clavicles, shoulders, spine, and mediastinum being most activated for age prediction, as one would expect biologically. Amongst incorrectly predicted CXRs, we have qualitatively identified disease patterns that could possibly make the anatomies appear older or younger than expected. A further technical and clinical evaluation would improve this work. As CXR is the most commonly requested imaging exam, a potential use case for estimating age may be found in the preventative counseling of patient health status compared to their age-expected average, particularly when there is a large discrepancy between predicted age and the real patient age.

Marina Bendersky, Joy Wu, Tanveer Syeda-Mahmood

Data labeling is currently a time-consuming task that often requires expert knowledge. In research settings, the availability of correctly labeled data is crucial to ensure that model predictions are accurate and useful. We propose relatively simple machine learning-based models that achieve high performance metrics in the binary and multiclass classification of radiology reports. We compare the performance of these algorithms to that of a data-driven approach based on NLP, and find that the logistic regression classifier outperforms all other models, in both the binary and multiclass classification tasks. We then choose the logistic regression binary classifier to predict chest X-ray (CXR)/ non-chest X-ray (non-CXR) labels in reports from different datasets, unseen during any training phase of any of the models. Even in unseen report collections, the binary logistic regression classifier achieves average precision values of above 0.9. Based on the regression coefficient values, we also identify frequent tokens in CXR and non-CXR reports that are features with possibly high predictive power.

Mehdi Moradi, Ali Madani, Yaniv Gur et al.

Medical image analysis practitioners have embraced big data methodologies. This has created a need for large annotated datasets. The source of big data is typically large image collections and clinical reports recorded for these images. In many cases, however, building algorithms aimed at segmentation and detection of disease requires a training dataset with markings of the areas of interest on the image that match with the described anomalies. This process of annotation is expensive and needs the involvement of clinicians. In this work we propose two separate deep neural network architectures for automatic marking of a region of interest (ROI) on the image best representing a finding location, given a textual report or a set of keywords. One architecture consists of LSTM and CNN components and is trained end to end with images, matching text, and markings of ROIs for those images. The output layer estimates the coordinates of the vertices of a polygonal region. The second architecture uses a network pre-trained on a large dataset of the same image types for learning feature representations of the findings of interest. We show that for a variety of findings from chest X-ray images, both proposed architectures learn to estimate the ROI, as validated by clinical annotations. There is a clear advantage obtained from the architecture with pre-trained imaging network. The centroids of the ROIs marked by this network were on average at a distance equivalent to 5.1% of the image width from the centroids of the ground truth ROIs.

Ken C. L. Wong, Mehdi Moradi, Hui Tang et al.

With the introduction of fully convolutional neural networks, deep learning has raised the benchmark for medical image segmentation on both speed and accuracy, and different networks have been proposed for 2D and 3D segmentation with promising results. Nevertheless, most networks only handle relatively small numbers of labels (<10), and there are very limited works on handling highly unbalanced object sizes especially in 3D segmentation. In this paper, we propose a network architecture and the corresponding loss function which improve segmentation of very small structures. By combining skip connections and deep supervision with respect to the computational feasibility of 3D segmentation, we propose a fast converging and computationally efficient network architecture for accurate segmentation. Furthermore, inspired by the concept of focal loss, we propose an exponential logarithmic loss which balances the labels not only by their relative sizes but also by their segmentation difficulties. We achieve an average Dice coefficient of 82% on brain segmentation with 20 labels, with the ratio of the smallest to largest object sizes as 0.14%. Less than 100 epochs are required to reach such accuracy, and segmenting a 128x128x128 volume only takes around 0.4 s.

Ken C. L. Wong, Tanveer Syeda-Mahmood, Mehdi Moradi

Deep learning has shown promising results in medical image analysis, however, the lack of very large annotated datasets confines its full potential. Although transfer learning with ImageNet pre-trained classification models can alleviate the problem, constrained image sizes and model complexities can lead to unnecessary increase in computational cost and decrease in performance. As many common morphological features are usually shared by different classification tasks of an organ, it is greatly beneficial if we can extract such features to improve classification with limited samples. Therefore, inspired by the idea of curriculum learning, we propose a strategy for building medical image classifiers using features from segmentation networks. By using a segmentation network pre-trained on similar data as the classification task, the machine can first learn the simpler shape and structural concepts before tackling the actual classification problem which usually involves more complicated concepts. Using our proposed framework on a 3D three-class brain tumor type classification problem, we achieved 82% accuracy on 191 testing samples with 91 training samples. When applying to a 2D nine-class cardiac semantic level classification problem, we achieved 86% accuracy on 263 testing samples with 108 training samples. Comparisons with ImageNet pre-trained classifiers and classifiers trained from scratch are presented.

Ken C. L. Wong, Alexandros Karargyris, Tanveer Syeda-Mahmood et al.

Although deep learning can provide promising results in medical image analysis, the lack of very large annotated datasets confines its full potential. Furthermore, limited positive samples also create unbalanced datasets which limit the true positive rates of trained models. As unbalanced datasets are mostly unavoidable, it is greatly beneficial if we can extract useful knowledge from negative samples to improve classification accuracy on limited positive samples. To this end, we propose a new strategy for building medical image analysis pipelines that target disease detection. We train a discriminative segmentation model only on normal images to provide a source of knowledge to be transferred to a disease detection classifier. We show that using the feature maps of a trained segmentation network, deviations from normal anatomy can be learned by a two-class classification network on an extremely unbalanced training dataset with as little as one positive for 17 negative samples. We demonstrate that even though the segmentation network is only trained on normal cardiac computed tomography images, the resulting feature maps can be used to detect pericardial effusion and cardiac septal defects with two-class convolutional classification networks.