Sebastián Wolf

Benjamin Huber, Reinhold Schneider, Sebastian Wolf

The hierarchical SVD provides a quasi-best low rank approximation of high dimensional data in the hierarchical Tucker framework. Similar to the SVD for matrices, it provides a fundamental but expensive tool for tensor computations. In the present work we examine generalizations of randomized matrix decomposition methods to higher order tensors in the framework of the hierarchical tensors representation. In particular we present and analyze a randomized algorithm for the calculation of the hierarchical SVD (HSVD) for the tensor train (TT) format.

Negin Ghamsarian, Javier Gamazo Tejero, Pablo Márquez Neila et al.

Models capable of leveraging unlabelled data are crucial in overcoming large distribution gaps between the acquired datasets across different imaging devices and configurations. In this regard, self-training techniques based on pseudo-labeling have been shown to be highly effective for semi-supervised domain adaptation. However, the unreliability of pseudo labels can hinder the capability of self-training techniques to induce abstract representation from the unlabeled target dataset, especially in the case of large distribution gaps. Since the neural network performance should be invariant to image transformations, we look to this fact to identify uncertain pseudo labels. Indeed, we argue that transformation invariant detections can provide more reasonable approximations of ground truth. Accordingly, we propose a semi-supervised learning strategy for domain adaptation termed transformation-invariant self-training (TI-ST). The proposed method assesses pixel-wise pseudo-labels' reliability and filters out unreliable detections during self-training. We perform comprehensive evaluations for domain adaptation using three different modalities of medical images, two different network architectures, and several alternative state-of-the-art domain adaptation methods. Experimental results confirm the superiority of our proposed method in mitigating the lack of target domain annotation and boosting segmentation performance in the target domain.

Javier Gamazo Tejero, Martin S. Zinkernagel, Sebastian Wolf et al.

Annotating new datasets for machine learning tasks is tedious, time-consuming, and costly. For segmentation applications, the burden is particularly high as manual delineations of relevant image content are often extremely expensive or can only be done by experts with domain-specific knowledge. Thanks to developments in transfer learning and training with weak supervision, segmentation models can now also greatly benefit from annotations of different kinds. However, for any new domain application looking to use weak supervision, the dataset builder still needs to define a strategy to distribute full segmentation and other weak annotations. Doing so is challenging, however, as it is a priori unknown how to distribute an annotation budget for a given new dataset. To this end, we propose a novel approach to determine annotation strategies for segmentation datasets, whereby estimating what proportion of segmentation and classification annotations should be collected given a fixed budget. To do so, our method sequentially determines proportions of segmentation and classification annotations to collect for budget-fractions by modeling the expected improvement of the final segmentation model. We show in our experiments that our approach yields annotations that perform very close to the optimal for a number of different annotation budgets and datasets.

Theodoros Pissas, Pablo Márquez-Neila, Sebastian Wolf et al.

This work explores the effectiveness of masked image modelling for learning representations of retinal OCT images. To this end, we leverage Masked Autoencoders (MAE), a simple and scalable method for self-supervised learning, to obtain a powerful and general representation for OCT images by training on 700K OCT images from 41K patients collected under real world clinical settings. We also provide the first extensive evaluation for a model of OCT on a challenging battery of 6 downstream tasks. Our model achieves strong performance when fully finetuned but can also serve as a versatile frozen feature extractor for many tasks using lightweight adapters. Furthermore, we propose an extension of the MAE pretraining to fuse OCT with an auxiliary modality, namely, IR fundus images and learn a joint model for both. We demonstrate our approach improves performance on a multimodal downstream application. Our experiments utilize most publicly available OCT datasets, thus enabling future comparisons. Our code and model weights are publicly available https://github.com/TheoPis/MIM_OCT.

Negin Ghamsarian, Yosuf El-Shabrawi, Sahar Nasirihaghighi et al.

In recent years, the landscape of computer-assisted interventions and post-operative surgical video analysis has been dramatically reshaped by deep-learning techniques, resulting in significant advancements in surgeons' skills, operation room management, and overall surgical outcomes. However, the progression of deep-learning-powered surgical technologies is profoundly reliant on large-scale datasets and annotations. Particularly, surgical scene understanding and phase recognition stand as pivotal pillars within the realm of computer-assisted surgery and post-operative assessment of cataract surgery videos. In this context, we present the largest cataract surgery video dataset that addresses diverse requisites for constructing computerized surgical workflow analysis and detecting post-operative irregularities in cataract surgery. We validate the quality of annotations by benchmarking the performance of several state-of-the-art neural network architectures for phase recognition and surgical scene segmentation. Besides, we initiate the research on domain adaptation for instrument segmentation in cataract surgery by evaluating cross-domain instrument segmentation performance in cataract surgery videos. The dataset and annotations will be publicly available upon acceptance of the paper.

Negin Ghamsarian, Sebastian Wolf, Martin Zinkernagel et al.

Semantic Segmentation plays a pivotal role in many applications related to medical image and video analysis. However, designing a neural network architecture for medical image and surgical video segmentation is challenging due to the diverse features of relevant classes, including heterogeneity, deformability, transparency, blunt boundaries, and various distortions. We propose a network architecture, DeepPyramid+, which addresses diverse challenges encountered in medical image and surgical video segmentation. The proposed DeepPyramid+ incorporates two major modules, namely "Pyramid View Fusion" (PVF) and "Deformable Pyramid Reception," (DPR), to address the outlined challenges. PVF replicates a deduction process within the neural network, aligning with the human visual system, thereby enhancing the representation of relative information at each pixel position. Complementarily, DPR introduces shape- and scale-adaptive feature extraction techniques using dilated deformable convolutions, enhancing accuracy and robustness in handling heterogeneous classes and deformable shapes. Extensive experiments conducted on diverse datasets, including endometriosis videos, MRI images, OCT scans, and cataract and laparoscopy videos, demonstrate the effectiveness of DeepPyramid+ in handling various challenges such as shape and scale variation, reflection, and blur degradation. DeepPyramid+ demonstrates significant improvements in segmentation performance, achieving up to a 3.65% increase in Dice coefficient for intra-domain segmentation and up to a 17% increase in Dice coefficient for cross-domain segmentation. DeepPyramid+ consistently outperforms state-of-the-art networks across diverse modalities considering different backbone networks, showcasing its versatility.

Andrés Marafioti, Michel Hayoz, Mathias Gallardo et al.

Cataract surgery is a sight saving surgery that is performed over 10 million times each year around the world. With such a large demand, the ability to organize surgical wards and operating rooms efficiently is critical to delivery this therapy in routine clinical care. In this context, estimating the remaining surgical duration (RSD) during procedures is one way to help streamline patient throughput and workflows. To this end, we propose CataNet, a method for cataract surgeries that predicts in real time the RSD jointly with two influential elements: the surgeon's experience, and the current phase of the surgery. We compare CataNet to state-of-the-art RSD estimation methods, showing that it outperforms them even when phase and experience are not considered. We investigate this improvement and show that a significant contributor is the way we integrate the elapsed time into CataNet's feature extractor.

Thomas Kurmann, Pablo Márquez-Neila, Siqing Yu et al.

Optical Coherence Tomography (OCT) is the primary imaging modality for detecting pathological biomarkers associated to retinal diseases such as Age-Related Macular Degeneration. In practice, clinical diagnosis and treatment strategies are closely linked to biomarkers visible in OCT volumes and the ability to identify these plays an important role in the development of ophthalmic pharmaceutical products. In this context, we present a method that automatically predicts the presence of biomarkers in OCT cross-sections by incorporating information from the entire volume. We do so by adding a bidirectional LSTM to fuse the outputs of a Convolutional Neural Network that predicts individual biomarkers. We thus avoid the need to use pixel-wise annotations to train our method, and instead provide fine-grained biomarker information regardless. On a dataset of 416 volumes, we show that our approach imposes coherence between biomarker predictions across volume slices and our predictions are superior to several existing approaches.

Thomas Kurmann, Pablo Marquez Neila, Sebastian Wolf et al.

Multi-label classification (MLC) problems are becoming increasingly popular in the context of medical imaging. This has in part been driven by the fact that acquiring annotations for MLC is far less burdensome than for semantic segmentation and yet provides more expressiveness than multi-class classification. However, to train MLCs, most methods have resorted to similar objective functions as with traditional multi-class classification settings. We show in this work that such approaches are not optimal and instead propose a novel deep MLC classification method in affine subspace. At its core, the method attempts to pull features of class-labels towards different affine subspaces while maximizing the distance between them. We evaluate the method using two MLC medical imaging datasets and show a large performance increase compared to previous multi-label frameworks. This method can be seen as a plug-in replacement loss function and is trainable in an end-to-end fashion.

Thomas Kurmann, Pablo Marquez Neila, Xiaofei Du et al.

Detection of surgical instruments plays a key role in ensuring patient safety in minimally invasive surgery. In this paper, we present a novel method for 2D vision-based recognition and pose estimation of surgical instruments that generalizes to different surgical applications. At its core, we propose a novel scene model in order to simultaneously recognize multiple instruments as well as their parts. We use a Convolutional Neural Network architecture to embody our model and show that the cross-entropy loss is well suited to optimize its parameters which can be trained in an end-to-end fashion. An additional advantage of our approach is that instrument detection at test time is achieved while avoiding the need for scale-dependent sliding window evaluation. This allows our approach to be relatively parameter free at test time and shows good performance for both instrument detection and tracking. We show that our approach surpasses state-of-the-art results on in-vivo retinal microsurgery image data, as well as ex-vivo laparoscopic sequences.

Stefanos Apostolopoulos, Sandro De Zanet, Carlos Ciller et al.

The automatic segmentation of retinal layer structures enables clinically-relevant quantification and monitoring of eye disorders over time in OCT imaging. Eyes with late-stage diseases are particularly challenging to segment, as their shape is highly warped due to pathological biomarkers. In this context, we propose a novel fully Convolutional Neural Network (CNN) architecture which combines dilated residual blocks in an asymmetric U-shape configuration, and can segment multiple layers of highly pathological eyes in one shot. We validate our approach on a dataset of late-stage AMD patients and demonstrate lower computational costs and higher performance compared to other state-of-the-art methods.

Stefanos Apostolopoulos, Carlos Ciller, Sandro I. De Zanet et al.

Optical Coherence Tomography (OCT) provides a unique ability to image the eye retina in 3D at micrometer resolution and gives ophthalmologist the ability to visualize retinal diseases such as Age-Related Macular Degeneration (AMD). While visual inspection of OCT volumes remains the main method for AMD identification, doing so is time consuming as each cross-section within the volume must be inspected individually by the clinician. In much the same way, acquiring ground truth information for each cross-section is expensive and time consuming. This fact heavily limits the ability to acquire large amounts of ground truth, which subsequently impacts the performance of learning-based methods geared at automatic pathology identification. To avoid this burden, we propose a novel strategy for automatic analysis of OCT volumes where only volume labels are needed. That is, we train a classifier in a semi-supervised manner to conduct this task. Our approach uses a novel Convolutional Neural Network (CNN) architecture, that only needs volume-level labels to be trained to automatically asses whether an OCT volume is healthy or contains AMD. Our architecture involves first learning a cross-section pathology classifier using pseudo-labels that could be corrupted and then leverage these towards a more accurate volume-level classification. We then show that our approach provides excellent performances on a publicly available dataset and outperforms a number of existing automatic techniques.