• Demonstration of effectiveness of SSL for surgical computer vision using the largest dataset reported to date. • Strong generalization and robust evaluation are shown across six surgical datasets, four procedures, and three tasks, outperforming current SOTA foundation models. • Providing insights into large-scale SSL for surgical computer vision in terms of scaling, pretraining time, dataset composition, and model architecture. • Release of the models and a curated dataset of 2.1 million surgical video frames, establishing a critical resource for advancing surgical foundation model training Foundation models have revolutionized computer vision by achieving vastly superior performance across diverse tasks through large-scale pretraining on extensive datasets. However, their application in surgical computer vision has been limited. This study addresses this gap by introducing SurgeNetXL, a novel surgical foundation model that sets a new benchmark in surgical computer vision. Trained on the largest reported surgical dataset to date, comprising over 4.7 million video frames, SurgeNetXL achieves consistent top-tier performance across six datasets spanning four surgical procedures and three tasks, including semantic segmentation, surgical phase recognition, and critical view of safety (CVS) classification. Compared with the best-performing surgical foundation model, SurgeNetXL shows mean improvements of 4.0%, 8.9%, and 11.4% for semantic segmentation, phase recognition, and CVS classification, respectively. Additionally, SurgeNetXL outperforms ImageNet1k by 16.1%, 8.0%, and 4.3% for the respective tasks. In addition to advancing model performance, this study provides key insights into scaling pretraining datasets, extending training durations, and optimizing model architectures specifically for surgical computer vision. These findings pave the way for improved generalization and robustness in data-scarce scenarios, offering a comprehensive framework for future research in this domain. All models and a subset of the SurgeNetXL dataset, including over 2 million video frames, are publicly available at: https://github.com/TimJaspers0801/SurgeNet .

Reliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context - such as the current procedural phase - has emerged as a promising strategy to improve robustness and interpretability. To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures. We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding.

Deep learning-based segmentation methods provide an effective and automated way for assessing the structure and function of the heart in cardiac magnetic resonance (CMR) images. However, despite their state-of-the-art performance on images acquired from the same source (same scanner or scanner vendor) as images used during training, their performance degrades significantly on images coming from different domains. A straightforward approach to tackle this issue consists of acquiring large quantities of multi-site and multi-vendor data, which is practically infeasible. Generative adversarial networks (GANs) for image synthesis present a promising solution for tackling data limitations in medical imaging and addressing the generalization capability of segmentation models. In this work, we explore the usability of synthesized short-axis CMR images generated using a segmentation-informed conditional GAN, to improve the robustness of heart cavity segmentation models in a variety of different settings. The GAN is trained on paired real images and corresponding segmentation maps belonging to both the heart and the surrounding tissue, reinforcing the synthesis of semantically-consistent and realistic images. First, we evaluate the segmentation performance of a model trained solely with synthetic data and show that it only slightly underperforms compared to the baseline trained with real data. By further combining real with synthetic data during training, we observe a substantial improvement in segmentation performance (up to 4% and 40% in terms of Dice score and Hausdorff distance) across multiple data-sets collected from various sites and scanner. This is additionally demonstrated across state-of-the-art 2D and 3D segmentation networks, whereby the obtained results demonstrate the potential of the proposed method in tackling the presence of the domain shift in medical data. Finally, we thoroughly analyze the quality of synthetic data and its ability to replace real MR images during training, as well as provide an insight into important aspects of utilizing synthetic images for segmentation.

In recent years, several deep learning models have been proposed to accurately quantify and diagnose cardiac pathologies. These automated tools heavily rely on the accurate segmentation of cardiac structures in MRI images. However, segmentation of the right ventricle is challenging due to its highly complex shape and ill-defined borders. Hence, there is a need for new methods to handle such structure's geometrical and textural complexities, notably in the presence of pathologies such as Dilated Right Ventricle, Tricuspid Regurgitation, Arrhythmogenesis, Tetralogy of Fallot, and Inter-atrial Communication. The last MICCAI challenge on right ventricle segmentation was held in 2012 and included only 48 cases from a single clinical center. As part of the 12th Workshop on Statistical Atlases and Computational Models of the Heart (STACOM 2021), the M&Ms-2 challenge was organized to promote the interest of the research community around right ventricle segmentation in multi-disease, multi-view, and multi-center cardiac MRI. Three hundred sixty CMR cases, including short-axis and long-axis 4-chamber views, were collected from three Spanish hospitals using nine different scanners from three different vendors, and included a diverse set of right and left ventricle pathologies. The solutions provided by the participants show that nnU-Net achieved the best results overall. However, multi-view approaches were able to capture additional information, highlighting the need to integrate multiple cardiac diseases, views, scanners, and acquisition protocols to produce reliable automatic cardiac segmentation algorithms.

One of the limiting factors for the development and adoption of novel deep-learning (DL) based medical image analysis methods is the scarcity of labeled medical images. Medical image simulation and synthesis can provide solutions by generating ample training data with corresponding ground truth labels. Despite recent advances, generated images demonstrate limited realism and diversity. In this work, we develop a flexible framework for simulating cardiac magnetic resonance (MR) images with variable anatomical and imaging characteristics for the purpose of creating a diversified virtual population. We advance previous works on both cardiac MR image simulation and anatomical modeling to increase the realism in terms of both image appearance and underlying anatomy. To diversify the generated images, we define parameters: 1)to alter the anatomy, 2) to assign MR tissue properties to various tissue types, and 3) to manipulate the image contrast via acquisition parameters. The proposed framework is optimized to generate a substantial number of cardiac MR images with ground truth labels suitable for downstream supervised tasks. A database of virtual subjects is simulated and its usefulness for aiding a DL segmentation method is evaluated. Our experiments show that training completely with simulated images can perform comparable with a model trained with real images for heart cavity segmentation in mid-ventricular slices. Moreover, such data can be used in addition to classical augmentation for boosting the performance when training data is limited, particularly by increasing the contrast and anatomical variation, leading to better regularization and generalization. The database is publicly available at https://osf.io/bkzhm/ and the simulation code will be available at https://github.com/sinaamirrajab/CMRI.

The following topics are dealt with: learning (artificial intelligence); feature extraction; image classification; feedforward neural nets; neural nets; convolution; object detection; image segmentation; face recognition; image representation.

One of the most recent advances in navigation systems is incorporating panoramic views. In this paper, we propose a mobile-edge computing (MEC) network architecture for presenting mobile end users with panoramic videos of the trip between two selected map locations with an improved quality of service compared to traditional networks. Our panoramic videos comprise of crowd-sourced recordings of various locations for cost reduction or centrally collected videos for more uniform quality. To synthesise quality panoramic videos of the path, we propose integrating video quality assessment, speed-adaptive frame-rates adjustment, and video segment merging based on the Dijkstra algorithm. We also consider other attributes such as the time and spatial coordinates at which the videos are captured, the overlap of spatial coverage, and the prediction of optimal base station for panoramic video delivery. We utilise a MEC architecture because our application requires a network with high-bandwidth and low-latency, which calls for the integration of technologies at the edge of the network. Part of our algorithm and our video database are replicated and migrated to the edge of mobile networks allowing us to use base stations as more than mere mobile access points.

In this paper, we propose an integrated caregiver-focused framework that aims to provide a health care and a fall detection service for elderly users. The proposed system looks at the responsibility of the elder-care from three different perspectives: maintenance of an accurate and updated health history, prevention of inappropriate dietary options, and detection of major fall accidents. We ensure a timely intervention by capitalizing on smart watches and their ability to notify the caregiver any time and anywhere. The integrated system provides the users with an organized medical journal that gives an insight of their medical status while being able to share it with their doctor Moreover, the system provides a food and nutrition guide that allows the users to evaluate their food intake both quantity and quality wise. Lastly, users can benefit from a fall detection service that uses the sensors available on the commercial smart watches and the cascade feed-forward neural network for classification. The experiments performed result in an accuracy of 93.33% of the proposed system in the classification of fall events.