Advances in deep learning (DL) have shown great promise in revolutionizing healthcare, notwithstanding their success hinging on the availability of centralized large and diverse data. Such centralization is challenging because of numerous concerns relating to privacy, data-ownership, intellectual property, and compliance with varying regulatory policies. Federated learning (FL), offers a new decentralized paradigm to train DL models in healthcare. In this study, we evaluate the effect of FL in developing DL models for the analysis of digitized tissue sections, specifically whole slide images (WSIs). A classification application was considered as the example use case, to quantify the distribution of Tumor Infiltrating Lymphocytes (TILs), which are a critical biomarker in cancer research, providing valuable insights into patient outcomes. We trained a VGG classification model using 50 × 50 micron patches extracted from the WSIs with their associated TIL/nonTIL label. We simulated a FL environment, where different cancer types are included across each collaborating node. Our results show that the model trained with the federated training approach achieves similar performance, both quantitatively and qualitatively, to that of a model trained with all the training data pooled at a centralized location. Our study shows that FL has tremendous potential for enabling the development of more robust and accurate models for histopathology image analysis without having to collect large and diverse training data at a single location. Particularly for TILs, our FL approach yields a single DL model trained across numerous anatomical sites and able to robustly generalize to unseen cancer types.

MOTIVATION: Software is vital for the advancement of biology and medicine. Impact evaluations of scientific software have primarily emphasized traditional citation metrics of associated papers, despite these metrics inadequately capturing the dynamic picture of impact and despite challenges with improper citation. RESULTS: To understand how software developers evaluate their tools, we conducted a survey of participants in the Informatics Technology for Cancer Research (ITCR) program funded by the National Cancer Institute (NCI). We found that although developers realize the value of more extensive metric collection, they find a lack of funding and time hindering. We also investigated software among this community for how often infrastructure that supports more nontraditional metrics were implemented and how this impacted rates of papers describing usage of the software. We found that infrastructure such as social media presence, more in-depth documentation, the presence of software health metrics, and clear information on how to contact developers seemed to be associated with increased mention rates. Analysing more diverse metrics can enable developers to better understand user engagement, justify continued funding, identify novel use cases, pinpoint improvement areas, and ultimately amplify their software's impact. Challenges are associated, including distorted or misleading metrics, as well as ethical and security concerns. More attention to nuances involved in capturing impact across the spectrum of biomedical software is needed. For funders and developers, we outline guidance based on experience from our community. By considering how we evaluate software, we can empower developers to create tools that more effectively accelerate biological and medical research progress. AVAILABILITY AND IMPLEMENTATION: More information about the analysis, as well as access to data and code is available at https://github.com/fhdsl/ITCR_Metrics_manuscript_website.

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.

Domain Adaptation (DA) has recently been of strong interest in the medical imaging community. While a large variety of DA techniques have been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality Domain Adaptation. The goal of the challenge is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are commonly performed using contrast-enhanced T1 (ceT1) MR imaging. However, there is growing interest in using non-contrast imaging sequences such as high-resolution T2 (hrT2) imaging. For this reason, we established an unsupervised cross-modality segmentation benchmark. The training dataset provides annotated ceT1 scans (N=105) and unpaired non-annotated hrT2 scans (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 scans as provided in the testing set (N=137). This problem is particularly challenging given the large intensity distribution gap across the modalities and the small volume of the structures. A total of 55 teams from 16 countries submitted predictions to the validation leaderboard. Among them, 16 teams from 9 different countries submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice score — VS: 88.4%; Cochleas: 85.7%) and close to full supervision (median Dice score — VS: 92.5%; Cochleas: 87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image.

Automatic Non-rigid Histological Image Registration (ANHIR) challenge was organized to compare the performance of image registration algorithms on several kinds of microscopy histology images in a fair and independent manner. We have assembled 8 datasets, containing 355 images with 18 different stains, resulting in 481 image pairs to be registered. Registration accuracy was evaluated using manually placed landmarks. In total, 256 teams registered for the challenge, 10 submitted the results, and 6 participated in the workshop. Here, we present the results of 7 well-performing methods from the challenge together with 6 well-known existing methods. The best methods used coarse but robust initial alignment, followed by non-rigid registration, used multiresolution, and were carefully tuned for the data at hand. They outperformed off-the-shelf methods, mostly by being more robust. The best methods could successfully register over 98% of all landmarks and their mean landmark registration accuracy (TRE) was 0.44% of the image diagonal. The challenge remains open to submissions and all images are available for download.

The problem of automatically segmenting images into different components of interest, and then tracking such components through a sequence of frames in a video, is relevant to many applications of video analysis in Intelligent Environments. Several video capture technologies preprocess the image frames, by adding false-colour, in order to improve the contrast for human viewers. However, such false-colouring can make automatic segmentation and object tracking from such videos much more difficult. In this paper, several intelligent dynamic approaches to these problems are proposed and evaluated, in the context of locating, segmenting and tracking salient regions in an example video dataset.