ZEAL: Surgical Skill Assessment with Zero-shot Tool Inference Using Unified Foundation Model

Surgical skill assessment is paramount for ensuring patient safety and enhancing surgical outcomes. This study addresses the need for efficient and objective evaluation methods by introducing ZEAL (surgical skill assessment with Zero-shot surgical tool segmentation with a unifiEd foundAtion modeL). ZEAL uses segmentation masks of surgical instruments obtained through a unified foundation model for proficiency assessment. Through zero-shot inference with text prompts, ZEAL predicts segmentation masks, capturing essential features of both instruments and surroundings. Utilizing sparse convolutional neural networks and segmentation masks, ZEAL extracts feature vectors for foreground (instruments) and background. Long Short-Term Memory (LSTM) networks encode temporal dynamics, modeling sequential data and dependencies in surgical videos. Combining LSTM-encoded vectors, ZEAL produces a surgical skill score, offering an objective measure of proficiency. Comparative analysis with conventional methods using open datasets demonstrates ZEAL's superiority, affirming its potential in advancing surgical training and evaluation. This innovative approach to surgical skill assessment addresses challenges in traditional supervised learning techniques, paving the way for enhanced surgical care quality and patient outcomes.

SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge

Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems. Nowadays, learning-based action recognition and segmentation approaches outperform classical methods, relying, however, on large, annotated datasets. Furthermore, action recognition and tool segmentation algorithms are often trained and make predictions in isolation from each other, without exploiting potential cross-task relationships. With the EndoVis 2022 SAR-RARP50 challenge, we release the first multimodal, publicly available, in-vivo, dataset for surgical action recognition and semantic instrumentation segmentation, containing 50 suturing video segments of Robotic Assisted Radical Prostatectomy (RARP). The aim of the challenge is twofold. First, to enable researchers to leverage the scale of the provided dataset and develop robust and highly accurate single-task action recognition and tool segmentation approaches in the surgical domain. Second, to further explore the potential of multitask-based learning approaches and determine their comparative advantage against their single-task counterparts. A total of 12 teams participated in the challenge, contributing 7 action recognition methods, 9 instrument segmentation techniques, and 4 multitask approaches that integrated both action recognition and instrument segmentation.

Domain generalization across tumor types, laboratories, and species -- insights from the 2022 edition of the Mitosis Domain Generalization Challenge

Recognition of mitotic figures in histologic tumor specimens is highly relevant to patient outcome assessment. This task is challenging for algorithms and human experts alike, with deterioration of algorithmic performance under shifts in image representations. Considerable covariate shifts occur when assessment is performed on different tumor types, images are acquired using different digitization devices, or specimens are produced in different laboratories. This observation motivated the inception of the 2022 challenge on MItosis Domain Generalization (MIDOG 2022). The challenge provided annotated histologic tumor images from six different domains and evaluated the algorithmic approaches for mitotic figure detection provided by nine challenge participants on ten independent domains. Ground truth for mitotic figure detection was established in two ways: a three-expert consensus and an independent, immunohistochemistry-assisted set of labels. This work represents an overview of the challenge tasks, the algorithmic strategies employed by the participants, and potential factors contributing to their success. With an $F_1$ score of 0.764 for the top-performing team, we summarize that domain generalization across various tumor domains is possible with today's deep learning-based recognition pipelines. When assessed against the immunohistochemistry-assisted reference standard, all methods resulted in reduced recall scores, but with only minor changes in the order of participants in the ranking.

Synthesizing 3D computed tomography from MRI or CBCT using 2.5D deep neural networks

Deep learning techniques, particularly convolutional neural networks (CNNs), have gained traction for synthetic computed tomography (sCT) generation from Magnetic resonance imaging (MRI), Cone-beam computed tomography (CBCT) and PET. In this report, we introduce a method to syn-thesize CT from MRI or CBCT. Our method is based on multi-slice (2.5D) CNNs. 2.5D CNNs offer distinct advantages over 3D CNNs when dealing with volumetric data. In the experiments, we evaluate the performance of our method for two tasks, MRI-to-sCT and CBCT-to-sCT generation. Target organs for both tasks are brain and pelvis.

The ACROBAT 2022 Challenge: Automatic Registration Of Breast Cancer Tissue

The alignment of tissue between histopathological whole-slide-images (WSI) is crucial for research and clinical applications. Advances in computing, deep learning, and availability of large WSI datasets have revolutionised WSI analysis. Therefore, the current state-of-the-art in WSI registration is unclear. To address this, we conducted the ACROBAT challenge, based on the largest WSI registration dataset to date, including 4,212 WSIs from 1,152 breast cancer patients. The challenge objective was to align WSIs of tissue that was stained with routine diagnostic immunohistochemistry to its H&E-stained counterpart. We compare the performance of eight WSI registration algorithms, including an investigation of the impact of different WSI properties and clinical covariates. We find that conceptually distinct WSI registration methods can lead to highly accurate registration performances and identify covariates that impact performances across methods. These results establish the current state-of-the-art in WSI registration and guide researchers in selecting and developing methods.

Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge

The ability to automatically detect and track surgical instruments in endoscopic videos can enable transformational interventions. Assessing surgical performance and efficiency, identifying skilled tool use and choreography, and planning operational and logistical aspects of OR resources are just a few of the applications that could benefit. Unfortunately, obtaining the annotations needed to train machine learning models to identify and localize surgical tools is a difficult task. Annotating bounding boxes frame-by-frame is tedious and time-consuming, yet large amounts of data with a wide variety of surgical tools and surgeries must be captured for robust training. Moreover, ongoing annotator training is needed to stay up to date with surgical instrument innovation. In robotic-assisted surgery, however, potentially informative data like timestamps of instrument installation and removal can be programmatically harvested. The ability to rely on tool installation data alone would significantly reduce the workload to train robust tool-tracking models. With this motivation in mind we invited the surgical data science community to participate in the challenge, SurgToolLoc 2022. The goal was to leverage tool presence data as weak labels for machine learning models trained to detect tools and localize them in video frames with bounding boxes. We present the results of this challenge along with many of the team's efforts. We conclude by discussing these results in the broader context of machine learning and surgical data science. The training data used for this challenge consisting of 24,695 video clips with tool presence labels is also being released publicly and can be accessed at https://console.cloud.google.com/storage/browser/isi-surgtoolloc-2022.

Why is the winner the best?

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 multi-center 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 postprocessing (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.

CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting

Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome. To drive innovation in this area, we setup a community-wide challenge using the largest available dataset of its kind to assess nuclear segmentation and cellular composition. Our challenge, named CoNIC, stimulated the development of reproducible algorithms for cellular recognition with real-time result inspection on public leaderboards. We conducted an extensive post-challenge analysis based on the top-performing models using 1,658 whole-slide images of colon tissue. With around 700 million detected nuclei per model, associated features were used for dysplasia grading and survival analysis, where we demonstrated that the challenge's improvement over the previous state-of-the-art led to significant boosts in downstream performance. Our findings also suggest that eosinophils and neutrophils play an important role in the tumour microevironment. We release challenge models and WSI-level results to foster the development of further methods for biomarker discovery.

Unsupervised Domain Adaptation for MRI Volume Segmentation and Classification Using Image-to-Image Translation

Unsupervised domain adaptation is a type of domain adaptation and exploits labeled data from the source domain and unlabeled data from the target one. In the Cross-Modality Domain Adaptation for Medical Image Segmenta-tion challenge (crossMoDA2022), contrast enhanced T1 MRI volumes for brain are provided as the source domain data, and high-resolution T2 MRI volumes are provided as the target domain data. The crossMoDA2022 challenge contains two tasks, segmentation of vestibular schwannoma (VS) and cochlea, and clas-sification of VS with Koos grade. In this report, we presented our solution for the crossMoDA2022 challenge. We employ an image-to-image translation method for unsupervised domain adaptation and residual U-Net the segmenta-tion task. We use SVM for the classification task. The experimental results show that the mean DSC and ASSD are 0.614 and 2.936 for the segmentation task and MA-MAE is 0.84 for the classification task.

Automated Lesion Segmentation in Whole-Body FDG-PET/CT with Multi-modality Deep Neural Networks

Recent progress in automated PET/CT lesion segmentation using deep learning methods has demonstrated the feasibility of this task. However, tumor lesion detection and segmentation in whole-body PET/CT is still a chal-lenging task. To promote research on machine learning-based automated tumor lesion segmentation on whole-body FDG-PET/CT data, Automated Lesion Segmentation in Whole-Body FDG-PET/CT (autoPET) challenge is held, and a large, publicly available training dataset is provided. In this report, we present our solution to the autoPET challenge. We employ multi-modal residual U-Net with deep super vision. The experimental results for five preliminary test cases show that Dice score is 0.79 +/- 0.21.