Domain Generalization in Computational Pathology: Survey and Guidelines

Deep learning models have exhibited exceptional effectiveness in Computational Pathology (CPath) by tackling intricate tasks across an array of histology image analysis applications. Nevertheless, the presence of out-of-distribution data (stemming from a multitude of sources such as disparate imaging devices and diverse tissue preparation methods) can cause \emph{domain shift} (DS). DS decreases the generalization of trained models to unseen datasets with slightly different data distributions, prompting the need for innovative \emph{domain generalization} (DG) solutions. Recognizing the potential of DG methods to significantly influence diagnostic and prognostic models in cancer studies and clinical practice, we present this survey along with guidelines on achieving DG in CPath. We rigorously define various DS types, systematically review and categorize existing DG approaches and resources in CPath, and provide insights into their advantages, limitations, and applicability. We also conduct thorough benchmarking experiments with 28 cutting-edge DG algorithms to address a complex DG problem. Our findings suggest that careful experiment design and CPath-specific Stain Augmentation technique can be very effective. However, there is no one-size-fits-all solution for DG in CPath. Therefore, we establish clear guidelines for detecting and managing DS depending on different scenarios. While most of the concepts, guidelines, and recommendations are given for applications in CPath, we believe that they are applicable to most medical image analysis tasks as well.

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.

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.

Stain-Robust Mitotic Figure Detection for MIDOG 2022 Challenge

The detection of mitotic figures from different scanners/sites remains an important topic of research, owing to its potential in assisting clinicians with tumour grading. The MItosis DOmain Generalization (MIDOG) 2022 challenge aims to test the robustness of detection models on unseen data from multiple scanners and tissue types for this task. We present a short summary of the approach employed by the TIA Centre team to address this challenge. Our approach is based on a hybrid detection model, where mitotic candidates are segmented, before being refined by a deep learning classifier. Cross-validation on the training images achieved the F1-score of 0.816 and 0.784 on the preliminary test set, demonstrating the generalizability of our model to unseen data from new scanners.

TIAger: Tumor-Infiltrating Lymphocyte Scoring in Breast Cancer for the TiGER Challenge

The quantification of tumor-infiltrating lymphocytes (TILs) has been shown to be an independent predictor for prognosis of breast cancer patients. Typically, pathologists give an estimate of the proportion of the stromal region that contains TILs to obtain a TILs score. The Tumor InfiltratinG lymphocytes in breast cancER (TiGER) challenge, aims to assess the prognostic significance of computer-generated TILs scores for predicting survival as part of a Cox proportional hazards model. For this challenge, as the TIAger team, we have developed an algorithm to first segment tumor vs. stroma, before localising the tumor bulk region for TILs detection. Finally, we use these outputs to generate a TILs score for each case. On preliminary testing, our approach achieved a tumor-stroma weighted Dice score of 0.791 and a FROC score of 0.572 for lymphocytic detection. For predicting survival, our model achieved a C-index of 0.719. These results achieved first place across the preliminary testing leaderboards of the TiGER challenge.

Cellular Segmentation and Composition in Routine Histology Images using Deep Learning

Identification and quantification of nuclei in colorectal cancer haematoxylin \& eosin (H\&E) stained histology images is crucial to prognosis and patient management. In computational pathology these tasks are referred to as nuclear segmentation, classification and composition and are used to extract meaningful interpretable cytological and architectural features for downstream analysis. The CoNIC challenge poses the task of automated nuclei segmentation, classification and composition into six different types of nuclei from the largest publicly known nuclei dataset - Lizard. In this regard, we have developed pipelines for the prediction of nuclei segmentation using HoVer-Net and ALBRT for cellular composition. On testing on the preliminary test set, HoVer-Net achieved a PQ of 0.58, a PQ+ of 0.58 and finally a mPQ+ of 0.35. For the prediction of cellular composition with ALBRT on the preliminary test set, we achieved an overall $R^2$ score of 0.53, consisting of 0.84 for lymphocytes, 0.70 for epithelial cells, 0.70 for plasma and .060 for eosinophils.

Stain-Robust Mitotic Figure Detection for the Mitosis Domain Generalization Challenge

The detection of mitotic figures from different scanners/sites remains an important topic of research, owing to its potential in assisting clinicians with tumour grading. The MItosis DOmain Generalization (MIDOG) challenge aims to test the robustness of detection models on unseen data from multiple scanners for this task. We present a short summary of the approach employed by the TIA Centre team to address this challenge. Our approach is based on a hybrid detection model, where mitotic candidates are segmented on stain normalised images, before being refined by a deep learning classifier. Cross-validation on the training images achieved the F1-score of 0.786 and 0.765 on the preliminary test set, demonstrating the generalizability of our model to unseen data from new scanners.