Oral epithelial dysplasia (OED) is a premalignant histopathological diagnosis given to lesions of the oral cavity. Its grading suffers from significant inter-/intra- observer variability, and does not reliably predict malignancy progression, potentially leading to suboptimal treatment decisions. To address this, we developed a novel artificial intelligence algorithm that can assign an Oral Malignant Transformation (OMT) risk score, based on histological patterns in the in Haematoxylin and Eosin stained whole slide images, to quantify the risk of OED progression. The algorithm is based on the detection and segmentation of nuclei within (and around) the epithelium using an in-house segmentation model. We then employed a shallow neural network fed with interpretable morphological/spatial features, emulating histological markers. We conducted internal cross-validation on our development cohort (Sheffield; n = 193 cases) followed by independent validation on two external cohorts (Birmingham and Belfast; n = 92 cases). The proposed OMTscore yields an AUROC = 0.74 in predicting whether an OED progresses to malignancy or not. Survival analyses showed the prognostic value of our OMTscore for predicting malignancy transformation, when compared to the manually-assigned WHO and binary grades. Analysis of the correctly predicted cases elucidated the presence of peri-epithelial and epithelium-infiltrating lymphocytes in the most predictive patches of cases that transformed (p < 0.0001). This is the first study to propose a completely automated algorithm for predicting OED transformation based on interpretable nuclear features, whilst being validated on external datasets. The algorithm shows better-than-human-level performance for prediction of OED malignant transformation and offers a promising solution to the challenges of grading OED in routine clinical practice.
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.
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.
Since the introduction of digital and computational pathology as a field, one of the major problems in the clinical application of algorithms has been the struggle to generalize well to examples outside the distribution of the training data. Existing work to address this in both pathology and natural images has focused almost exclusively on classification tasks. We explore and evaluate the robustness of the 7 best performing nuclear segmentation and classification models from the largest computational pathology challenge for this problem to date, the CoNIC challenge. We demonstrate that existing state-of-the-art (SoTA) models are robust towards compression artifacts but suffer substantial performance reduction when subjected to shifts in the color domain. We find that using stain normalization to address the domain shift problem can be detrimental to the model performance. On the other hand, neural style transfer is more consistent in improving test performance when presented with large color variations in the wild.
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.
The appearance of histopathology images depends on tissue type, staining and digitization procedure. These vary from source to source and are the potential causes for domain-shift problems. Owing to this problem, despite the great success of deep learning models in computational pathology, a model trained on a specific domain may still perform sub-optimally when we apply them to another domain. To overcome this, we propose a new augmentation called PatchShuffling and a novel self-supervised contrastive learning framework named IMPaSh for pre-training deep learning models. Using these, we obtained a ResNet50 encoder that can extract image representation resistant to domain-shift. We compared our derived representation against those acquired based on other domain-generalization techniques by using them for the cross-domain classification of colorectal tissue images. We show that the proposed method outperforms other traditional histology domain-adaptation and state-of-the-art self-supervised learning methods. Code is available at: https://github.com/trinhvg/IMPash .
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.
The density of mitotic figures within tumor tissue is known to be highly correlated with tumor proliferation and thus is an important marker in tumor grading. Recognition of mitotic figures by pathologists is known to be subject to a strong inter-rater bias, which limits the prognostic value. State-of-the-art deep learning methods can support the expert in this assessment but are known to strongly deteriorate when applied in a different clinical environment than was used for training. One decisive component in the underlying domain shift has been identified as the variability caused by using different whole slide scanners. The goal of the MICCAI MIDOG 2021 challenge has been to propose and evaluate methods that counter this domain shift and derive scanner-agnostic mitosis detection algorithms. The challenge used a training set of 200 cases, split across four scanning systems. As a test set, an additional 100 cases split across four scanning systems, including two previously unseen scanners, were given. The best approaches performed on an expert level, with the winning algorithm yielding an F_1 score of 0.748 (CI95: 0.704-0.781). In this paper, we evaluate and compare the approaches that were submitted to the challenge and identify methodological factors contributing to better performance.
The recent surge in performance for image analysis of digitised pathology slides can largely be attributed to the advance of deep learning. Deep models can be used to initially localise various structures in the tissue and hence facilitate the extraction of interpretable features for biomarker discovery. However, these models are typically trained for a single task and therefore scale poorly as we wish to adapt the model for an increasing number of different tasks. Also, supervised deep learning models are very data hungry and therefore rely on large amounts of training data to perform well. In this paper we present a multi-task learning approach for segmentation and classification of nuclei, glands, lumen and different tissue regions that leverages data from multiple independent data sources. While ensuring that our tasks are aligned by the same tissue type and resolution, we enable simultaneous prediction with a single network. As a result of feature sharing, we also show that the learned representation can be used to improve downstream tasks, including nuclear classification and signet ring cell detection. As part of this work, we use a large dataset consisting of over 600K objects for segmentation and 440K patches for classification and make the data publicly available. We use our approach to process the colorectal subset of TCGA, consisting of 599 whole-slide images, to localise 377 million, 900K and 2.1 million nuclei, glands and lumen respectively. We make this resource available to remove a major barrier in the development of explainable models for computational pathology.
Nuclear segmentation, classification and quantification within Haematoxylin & Eosin stained histology images enables the extraction of interpretable cell-based features that can be used in downstream explainable models in computational pathology (CPath). However, automatic recognition of different nuclei is faced with a major challenge in that there are several different types of nuclei, some of them exhibiting large intra-class variability. To help drive forward research and innovation for automatic nuclei recognition in CPath, we organise the Colon Nuclei Identification and Counting (CoNIC) Challenge. The challenge encourages researchers to develop algorithms that perform segmentation, classification and counting of nuclei within the current largest known publicly available nuclei-level dataset in CPath, containing around half a million labelled nuclei. Therefore, the CoNIC challenge utilises over 10 times the number of nuclei as the previous largest challenge dataset for nuclei recognition. It is important for algorithms to be robust to input variation if we wish to deploy them in a clinical setting. Therefore, as part of this challenge we will also test the sensitivity of each submitted algorithm to certain input variations.