Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study

Computational pathology: A survey review and the way forward

Computational Pathology (CPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath is to develop infrastructure and workflows of digital diagnostics as an assistive CAD system for clinical pathology, facilitating transformational changes in the diagnosis and treatment of cancer that are mainly address by CPath tools. With evergrowing developments in deep learning and computer vision algorithms, and the ease of the data flow from digital pathology, currently CPath is witnessing a paradigm shift. Despite the sheer volume of engineering and scientific works being introduced for cancer image analysis, there is still a considerable gap of adopting and integrating these algorithms in clinical practice. This raises a significant question regarding the direction and trends that are undertaken in CPath. In this article we provide a comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints. We have catalogued each paper into a model-card by examining the key works and challenges faced to layout the current landscape in CPath. We hope this helps the community to locate relevant works and facilitate understanding of the field's future directions. In a nutshell, we oversee the CPath developments in cycle of stages which are required to be cohesively linked together to address the challenges associated with such multidisciplinary science. We overview this cycle from different perspectives of data-centric, model-centric, and application-centric problems. We finally sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath. For updated information on this survey review paper and accessing to the original model cards repository, please refer to GitHub. Updated version of this draft can also be found from arXiv.

Deep learning application in prediction of cancer molecular alterations based on pathological images: a bibliographic analysis via CiteSpace

BACKGROUND

The advancements in artificial intelligence (AI) technology for image recognition were propelling molecular pathology research into a new era.

OBJECTIVE

To summarize the hot spots and research trends in the field of molecular pathology image recognition.

METHODS

Relevant articles from January 1st, 2010, to August 25th, 2023, were retrieved from the Web of Science Core Collection. Subsequently, CiteSpace was employed for bibliometric and visual analysis, generating diverse network diagrams illustrating keywords, highly cited references, hot topics, and research trends.

RESULTS

A total of 110 relevant articles were extracted from a pool of 10,205 articles. The overall publication count exhibited a rising trend each year. The leading contributors in terms of institutions, countries, and authors were Maastricht University (11 articles), the United States (38 articles), and Kather Jacob Nicholas (9 articles), respectively. Half of the top ten research institutions, based on publication volume, were affiliated with Germany. The most frequently cited article was authored by Nicolas Coudray et al. accumulating 703 citations. The keyword "Deep learning" had the highest frequency in 2019. Notably, the highlighted keywords from 2022 to 2023 included "microsatellite instability", and there were 21 articles focusing on utilizing algorithms to recognize microsatellite instability (MSI) in colorectal cancer (CRC) pathological images.

CONCLUSION

The use of DL is expected to provide a new strategy to effectively solve the current problem of time-consuming and expensive molecular pathology detection. Therefore, further research is needed to address issues, such as data quality and standardization, model interpretability, and resource and infrastructure requirements.

A foundation model for clinical-grade computational pathology and rare cancers detection

The analysis of histopathology images with artificial intelligence aims to enable clinical decision support systems and precision medicine. The success of such applications depends on the ability to model the diverse patterns observed in pathology images. To this end, we present Virchow, the largest foundation model for computational pathology to date. In addition to the evaluation of biomarker prediction and cell identification, we demonstrate that a large foundation model enables pan-cancer detection, achieving 0.95 specimen-level area under the (receiver operating characteristic) curve across nine common and seven rare cancers. Furthermore, we show that with less training data, the pan-cancer detector built on Virchow can achieve similar performance to tissue-specific clinical-grade models in production and outperform them on some rare variants of cancer. Virchow's performance gains highlight the value of a foundation model and open possibilities for many high-impact applications with limited amounts of labeled training data.

Single-cell AI-based detection and prognostic and predictive value of DNA mismatch repair deficiency in colorectal cancer

Testing for DNA mismatch repair deficiency (MMRd) is recommended for all colorectal cancers (CRCs). Automating this would enable precision medicine, particularly if providing information on etiology not captured by deep learning (DL) methods. We present AIMMeR, an AI-based method for determination of mismatch repair (MMR) protein expression at a single-cell level in routine pathology samples. AIMMeR shows an area under the receiver-operator curve (AUROC) of 0.98, and specificity of ≥75% at 98% sensitivity against pathologist ground truth in stage II/III in two trial cohorts, with positive predictive value of ≥98% for the commonest pattern of somatic MMRd. Lower agreement with microsatellite instability (MSI) testing (AUROC 0.86) reflects discordance between MMR and MSI PCR rather than AIMMeR misclassification. Analysis of the SCOT trial confirms MMRd prognostic value in oxaliplatin-treated patients; while MMRd does not predict differential benefit of chemotherapy duration, it correlates with difference in relapse by regimen (PInteraction = 0.04). AIMMeR may help reduce pathologist workload and streamline diagnostics in CRC.

Deep learning-based histological predictions of chromosomal instability in colorectal cancer

Colorectal cancer (CRC) is a lethal malignancy and a leading cause of cancer-related mortality worldwide. Chromosomal instability (CIN) is a key driver of genomic instability in CRC and is characterized by aneuploidy and somatic copy-number alterations. This study aimed to predict CIN in CRC using histological data from whole slide images (WSIs). CRC samples from TCGA were analyzed, with tumor regions segmented into tiles and nuclei for feature extraction using convolutional neural network (CNN) and morphologic analysis. Binary classification models were developed to distinguish high and low aneuploidy scores (AS) based on slide-level features. The analysis included 313 patients with 315 WSIs, resulting in over 350,000 tumor tiles and nearly 2.7 million tumor cell nuclei. The ResNet18-SSL model, pre-trained on histopathological images, demonstrated superior accuracy in tile-based AS prediction, while DenseNet121 excelled in nucleus-based prediction. Combining CNN-based and morphological features enhanced the classification accuracy of nucleus-based predictions. Additionally, significant correlations were observed between morphological features and copy-number signatures. Unsupervised clustering of nuclear features revealed that distinct groups are significantly correlated with CIN and TP53 mutations. This study underscores the potential of histological features from WSIs to predict CIN in CRC samples. Nuclear feature analysis, combined with deep-learning techniques, offers a robust method for CIN prediction, highlighting the importance of further research into the relationships between histological and molecular phenotypes.

Exploring the interplay between colorectal cancer subtypes genomic variants and cellular morphology: A deep-learning approach

Molecular subtypes of colorectal cancer (CRC) significantly influence treatment decisions. While convolutional neural networks (CNNs) have recently been introduced for automated CRC subtype identification using H&E stained histopathological images, the correlation between CRC subtype genomic variants and their corresponding cellular morphology expressed by their imaging phenotypes is yet to be fully explored. The goal of this study was to determine such correlations by incorporating genomic variants in CNN models for CRC subtype classification from H&E images. We utilized the publicly available TCGA-CRC-DX dataset, which comprises whole slide images from 360 CRC-diagnosed patients (260 for training and 100 for testing). This dataset also provides information on CRC subtype classifications and genomic variations. We trained CNN models for CRC subtype classification that account for potential correlation between genomic variations within CRC subtypes and their corresponding cellular morphology patterns. We assessed the interplay between CRC subtypes' genomic variations and cellular morphology patterns by evaluating the CRC subtype classification accuracy of the different models in a stratified 5-fold cross-validation experimental setup using the area under the ROC curve (AUROC) and average precision (AP) as the performance metrics. The CNN models that account for potential correlation between genomic variations within CRC subtypes and their cellular morphology pattern achieved superior accuracy compared to the baseline CNN classification model that does not account for genomic variations when using either single-nucleotide-polymorphism (SNP) molecular features (AUROC: 0.824±0.02 vs. 0.761±0.04, p<0.05, AP: 0.652±0.06 vs. 0.58±0.08) or CpG-Island methylation phenotype (CIMP) molecular features (AUROC: 0.834±0.01 vs. 0.787±0.03, p<0.05, AP: 0.687±0.02 vs. 0.64±0.05). Combining the CNN models account for variations in CIMP and SNP further improved classification accuracy (AUROC: 0.847±0.01 vs. 0.787±0.03, p = 0.01, AP: 0.68±0.02 vs. 0.64±0.05). The improved accuracy of CNN models for CRC subtype classification that account for potential correlation between genomic variations within CRC subtypes and their corresponding cellular morphology as expressed by H&E imaging phenotypes may elucidate the biological cues impacting cancer histopathological imaging phenotypes. Moreover, considering CRC subtypes genomic variations has the potential to improve the accuracy of deep-learning models in discerning cancer subtype from histopathological imaging data.

Ouroboros: cross-linking protein expression perturbations and cancer histology imaging with generative-predictive modeling

SUMMARY

Imagine if we could simultaneously predict spatial protein expression in tissues from their routine Hematoxylin and Eosin (H&E) stained images, and create tissue images given protein expression profiles thus enabling virtual simulations of how protein expression alterations impact histology in complex diseases like cancer. Such an approach could lead to more informed diagnostic and therapeutic decisions for precision medicine at lower costs and shorter turnaround times, more detailed insights into underlying disease pathology as well as improvement in predictive and generative performance. In this study, we investigate the intricate correlation between protein expressions obtained from Hyperion mass cytometry and histopathological microstructures in conventional H&E stained glioblastoma (GBM) samples, unveiling morphological patterns and cellular-level spatial alterations associated with protein expression changes. To model these complex relationships, we propose a novel generative-predictive framework called Ouroboros for producing H&E images from protein expressions and simultaneously predicting protein expressions from H&E images. Our comprehensive sample-independent validation over 9920 tissue spots from 4 GBM samples encompassing visual image analysis, quantitative analysis, subspace alignment and perturbation experiments shows that the proposed generative-predictive approach offers significant improvements in predicting protein expression from images in comparison to baseline methods as well as accurate generation of virtual GBM sample images. This proof of concept study can contribute to advancing our understanding of histological responses to protein expression perturbations and lays the foundations for further developments in this area.

AVAILABILITY AND IMPLEMENTATION

Implementation and associated data for the proposed approach are available at the URL: https://github.com/Srijay/Ouroboros.

A Deep Learning Approach for the Identification of the Molecular Subtypes of Pancreatic Ductal Adenocarcinoma Based on Whole Slide Pathology Images

Delayed diagnosis and treatment resistance make pancreatic ductal adenocarcinoma (PDAC) mortality rates high. Identifying molecular subtypes can improve treatment, but current methods are costly and time-consuming. In this study, deep learning models were used to identify histologic features that classify PDAC molecular subtypes based on routine hematoxylin-eosin-stained histopathologic slides. A total of 97 histopathology slides associated with resectable PDAC from The Cancer Genome Atlas project were used to train a deep learning model and tested the performance on 44 needle biopsy material (110 slides) from a local annotated patient cohort. The model achieved balanced accuracy of 96.19% and 83.03% in identifying the classical and basal subtypes of PDAC in The Cancer Genome Atlas and the local cohort, respectively. This study provides a promising method to cost-effectively and rapidly classifying PDAC molecular subtypes based on routine hematoxylin-eosin-stained slides, potentially leading to more effective clinical management of this disease.

Preoperative prediction of rectal Cancer staging combining MRI deep transfer learning, radiomics features, and clinical factors: accurate differentiation from stage T2 to T3

BACKGROUND

This study evaluates the efficacy of integrating MRI deep transfer learning, radiomic signatures, and clinical variables to accurately preoperatively differentiate between stage T2 and T3 rectal cancer.

METHODS

We included 361 patients with pathologically confirmed stage T2 or T3 rectal cancer, divided into a training set (252 patients) and a test set (109 patients) at a 7:3 ratio. The study utilized features derived from deep transfer learning and radiomics, with Spearman rank correlation and the Least Absolute Shrinkage and Selection Operator (LASSO) regression techniques to reduce feature redundancy. Predictive models were developed using Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM), selecting the best-performing model for a comprehensive predictive framework incorporating clinical data.

RESULTS

After removing redundant features, 24 key features were identified. In the training set, the area under the curve (AUC)values for LR, RF, DT, and SVM were 0.867, 0.834, 0.900, and 0.944, respectively; in the test set, they were 0.847, 0.803, 0.842, and 0.910, respectively. The combined model, using SVM and clinical variables, achieved AUCs of 0.946 in the trainingset and 0.920 in the test set.

CONCLUSION

The study confirms the utility of a combined model of MRI deep transfer learning, radiomic features, and clinical factors for preoperative classification of stage T2 vs. T3 rectal cancer, offering significant technological support for precise diagnosis and potential clinical application.

Artificial Intelligence Models for the Detection of Microsatellite Instability from Whole-Slide Imaging of Colorectal Cancer

With the advent of whole-slide imaging (WSI), a technology that can digitally scan whole slides in high resolution, pathology is undergoing a digital revolution. Detecting microsatellite instability (MSI) in colorectal cancer is crucial for proper treatment, as it identifies patients responsible for immunotherapy. Even though universal testing for MSI is recommended, particularly in patients affected by colorectal cancer (CRC), many patients remain untested, and they reside mainly in low-income countries. A critical need exists for accessible, low-cost tools to perform MSI pre-screening. Here, the potential predictive role of the most relevant artificial intelligence-driven models in predicting microsatellite instability directly from histology alone is discussed, focusing on CRC. The role of deep learning (DL) models in identifying the MSI status is here analyzed in the most relevant studies reporting the development of algorithms trained to this end. The most important performance and the most relevant deficiencies are discussed for every AI method. The models proposed for algorithm sharing among multiple research and clinical centers, including federal learning (FL) and swarm learning (SL), are reported. According to all the studies reported here, AI models are valuable tools for predicting MSI status on WSI alone in CRC. The use of digitized H&E-stained sections and a trained algorithm allow the extraction of relevant molecular information, such as MSI status, in a short time and at a low cost. The possible advantages related to introducing DL methods in routine surgical pathology are underlined here, and the acceleration of the digital transformation of pathology departments and services is recommended.

KRASFormer: a fully vision transformer-based framework for predictingKRASgene mutations in histopathological images of colorectal cancer

Detecting the Kirsten Rat Sarcoma Virus (KRAS) gene mutation is significant for colorectal cancer (CRC) patients. TheKRASgene encodes a protein involved in the epidermal growth factor receptor (EGFR) signaling pathway, and mutations in this gene can negatively impact the use of monoclonal antibodies in anti-EGFR therapy and affect treatment decisions. Currently, commonly used methods like next-generation sequencing (NGS) identifyKRASmutations but are expensive, time-consuming, and may not be suitable for every cancer patient sample. To address these challenges, we have developedKRASFormer, a novel framework that predictsKRASgene mutations from Haematoxylin and Eosin (H & E) stained WSIs that are widely available for most CRC patients.KRASFormerconsists of two stages: the first stage filters out non-tumor regions and selects only tumour cells using a quality screening mechanism, and the second stage predicts theKRASgene either wildtype' or mutant' using a Vision Transformer-based XCiT method. The XCiT employs cross-covariance attention to capture clinically meaningful long-range representations of textural patterns in tumour tissue andKRASmutant cells. We evaluated the performance of the first stage using an independent CRC-5000 dataset, and the second stage included both The Cancer Genome Atlas colon and rectal cancer (TCGA-CRC-DX) and in-house cohorts. The results of our experiments showed that the XCiT outperformed existing state-of-the-art methods, achieving AUCs for ROC curves of 0.691 and 0.653 on TCGA-CRC-DX and in-house datasets, respectively. Our findings emphasize three key consequences: the potential of using H & E-stained tissue slide images for predictingKRASgene mutations as a cost-effective and time-efficient means for guiding treatment choice with CRC patients; the increase in performance metrics of a Transformer-based model; and the value of the collaboration between pathologists and data scientists in deriving a morphologically meaningful model.

A fully automated and explainable algorithm for predicting malignant transformation in oral epithelial dysplasia

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 an artificial intelligence (AI) algorithm, that assigns an Oral Malignant Transformation (OMT) risk score based on the Haematoxylin and Eosin (H&E) stained whole slide images (WSIs). Our AI pipeline leverages an in-house segmentation model to detect and segment both nuclei and epithelium. Subsequently, a shallow neural network utilises interpretable morphological and spatial features, emulating histological markers, to predict progression. We conducted internal cross-validation on our development cohort (Sheffield; n = 193 cases) and independent validation on two external cohorts (Birmingham and Belfast; n = 89 cases). On external validation, the proposed OMTscore achieved an AUROC = 0.75 (Recall = 0.92) in predicting OED progression, outperforming other grading systems (Binary: AUROC = 0.72, Recall = 0.85). Survival analyses showed the prognostic value of our OMTscore (C-index = 0.60, p = 0.02), compared to WHO (C-index = 0.64, p = 0.003) and binary grades (C-index = 0.65, p < 0.001). Nuclear analyses elucidated the presence of peri-epithelial and intra-epithelial lymphocytes in highly predictive patches of transforming cases (p < 0.001). This is the first study to propose a completely automated, explainable, and externally validated algorithm for predicting OED transformation. Our algorithm shows comparable-to-human-level performance, offering a promising solution to the challenges of grading OED in routine clinical practice.

Development of high-quality artificial intelligence for computer-aided diagnosis in determining subtypes of colorectal cancer

BACKGROUND AND AIM

There are no previous studies in which computer-aided diagnosis (CAD) diagnosed colorectal cancer (CRC) subtypes correctly. In this study, we developed an original CAD for the diagnosis of CRC subtypes.

METHODS

Pretraining for the CAD based on ResNet was performed using ImageNet and five open histopathological pretraining image datasets (HiPreD) containing 3 million images. In addition, sparse attention was introduced to improve the CAD compared to other attention networks. One thousand and seventy-two histopathological images from 29 early CRC cases at Kyoto Prefectural University of Medicine from 2019 to 2022 were collected (857 images for training and validation, 215 images for test). All images were annotated by a qualified histopathologist for segmentation of normal mucosa, adenoma, pure well-differentiated adenocarcinoma (PWDA), and moderately/poorly differentiated adenocarcinoma (MPDA). Diagnostic ability including dice sufficient coefficient (DSC) and diagnostic accuracy were evaluated.

RESULTS

Our original CAD, named Colon-seg, with the pretraining of both HiPreD and ImageNET showed a better DSC (88.4%) compared to CAD without both pretraining (76.8%). Regarding the attentional mechanism, Colon-seg with sparse attention showed a better DSC (88.4%) compared to other attentional mechanisms (dual: 79.7%, ECA: 80.7%, shuffle: 84.7%, SK: 86.9%). In addition, the DSC of Colon-seg (88.4%) was better than other types of CADs (TransUNet: 84.7%, MultiResUnet: 86.1%, Unet++: 86.7%). The diagnostic accuracy of Colon-seg for each histopathological type was 94.3% for adenoma, 91.8% for PWDA, and 92.8% for MPDA.

CONCLUSION

A deep learning-based CAD for CRC subtype differentiation was developed with pretraining and fine-tuning of abundant histopathological images.

AI-based histopathology image analysis reveals a distinct subset of endometrial cancers

Endometrial cancer (EC) has four molecular subtypes with strong prognostic value and therapeutic implications. The most common subtype (NSMP; No Specific Molecular Profile) is assigned after exclusion of the defining features of the other three molecular subtypes and includes patients with heterogeneous clinical outcomes. In this study, we employ artificial intelligence (AI)-powered histopathology image analysis to differentiate between p53abn and NSMP EC subtypes and consequently identify a sub-group of NSMP EC patients that has markedly inferior progression-free and disease-specific survival (termed 'p53abn-like NSMP'), in a discovery cohort of 368 patients and two independent validation cohorts of 290 and 614 from other centers. Shallow whole genome sequencing reveals a higher burden of copy number abnormalities in the 'p53abn-like NSMP' group compared to NSMP, suggesting that this group is biologically distinct compared to other NSMP ECs. Our work demonstrates the power of AI to detect prognostically different and otherwise unrecognizable subsets of EC where conventional and standard molecular or pathologic criteria fall short, refining image-based tumor classification. This study's findings are applicable exclusively to females.

Artificial Intelligence in Colorectal Cancer: From Patient Screening over Tailoring Treatment Decisions to Identification of Novel Biomarkers

BACKGROUND

Artificial intelligence (AI) is increasingly entering and transforming not only medical research but also clinical practice. In the last 10 years, new AI methods have enabled computers to perform visual tasks, reaching high performance and thereby potentially supporting and even outperforming human experts. This is in particular relevant for colorectal cancer (CRC), which is the 3rd most common cancer type in general, as along the CRC patient journey many complex visual tasks need to be performed: from endoscopy over imaging to histopathology; the screening, diagnosis, and treatment of CRC involve visual image analysis tasks.

SUMMARY

In all these clinical areas, AI models have shown promising results by supporting physicians, improving accuracy, and providing new biological insights and biomarkers. By predicting prognostic and predictive biomarkers from routine images/slides, AI models could lead to an improved patient stratification for precision oncology approaches in the near future. Moreover, it is conceivable that AI models, in particular together with innovative techniques such as single-cell or spatial profiling, could help identify novel clinically as well as biologically meaningful biomarkers that could pave the way to new therapeutic approaches.

KEY MESSAGES

Here, we give a comprehensive overview of AI in colorectal cancer, describing and discussing these developments as well as the next steps which need to be taken to incorporate AI methods more broadly into the clinical care of CRC.

A Systematic Review of Genetics- and Molecular-Pathway-Based Machine Learning Models for Neurological Disorder Diagnosis

The process of identification and management of neurological disorder conditions faces challenges, prompting the investigation of novel methods in order to improve diagnostic accuracy. In this study, we conducted a systematic literature review to identify the significance of genetics- and molecular-pathway-based machine learning (ML) models in treating neurological disorder conditions. According to the study's objectives, search strategies were developed to extract the research studies using digital libraries. We followed rigorous study selection criteria. A total of 24 studies met the inclusion criteria and were included in the review. We classified the studies based on neurological disorders. The included studies highlighted multiple methodologies and exceptional results in treating neurological disorders. The study findings underscore the potential of the existing models, presenting personalized interventions based on the individual's conditions. The findings offer better-performing approaches that handle genetics and molecular data to generate effective outcomes. Moreover, we discuss the future research directions and challenges, emphasizing the demand for generalizing existing models in real-world clinical settings. This study contributes to advancing knowledge in the field of diagnosis and management of neurological disorders.

A guide to artificial intelligence for cancer researchers

Artificial intelligence (AI) has been commoditized. It has evolved from a specialty resource to a readily accessible tool for cancer researchers. AI-based tools can boost research productivity in daily workflows, but can also extract hidden information from existing data, thereby enabling new scientific discoveries. Building a basic literacy in these tools is useful for every cancer researcher. Researchers with a traditional biological science focus can use AI-based tools through off-the-shelf software, whereas those who are more computationally inclined can develop their own AI-based software pipelines. In this article, we provide a practical guide for non-computational cancer researchers to understand how AI-based tools can benefit them. We convey general principles of AI for applications in image analysis, natural language processing and drug discovery. In addition, we give examples of how non-computational researchers can get started on the journey to productively use AI in their own work.

Deep learning for dual detection of microsatellite instability and POLE mutations in colorectal cancer histopathology

In the spectrum of colorectal tumors, microsatellite-stable (MSS) tumors with DNA polymerase ε (POLE) mutations exhibit a hypermutated profile, holding the potential to respond to immunotherapy similarly to their microsatellite-instable (MSI) counterparts. Yet, due to their rarity and the associated testing costs, systematic screening for these mutations is not commonly pursued. Notably, the histopathological phenotype resulting from POLE mutations is theorized to resemble that of MSI. This resemblance not only could facilitate their detection by a transformer-based Deep Learning (DL) system trained on MSI pathology slides, but also indicates the possibility for MSS patients with POLE mutations to access enhanced treatment options, which might otherwise be overlooked. To harness this potential, we trained a Deep Learning classifier on a large dataset with the ground truth for microsatellite status and subsequently validated its capabilities for MSI and POLE detection across three external cohorts. Our model accurately identified MSI status in both the internal and external resection cohorts using pathology images alone. Notably, with a classification threshold of 0.5, over 75% of POLE driver mutant patients in the external resection cohorts were flagged as "positive" by a DL system trained on MSI status. In a clinical setting, deploying this DL model as a preliminary screening tool could facilitate the efficient identification of clinically relevant MSI and POLE mutations in colorectal tumors, in one go.

Deep learning framework for comprehensive molecular and prognostic stratifications of triple-negative breast cancer

Triple-negative breast cancer (TNBC) is the most challenging breast cancer subtype. Molecular stratification and target therapy bring clinical benefit for TNBC patients, but it is difficult to implement comprehensive molecular testing in clinical practice. Here, using our multi-omics TNBC cohort (N = 425), a deep learning-based framework was devised and validated for comprehensive predictions of molecular features, subtypes and prognosis from pathological whole slide images. The framework first incorporated a neural network to decompose the tissue on WSIs, followed by a second one which was trained based on certain tissue types for predicting different targets. Multi-omics molecular features were analyzed including somatic mutations, copy number alterations, germline mutations, biological pathway activities, metabolomics features and immunotherapy biomarkers. It was shown that the molecular features with therapeutic implications can be predicted including the somatic PIK3CA mutation, germline BRCA2 mutation and PD-L1 protein expression (area under the curve [AUC]: 0.78, 0.79 and 0.74 respectively). The molecular subtypes of TNBC can be identified (AUC: 0.84, 0.85, 0.93 and 0.73 for the basal-like immune-suppressed, immunomodulatory, luminal androgen receptor, and mesenchymal-like subtypes respectively) and their distinctive morphological patterns were revealed, which provided novel insights into the heterogeneity of TNBC. A neural network integrating image features and clinical covariates stratified patients into groups with different survival outcomes (log-rank P < 0.001). Our prediction framework and neural network models were externally validated on the TNBC cases from TCGA (N = 143) and appeared robust to the changes in patient population. For potential clinical translation, we built a novel online platform, where we modularized and deployed our framework along with the validated models. It can realize real-time one-stop prediction for new cases. In summary, using only pathological WSIs, our proposed framework can enable comprehensive stratifications of TNBC patients and provide valuable information for therapeutic decision-making. It had the potential to be clinically implemented and promote the personalized management of TNBC.

Semi-Supervised, Attention-Based Deep Learning for Predicting TMPRSS2:ERG Fusion Status in Prostate Cancer Using Whole Slide Images

IMPLICATIONS

Our study illuminates the potential of deep learning in effectively inferring key prostate cancer genetic alterations from the tissue morphology depicted in routinely available histology slides, offering a cost-effective method that could revolutionize diagnostic strategies in oncology.

Social network analysis of cell networks improves deep learning for prediction of molecular pathways and key mutations in colorectal cancer

Colorectal cancer (CRC) is a primary global health concern, and identifying the molecular pathways, genetic subtypes, and mutations associated with CRC is crucial for precision medicine. However, traditional measurement techniques such as gene sequencing are costly and time-consuming, while most deep learning methods proposed for this task lack interpretability. This study offers a new approach to enhance the state-of-the-art deep learning methods for molecular pathways and key mutation prediction by incorporating cell network information. We build cell graphs with nuclei as nodes and nuclei connections as edges of the network and leverage Social Network Analysis (SNA) measures to extract abstract, perceivable, and interpretable features that explicitly describe the cell network characteristics in an image. Our approach does not rely on precise nuclei segmentation or feature extraction, is computationally efficient, and is easily scalable. In this study, we utilize the TCGA-CRC-DX dataset, comprising 499 patients and 502 diagnostic slides from primary colorectal tumours, sourced from 36 distinct medical centres in the United States. By incorporating the SNA features alongside deep features in two multiple instance learning frameworks, we demonstrate improved performance for chromosomal instability (CIN), hypermutated tumour (HM), TP53 gene, BRAF gene, and Microsatellite instability (MSI) status prediction tasks (2.4%-4% and 7-8.8% improvement in AUROC and AUPRC on average). Additionally, our method achieves outstanding performance on MSI prediction in an external PAIP dataset (99% AUROC and 98% AUPRC), demonstrating its generalizability. Our findings highlight the discrimination power of SNA features and how they can be beneficial to deep learning models' performance and provide insights into the correlation of cell network profiles with molecular pathways and key mutations.

Self-Supervised Learning Reveals Clinically Relevant Histomorphological Patterns for Therapeutic Strategies in Colon Cancer

Self-supervised learning (SSL) automates the extraction and interpretation of histopathology features on unannotated hematoxylin-and-eosin-stained whole-slide images (WSIs). We trained an SSL Barlow Twins-encoder on 435 TCGA colon adenocarcinoma WSIs to extract features from small image patches. Leiden community detection then grouped tiles into histomorphological phenotype clusters (HPCs). HPC reproducibility and predictive ability for overall survival was confirmed in an independent clinical trial cohort (N=1213 WSIs). This unbiased atlas resulted in 47 HPCs displaying unique and sharing clinically significant histomorphological traits, highlighting tissue type, quantity, and architecture, especially in the context of tumor stroma. Through in-depth analysis of these HPCs, including immune landscape and gene set enrichment analysis, and association to clinical outcomes, we shed light on the factors influencing survival and responses to treatments like standard adjuvant chemotherapy and experimental therapies. Further exploration of HPCs may unveil new insights and aid decision-making and personalized treatments for colon cancer patients.

Fully semantic segmentation for rectal cancer based on post-nCRT MRl modality and deep learning framework

PURPOSE

Rectal tumor segmentation on post neoadjuvant chemoradiotherapy (nCRT) magnetic resonance imaging (MRI) has great significance for tumor measurement, radiomics analysis, treatment planning, and operative strategy. In this study, we developed and evaluated segmentation potential exclusively on post-chemoradiation T2-weighted MRI using convolutional neural networks, with the aim of reducing the detection workload for radiologists and clinicians.

METHODS

A total of 372 consecutive patients with LARC were retrospectively enrolled from October 2015 to December 2017. The standard-of-care neoadjuvant process included 22-fraction intensity-modulated radiation therapy and oral capecitabine. Further, 243 patients (3061 slices) were grouped into training and validation datasets with a random 80:20 split, and 41 patients (408 slices) were used as the test dataset. A symmetric eight-layer deep network was developed using the nnU-Net Framework, which outputs the segmentation result with the same size. The trained deep learning (DL) network was examined using fivefold cross-validation and tumor lesions with different TRGs.

RESULTS

At the stage of testing, the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and mean surface distance (MSD) were applied to quantitatively evaluate the performance of generalization. Considering the test dataset (41 patients, 408 slices), the average DSC, HD95, and MSD were 0.700 (95% CI: 0.680-0.720), 17.73 mm (95% CI: 16.08-19.39), and 3.11 mm (95% CI: 2.67-3.56), respectively. Eighty-two percent of the MSD values were less than 5 mm, and fifty-five percent were less than 2 mm (median 1.62 mm, minimum 0.07 mm).

CONCLUSIONS

The experimental results indicated that the constructed pipeline could achieve relatively high accuracy. Future work will focus on assessing the performances with multicentre external validation.

Artificial Intelligence in the Diagnosis of Colorectal Cancer: A Literature Review

BACKGROUND

The aim of this review is to explore the role of artificial intelligence in the diagnosis of colorectal cancer, how it impacts CRC morbidity and mortality, and why its role in clinical medicine is limited.

METHODS

A targeted, non-systematic review of the published literature relating to colorectal cancer diagnosis was performed with PubMed databases that were scouted to help provide a more defined understanding of the recent advances regarding artificial intelligence and their impact on colorectal-related morbidity and mortality. Articles were included if deemed relevant and including information associated with the keywords.

RESULTS

The advancements in artificial intelligence have been significant in facilitating an earlier diagnosis of CRC. In this review, we focused on evaluating genomic biomarkers, the integration of instruments with artificial intelligence, MR and hyperspectral imaging, and the architecture of neural networks. We found that these neural networks seem practical and yield positive results in initial testing. Furthermore, we explored the use of deep-learning-based majority voting methods, such as bag of words and PAHLI, in improving diagnostic accuracy in colorectal cancer detection. Alongside this, the autonomous and expansive learning ability of artificial intelligence, coupled with its ability to extract increasingly complex features from images or videos without human reliance, highlight its impact in the diagnostic sector. Despite this, as most of the research involves a small sample of patients, a diversification of patient data is needed to enhance cohort stratification for a more sensitive and specific neural model. We also examined the successful application of artificial intelligence in predicting microsatellite instability, showcasing its potential in stratifying patients for targeted therapies.

CONCLUSIONS

Since its commencement in colorectal cancer, artificial intelligence has revealed a multitude of functionalities and augmentations in the diagnostic sector of CRC. Given its early implementation, its clinical application remains a fair way away, but with steady research dedicated to improving neural architecture and expanding its applicational range, there is hope that these advanced neural software could directly impact the early diagnosis of CRC. The true promise of artificial intelligence, extending beyond the medical sector, lies in its potential to significantly influence the future landscape of CRC's morbidity and mortality.

Review of Molecular Technologies for Investigating Canine Cancer

Genetic molecular testing is starting to gain traction as part of standard clinical practice for dogs with cancer due to its multi-faceted benefits, such as potentially being able to provide diagnostic, prognostic and/or therapeutic information. However, the benefits and ultimate success of genomic analysis in the clinical setting are reliant on the robustness of the tools used to generate the results, which continually expand as new technologies are developed. To this end, we review the different materials from which tumour cells, DNA, RNA and the relevant proteins can be isolated and what methods are available for interrogating their molecular profile, including analysis of the genetic alterations (both somatic and germline), transcriptional changes and epigenetic modifications (including DNA methylation/acetylation and microRNAs). We also look to the future and the tools that are currently being developed, such as using artificial intelligence (AI) to identify genetic mutations from histomorphological criteria. In summary, we find that the molecular genetic characterisation of canine neoplasms has made a promising start. As we understand more of the genetics underlying these tumours and more targeted therapies become available, it will no doubt become a mainstay in the delivery of precision veterinary care to dogs with cancer.

Hypoxia-derived molecular subtype and gene signature characterize prognoses and therapeutic responses in head and neck squamous cell carcinoma

Intratumoral hypoxia is widely associated with the development of malignancy, treatment resistance, and worse prognoses. This study aims to investigate the role of hypoxia-related genes (HRG) in the immune landscape, treatment response, and prognosis of head and neck squamous cell carcinoma (HNSCC). The transcriptome and clinical data of HNSCC were downloaded from TCGA and GEO databases, and HNSCC molecular subtypes were identified using non-negative matrix factorization (NMF) clustering. Prognostic models were constructed using univariate, Lasso, and multivariate Cox regression analyses. The relationship between HRGs and immune cell infiltration, immune therapy response, and drug sensitivity was evaluated, and a nomogram was constructed. 47 HRGs were differentially expressed in HNSCC, among which 10 genes were significantly associated with HNSCC prognosis. Based on these 10 genes, 2 HNSCC molecular subtypes were identified, which showed significant heterogeneity in terms of prognosis, immune infiltration, and treatment response. A total of 3280 differentially expressed genes were identified between the subtypes. After univariate, Lasso, and multivariate Cox regression analysis, 18 genes were selected to construct a novel prognostic model, which showed a significant correlation with B cells, T cells, and macrophages. Using this model, HNSCC was classified into high-risk and low-risk groups, which exhibited significant differences in terms of prognosis, immune cell infiltration, immune therapy response, and drug sensitivity. Finally, a nomogram based on this model and radiotherapy was constructed, which showed good performance in predicting HNSCC prognosis and guiding personalized treatment strategies. The decision curve analysis demonstrated its better clinical applicability compared to other strategies. HRGs can identify 2 HNSCC molecular subtypes with significant heterogeneity, and the HRG-derived risk model has the potential for prognostic prediction and guiding personalized treatment strategies.

Cancer drug sensitivity prediction from routine histology images

Drug sensitivity prediction models can aid in personalising cancer therapy, biomarker discovery, and drug design. Such models require survival data from randomised controlled trials which can be time consuming and expensive. In this proof-of-concept study, we demonstrate for the first time that deep learning can link histological patterns in whole slide images (WSIs) of Haematoxylin & Eosin (H&E) stained breast cancer sections with drug sensitivities inferred from cell lines. We employ patient-wise drug sensitivities imputed from gene expression-based mapping of drug effects on cancer cell lines to train a deep learning model that predicts patients' sensitivity to multiple drugs from WSIs. We show that it is possible to use routine WSIs to predict the drug sensitivity profile of a cancer patient for a number of approved and experimental drugs. We also show that the proposed approach can identify cellular and histological patterns associated with drug sensitivity profiles of cancer patients.

Consistency regularisation in varying contexts and feature perturbations for semi-supervised semantic segmentation of histology images

Semantic segmentation of various tissue and nuclei types in histology images is fundamental to many downstream tasks in the area of computational pathology (CPath). In recent years, Deep Learning (DL) methods have been shown to perform well on segmentation tasks but DL methods generally require a large amount of pixel-wise annotated data. Pixel-wise annotation sometimes requires expert's knowledge and time which is laborious and costly to obtain. In this paper, we present a consistency based semi-supervised learning (SSL) approach that can help mitigate this challenge by exploiting a large amount of unlabelled data for model training thus alleviating the need for a large annotated dataset. However, SSL models might also be susceptible to changing context and features perturbations exhibiting poor generalisation due to the limited training data. We propose an SSL method that learns robust features from both labelled and unlabelled images by enforcing consistency against varying contexts and feature perturbations. The proposed method incorporates context-aware consistency by contrasting pairs of overlapping images in a pixel-wise manner from changing contexts resulting in robust and context invariant features. We show that cross-consistency training makes the encoder features invariant to different perturbations and improves the prediction confidence. Finally, entropy minimisation is employed to further boost the confidence of the final prediction maps from unlabelled data. We conduct an extensive set of experiments on two publicly available large datasets (BCSS and MoNuSeg) and show superior performance compared to the state-of-the-art methods.

A population-level digital histologic biomarker for enhanced prognosis of invasive breast cancer

Breast cancer is a heterogeneous disease with variable survival outcomes. Pathologists grade the microscopic appearance of breast tissue using the Nottingham criteria, which are qualitative and do not account for noncancerous elements within the tumor microenvironment. Here we present the Histomic Prognostic Signature (HiPS), a comprehensive, interpretable scoring of the survival risk incurred by breast tumor microenvironment morphology. HiPS uses deep learning to accurately map cellular and tissue structures to measure epithelial, stromal, immune, and spatial interaction features. It was developed using a population-level cohort from the Cancer Prevention Study-II and validated using data from three independent cohorts, including the Prostate, Lung, Colorectal, and Ovarian Cancer trial, Cancer Prevention Study-3, and The Cancer Genome Atlas. HiPS consistently outperformed pathologists in predicting survival outcomes, independent of tumor-node-metastasis stage and pertinent variables. This was largely driven by stromal and immune features. In conclusion, HiPS is a robustly validated biomarker to support pathologists and improve patient prognosis.

Differentiation and risk stratification of basal cell carcinoma with deep learning on histopathologic images and measuring nuclei and tumor microenvironment features

BACKGROUND

Nuclear pleomorphism and tumor microenvironment (TME) play a critical role in cancer development and progression. Identifying most predictive nuclei and TME features of basal cell carcinoma (BCC) may provide insights into which characteristics pathologists can use to distinguish and stratify this entity.

OBJECTIVES

To develop an automated workflow based on nuclei and TME features from basaloid cell tumor regions to differentiate BCC from trichoepithelioma (TE) and stratify BCC into high-risk (HR) and low-risk (LR) subtypes, and to identify the nuclear and TME characteristics profile of different basaloid cell tumors.

METHODS

The deep learning systems were trained on 161 H&E -stained sections which contained 51 sections of HR-BCC, 50 sections of LR-BCC and 60 sections of TE from one institution (D1), and externally and independently validated on D2 (46 sections) and D3 (76 sections), from 2015 to 2022. 60%, 20% and 20% of D1 data were randomly splitted for training, validation and testing, respectively. The framework comprised four stages: tumor regions identification by multi-head self-attention (MSA) U-Net, nuclei segmentation by HoVer-Net, quantitative feature by handcrafted extraction, and differentiation and risk stratification classifier construction. Pixel accuracy, precision, recall, dice score, intersection over union (IoU) and area under the curve (AUC) were used to evaluate the performance of tumor segmentation model and classifiers.

RESULTS

MSA-U-Net model detected tumor regions with 0.910 precision, 0.869 recall, 0.889 dice score and 0.800 IoU. The differentiation classifier achieved 0.977 ± 0.0159, 0.955 ± 0.0181, 0.885 ± 0.0237 AUC in D1, D2 and D3, respectively. The most discriminative features between BCC and TE contained Homogeneity, Elongation, T-T_meanEdgeLength, T-T_Nsubgraph, S-T_HarmonicCentrality, S-S_Degrees. The risk stratification model can well predict HR-BCC and LR-BCC with 0.920 ± 0.0579, 0.839 ± 0.0176, 0.825 ± 0.0153 AUC in D1, D2 and D3, respectively. The most discriminative features between HR-BCC and LR-BCC comprised IntensityMin, Solidity, T-T_minEdgeLength, T-T_Coreness, T-T_Degrees, T-T_Betweenness, S-T_Degrees.

CONCLUSIONS

This framework hold potential for future use as a second opinion helping inform diagnosis of BCC, and identify nuclei and TME features related with malignancy and tumor risk stratification.

Artificial Intelligence in Predicting Microsatellite Instability and KRAS, BRAF Mutations from Whole-Slide Images in Colorectal Cancer: A Systematic Review

Mismatch repair deficiency (d-MMR)/microsatellite instability (MSI), KRAS, and BRAF mutational status are crucial for treating advanced colorectal cancer patients. Traditional methods like immunohistochemistry or polymerase chain reaction (PCR) can be challenged by artificial intelligence (AI) based on whole slide images (WSI) to predict tumor status. In this systematic review, we evaluated the role of AI in predicting MSI status, KRAS, and BRAF mutations in colorectal cancer. Studies published in PubMed up to June 2023 were included (n = 17), and we reported the risk of bias and the performance for each study. Some studies were impacted by the reduced number of slides included in the data set and the lack of external validation cohorts. Deep learning models for the d-MMR/MSI status showed a good performance in training cohorts (mean AUC = 0.89, [0.74-0.97]) but slightly less than expected in the validation cohort when available (mean AUC = 0.82, [0.63-0.98]). Contrary to the MSI status, the prediction of KRAS and BRAF mutations was less explored with a less robust methodology. The performance was lower, with a maximum of 0.77 in the training cohort, 0.58 in the validation cohort for KRAS, and 0.82 AUC in the training cohort for BRAF.

A Novel Deep Learning Algorithm for Human Papillomavirus Infection Prediction in Head and Neck Cancers Using Routine Histology Images

The etiology of head and neck squamous cell carcinoma (HNSCC) involves multiple carcinogens, such as alcohol, tobacco, and infection with human papillomavirus (HPV). Because HPV infection influences the prognosis, treatment, and survival of patients with HNSCC, it is important to determine the HPV status of these tumors. In this article, we propose a novel deep learning pipeline for HPV infection status prediction with state-of-the-art performance in HPV detection using only whole-slide images of routine hematoxylin and eosin-stained HNSCC sections. We show that our Digital-HPV score generated from hematoxylin and eosin slides produces statistically significant patient stratifications in terms of overall and disease-specific survival. In addition, quantitative profiling of the spatial tumor microenvironment and analysis of the immune profiles show relatively high levels of lymphocytic infiltration in tumor and tumor-associated stroma. High levels of B cells and T cells and low macrophage levels were also identified in HPV-positive patients compared to HPV-negative patients, confirming different immune response patterns elicited by HPV infection in patients with HNSCC.

A Novel and Efficient Digital Pathology Classifier for Predicting Cancer Biomarkers Using Sequencer Architecture

In digital pathology tasks, transformers have achieved state-of-the-art results, surpassing convolutional neural networks (CNNs). However, transformers are usually complex and resource intensive. This study developed a novel and efficient digital pathology classifier called DPSeq to predict cancer biomarkers through fine-tuning a sequencer architecture integrating horizontal and vertical bidirectional long short-term memory networks. Using hematoxylin and eosin-stained histopathologic images of colorectal cancer from two international data sets (The Cancer Genome Atlas and Molecular and Cellular Oncology), the predictive performance of DPSeq was evaluated in a series of experiments. DPSeq demonstrated exceptional performance for predicting key biomarkers in colorectal cancer (microsatellite instability status, hypermutation, CpG island methylator phenotype status, BRAF mutation, TP53 mutation, and chromosomal instability), outperforming most published state-of-the-art classifiers in a within-cohort internal validation and a cross-cohort external validation. In addition, under the same experimental conditions using the same set of training and testing data sets, DPSeq surpassed four CNNs (ResNet18, ResNet50, MobileNetV2, and EfficientNet) and two transformer (Vision Transformer and Swin Transformer) models, achieving the highest area under the receiver operating characteristic curve and area under the precision-recall curve values in predicting microsatellite instability status, BRAF mutation, and CpG island methylator phenotype status. Furthermore, DPSeq required less time for both training and prediction because of its simple architecture. Therefore, DPSeq appears to be the preferred choice over transformer and CNN models for predicting cancer biomarkers.

One label is all you need: Interpretable AI-enhanced histopathology for oncology

Artificial Intelligence (AI)-enhanced histopathology presents unprecedented opportunities to benefit oncology through interpretable methods that require only one overall label per hematoxylin and eosin (H&E) slide with no tissue-level annotations. We present a structured review of these methods organized by their degree of verifiability and by commonly recurring application areas in oncological characterization. First, we discuss morphological markers (tumor presence/absence, metastases, subtypes, grades) in which AI-identified regions of interest (ROIs) within whole slide images (WSIs) verifiably overlap with pathologist-identified ROIs. Second, we discuss molecular markers (gene expression, molecular subtyping) that are not verified via H&E but rather based on overlap with positive regions on adjacent tissue. Third, we discuss genetic markers (mutations, mutational burden, microsatellite instability, chromosomal instability) that current technologies cannot verify if AI methods spatially resolve specific genetic alterations. Fourth, we discuss the direct prediction of survival to which AI-identified histopathological features quantitatively correlate but are nonetheless not mechanistically verifiable. Finally, we discuss in detail several opportunities and challenges for these one-label-per-slide methods within oncology. Opportunities include reducing the cost of research and clinical care, reducing the workload of clinicians, personalized medicine, and unlocking the full potential of histopathology through new imaging-based biomarkers. Current challenges include explainability and interpretability, validation via adjacent tissue sections, reproducibility, data availability, computational needs, data requirements, domain adaptability, external validation, dataset imbalances, and finally commercialization and clinical potential. Ultimately, the relative ease and minimum upfront cost with which relevant data can be collected in addition to the plethora of available AI methods for outcome-driven analysis will surmount these current limitations and achieve the innumerable opportunities associated with AI-driven histopathology for the benefit of oncology.

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment

Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.

Validation of MSIntuit as an AI-based pre-screening tool for MSI detection from colorectal cancer histology slides

Mismatch Repair Deficiency (dMMR)/Microsatellite Instability (MSI) is a key biomarker in colorectal cancer (CRC). Universal screening of CRC patients for MSI status is now recommended, but contributes to increased workload for pathologists and delayed therapeutic decisions. Deep learning has the potential to ease dMMR/MSI testing and accelerate oncologist decision making in clinical practice, yet no comprehensive validation of a clinically approved tool has been conducted. We developed MSIntuit, a clinically approved artificial intelligence (AI) based pre-screening tool for MSI detection from haematoxylin-eosin (H&E) stained slides. After training on samples from The Cancer Genome Atlas (TCGA), a blind validation is performed on an independent dataset of 600 consecutive CRC patients. Inter-scanner reliability is studied by digitising each slide using two different scanners. MSIntuit yields a sensitivity of 0.96-0.98, a specificity of 0.47-0.46, and an excellent inter-scanner agreement (Cohen's κ: 0.82). By reaching high sensitivity comparable to gold standard methods while ruling out almost half of the non-MSI population, we show that MSIntuit can effectively serve as a pre-screening tool to alleviate MSI testing burden in clinical practice.

Development and validation of artificial intelligence-based prescreening of large-bowel biopsies taken in the UK and Portugal: a retrospective cohort study

BACKGROUND

Histopathological examination is a crucial step in the diagnosis and treatment of many major diseases. Aiming to facilitate diagnostic decision making and improve the workload of pathologists, we developed an artificial intelligence (AI)-based prescreening tool that analyses whole-slide images (WSIs) of large-bowel biopsies to identify typical, non-neoplastic, and neoplastic biopsies.

METHODS

This retrospective cohort study was conducted with an internal development cohort of slides acquired from a hospital in the UK and three external validation cohorts of WSIs acquired from two hospitals in the UK and one clinical laboratory in Portugal. To learn the differential histological patterns from digitised WSIs of large-bowel biopsy slides, our proposed weakly supervised deep-learning model (Colorectal AI Model for Abnormality Detection [CAIMAN]) used slide-level diagnostic labels and no detailed cell or region-level annotations. The method was developed with an internal development cohort of 5054 biopsy slides from 2080 patients that were labelled with corresponding diagnostic categories assigned by pathologists. The three external validation cohorts, with a total of 1536 slides, were used for independent validation of CAIMAN. Each WSI was classified into one of three classes (ie, typical, atypical non-neoplastic, and atypical neoplastic). Prediction scores of image tiles were aggregated into three prediction scores for the whole slide, one for its likelihood of being typical, one for its likelihood of being non-neoplastic, and one for its likelihood of being neoplastic. The assessment of the external validation cohorts was conducted by the trained and frozen CAIMAN model. To evaluate model performance, we calculated area under the convex hull of the receiver operating characteristic curve (AUROC), area under the precision-recall curve, and specificity compared with our previously published iterative draw and rank sampling (IDaRS) algorithm. We also generated heat maps and saliency maps to analyse and visualise the relationship between the WSI diagnostic labels and spatial features of the tissue microenvironment. The main outcome of this study was the ability of CAIMAN to accurately identify typical and atypical WSIs of colon biopsies, which could potentially facilitate automatic removing of typical biopsies from the diagnostic workload in clinics.

FINDINGS

A randomly selected subset of all large bowel biopsies was obtained between Jan 1, 2012, and Dec 31, 2017. The AI training, validation, and assessments were done between Jan 1, 2021, and Sept 30, 2022. WSIs with diagnostic labels were collected between Jan 1 and Sept 30, 2022. Our analysis showed no statistically significant differences across prediction scores from CAIMAN for typical and atypical classes based on anatomical sites of the biopsy. At 0·99 sensitivity, CAIMAN (specificity 0·5592) was more accurate than an IDaRS-based weakly supervised WSI-classification pipeline (0·4629) in identifying typical and atypical biopsies on cross-validation in the internal development cohort (p<0·0001). At 0·99 sensitivity, CAIMAN was also more accurate than IDaRS for two external validation cohorts (p<0·0001), but not for a third external validation cohort (p=0·10). CAIMAN provided higher specificity than IDaRS at some high-sensitivity thresholds (0·7763 vs 0·6222 for 0·95 sensitivity, 0·7126 vs 0·5407 for 0·97 sensitivity, and 0·5615 vs 0·3970 for 0·99 sensitivity on one of the external validation cohorts) and showed high classification performance in distinguishing between neoplastic biopsies (AUROC 0·9928, 95% CI 0·9927-0·9929), inflammatory biopsies (0·9658, 0·9655-0·9661), and atypical biopsies (0·9789, 0·9786-0·9792). On the three external validation cohorts, CAIMAN had AUROC values of 0·9431 (95% CI 0·9165-0·9697), 0·9576 (0·9568-0·9584), and 0·9636 (0·9615-0·9657) for the detection of atypical biopsies. Saliency maps supported the representation of disease heterogeneity in model predictions and its association with relevant histological features.

INTERPRETATION

CAIMAN, with its high sensitivity in detecting atypical large-bowel biopsies, might be a promising improvement in clinical workflow efficiency and diagnostic decision making in prescreening of typical colorectal biopsies.

FUNDING

The Pathology Image Data Lake for Analytics, Knowledge and Education Centre of Excellence; the UK Government's Industrial Strategy Challenge Fund; and Innovate UK on behalf of UK Research and Innovation.

Deep Learning for Detecting BRCA Mutations in High-Grade Ovarian Cancer Based on an Innovative Tumor Segmentation Method From Whole Slide Images

BRCA1 and BRCA2 genes play a crucial role in repairing DNA double-strand breaks through homologous recombination. Their mutations represent a significant proportion of homologous recombination deficiency and are a reliable effective predictor of sensitivity of high-grade ovarian cancer (HGOC) to poly(ADP-ribose) polymerase inhibitors. However, their testing by next-generation sequencing is costly and time-consuming and can be affected by various preanalytical factors. In this study, we present a deep learning classifier for BRCA mutational status prediction from hematoxylin-eosin-safran-stained whole slide images (WSI) of HGOC. We constituted the OvarIA cohort composed of 867 patients with HGOC with known BRCA somatic mutational status from 2 different pathology departments. We first developed a tumor segmentation model according to dynamic sampling and then trained a visual representation encoder with momentum contrastive learning on the predicted tumor tiles. We finally trained a BRCA classifier on more than a million tumor tiles in multiple instance learning with an attention-based mechanism. The tumor segmentation model trained on 8 WSI obtained a dice score of 0.915 and an intersection-over-union score of 0.847 on a test set of 50 WSI, while the BRCA classifier achieved the state-of-the-art area under the receiver operating characteristic curve of 0.739 in 5-fold cross-validation and 0.681 on the testing set. An additional multiscale approach indicates that the relevant information for predicting BRCA mutations is located more in the tumor context than in the cell morphology. Our results suggest that BRCA somatic mutations have a discernible phenotypic effect that could be detected by deep learning and could be used as a prescreening tool in the future.

Focalizing regions of biomarker relevance facilitates biomarker prediction on histopathological images

Image-based AI has thrived as a potentially revolutionary tool for predicting molecular biomarker statuses, which aids in categorizing patients for appropriate medical treatments. However, many methods using hematoxylin and eosin-stained (H&E) whole-slide images (WSIs) have been found to be inefficient because of the presence of numerous uninformative or irrelevant image patches. In this study, we introduced the region of biomarker relevance (ROB) concept to identify the morphological areas most closely associated with biomarkers for accurate status prediction. We actualized this concept within a framework called saliency ROB search (SRS) to enable efficient and effective predictions. By evaluating various lung adenocarcinoma (LUAD) biomarkers, we showcased the superior performance of SRS compared to current state-of-the-art AI approaches. These findings suggest that AI tools, built on the ROB concept, can achieve enhanced molecular biomarker prediction accuracy from pathological images.

Neuropathologist-level integrated classification of adult-type diffuse gliomas using deep learning from whole-slide pathological images

Current diagnosis of glioma types requires combining both histological features and molecular characteristics, which is an expensive and time-consuming procedure. Determining the tumor types directly from whole-slide images (WSIs) is of great value for glioma diagnosis. This study presents an integrated diagnosis model for automatic classification of diffuse gliomas from annotation-free standard WSIs. Our model is developed on a training cohort (n = 1362) and a validation cohort (n = 340), and tested on an internal testing cohort (n = 289) and two external cohorts (n = 305 and 328, respectively). The model can learn imaging features containing both pathological morphology and underlying biological clues to achieve the integrated diagnosis. Our model achieves high performance with area under receiver operator curve all above 0.90 in classifying major tumor types, in identifying tumor grades within type, and especially in distinguishing tumor genotypes with shared histological features. This integrated diagnosis model has the potential to be used in clinical scenarios for automated and unbiased classification of adult-type diffuse gliomas.

Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise

In the past years, deep learning has seen an increase in usage in the domain of histopathological applications. However, while these approaches have shown great potential, in high-risk environments deep learning models need to be able to judge their uncertainty and be able to reject inputs when there is a significant chance of misclassification. In this work, we conduct a rigorous evaluation of the most commonly used uncertainty and robustness methods for the classification of Whole Slide Images, with a focus on the task of selective classification, where the model should reject the classification in situations in which it is uncertain. We conduct our experiments on tile-level under the aspects of domain shift and label noise, as well as on slide-level. In our experiments, we compare Deep Ensembles, Monte-Carlo Dropout, Stochastic Variational Inference, Test-Time Data Augmentation as well as ensembles of the latter approaches. We observe that ensembles of methods generally lead to better uncertainty estimates as well as an increased robustness towards domain shifts and label noise, while contrary to results from classical computer vision benchmarks no systematic gain of the other methods can be shown. Across methods, a rejection of the most uncertain samples reliably leads to a significant increase in classification accuracy on both in-distribution as well as out-of-distribution data. Furthermore, we conduct experiments comparing these methods under varying conditions of label noise. Lastly, we publish our code framework to facilitate further research on uncertainty estimation on histopathological data.

PAIP 2020: Microsatellite instability prediction in colorectal cancer

Microsatellite instability (MSI) refers to alterations in the length of simple repetitive genomic sequences. MSI status serves as a prognostic and predictive factor in colorectal cancer. The MSI-high status is a good prognostic factor in stage II/III cancer, and predicts a lack of benefit to adjuvant fluorouracil chemotherapy in stage II cancer but a good response to immunotherapy in stage IV cancer. Therefore, determining MSI status in patients with colorectal cancer is important for identifying the appropriate treatment protocol. In the Pathology Artificial Intelligence Platform (PAIP) 2020 challenge, artificial intelligence researchers were invited to predict MSI status based on colorectal cancer slide images. Participants were required to perform two tasks. The primary task was to classify a given slide image as belonging to either the MSI-high or the microsatellite-stable group. The second task was tumor area segmentation to avoid ties with the main task. A total of 210 of the 495 participants enrolled in the challenge downloaded the images, and 23 teams submitted their final results. Seven teams from the top 10 participants agreed to disclose their algorithms, most of which were convolutional neural network-based deep learning models, such as EfficientNet and UNet. The top-ranked system achieved the highest F1 score (0.9231). This paper summarizes the various methods used in the PAIP 2020 challenge. This paper supports the effectiveness of digital pathology for identifying the relationship between colorectal cancer and the MSI characteristics.

HAVOC: Small-scale histomic mapping of cancer biodiversity across large tissue distances using deep neural networks

Intratumoral heterogeneity can wreak havoc on current precision medicine strategies because of challenges in sufficient sampling of geographically separated areas of biodiversity distributed across centimeter-scale tumor distances. To address this gap, we developed a deep learning pipeline that leverages histomorphologic fingerprints of tissue to create "Histomic Atlases of Variation Of Cancers" (HAVOC). Using a number of objective molecular readouts, we demonstrate that HAVOC can define regional cancer boundaries with distinct biology. Using larger tumor specimens, we show that HAVOC can map biodiversity even across multiple tissue sections. By guiding profiling of 19 partitions across six high-grade gliomas, HAVOC revealed that distinct differentiation states can often coexist and be regionally distributed within these tumors. Last, to highlight generalizability, we benchmark HAVOC on additional tumor types. Together, we establish HAVOC as a versatile tool to generate small-scale maps of tissue heterogeneity and guide regional deployment of molecular resources to relevant biodiverse niches.

A Federated Learning Approach to Tumor Detection in Colon Histology Images

Federated learning (FL), a relatively new area of research in medical image analysis, enables collaborative learning of a federated deep learning model without sharing the data of participating clients. In this paper, we propose FedDropoutAvg, a new federated learning approach for detection of tumor in images of colon tissue slides. The proposed method leverages the power of dropout, a commonly employed scheme to avoid overfitting in neural networks, in both client selection and federated averaging processes. We examine FedDropoutAvg against other FL benchmark algorithms for two different image classification tasks using a publicly available multi-site histopathology image dataset. We train and test the proposed model on a large dataset consisting of 1.2 million image tiles from 21 different sites. For testing the generalization of all models, we select held-out test sets from sites that were not used during training. We show that the proposed approach outperforms other FL methods and reduces the performance gap (to less than 3% in terms of AUC on independent test sites) between FL and a central deep learning model that requires all data to be shared for centralized training, demonstrating the potential of the proposed FedDropoutAvg model to be more generalizable than other state-of-the-art federated models. To the best of our knowledge, ours is the first study to effectively utilize the dropout strategy in a federated setting for tumor detection in histology images.

Transformer-based biomarker prediction from colorectal cancer histology: A large-scale multicentric study

Deep learning (DL) can accelerate the prediction of prognostic biomarkers from routine pathology slides in colorectal cancer (CRC). However, current approaches rely on convolutional neural networks (CNNs) and have mostly been validated on small patient cohorts. Here, we develop a new transformer-based pipeline for end-to-end biomarker prediction from pathology slides by combining a pre-trained transformer encoder with a transformer network for patch aggregation. Our transformer-based approach substantially improves the performance, generalizability, data efficiency, and interpretability as compared with current state-of-the-art algorithms. After training and evaluating on a large multicenter cohort of over 13,000 patients from 16 colorectal cancer cohorts, we achieve a sensitivity of 0.99 with a negative predictive value of over 0.99 for prediction of microsatellite instability (MSI) on surgical resection specimens. We demonstrate that resection specimen-only training reaches clinical-grade performance on endoscopic biopsy tissue, solving a long-standing diagnostic problem.

Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study

OBJECTIVE

To develop an interpretable artificial intelligence algorithm to rule out normal large bowel endoscopic biopsies, saving pathologist resources and helping with early diagnosis.

DESIGN

A graph neural network was developed incorporating pathologist domain knowledge to classify 6591 whole-slides images (WSIs) of endoscopic large bowel biopsies from 3291 patients (approximately 54% female, 46% male) as normal or abnormal (non-neoplastic and neoplastic) using clinically driven interpretable features. One UK National Health Service (NHS) site was used for model training and internal validation. External validation was conducted on data from two other NHS sites and one Portuguese site.

RESULTS

Model training and internal validation were performed on 5054 WSIs of 2080 patients resulting in an area under the curve-receiver operating characteristic (AUC-ROC) of 0.98 (SD=0.004) and AUC-precision-recall (PR) of 0.98 (SD=0.003). The performance of the model, named Interpretable Gland-Graphs using a Neural Aggregator (IGUANA), was consistent in testing over 1537 WSIs of 1211 patients from three independent external datasets with mean AUC-ROC=0.97 (SD=0.007) and AUC-PR=0.97 (SD=0.005). At a high sensitivity threshold of 99%, the proposed model can reduce the number of normal slides to be reviewed by a pathologist by approximately 55%. IGUANA also provides an explainable output highlighting potential abnormalities in a WSI in the form of a heatmap as well as numerical values associating the model prediction with various histological features.

CONCLUSION

The model achieved consistently high accuracy showing its potential in optimising increasingly scarce pathologist resources. Explainable predictions can guide pathologists in their diagnostic decision-making and help boost their confidence in the algorithm, paving the way for its future clinical adoption.

Prediction of Medical Disputes Between Health Care Workers and Patients in Terms of Hospital Legal Construction Using Machine Learning Techniques: Externally Validated Cross-Sectional Study

BACKGROUND

Medical disputes are a global public health issue that is receiving increasing attention. However, studies investigating the relationship between hospital legal construction and medical disputes are scarce. The development of a multicenter model incorporating machine learning (ML) techniques for the individualized prediction of medical disputes would be beneficial for medical workers.

OBJECTIVE

This study aimed to identify predictors related to medical disputes from the perspective of hospital legal construction and the use of ML techniques to build models for predicting the risk of medical disputes.

METHODS

This study enrolled 38,053 medical workers from 130 tertiary hospitals in Hunan province, China. The participants were randomly divided into a training cohort (34,286/38,053, 90.1%) and an internal validation cohort (3767/38,053, 9.9%). Medical workers from 87 tertiary hospitals in Beijing were included in an external validation cohort (26,285/26,285, 100%). This study used logistic regression and 5 ML techniques: decision tree, random forest, support vector machine, gradient boosting decision tree (GBDT), and deep neural network. In total, 12 metrics, including discrimination and calibration, were used for performance evaluation. A scoring system was developed to select the optimal model. Shapley additive explanations was used to generate the importance coefficients for characteristics. To promote the clinical practice of our proposed optimal model, reclassification of patients was performed, and a web-based app for medical dispute prediction was created, which can be easily accessed by the public.

RESULTS

Medical disputes occurred among 46.06% (17,527/38,053) of the medical workers in Hunan province, China. Among the 26 clinical characteristics, multivariate analysis demonstrated that 18 characteristics were significantly associated with medical disputes, and these characteristics were used for ML model development. Among the ML techniques, GBDT was identified as the optimal model, demonstrating the lowest Brier score (0.205), highest area under the receiver operating characteristic curve (0.738, 95% CI 0.722-0.754), and the largest discrimination slope (0.172) and Youden index (1.355). In addition, it achieved the highest metrics score (63 points), followed by deep neural network (46 points) and random forest (45 points), in the internal validation set. In the external validation set, GBDT still performed comparably, achieving the second highest metrics score (52 points). The high-risk group had more than twice the odds of experiencing medical disputes compared with the low-risk group.

CONCLUSIONS

We established a prediction model to stratify medical workers into different risk groups for encountering medical disputes. Among the 5 ML models, GBDT demonstrated the optimal comprehensive performance and was used to construct the web-based app. Our proposed model can serve as a useful tool for identifying medical workers at high risk of medical disputes. We believe that preventive strategies should be implemented for the high-risk group.

Deep learning for the prediction of the chemotherapy response of metastatic colorectal cancer: comparing and combining H&E staining histopathology and infrared spectral histopathology

Colorectal cancer is a global public health problem with one of the highest death rates. It is the second most deadly type of cancer and the third most frequently diagnosed in the world. The present study focused on metastatic colorectal cancer (mCRC) patients who had been treated with chemotherapy-based regimen for which it remains uncertainty about the efficacy for all eligible patients. This is a major problem, as it is not yet possible to test different therapies in view of the consequences on the health of the patients and the risk of progression. Here, we propose a method to predict the efficacy of an anticancer treatment in an individualized way, using a deep learning model constructed on the retrospective analysis of the primary tumor of several patients. Histological sections from tumors were imaged by standard hematoxylin and eosin (HE) staining and infrared spectroscopy (IR). Images obtained were then processed by a convolutional neural network (CNN) to extract features and correlate them with the subsequent progression-free survival (PFS) of each patient. Separately, HE and IR imaging resulted in a PFS prediction with an error of 6.6 and 6.3 months respectively (28% and 26% of the average PFS). Combining both modalities allowed to decrease the error to 5.0 months (21%). The inflammatory state of the stroma seemed to be one of the main features detected by the CNN. Our pilot study suggests that multimodal imaging analyzed with deep learning methods allow to give an indication of the effectiveness of a treatment when choosing.

A digital score of peri-epithelial lymphocytic activity predicts malignant transformation in oral epithelial dysplasia

Oral squamous cell carcinoma (OSCC) is amongst the most common cancers, with more than 377,000 new cases worldwide each year. OSCC prognosis remains poor, related to cancer presentation at a late stage, indicating the need for early detection to improve patient prognosis. OSCC is often preceded by a premalignant state known as oral epithelial dysplasia (OED), which is diagnosed and graded using subjective histological criteria leading to variability and prognostic unreliability. In this work, we propose a deep learning approach for the development of prognostic models for malignant transformation and their association with clinical outcomes in histology whole slide images (WSIs) of OED tissue sections. We train a weakly supervised method on OED cases (n = 137) with malignant transformation (n = 50) and mean malignant transformation time of 6.51 years (±5.35 SD). Stratified five-fold cross-validation achieved an average area under the receiver-operator characteristic curve (AUROC) of 0.78 for predicting malignant transformation in OED. Hotspot analysis revealed various features of nuclei in the epithelium and peri-epithelial tissue to be significant prognostic factors for malignant transformation, including the count of peri-epithelial lymphocytes (PELs) (p < 0.05), epithelial layer nuclei count (NC) (p < 0.05), and basal layer NC (p < 0.05). Progression-free survival (PFS) using the epithelial layer NC (p < 0.05, C-index = 0.73), basal layer NC (p < 0.05, C-index = 0.70), and PELs count (p < 0.05, C-index = 0.73) all showed association of these features with a high risk of malignant transformation in our univariate analysis. Our work shows the application of deep learning for the prognostication and prediction of PFS of OED for the first time and offers potential to aid patient management. Further evaluation and testing on multi-centre data is required for validation and translation to clinical practice. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Integrative deep learning analysis improves colon adenocarcinoma patient stratification at risk for mortality

BACKGROUND

Colorectal cancers are the fourth most diagnosed cancer and the second leading cancer in number of deaths. Many clinical variables, pathological features, and genomic signatures are associated with patient risk, but reliable patient stratification in the clinic remains a challenging task. Here we assess how image, clinical, and genomic features can be combined to predict risk.

METHODS

We developed and evaluated integrative deep learning models combining formalin-fixed, paraffin-embedded (FFPE) whole slide images (WSIs), clinical variables, and mutation signatures to stratify colon adenocarcinoma (COAD) patients based on their risk of mortality. Our models were trained using a dataset of 108 patients from The Cancer Genome Atlas (TCGA), and were externally validated on newly generated dataset from Wayne State University (WSU) of 123 COAD patients and rectal adenocarcinoma (READ) patients in TCGA (N = 52).

FINDINGS

We first observe that deep learning models trained on FFPE WSIs of TCGA-COAD separate high-risk (OS < 3 years, N = 38) and low-risk (OS > 5 years, N = 25) patients (AUC = 0.81 ± 0.08, 5 year survival p < 0.0001, 5 year relative risk = 1.83 ± 0.04) though such models are less effective at predicting overall survival (OS) for moderate-risk (3 years < OS < 5 years, N = 45) patients (5 year survival p-value = 0.5, 5 year relative risk = 1.05 ± 0.09). We find that our integrative models combining WSIs, clinical variables, and mutation signatures can improve patient stratification for moderate-risk patients (5 year survival p < 0.0001, 5 year relative risk = 1.87 ± 0.07). Our integrative model combining image and clinical variables is also effective on an independent pathology dataset (WSU-COAD, N = 123) generated by our team (5 year survival p < 0.0001, 5 year relative risk = 1.52 ± 0.08), and the TCGA-READ data (5 year survival p < 0.0001, 5 year relative risk = 1.18 ± 0.17). Our multicenter integrative image and clinical model trained on combined TCGA-COAD and WSU-COAD is effective in predicting risk on TCGA-READ (5 year survival p < 0.0001, 5 year relative risk = 1.82 ± 0.13) data. Pathologist review of image-based heatmaps suggests that nuclear size pleomorphism, intense cellularity, and abnormal structures are associated with high-risk, while low-risk regions have more regular and small cells. Quantitative analysis shows high cellularity, high ratios of tumor cells, large tumor nuclei, and low immune infiltration are indicators of high-risk tiles.

INTERPRETATION

The improved stratification of colorectal cancer patients from our computational methods can be beneficial for treatment plans and enrollment of patients in clinical trials.

FUNDING

This study was supported by the National Cancer Institutes (Grant No. R01CA230031 and P30CA034196). The funders had no roles in study design, data collection and analysis or preparation of the manuscript.