Wnt-ß-catenin activation epigenetically reprograms Treg cells in inflammatory bowel disease and dysplastic progression.

The diversity of regulatory T (Treg) cells in health and in disease remains unclear. Individuals with colorectal cancer harbor a subpopulation of RORγt+ Treg cells with elevated expression of ß-catenin and pro-inflammatory properties. Here we show progressive expansion of RORγt+ Treg cells in individuals with inflammatory bowel disease during inflammation and early dysplasia. Activating Wnt-ß-catenin signaling in human and murine Treg cells was sufficient to recapitulate the disease-associated increase in the frequency of RORγt+ Treg cells coexpressing multiple pro-inflammatory cytokines. Binding of the ß-catenin interacting partner, TCF-1, to DNA overlapped with Foxp3 binding at enhancer sites of pro-inflammatory pathway genes. Sustained Wnt-ß-catenin activation induced newly accessible chromatin sites in these genes and upregulated their expression. These findings indicate that TCF-1 and Foxp3 together limit the expression of pro-inflammatory genes in Treg cells. Activation of ß-catenin signaling interferes with this function and promotes the disease-associated RORγt+ Treg phenotype.

Slideflow: deep learning for digital histopathology with real-time whole-slide visualization.

Deep learning methods have emerged as powerful tools for analyzing histopathological images, but current methods are often specialized for specific domains and software environments, and few open-source options exist for deploying models in an interactive interface. Experimenting with different deep learning approaches typically requires switching software libraries and reprocessing data, reducing the feasibility and practicality of experimenting with new architectures. We developed a flexible deep learning library for histopathology called Slideflow, a package which supports a broad array of deep learning methods for digital pathology and includes a fast whole-slide interface for deploying trained models. Slideflow includes unique tools for whole-slide image data processing, efficient stain normalization and augmentation, weakly-supervised whole-slide classification, uncertainty quantification, feature generation, feature space analysis, and explainability. Whole-slide image processing is highly optimized, enabling whole-slide tile extraction at 40x magnification in 2.5 s per slide. The framework-agnostic data processing pipeline enables rapid experimentation with new methods built with either Tensorflow or PyTorch, and the graphical user interface supports real-time visualization of slides, predictions, heatmaps, and feature space characteristics on a variety of hardware devices, including ARM-based devices such as the Raspberry Pi.

Validation of the RSClin risk calculator in the National Cancer Data Base.

BACKGROUND: Guidelines recommend the use of genomic assays such as OncotypeDx to aid in decisions regarding the use of chemotherapy for hormone receptor-positive, HER2-negative (HR+/HER2-) breast cancer. The RSClin prognostic tool integrates OncotypeDx and clinicopathologic features to predict distant recurrence and chemotherapy benefit, but further validation is needed before broad clinical adoption. METHODS: This study included patients from the National Cancer Data Base (NCDB) who were diagnosed with stage I-III HR+/HER2- breast cancer from 2010 to 2020 and received adjuvant endocrine therapy with or without chemotherapy. RSClin-predicted chemotherapy benefit was stratified into low (<3% reduction in distant recurrence), intermediate (3%-5%), and high (>5%). Cox models were used to model mortality adjusted for age, comorbidity index, insurance, and race/ethnicity. RESULTS: A total of 285,441 patients were identified for inclusion from the NCDB, with an average age of 60 years and a median follow-up of 58 months. Chemotherapy was associated with improved overall survival only for those predicted to have intermediate (adjusted hazard ratio [aHR], 0.68; 95% confidence interval [CI], 0.60-0.79) and high benefit per RSClin (aHR, 0.66; 95% CI, 0.61-0.72). Consistent benefit was seen in the subset with a low OncotypeDx score (<26) and intermediate (aHR, 0.66; 95% CI, 0.53-0.82) or high (aHR, 0.71; 95% CI, 0.58-0.86) RSClin-predicted benefit. No survival benefit with chemotherapy was seen in patients with a high OncotypeDx score (≥26) and low benefit per RSClin (aHR, 1.70; 95% CI, 0.41-6.99). CONCLUSIONS: RSClin may identify high-risk patients who benefit from treatment intensification more accurately than OncotypeDx, and further prospective study is needed.

Deep learning applications in visual data for benign and malignant hematologic conditions: a systematic review and visual glossary.

Deep learning (DL) is a subdomain of artificial intelligence algorithms capable of automatically evaluating subtle graphical features to make highly accurate predictions, which was recently popularized in multiple imaging-related tasks. Because of its capabilities to analyze medical imaging such as radiology scans and digitized pathology specimens, DL has significant clinical potential as a diagnostic or prognostic tool. Coupled with rapidly increasing quantities of digital medical data, numerous novel research questions and clinical applications of DL within medicine have already been explored. Similarly, DL research and applications within hematology are rapidly emerging, although these are still largely in their infancy. Given the exponential rise of DL research for hematologic conditions, it is essential for the practising hematologist to be familiar with the broad concepts and pitfalls related to these new computational techniques. This narrative review provides a visual glossary for key deep learning principles, as well as a systematic review of published investigations within malignant and non-malignant hematologic conditions, organized by the different phases of clinical care. In order to assist the unfamiliar reader, this review highlights key portions of current literature and summarizes important considerations for the critical understanding of deep learning development and implementations in clinical practice.

Classical mathematical models for prediction of response to chemotherapy and immunotherapy.

Classical mathematical models of tumor growth have shaped our understanding of cancer and have broad practical implications for treatment scheduling and dosage. However, even the simplest textbook models have been barely validated in real world-data of human patients. In this study, we fitted a range of differential equation models to tumor volume measurements of patients undergoing chemotherapy or cancer immunotherapy for solid tumors. We used a large dataset of 1472 patients with three or more measurements per target lesion, of which 652 patients had six or more data points. We show that the early treatment response shows only moderate correlation with the final treatment response, demonstrating the need for nuanced models. We then perform a head-to-head comparison of six classical models which are widely used in the field: the Exponential, Logistic, Classic Bertalanffy, General Bertalanffy, Classic Gompertz and General Gompertz model. Several models provide a good fit to tumor volume measurements, with the Gompertz model providing the best balance between goodness of fit and number of parameters. Similarly, when fitting to early treatment data, the general Bertalanffy and Gompertz models yield the lowest mean absolute error to forecasted data, indicating that these models could potentially be effective at predicting treatment outcome. In summary, we provide a quantitative benchmark for classical textbook models and state-of-the art models of human tumor growth. We publicly release an anonymized version of our original data, providing the first benchmark set of human tumor growth data for evaluation of mathematical models.

Deep learning-based subtyping of gastric cancer histology predicts clinical outcome: a multi-institutional retrospective study.

INTRODUCTION: The Laurén classification is widely used for Gastric Cancer (GC) histology subtyping. However, this classification is prone to interobserver variability and its prognostic value remains controversial. Deep Learning (DL)-based assessment of hematoxylin and eosin (H&E) stained slides is a potentially useful tool to provide an additional layer of clinically relevant information, but has not been systematically assessed in GC. OBJECTIVE: We aimed to train, test and externally validate a deep learning-based classifier for GC histology subtyping using routine H&E stained tissue sections from gastric adenocarcinomas and to assess its potential prognostic utility. METHODS: We trained a binary classifier on intestinal and diffuse type GC whole slide images for a subset of the TCGA cohort (N = 166) using attention-based multiple instance learning. The ground truth of 166 GC was obtained by two expert pathologists. We deployed the model on two external GC patient cohorts, one from Europe (N = 322) and one from Japan (N = 243). We assessed classification performance using the Area Under the Receiver Operating Characteristic Curve (AUROC) and prognostic value (overall, cancer specific and disease free survival) of the DL-based classifier with uni- and multivariate Cox proportional hazard models and Kaplan-Meier curves with log-rank test statistics. RESULTS: Internal validation using the TCGA GC cohort using five-fold cross-validation achieved a mean AUROC of 0.93 ± 0.07. External validation showed that the DL-based classifier can better stratify GC patients' 5-year survival compared to pathologist-based Laurén classification for all survival endpoints, despite frequently divergent model-pathologist classifications. Univariate overall survival Hazard Ratios (HRs) of pathologist-based Laurén classification (diffuse type versus intestinal type) were 1.14 (95% Confidence Interval (CI) 0.66-1.44, p-value = 0.51) and 1.23 (95% CI 0.96-1.43, p-value = 0.09) in the Japanese and European cohorts, respectively. DL-based histology classification resulted in HR of 1.46 (95% CI 1.18-1.65, p-value < 0.005) and 1.41 (95% CI 1.20-1.57, p-value < 0.005), in the Japanese and European cohorts, respectively. In diffuse type GC (as defined by the pathologist), classifying patients using the DL diffuse and intestinal classifications provided a superior survival stratification, and demonstrated statistically significant survival stratification when combined with pathologist classification for both the Asian (overall survival log-rank test p-value < 0.005, HR 1.43 (95% CI 1.05-1.66, p-value = 0.03) and European cohorts (overall survival log-rank test p-value < 0.005, HR 1.56 (95% CI 1.16-1.76, p-value < 0.005)). CONCLUSION: Our study shows that gastric adenocarcinoma subtyping using pathologist's Laurén classification as ground truth can be performed using current state of the art DL techniques. Patient survival stratification seems to be better by DL-based histology typing compared with expert pathologist histology typing. DL-based GC histology typing has potential as an aid in subtyping. Further investigations are warranted to fully understand the underlying biological mechanisms for the improved survival stratification despite apparent imperfect classification by the DL algorithm.

Machine learning for detection and classification of oral potentially malignant disorders: A conceptual review.

Oral potentially malignant disorders represent precursor lesions that may undergo malignant transformation to oral cancer. There are many known risk factors associated with the development of oral potentially malignant disorders, and contribute to the risk of malignant transformation. Although many advances have been reported to understand the biological behavior of oral potentially malignant disorders, their clinical features that indicate the characteristics of malignant transformation are not well established. Early diagnosis of malignancy is the most important factor to improve patients' prognosis. The integration of machine learning into routine diagnosis has recently emerged as an adjunct to aid clinical examination. Increased performances of artificial intelligence AI-assisted medical devices are claimed to exceed the human capability in the clinical detection of early cancer. Therefore, the aim of this narrative review is to introduce artificial intelligence terminology, concepts, and models currently used in oncology to familiarize oral medicine scientists with the language skills, best research practices, and knowledge for developing machine learning models applied to the clinical detection of oral potentially malignant disorders.

Machine learning concepts applied to oral pathology and oral medicine: A convolutional neural networks' approach.

INTRODUCTION: Artificial intelligence models and networks can learn and process dense information in a short time, leading to an efficient, objective, and accurate clinical and histopathological analysis, which can be useful to improve treatment modalities and prognostic outcomes. This paper targets oral pathologists, oral medicinists, and head and neck surgeons to provide them with a theoretical and conceptual foundation of artificial intelligence-based diagnostic approaches, with a special focus on convolutional neural networks, the state-of-the-art in artificial intelligence and deep learning. METHODS: The authors conducted a literature review, and the convolutional neural network's conceptual foundations and functionality were illustrated based on a unique interdisciplinary point of view. CONCLUSION: The development of artificial intelligence-based models and computer vision methods for pattern recognition in clinical and histopathological image analysis of head and neck cancer has the potential to aid diagnosis and prognostic prediction.

The use of deep learning state-of-the-art architectures for oral epithelial dysplasia grading: A comparative appraisal.

BACKGROUND: Dysplasia grading systems for oral epithelial dysplasia are a source of disagreement among pathologists. Therefore, machine learning approaches are being developed to mitigate this issue. METHODS: This cross-sectional study included a cohort of 82 patients with oral potentially malignant disorders and correspondent 98 hematoxylin and eosin-stained whole slide images with biopsied-proven dysplasia. All whole-slide images were manually annotated based on the binary system for oral epithelial dysplasia. The annotated regions of interest were segmented and fragmented into small patches and non-randomly sampled into training/validation and test subsets. The training/validation data were color augmented, resulting in a total of 81,786 patches for training. The held-out independent test set enrolled a total of 4,486 patches. Seven state-of-the-art convolutional neural networks were trained, validated, and tested with the same dataset. RESULTS: The models presented a high learning rate, yet very low generalization potential. At the model development, VGG16 performed the best, but with massive overfitting. In the test set, VGG16 presented the best accuracy, sensitivity, specificity, and area under the curve (62%, 62%, 66%, and 65%, respectively), associated with the higher loss among all Convolutional Neural Networks (CNNs) tested. EfficientB0 has comparable metrics and the lowest loss among all convolutional neural networks, being a great candidate for further studies. CONCLUSION: The models were not able to generalize enough to be applied in real-life datasets due to an overlapping of features between the two classes (i.e., high risk and low risk of malignization).

4-Hydroxyacetophenone modulates the actomyosin cytoskeleton to reduce metastasis.

Metastases are the cause of the vast majority of cancer deaths. In the metastatic process, cells migrate to the vasculature, intravasate, extravasate, and establish metastatic colonies. This pattern of spread requires the cancer cells to change shape and to navigate tissue barriers. Approaches that block this mechanical program represent new therapeutic avenues. We show that 4-hydroxyacetophenone (4-HAP) inhibits colon cancer cell adhesion, invasion, and migration in vitro and reduces the metastatic burden in an in vivo model of colon cancer metastasis to the liver. Treatment with 4-HAP activates nonmuscle myosin-2C (NM2C) (MYH14) to alter actin organization, inhibiting the mechanical program of metastasis. We identify NM2C as a specific therapeutic target. Pharmacological control of myosin isoforms is a promising approach to address metastatic disease, one that may be readily combined with other therapeutic strategies.

Adapting a Medical School Cancer Research Education Program to the Virtual Environment: a Mixed-Methods Study.

With cancer incidence increasing worldwide, physicians with cancer research training are needed. The Scholars in Oncology-Associated Research (SOAR) cancer research education program was developed to train medical students in cancer research while exposing them to the breadth of clinical oncology. Due to the COVID-19 pandemic, SOAR transitioned from in-person in 2019 to virtual in 2020 and hybrid in 2021. This study investigates positive and negative aspects of the varying educational formats. A mixed-methods approach was used to evaluate the educational formats. Pre- and post-surveys were collected from participants to assess their understanding of cancer as a clinical and research discipline. Structured interviews were conducted across all three cohorts, and thematic analysis was used to generate themes. A total of 37 students participated in SOAR and completed surveys (2019 n = 11, 2020 n = 14, and 2021 n = 12), and 18 interviews were conducted. Understanding of oncology as a clinical (p < 0.01 for all) and research discipline (p < 0.01 for all) improved within all three cohorts. There was no difference between each cohort's improvement in research understanding (p = 0.6). There was no difference between each cohort's understanding of oncology-related disciplines as both clinical and research disciplines (p > 0.1 for all). Thematic analysis demonstrated that hybrid and in-person formats were favored over a completely virtual one. Our findings demonstrate that a medical student cancer research education program is effective using in-person or hybrid formats for research education, although virtual experiences may be suboptimal to learning about clinical oncology.

A robust and interpretable gene signature for predicting the lymph node status of primary T1/T2 oral cavity squamous cell carcinoma.

Oral cavity squamous cell carcinoma (OSCC) affects more than 30 000 individuals in the United States annually, with smoking and alcohol consumption being the main risk factors. Management of early-stage tumors usually includes surgical resection followed by postoperative radiotherapy in certain cases. The cervical lymph nodes (LNs) are the most common site for local metastasis, and elective neck dissection is usually performed if the primary tumor thickness is greater than 3.5 mm. However, postoperative histological examination often reveals that many patients with early-stage disease are negative for neck nodal metastasis, posing a pressing need for improved risk stratification to either avoid overtreatment or prevent the disease progression. To this end, we aimed to identify a primary tumor gene signature that can accurately predict cervical LN metastasis in patients with early-stage OSCC. Using gene expression profiles from 189 samples, we trained K-top scoring pairs models and identified six gene pairs that can distinguish primary tumors with nodal metastasis from those without metastasis. The signature was further validated on an independent cohort of 35 patients using real-time polymerase chain reaction (PCR) in which it achieved an area under the receiver operating characteristic (ROC) curve and accuracy of 90% and 91%, respectively. These results indicate that such signature holds promise as a quick and cost effective method for detecting patients at high risk of developing cervical LN metastasis, and may be potentially used to guide the neck treatment regimen in early-stage OSCC.

Application of liquid biopsy as multi-functional biomarkers in head and neck cancer.

Head and neck squamous cell carcinoma (HNSCC) is a molecularly heterogeneous disease, with a 5-year survival rate that still hovers at ~60% despite recent advancements. The advanced stage upon diagnosis, limited success with effective targeted therapy and lack of reliable biomarkers are among the key factors underlying the marginally improved survival rates over the decades. Prevention, early detection and biomarker-driven treatment adaptation are crucial for timely interventions and improved clinical outcomes. Liquid biopsy, analysis of tumour-specific biomarkers circulating in bodily fluids, is a rapidly evolving field that may play a striking role in optimising patient care. In recent years, significant progress has been made towards advancing liquid biopsies for non-invasive early cancer detection, prognosis, treatment adaptation, monitoring of residual disease and surveillance of recurrence. While these emerging technologies have immense potential to improve patient survival, numerous methodological and biological limitations must be overcome before their implementation into clinical practice. This review outlines the current state of knowledge on various types of liquid biopsies in HNSCC, and their potential applications for diagnosis, prognosis, grading treatment response and post-treatment surveillance. It also discusses challenges associated with the clinical applicability of liquid biopsies and prospects of the optimised approaches in the management of HNSCC.

Phase I study of nab-paclitaxel-based induction followed by nab-paclitaxel-based concurrent chemotherapy and re-irradiation in previously treated head and neck squamous cell carcinoma.

BACKGROUND: Recurrent head and neck squamous cell carcinoma (HNSCC) is associated with poor overall survival (OS). Prior studies suggested incorporation of nab-paclitaxel (A) may improve outcomes in recurrent HNSCC. METHODS: This Phase I study evaluated induction with carboplatin and A followed by concomitant FHX (infusional 5-fluorouracil, hydroxyurea and twice-daily radiation therapy administered every other week) plus A with cohort dose escalation ranging from 10-100 mg/m2 in recurrent HNSCC. The primary endpoint was maximally tolerated dose (MTD) and dose-limiting toxicity (DLT) of A when given in combination with FHX (AFHX). RESULTS: Forty-eight eligible pts started induction; 28 pts started AFHX and were evaluable for toxicity. Two DLTs occurred (both Grade 4 mucositis) at a dose level 20 mg/m2. No further DLTs were observed with subsequent dose escalation. The MTD and recommended Phase II dose (RP2D) of A was 100 mg/m2. CONCLUSIONS: In this Phase I study, the RP2D of A with FHX is 100 mg/m2 (AFHX). The role of re-irradiation with immunotherapy warrants further investigation. CLINICAL TRIAL INFORMATION: This clinical trial was registered with ClinicalTrials.gov identifier: NCT01847326.

Clinical trials of immunotherapy in triple-negative breast cancer.

PURPOSE: Immunotherapy has started to transform the treatment of triple-negative breast cancer (TNBC), in part due to the unique immunogenicity of this breast cancer subtype. This review summarizes clinical studies of immunotherapy in advanced and early-stage TNBC. FINDINGS: Initial studies of checkpoint blockade monotherapy demonstrated occasional responses, especially in patients with untreated programmed death-ligand 1 (PD-L1) positive advanced TNBC, but failed to confirm a survival advantage over chemotherapy. Nonetheless, pembrolizumab monotherapy has tumor agnostic approval for microsatellite instability-high or high tumor mutational burden cancers, and thus can be considered for select patients with advanced TNBC. Combination chemoimmunotherapy approaches have been more successful, and pembrolizumab is approved for PD-L1 positive advanced TNBC in combination with chemotherapy. This success has been translated to the curative setting, where pembrolizumab is now approved in combination with neoadjuvant chemotherapy for high-risk early-stage TNBC. CONCLUSION: Immunotherapy has been a welcome addition to the growing armamentarium for TNBC, but responses remain limited to a subset of patients. Innovative strategies are under investigation in an attempt to induce immune responses in resistant tumors-with regimens incorporating small-molecule inhibitors, novel immune checkpoint targets, and intratumoral injections that directly alter the tumor microenvironment. As the focus shifts toward the use of immunotherapy for early-stage TNBC, it will be critical to identify those who derive the most benefit from treatment, given the potential for irreversible autoimmune toxicity and the lack of predictive accuracy of PD-L1 expression in the early-stage setting.

Highly accurate response prediction in high-risk early breast cancer patients using a biophysical simulation platform.

PURPOSE: Pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) in early breast cancer (EBC) is largely dependent on breast cancer subtype, but no clinical-grade model exists to predict response and guide selection of treatment. A biophysical simulation of response to NAC has the potential to address this unmet need. METHODS: We conducted a retrospective evaluation of a biophysical simulation model as a predictor of pCR. Patients who received standard NAC at the University of Chicago for EBC between January 1st, 2010 and March 31st, 2020 were included. Response was predicted using baseline breast MRI, clinicopathologic features, and treatment regimen by investigators who were blinded to patient outcomes. RESULTS: A total of 144 tumors from 141 patients were included; 59 were triple-negative, 49 HER2-positive, and 36 hormone-receptor positive/HER2 negative. Lymph node disease was present in half of patients, and most were treated with an anthracycline-based regimen (58.3%). Sensitivity and specificity of the biophysical simulation for pCR were 88.0% (95% confidence interval [CI] 75.7 - 95.5) and 89.4% (95% CI 81.3 - 94.8), respectively, with robust results regardless of subtype. In patients with predicted pCR, 5-year event-free survival was 98%, versus 79% with predicted residual disease (log-rank p = 0.01, HR 4.57, 95% CI 1.36 - 15.34). At a median follow-up of 5.4 years, no patients with predicted pCR experienced disease recurrence. CONCLUSION: A biophysical simulation model accurately predicts pCR and long-term outcomes from baseline MRI and clinical data, and is a promising tool to guide escalation/de-escalation of NAC.

COVIDomic: A multi-modal cloud-based platform for identification of risk factors associated with COVID-19 severity.

Coronavirus disease 2019 (COVID-19) is an acute infection of the respiratory tract that emerged in December 2019 in Wuhan, China. It was quickly established that both the symptoms and the disease severity may vary from one case to another and several strains of SARS-CoV-2 have been identified. To gain a better understanding of the wide variety of SARS-CoV-2 strains and their associated symptoms, thousands of SARS-CoV-2 genomes have been sequenced in dozens of countries. In this article, we introduce COVIDomic, a multi-omics online platform designed to facilitate the analysis and interpretation of the large amount of health data collected from patients with COVID-19. The COVIDomic platform provides a comprehensive set of bioinformatic tools for the multi-modal metatranscriptomic data analysis of COVID-19 patients to determine the origin of the coronavirus strain and the expected severity of the disease. An integrative analytical workflow, which includes microbial pathogens community analysis, COVID-19 genetic epidemiology and patient stratification, allows to analyze the presence of the most common microbial organisms, their antibiotic resistance, the severity of the infection and the set of the most probable geographical locations from which the studied strain could have originated. The online platform integrates a user friendly interface which allows easy visualization of the results. We envision this tool will not only have immediate implications for management of the ongoing COVID-19 pandemic, but will also improve our readiness to respond to other infectious outbreaks.

Deep learning detects genetic alterations in cancer histology generated by adversarial networks.

Deep learning can detect microsatellite instability (MSI) from routine histology images in colorectal cancer (CRC). However, ethical and legal barriers impede sharing of images and genetic data, hampering development of new algorithms for detection of MSI and other biomarkers. We hypothesized that histology images synthesized by conditional generative adversarial networks (CGANs) retain information about genetic alterations. To test this, we developed a 'histology CGAN' which was trained on 256 patients (training cohort 1) and 1457 patients (training cohort 2). The CGAN synthesized 10 000 synthetic MSI and non-MSI images which contained a range of tissue types and were deemed realistic by trained observers in a blinded study. Subsequently, we trained a deep learning detector of MSI on real or synthetic images and evaluated the performance of MSI detection in a held-out set of 142 patients. When trained on real images from training cohort 1, this system achieved an area under the receiver operating curve (AUROC) of 0.742 [0.681, 0.854]. Training on the larger cohort 2 only marginally improved the AUROC to 0.757 [0.707, 0.869]. Training on purely synthetic data resulted in an AUROC of 0.743 [0.658, 0.801]. Training on both real and synthetic data further increased AUROC to 0.777 [0.715, 0.821]. We conclude that synthetic histology images retain information reflecting underlying genetic alterations in colorectal cancer. Using synthetic instead of real images to train deep learning systems yields non-inferior classifiers. This approach can be used to create large shareable data sets or to augment small data sets with rare molecular features. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.

Academics as leaders in the cancer artificial intelligence revolution.

The successful translation of artificial intelligence (AI) applications into clinical cancer care practice requires guidance by academic cancer researchers and providers who are well poised to step into leadership roles. In this commentary, the authors describe the landscape of the deep learning-based AI innovation boom in cancer research. For progress in applied AI research to continue, 4 essential components must be present: algorithms, data, computational resources, and domain-specific expertise. Each of these components is available to researchers and providers in academic settings; in particular, cancer care domain-specific expertise in academia is superb. Three common pitfalls for deep learning research also are detailed along with a discussion of how the academic oncology research environment is well suited to guard against these challenges. In this rapidly developing field, there are few established standards, and oncology researchers and providers must educate themselves about emerging AI technology to avoid common pitfalls and ensure responsible use.

Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning.

BACKGROUND & AIMS: Microsatellite instability (MSI) and mismatch-repair deficiency (dMMR) in colorectal tumors are used to select treatment for patients. Deep learning can detect MSI and dMMR in tumor samples on routine histology slides faster and less expensively than molecular assays. However, clinical application of this technology requires high performance and multisite validation, which have not yet been performed. METHODS: We collected H&E-stained slides and findings from molecular analyses for MSI and dMMR from 8836 colorectal tumors (of all stages) included in the MSIDETECT consortium study, from Germany, the Netherlands, the United Kingdom, and the United States. Specimens with dMMR were identified by immunohistochemistry analyses of tissue microarrays for loss of MLH1, MSH2, MSH6, and/or PMS2. Specimens with MSI were identified by genetic analyses. We trained a deep-learning detector to identify samples with MSI from these slides; performance was assessed by cross-validation (N = 6406 specimens) and validated in an external cohort (n = 771 specimens). Prespecified endpoints were area under the receiver operating characteristic (AUROC) curve and area under the precision-recall curve (AUPRC). RESULTS: The deep-learning detector identified specimens with dMMR or MSI with a mean AUROC curve of 0.92 (lower bound, 0.91; upper bound, 0.93) and an AUPRC of 0.63 (range, 0.59-0.65), or 67% specificity and 95% sensitivity, in the cross-validation development cohort. In the validation cohort, the classifier identified samples with dMMR with an AUROC of 0.95 (range, 0.92-0.96) without image preprocessing and an AUROC of 0.96 (range, 0.93-0.98) after color normalization. CONCLUSIONS: We developed a deep-learning system that detects colorectal cancer specimens with dMMR or MSI using H&E-stained slides; it detected tissues with dMMR with an AUROC of 0.96 in a large, international validation cohort. This system might be used for high-throughput, low-cost evaluation of colorectal tissue specimens.