Prediction of immunotherapy response using mutations to cancer protein assemblies.

While immune checkpoint inhibitors have revolutionized cancer therapy, many patients exhibit poor outcomes. Here, we show immunotherapy responses in bladder and non-small cell lung cancers are effectively predicted by factoring tumor mutation burden (TMB) into burdens on specific protein assemblies. This approach identifies 13 protein assemblies for which the assembly-level mutation burden (AMB) predicts treatment outcomes, which can be combined to powerfully separate responders from nonresponders in multiple cohorts (e.g., 76% versus 37% bladder cancer 1-year survival). These results are corroborated by (i) engineered disruptions in the predictive assemblies, which modulate immunotherapy response in mice, and (ii) histochemistry showing that predicted responders have elevated inflammation. The 13 assemblies have diverse roles in DNA damage checkpoints, oxidative stress, or Janus kinase/signal transducers and activators of transcription signaling and include unexpected genes (e.g., PIK3CG and FOXP1) for which mutation affects treatment response. This study provides a roadmap for using tumor cell biology to factor mutational effects on immune response.

A pathologist-AI collaboration framework for enhancing diagnostic accuracies and efficiencies.

In pathology, the deployment of artificial intelligence (AI) in clinical settings is constrained by limitations in data collection and in model transparency and interpretability. Here we describe a digital pathology framework, nuclei.io, that incorporates active learning and human-in-the-loop real-time feedback for the rapid creation of diverse datasets and models. We validate the effectiveness of the framework via two crossover user studies that leveraged collaboration between the AI and the pathologist, including the identification of plasma cells in endometrial biopsies and the detection of colorectal cancer metastasis in lymph nodes. In both studies, nuclei.io yielded considerable diagnostic performance improvements. Collaboration between clinicians and AI will aid digital pathology by enhancing accuracies and efficiencies.

Prediction of immunochemotherapy response for diffuse large B-cell lymphoma using artificial intelligence digital pathology.

Diffuse large B-cell lymphoma (DLBCL) is a heterogeneous and prevalent subtype of aggressive non-Hodgkin lymphoma that poses diagnostic and prognostic challenges, particularly in predicting drug responsiveness. In this study, we used digital pathology and deep learning to predict responses to immunochemotherapy in patients with DLBCL. We retrospectively collected 251 slide images from 216 DLBCL patients treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP), with their immunochemotherapy response labels. The digital pathology images were processed using contrastive learning for feature extraction. A multi-modal prediction model was developed by integrating clinical data and pathology image features. Knowledge distillation was employed to mitigate overfitting on gigapixel histopathology images to create a model that predicts responses based solely on pathology images. Based on the importance derived from the attention mechanism of the model, we extracted histological features that were considered key textures associated with drug responsiveness. The multi-modal prediction model achieved an impressive area under the ROC curve of 0.856, demonstrating significant associations with clinical variables such as Ann Arbor stage, International Prognostic Index, and bulky disease. Survival analyses indicated their effectiveness in predicting relapse-free survival. External validation using TCGA datasets supported the model's ability to predict survival differences. Additionally, pathology-based predictions show promise as independent prognostic indicators. Histopathological analysis identified centroblastic and immunoblastic features to be associated with treatment response, aligning with previous morphological classifications and highlighting the objectivity and reproducibility of artificial intelligence-based diagnosis. This study introduces a novel approach that combines digital pathology and clinical data to predict the response to immunochemotherapy in patients with DLBCL. This model shows great promise as a diagnostic and prognostic tool for clinical management of DLBCL. Further research and genomic data integration hold the potential to enhance its impact on clinical practice, ultimately improving patient outcomes.

Spatially Segregated Macrophage Populations Predict Distinct Outcomes in Colon Cancer.

Tumor-associated macrophages are transcriptionally heterogeneous, but the spatial distribution and cell interactions that shape macrophage tissue roles remain poorly characterized. Here, we spatially resolve five distinct human macrophage populations in normal and malignant human breast and colon tissue and reveal their cellular associations. This spatial map reveals that distinct macrophage populations reside in spatially segregated micro-environmental niches with conserved cellular compositions that are repeated across healthy and diseased tissue. We show that IL4I1+ macrophages phagocytose dying cells in areas with high cell turnover and predict good outcome in colon cancer. In contrast, SPP1+ macrophages are enriched in hypoxic and necrotic tumor regions and portend worse outcome in colon cancer. A subset of FOLR2+ macrophages is embedded in plasma cell niches. NLRP3+ macrophages co-localize with neutrophils and activate an inflammasome in tumors. Our findings indicate that a limited number of unique human macrophage niches function as fundamental building blocks in tissue. Significance: This work broadens our understanding of the distinct roles different macrophage populations may exert on cancer growth and reveals potential predictive markers and macrophage population-specific therapy targets.

Generation of synthetic whole-slide image tiles of tumours from RNA-sequencing data via cascaded diffusion models.

Training machine-learning models with synthetically generated data can alleviate the problem of data scarcity when acquiring diverse and sufficiently large datasets is costly and challenging. Here we show that cascaded diffusion models can be used to synthesize realistic whole-slide image tiles from latent representations of RNA-sequencing data from human tumours. Alterations in gene expression affected the composition of cell types in the generated synthetic image tiles, which accurately preserved the distribution of cell types and maintained the cell fraction observed in bulk RNA-sequencing data, as we show for lung adenocarcinoma, kidney renal papillary cell carcinoma, cervical squamous cell carcinoma, colon adenocarcinoma and glioblastoma. Machine-learning models pretrained with the generated synthetic data performed better than models trained from scratch. Synthetic data may accelerate the development of machine-learning models in scarce-data settings and allow for the imputation of missing data modalities.

Inflamed immune phenotype predicts favorable clinical outcomes of immune checkpoint inhibitor therapy across multiple cancer types.

BACKGROUND: The inflamed immune phenotype (IIP), defined by enrichment of tumor-infiltrating lymphocytes (TILs) within intratumoral areas, is a promising tumor-agnostic biomarker of response to immune checkpoint inhibitor (ICI) therapy. However, it is challenging to define the IIP in an objective and reproducible manner during manual histopathologic examination. Here, we investigate artificial intelligence (AI)-based immune phenotypes capable of predicting ICI clinical outcomes in multiple solid tumor types. METHODS: Lunit SCOPE IO is a deep learning model which determines the immune phenotype of the tumor microenvironment based on TIL analysis. We evaluated the correlation between the IIP and ICI treatment outcomes in terms of objective response rates (ORR), progression-free survival (PFS), and overall survival (OS) in a cohort of 1,806 ICI-treated patients representing over 27 solid tumor types retrospectively collected from multiple institutions. RESULTS: We observed an overall IIP prevalence of 35.2% and significantly more favorable ORRs (26.3% vs 15.8%), PFS (median 5.3 vs 3.1 months, HR 0.68, 95% CI 0.61 to 0.76), and OS (median 25.3 vs 13.6 months, HR 0.66, 95% CI 0.57 to 0.75) after ICI therapy in IIP compared with non-IIP patients, respectively (p<0.001 for all comparisons). On subgroup analysis, the IIP was generally prognostic of favorable PFS across major patient subgroups, with the exception of the microsatellite unstable/mismatch repair deficient subgroup. CONCLUSION: The AI-based IIP may represent a practical, affordable, clinically actionable, and tumor-agnostic biomarker prognostic of ICI therapy response across diverse tumor types.

A spatially mapped gene expression signature for intestinal stem-like cells identifies high-risk precursors of gastric cancer.

Objective: Gastric intestinal metaplasia (GIM) is a precancerous lesion that increases gastric cancer (GC) risk. The Operative Link on GIM (OLGIM) is a combined clinical-histopathologic system to risk-stratify patients with GIM. The identification of molecular biomarkers that are indicators for advanced OLGIM lesions may improve cancer prevention efforts. Methods: This study was based on clinical and genomic data from four cohorts: 1) GAPS, a GIM cohort with detailed OLGIM severity scoring (N=303 samples); 2) the Cancer Genome Atlas (N=198); 3) a collation of in-house and publicly available scRNA-seq data (N=40), and 4) a spatial validation cohort (N=5) consisting of annotated histology slides of patients with either GC or advanced GIM. We used a multi-omics pipeline to identify, validate and sequentially parse a highly-refined signature of 26 genes which characterize high-risk GIM. Results: Using standard RNA-seq, we analyzed two separate, non-overlapping discovery (N=88) and validation (N=215) sets of GIM. In the discovery phase, we identified 105 upregulated genes specific for high-risk GIM (defined as OLGIM III-IV), of which 100 genes were independently confirmed in the validation set. Spatial transcriptomic profiling revealed 36 of these 100 genes to be expressed in metaplastic foci in GIM. Comparison with bulk GC sequencing data revealed 26 of these genes to be expressed in intestinal-type GC. Single-cell profiling resolved the 26-gene signature to both mature intestinal lineages (goblet cells, enterocytes) and immature intestinal lineages (stem-like cells). A subset of these genes was further validated using single-molecule multiplex fluorescence in situ hybridization. We found certain genes (TFF3 and ANPEP) to mark differentiated intestinal lineages, whereas others (OLFM4 and CPS1) localized to immature cells in the isthmic/crypt region of metaplastic glands, consistent with the findings from scRNAseq analysis. Conclusions: using an integrated multi-omics approach, we identified a novel 26-gene expression signature for high-OLGIM precursors at increased risk for GC. We found this signature localizes to aberrant intestinal stem-like cells within the metaplastic microenvironment. These findings hold important translational significance for future prevention and early detection efforts.

Ampullary Adenocarcinoma, Version 1.2023, NCCN Clinical Practice Guidelines in Oncology.

Ampullary cancers refer to tumors originating from the ampulla of Vater (the ampulla, the intraduodenal portion of the bile duct, and the intraduodenal portion of the pancreatic duct), while periampullary cancers may arise from locations encompassing the head of the pancreas, distal bile duct, duodenum, or ampulla of Vater. Ampullary cancers are rare gastrointestinal malignancies, and prognosis varies greatly based on factors such as patient age, TNM classification, differentiation grade, and treatment modality received. Systemic therapy is used in all stages of ampullary cancer, including neoadjuvant therapy, adjuvant therapy, and first-line or subsequent-line therapy for locally advanced, metastatic, and recurrent disease. Radiation therapy may be used in localized ampullary cancer, sometimes in combination with chemotherapy, but there is no high-level evidence to support its utility. Select tumors may be treated surgically. This article describes NCCN recommendations regarding management of ampullary adenocarcinoma.

Predicting lymph node metastasis from primary tumor histology and clinicopathologic factors in colorectal cancer using deep learning.

BACKGROUND: Presence of lymph node metastasis (LNM) influences prognosis and clinical decision-making in colorectal cancer. However, detection of LNM is variable and depends on a number of external factors. Deep learning has shown success in computational pathology, but has struggled to boost performance when combined with known predictors. METHODS: Machine-learned features are created by clustering deep learning embeddings of small patches of tumor in colorectal cancer via k-means, and then selecting the top clusters that add predictive value to a logistic regression model when combined with known baseline clinicopathological variables. We then analyze performance of logistic regression models trained with and without these machine-learned features in combination with the baseline variables. RESULTS: The machine-learned extracted features provide independent signal for the presence of LNM (AUROC: 0.638, 95% CI: [0.590, 0.683]). Furthermore, the machine-learned features add predictive value to the set of 6 clinicopathologic variables in an external validation set (likelihood ratio test, p < 0.00032; AUROC: 0.740, 95% CI: [0.701, 0.780]). A model incorporating these features can also further risk-stratify patients with and without identified metastasis (p < 0.001 for both stage II and stage III). CONCLUSION: This work demonstrates an effective approach to combine deep learning with established clinicopathologic factors in order to identify independently informative features associated with LNM. Further work building on these specific results may have important impact in prognostication and therapeutic decision making for LNM. Additionally, this general computational approach may prove useful in other contexts.

When colorectal cancers spread to the lymph nodes, it can indicate a poorer prognosis. However, detecting lymph node metastasis (spread) can be difficult and depends on a number of factors such as how samples are taken and processed. Here, we show that machine learning, which involves computer software learning from patterns in data, can predict lymph node metastasis in patients with colorectal cancer from the microscopic appearance of their primary tumor and the clinical characteristics of the patients. We also show that the same approach can predict patient survival. With further work, our approach may help clinicians to inform patients about their prognosis and decide on appropriate treatments.

Xanthogranulomatous inflammation requiring small bowel anastomosis revision: A case report.

BACKGROUND: Xanthogranulomatous inflammation (XGI) is an uncommon process involving an accumulation of inflammatory cells, commonly lipid-laden macrophages. XGI has been described to occur throughout the body but only rarely in the lower gastrointestinal tract. We describe a case of XGI contributing to chronic obstructive symptoms in the terminal ileum, in which the patient had an initial diagnostic laparoscopy, continued to have symptoms, then proceeded to have the definitive treatment. To our knowledge, this is the first report of XGI associated with a prior small bowel anastomosis. CASE SUMMARY: We report the case of a 42-year-old female who presented with intermittent epigastric pain and subjective fevers. She had undergone a laparoscopic small bowel resection for Meckel's diverticulum five years prior. Her workup was notable for computed tomography scan demonstrating mild inflammation and surrounding stranding at the level of the prior anastomosis. She underwent a laparotomy, resection of the prior anastomosis and re-anastomosis, with final histopathological examination findings consistent with mural XGI. CONCLUSION: XGI can occur at the site of a prior bowel anastomosis and cause chronic obstructive symptoms.

Small bowel adenocarcinoma in neoterminal ileum in setting of stricturing Crohn's disease: A case report and review of literature.

BACKGROUND: Small bowel adenocarcinomas (SBA) are rare malignancies with exceedingly low survival rates, with different presentation in Crohn's disease (CD). CD-induced SBA poses diagnostic challenges given overlapping presentation with stricturing CD and lack of diagnostics for early detection. Moreover, guidance is lacking on the impact of recently approved therapeutics in CD on SBA management. Here, we aim to highlight the future of CD-induced SBA management and discuss the potential merit of balloon enteroscopy and genetic testing for earlier detection. CASE SUMMARY: We report the case of a 60-year-old female with longstanding Crohn's ileitis, presenting with acute obstructive symptoms attributed to stricturing phenotype. Her obstructive symptoms were refractory to intravenous (IV) steroids, with further investigation via computed tomography enterography not providing additional diagnostic yield. Ultimately, surgical resection revealed SBA in the neoterminal ileum, with oncologic therapy plan created. However, this therapy plan could not be initiated due to continued obstructive symptoms attributed to active CD. Ultimately, infused biologic therapy was initiated, but her obstructive symptoms continued to remain dependent on IV corticosteroids. Review of diagnostics by a multidisciplinary care team suggested metastatic disease in the peritoneum, lending to a shift in the goals of care to comfort. CONCLUSION: With the diagnostic and therapeutic challenges of concurrent SBA and CD, multidisciplinary care and algorithmic management can optimize outcomes.

Development and Validation of a Machine Learning Model for Detection and Classification of Tertiary Lymphoid Structures in Gastrointestinal Cancers.

Importance: Tertiary lymphoid structures (TLSs) are associated with a favorable prognosis and improved response to cancer immunotherapy. The current approach for evaluation of TLSs is limited by interobserver variability and high complexity and cost of specialized imaging techniques. Objective: To develop a machine learning model for automated and quantitative evaluation of TLSs based on routine histopathology images. Design, Setting, and Participants: In this multicenter, international diagnostic/prognostic study, an interpretable machine learning model was developed and validated for automated detection, enumeration, and classification of TLSs in hematoxylin-eosin-stained images. A quantitative scoring system for TLSs was proposed, and its association with survival was investigated in patients with 1 of 6 types of gastrointestinal cancers. Data analysis was performed between June 2021 and March 2022. Main Outcomes and Measures: The diagnostic accuracy for classification of TLSs into 3 maturation states and the association of TLS score with survival were investigated. Results: A total of 1924 patients with gastrointestinal cancer from 7 independent cohorts (median [IQR] age ranging from 57 [49-64] years to 68 [58-77] years; proportion by sex ranging from 214 of 409 patients who were male [52.3%] to 134 of 155 patients who were male [86.5%]). The machine learning model achieved high accuracies for detecting and classifying TLSs into 3 states (TLS1: 97.7%; 95% CI, 96.4%-99.0%; TLS2: 96.3%; 95% CI, 94.6%-98.0%; TLS3: 95.7%; 95% CI, 93.9%-97.5%). TLSs were detected in 62 of 155 esophageal cancers (40.0%) and up to 267 of 353 gastric cancers (75.6%). Across 6 cancer types, patients were stratified into 3 risk groups (higher and lower TLS score and no TLS) and survival outcomes compared between groups: higher vs lower TLS score (hazard ratio [HR]; 0.27; 95% CI, 0.18-0.41; P < .001) and lower TLS score vs no TLSs (HR, 0.65; 95% CI, 0.56-0.76; P < .001). TLS score remained an independent prognostic factor associated with survival after adjusting for clinicopathologic variables and tumor-infiltrating lymphocytes (eg, for colon cancer: HR, 0.11; 95% CI, 0.02-0.47; P = .003). Conclusions and Relevance: In this study, an interpretable machine learning model was developed that may allow automated and accurate detection of TLSs on routine tissue slide. This model is complementary to the cancer staging system for risk stratification in gastrointestinal cancers.

RNA-to-image multi-cancer synthesis using cascaded diffusion models.

Data scarcity presents a significant obstacle in the field of biomedicine, where acquiring diverse and sufficient datasets can be costly and challenging. Synthetic data generation offers a potential solution to this problem by expanding dataset sizes, thereby enabling the training of more robust and generalizable machine learning models. Although previous studies have explored synthetic data generation for cancer diagnosis, they have predominantly focused on single modality settings, such as whole-slide image tiles or RNA-Seq data. To bridge this gap, we propose a novel approach, RNA-Cascaded-Diffusion-Model or RNA-CDM, for performing RNA-to-image synthesis in a multi-cancer context, drawing inspiration from successful text-to-image synthesis models used in natural images. In our approach, we employ a variational auto-encoder to reduce the dimensionality of a patient's gene expression profile, effectively distinguishing between different types of cancer. Subsequently, we employ a cascaded diffusion model to synthesize realistic whole-slide image tiles using the latent representation derived from the patient's RNA-Seq data. Our results demonstrate that the generated tiles accurately preserve the distribution of cell types observed in real-world data, with state-of-the-art cell identification models successfully detecting important cell types in the synthetic samples. Furthermore, we illustrate that the synthetic tiles maintain the cell fraction observed in bulk RNA-Seq data and that modifications in gene expression affect the composition of cell types in the synthetic tiles. Next, we utilize the synthetic data generated by RNA-CDM to pretrain machine learning models and observe improved performance compared to training from scratch. Our study emphasizes the potential usefulness of synthetic data in developing machine learning models in sarce-data settings, while also highlighting the possibility of imputing missing data modalities by leveraging the available information. In conclusion, our proposed RNA-CDM approach for synthetic data generation in biomedicine, particularly in the context of cancer diagnosis, offers a novel and promising solution to address data scarcity. By generating synthetic data that aligns with real-world distributions and leveraging it to pretrain machine learning models, we contribute to the development of robust clinical decision support systems and potential advancements in precision medicine.

A spatial map of human macrophage niches reveals context-dependent macrophage functions in colon and breast cancer.

Tumor-associated macrophages (TAMs) display heterogeneous phenotypes. Yet the exact tissue cues that shape macrophage functional diversity are incompletely understood. Here we discriminate, spatially resolve and reveal the function of five distinct macrophage niches within malignant and benign breast and colon tissue. We found that SPP1 TAMs reside in hypoxic and necrotic tumor regions, and a novel subset of FOLR2 tissue resident macrophages (TRMs) supports the plasma cell tissue niche. We discover that IL4I1 macrophages populate niches with high cell turnover where they phagocytose dying cells. Significantly, IL4I1 TAMs abundance correlates with anti-PD1 treatment response in breast cancer. Furthermore, NLRP3 inflammasome activation in NLRP3 TAMs correlates with neutrophil infiltration in the tumors and is associated with poor outcome in breast cancer patients. This suggests the NLRP3 inflammasome as a novel cancer immunetherapy target. Our work uncovers context-dependent roles of macrophage subsets, and suggests novel predictive markers and macrophage subset-specific therapy targets.

Single-cell analyses define a continuum of cell state and composition changes in the malignant transformation of polyps to colorectal cancer.

To chart cell composition and cell state changes that occur during the transformation of healthy colon to precancerous adenomas to colorectal cancer (CRC), we generated single-cell chromatin accessibility profiles and single-cell transcriptomes from 1,000 to 10,000 cells per sample for 48 polyps, 27 normal tissues and 6 CRCs collected from patients with or without germline APC mutations. A large fraction of polyp and CRC cells exhibit a stem-like phenotype, and we define a continuum of epigenetic and transcriptional changes occurring in these stem-like cells as they progress from homeostasis to CRC. Advanced polyps contain increasing numbers of stem-like cells, regulatory T cells and a subtype of pre-cancer-associated fibroblasts. In the cancerous state, we observe T cell exhaustion, RUNX1-regulated cancer-associated fibroblasts and increasing accessibility associated with HNF4A motifs in epithelia. DNA methylation changes in sporadic CRC are strongly anti-correlated with accessibility changes along this continuum, further identifying regulatory markers for molecular staging of polyps.

Pepsinogens and Gastrin Demonstrate Low Discrimination for Gastric Precancerous Lesions in a Multi-Ethnic United States Cohort.

Early identification of gastric precancerous lesions, including atrophic gastritis (AG) and intestinal metaplasia (IM), may improve gastric cancer detection and prevention. Because AG and IM are generally asymptomatic, many of the estimated 15 million Americans who carry these lesions remain undiagnosed.1 AG and IM are associated with either active or prior Helicobacter pylori (Hp) infection. Hp infection leads to perturbations in the serum concentration of gastric hormones pepsinogen I (PGI), pepsinogen II, the pepsinogen I/II ratio (PGR), gastrin-17 (G-17), and Hp IgG.2,3 In East Asia and other regions with high burden of Hp infection and gastric cancer, these biomarkers have been used as screening tools for AG and IM.4 However, there exists limited data on the sensitivity and discrimination of these serologic markers in low-Hp-prevalence populations, such as the United States.

Pancreatic Adenocarcinoma, Version 2.2021, NCCN Clinical Practice Guidelines in Oncology.

Pancreatic cancer is the fourth leading cause of cancer-related death among men and women in the United States. A major challenge in treatment remains patients' advanced disease at diagnosis. The NCCN Guidelines for Pancreatic Adenocarcinoma provides recommendations for the diagnosis, evaluation, treatment, and follow-up for patients with pancreatic cancer. Although survival rates remain relatively unchanged, newer modalities of treatment, including targeted therapies, provide hope for improving patient outcomes. Sections of the manuscript have been updated to be concordant with the most recent update to the guidelines. This manuscript focuses on the available systemic therapy approaches, specifically the treatment options for locally advanced and metastatic disease.

Development and Use of Natural Language Processing for Identification of Distant Cancer Recurrence and Sites of Distant Recurrence Using Unstructured Electronic Health Record Data.

PURPOSE: Large-scale analysis of real-world evidence is often limited to structured data fields that do not contain reliable information on recurrence status and disease sites. In this report, we describe a natural language processing (NLP) framework that uses data from free-text, unstructured reports to classify recurrence status and sites of recurrence for patients with breast and hepatocellular carcinomas (HCC). METHODS: Using two cohorts of breast cancer and HCC cases, we validated the ability of a previously developed NLP model to distinguish between no recurrence, local recurrence, and distant recurrence, based on clinician notes, radiology reports, and pathology reports compared with manual curation. A second NLP model was trained and validated to identify sites of recurrence. We compared the ability of each NLP model to identify the presence, timing, and site of recurrence, when compared against manual chart review and International Classification of Diseases coding. RESULTS: A total of 1,273 patients were included in the development and validation of the two models. The NLP model for recurrence detects distant recurrence with an area under the curve of 0.98 (95% CI, 0.96 to 0.99) and 0.95 (95% CI, 0.88 to 0.98) in breast and HCC cohorts, respectively. The mean accuracy of the NLP model for detecting any site of distant recurrence was 0.9 for breast cancer and 0.83 for HCC. The NLP model for recurrence identified a larger proportion of patients with distant recurrence in a breast cancer database (11.1%) compared with International Classification of Diseases coding (2.31%). CONCLUSION: We developed two NLP models to identify distant cancer recurrence, timing of recurrence, and sites of recurrence based on unstructured electronic health record data. These models can be used to perform large-scale retrospective studies in oncology.

Deep learning predicts postsurgical recurrence of hepatocellular carcinoma from digital histopathologic images.

Recurrence risk stratification of patients undergoing primary surgical resection for hepatocellular carcinoma (HCC) is an area of active investigation, and several staging systems have been proposed to optimize treatment strategies. However, as many as 70% of patients still experience tumor recurrence at 5 years post-surgery. We developed and validated a deep learning-based system (HCC-SurvNet) that provides risk scores for disease recurrence after primary resection, directly from hematoxylin and eosin-stained digital whole-slide images of formalin-fixed, paraffin embedded liver resections. Our model achieved concordance indices of 0.724 and 0.683 on the internal and external test cohorts, respectively, exceeding the performance of the standard Tumor-Node-Metastasis classification system. The model's risk score stratified patients into low- and high-risk subgroups with statistically significant differences in their survival distributions, and was an independent risk factor for post-surgical recurrence in both test cohorts. Our results suggest that deep learning-based models can provide recurrence risk scores which may augment current patient stratification methods and help refine the clinical management of patients undergoing primary surgical resection for HCC.

Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study.

BACKGROUND: Detecting microsatellite instability (MSI) in colorectal cancer is crucial for clinical decision making, as it identifies patients with differential treatment response and prognosis. Universal MSI testing is recommended, but many patients remain untested. A critical need exists for broadly accessible, cost-efficient tools to aid patient selection for testing. Here, we investigate the potential of a deep learning-based system for automated MSI prediction directly from haematoxylin and eosin (H&E)-stained whole-slide images (WSIs). METHODS: Our deep learning model (MSINet) was developed using 100 H&E-stained WSIs (50 with microsatellite stability [MSS] and 50 with MSI) scanned at 40× magnification, each from a patient randomly selected in a class-balanced manner from the pool of 343 patients who underwent primary colorectal cancer resection at Stanford University Medical Center (Stanford, CA, USA; internal dataset) between Jan 1, 2015, and Dec 31, 2017. We internally validated the model on a holdout test set (15 H&E-stained WSIs from 15 patients; seven cases with MSS and eight with MSI) and externally validated the model on 484 H&E-stained WSIs (402 cases with MSS and 77 with MSI; 479 patients) from The Cancer Genome Atlas, containing WSIs scanned at 40× and 20× magnification. Performance was primarily evaluated using the sensitivity, specificity, negative predictive value (NPV), and area under the receiver operating characteristic curve (AUROC). We compared the model's performance with that of five gastrointestinal pathologists on a class-balanced, randomly selected subset of 40× magnification WSIs from the external dataset (20 with MSS and 20 with MSI). FINDINGS: The MSINet model achieved an AUROC of 0·931 (95% CI 0·771-1·000) on the holdout test set from the internal dataset and 0·779 (0·720-0·838) on the external dataset. On the external dataset, using a sensitivity-weighted operating point, the model achieved an NPV of 93·7% (95% CI 90·3-96·2), sensitivity of 76·0% (64·8-85·1), and specificity of 66·6% (61·8-71·2). On the reader experiment (40 cases), the model achieved an AUROC of 0·865 (95% CI 0·735-0·995). The mean AUROC performance of the five pathologists was 0·605 (95% CI 0·453-0·757). INTERPRETATION: Our deep learning model exceeded the performance of experienced gastrointestinal pathologists at predicting MSI on H&E-stained WSIs. Within the current universal MSI testing paradigm, such a model might contribute value as an automated screening tool to triage patients for confirmatory testing, potentially reducing the number of tested patients, thereby resulting in substantial test-related labour and cost savings. FUNDING: Stanford Cancer Institute and Stanford Departments of Pathology and Biomedical Data Science.