Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning

Defining a 'cells to society' research framework for appendiceal tumours

Tumours of the appendix - a vestigial digestive organ attached to the colon - are rare. Although we estimate that around 3,000 new appendiceal cancer cases are diagnosed annually in the USA, the challenges of accurately diagnosing and identifying this tumour type suggest that this number may underestimate true population incidence. In the current absence of disease-specific screening and diagnostic imaging modalities, or well-established risk factors, the incidental discovery of appendix tumours is often prompted by acute presentations mimicking appendicitis or when the tumour has already spread into the abdominal cavity - wherein the potential misclassification of appendiceal tumours as malignancies of the colon and ovaries also increases. Notwithstanding these diagnostic difficulties, our understanding of appendix carcinogenesis has advanced in recent years. However, there persist considerable challenges to accelerating the pace of research discoveries towards the path to improved treatments and cures for patients with this group of orphan malignancies. The premise of this Expert Recommendation article is to discuss the current state of the field, to delineate unique challenges for the study of appendiceal tumours, and to propose key priority research areas that will deliver a more complete picture of appendix carcinogenesis and metastasis. The Appendix Cancer Pseudomyxoma Peritonei (ACPMP) Research Foundation Scientific Think Tank delivered a consensus of core research priorities for appendiceal tumours that are poised to be ground-breaking and transformative for scientific discovery and innovation. On the basis of these six research areas, here, we define the first 'cells to society' research framework for appendix tumours.

Decoding pathology: the role of computational pathology in research and diagnostics

Traditional histopathology, characterized by manual quantifications and assessments, faces challenges such as low-throughput and inter-observer variability that hinder the introduction of precision medicine in pathology diagnostics and research. The advent of digital pathology allowed the introduction of computational pathology, a discipline that leverages computational methods, especially based on deep learning (DL) techniques, to analyze histopathology specimens. A growing body of research shows impressive performances of DL-based models in pathology for a multitude of tasks, such as mutation prediction, large-scale pathomics analyses, or prognosis prediction. New approaches integrate multimodal data sources and increasingly rely on multi-purpose foundation models. This review provides an introductory overview of advancements in computational pathology and discusses their implications for the future of histopathology in research and diagnostics.

Self-interactive learning: Fusion and evolution of multi-scale histomorphology features for molecular traits prediction in computational pathology

Predicting disease-related molecular traits from histomorphology brings great opportunities for precision medicine. Despite the rich information present in histopathological images, extracting fine-grained molecular features from standard whole slide images (WSI) is non-trivial. The task is further complicated by the lack of annotations for subtyping and contextual histomorphological features that might span multiple scales. This work proposes a novel multiple-instance learning (MIL) framework capable of WSI-based cancer morpho-molecular subtyping by fusion of different-scale features. Our method, debuting as Inter-MIL, follows a weakly-supervised scheme. It enables the training of the patch-level encoder for WSI in a task-aware optimisation procedure, a step normally not modelled in most existing MIL-based WSI analysis frameworks. We demonstrate that optimising the patch-level encoder is crucial to achieving high-quality fine-grained and tissue-level subtyping results and offers a significant improvement over task-agnostic encoders. Our approach deploys a pseudo-label propagation strategy to update the patch encoder iteratively, allowing discriminative subtype features to be learned. This mechanism also empowers extracting fine-grained attention within image tiles (the small patches), a task largely ignored in most existing weakly supervised-based frameworks. With Inter-MIL, we carried out four challenging cancer molecular subtyping tasks in the context of ovarian, colorectal, lung, and breast cancer. Extensive evaluation results show that Inter-MIL is a robust framework for cancer morpho-molecular subtyping with superior performance compared to several recently proposed methods, in small dataset scenarios where the number of available training slides is less than 100. The iterative optimisation mechanism of Inter-MIL significantly improves the quality of the image features learned by the patch embedded and generally directs the attention map to areas that better align with experts' interpretation, leading to the identification of more reliable histopathology biomarkers. Moreover, an external validation cohort is used to verify the robustness of Inter-MIL on molecular trait prediction.

Differentiating Separate Primary Lung Adenocarcinomas From Intrapulmonary Metastases With Emphasis on Pathological and Molecular Considerations: Recommendations From the International Association for the Study of Lung Cancer Pathology Committee

INTRODUCTION

With the implementation of low-dose computed tomography screening, multiple pulmonary tumor nodules are diagnosed with increasing frequency and the selection of surgical treatments versus systemic therapies has become challenging on a daily basis in clinical practice. In the presence of multiple carcinomas, especially adenocarcinomas, pathologically determined to be of pulmonary origin, the distinction between separate primary lung carcinomas (SPLCs) and intrapulmonary metastases (IPMs) is important for staging, management, and prognostication.

METHODS

We systemically reviewed various means that aid in the differentiation between SPLCs and IPMs explored by histopathologic evaluation and molecular profiling, the latter includes DNA microsatellite analysis, array comparative genomic hybridization, TP53 and oncogenic driver mutation testing and, more recently, with promising effectiveness, next-generation sequencing comprising small- or large-scale multi-gene panels.

RESULTS

Comprehensive histologic evaluation may suffice to differentiate between SPLCs and IPMs. Nevertheless, molecular profiling using larger-scale next-generation sequencing typically provides superior discriminatory power, allowing for more accurate classification. On the basis of the literature review and expert opinions, we proposed a combined four-step histologic and molecular classification algorithm for addressing multiple pulmonary tumor nodules of adenocarcinoma histology that encourages a multidisciplinary approach. It is also noteworthy that new technologies combining machine learning and digital pathology may develop into valuable diagnostic tools for distinguishing SPLCs from IPMs in the future.

CONCLUSIONS

Although histopathologic evaluation is often adequate to differentiate SPLCs from IPMs, molecular profiling should be performed when possible, especially in cases with tumors exhibiting similar morphology. This manuscript summarized the previous efforts in resolving the current challenges and highlighted the recent progress in the differentiation methods and algorithms used in categorizing multiple lung adenocarcinomas into SPLCs or IPMs, which are becoming more and more critical in precision lung cancer management.

Prognosis in stage II colon cancer: Expanding the horizons of risk factors

In the following editorial, we discuss the article by Wu et al. In this contribution, we critically review the authors' perspective and analyze the relevance of the results obtained in the original article of clinical research by Liu et al. We consider that additional factors associated with colon cancer progression have recently been described in extensive clinical research, and should be included in this analysis to achieve a more accurate prognosis. These factors include inflammation, gut microbiota composition, immune status and nutritional balance, as they influence the post-surgical survival profile of patients with stage II colorectal cancer. We also address the clinical implementation and limitations of these analyses. Evaluation of the patient´s entire context is essential for selection of the most appropriate therapy.

Deep learning-assisted colonoscopy images for prediction of mismatch repair deficiency in colorectal cancer

BACKGROUND

Deficient mismatch repair or microsatellite instability is a major predictive biomarker for the efficacy of immune checkpoint inhibitors of colorectal cancer. However, routine testing has not been uniformly implemented due to cost and resource constraints.

METHODS

We developed and validated a deep learning-based classifiers to detect mismatch repair-deficient status from routine colonoscopy images. We obtained the colonoscopy images from the imaging database at Endoscopic Center of the Sixth Affiliated Hospital, Sun Yat-sen University. Colonoscopy images from a prospective trial (Neoadjuvant PD-1 blockade by toripalimab with or without celecoxib in mismatch repair-deficient or microsatellite instability-high locally advanced colorectal cancer) were used to test the model.

RESULTS

A total of 5226 eligible images from 892 tumors from the consecutive patients were utilized to develop and validate the deep learning model. 2105 colorectal cancer images from 306 tumors were randomly selected to form model development dataset with a class-balanced approach. 3121 images of 488 proficient mismatch repair tumors and 98 deficient mismatch repair tumors were used to form the independent dataset. The model achieved an AUROC of 0.948 (95% CI 0.919-0.977) on the test dataset. On the independent validation dataset, the AUROC was 0.807 (0.760-0.854), and the NPV in was 94.2% (95% CI 0.918-0.967). On the prospective trial dataset, the model identified 29 tumors among the 33 deficient mismatch repair tumors (87.88%).

CONCLUSIONS

The model achieved a high NPV in detecting deficient mismatch repair colorectal cancers. This model might serve as an automatic screening tool.

Tumour purity assessment with deep learning in colorectal cancer and impact on molecular analysis

Tumour content plays a pivotal role in directing the bioinformatic analysis of molecular profiles such as copy number variation (CNV). In clinical application, tumour purity estimation (TPE) is achieved either through visual pathological review [conventional pathology (CP)] or the deconvolution of molecular data. While CP provides a direct measurement, it demonstrates modest reproducibility and lacks standardisation. Conversely, deconvolution methods offer an indirect assessment with uncertain accuracy, underscoring the necessity for innovative approaches. SoftCTM is an open-source, multiorgan deep-learning (DL) model for the detection of tumour and non-tumour cells in H&E-stained slides, developed within the Overlapped Cell on Tissue Dataset for Histopathology (OCELOT) Challenge 2023. Here, using three large multicentre colorectal cancer (CRC) cohorts (N = 1,097 patients) with digital pathology and multi-omic data, we compare the utility and accuracy of TPE with SoftCTM versus CP and bioinformatic deconvolution methods (RNA expression, DNA methylation) for downstream molecular analysis, including CNV profiling. SoftCTM showed technical repeatability when applied twice on the same slide (r = 1.0) and excellent correlations in paired H&E slides (r > 0.9). TPEs profiled by SoftCTM correlated highly with RNA expression (r = 0.59) and DNA methylation (r = 0.40), while TPEs by CP showed a lower correlation with RNA expression (r = 0.41) and DNA methylation (r = 0.29). We show that CP and deconvolution methods respectively underestimate and overestimate tumour content compared to SoftCTM, resulting in 6-13% differing CNV calls. In summary, TPE with SoftCTM enables reproducibility, automation, and standardisation at single-cell resolution. SoftCTM estimates (M = 58.9%, SD ±16.3%) reconcile the overestimation by molecular data extrapolation (RNA expression: M = 79.2%, SD ±10.5, DNA methylation: M = 62.7%, SD ±11.8%) and underestimation by CP (M = 35.9%, SD ±13.1%), providing a more reliable middle ground. A fully integrated computational pathology solution could therefore be used to improve downstream molecular analyses for research and clinics. © 2024 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Cancer molecular subtyping using limited multi-omics data with missingness

Diagnosing cancer subtypes is a prerequisite for precise treatment. Existing multi-omics data fusion-based diagnostic solutions build on the requisite of sufficient samples with complete multi-omics data, which is challenging to obtain in clinical applications. To address the bottleneck of collecting sufficient samples with complete data in clinical applications, we proposed a flexible integrative model (CancerSD) to diagnose cancer subtype using limited samples with incomplete multi-omics data. CancerSD designs contrastive learning tasks and masking-and-reconstruction tasks to reliably impute missing omics, and fuses available omics data with the imputed ones to accurately diagnose cancer subtypes. To address the issue of limited clinical samples, it introduces a category-level contrastive loss to extend the meta-learning framework, effectively transferring knowledge from external datasets to pretrain the diagnostic model. Experiments on benchmark datasets show that CancerSD not only gives accurate diagnosis, but also maintains a high authenticity and good interpretability. In addition, CancerSD identifies important molecular characteristics associated with cancer subtypes, and it defines the Integrated CancerSD Score that can serve as an independent predictive factor for patient prognosis.

Molecular profiling of risk factors for relapse in Japanese patients with stage II colorectal cancer: a retrospective cohort study

BACKGROUND

The association between the molecular profiles and prognosis of Stage II colorectal cancer remains unclear. This study aimed to examine the risk factors for relapse of Stage II colorectal cancer using molecular profiling.

METHODS

We retrospectively enrolled patients with pStage II colorectal cancer who did not receive perioperative adjuvant therapy and whose surgically resected specimens were evaluated using gene expression and whole-exome analyses between January 2014 and December 2018. We evaluated the long-term outcomes and examined the risk factors for relapse-free survival.

RESULTS

We evaluated 322 patients with pStage II colorectal cancer, including 126 (39.1%) with right colon cancer. Eighty-seven patients (27.0%) had pT4 tumor, 175 (54.3%) had positive venous invasion, 120 (37.3%) had positive lymphatic invasion, and 68 (21.1%) had perineural invasion. The presence of mutations in key genes for colorectal cancer development based on whole-exome analyses was as follows: APC, 245 (76.1%); TP53, 208 (64.6%); and KRAS, 134 (41.6%). According to the consensus molecular subtype classification based on gene expression, 76 patients (23.6%) had consensus molecular subtype 4 and a significantly lower relapse-free survival than the other patients (5-year relapse-free survival: 83.8% vs. 92.9%, p = 0.017). Perineural invasion (hazard ratio: 5.316, p < 0.001) and consensus molecular subtype 4 (hazard ratio: 2.399, p = 0.020) were identified as independent risk factors for relapse-free survival.

CONCLUSIONS

Molecular profiling of Stage II colorectal cancer to assess the risk factors for relapse may contribute to the indication and drug selection for adjuvant chemotherapy.

Advancements and Challenges in the Image-Based Diagnosis of Lung and Colon Cancer: A Comprehensive Review

Image-based diagnosis has become a crucial tool in the identification and management of various cancers, particularly lung and colon cancer. This review delves into the latest advancements and ongoing challenges in the field, with a focus on deep learning, machine learning, and image processing techniques applied to X-rays, CT scans, and histopathological images. Significant progress has been made in imaging technologies like computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET), which, when combined with machine learning and artificial intelligence (AI) methodologies, have greatly enhanced the accuracy of cancer detection and characterization. These advances have enabled early detection, more precise tumor localization, personalized treatment plans, and overall improved patient outcomes. However, despite these improvements, challenges persist. Variability in image interpretation, the lack of standardized diagnostic protocols, unequal access to advanced imaging technologies, and concerns over data privacy and security within AI-based systems remain major obstacles. Furthermore, integrating imaging data with broader clinical information is crucial to achieving a more comprehensive approach to cancer diagnosis and treatment. This review provides valuable insights into the recent developments and challenges in image-based diagnosis for lung and colon cancers, underscoring both the remarkable progress and the hurdles that still need to be overcome to optimize cancer care.

Deep learning model with pathological knowledge for detection of colorectal neuroendocrine tumor

Colorectal neuroendocrine tumors (NETs) differ significantly from colorectal carcinoma (CRC) in terms of treatment strategy and prognosis, necessitating a cost-effective approach for accurate discrimination. Here, we propose an approach for distinguishing between colorectal NET and CRC based on pathological images by utilizing pathological prior information to facilitate the generation of robust slide-level features. By calculating the similarity between morphological descriptions and patches, our approach selects only 2% of the diagnostically relevant patches for both training and inference, achieving an area under the receiver operating characteristic curve (AUROC) of 0.9974 on the internal dataset, and AUROCs of 0.9724 and 0.9513 on two external datasets. Our model effectively identifies NETs from CRCs, reducing unnecessary immunohistochemical tests and enhancing the precise treatment for patients with colorectal tumors. Our approach also enables researchers to investigate methods with high accuracy and low computational complexity, thereby advancing the application of artificial intelligence in clinical settings.

Artificial intelligence methods available for cancer research

Cancer is a heterogeneous and multifaceted disease with a significant global footprint. Despite substantial technological advancements for battling cancer, early diagnosis and selection of effective treatment remains a challenge. With the convenience of large-scale datasets including multiple levels of data, new bioinformatic tools are needed to transform this wealth of information into clinically useful decision-support tools. In this field, artificial intelligence (AI) technologies with their highly diverse applications are rapidly gaining ground. Machine learning methods, such as Bayesian networks, support vector machines, decision trees, random forests, gradient boosting, and K-nearest neighbors, including neural network models like deep learning, have proven valuable in predictive, prognostic, and diagnostic studies. Researchers have recently employed large language models to tackle new dimensions of problems. However, leveraging the opportunity to utilize AI in clinical settings will require surpassing significant obstacles-a major issue is the lack of use of the available reporting guidelines obstructing the reproducibility of published studies. In this review, we discuss the applications of AI methods and explore their benefits and limitations. We summarize the available guidelines for AI in healthcare and highlight the potential role and impact of AI models on future directions in cancer research.

Improving performance in colorectal cancer histology decomposition using deep and ensemble machine learning

In routine colorectal cancer management, histologic samples stained with hematoxylin and eosin are commonly used. Nonetheless, their potential for defining objective biomarkers for patient stratification and treatment selection is still being explored. The current gold standard relies on expensive and time-consuming genetic tests. However, recent research highlights the potential of convolutional neural networks (CNNs) to facilitate the extraction of clinically relevant biomarkers from these readily available images. These CNN-based biomarkers can predict patient outcomes comparably to golden standards, with the added advantages of speed, automation, and minimal cost. The predictive potential of CNN-based biomarkers fundamentally relies on the ability of CNNs to accurately classify diverse tissue types from whole slide microscope images. Consequently, enhancing the accuracy of tissue class decomposition is critical to amplifying the prognostic potential of imaging-based biomarkers. This study introduces a hybrid deep transfer learning and ensemble machine learning model that improves upon previous approaches, including a transformer and neural architecture search baseline for this task. We employed a pairing of the EfficientNetV2 architecture with a random forest classification head. Our model achieved 96.74% accuracy (95% CI: 96.3%-97.1%) on the external test set and 99.89% on the internal test set. Recognizing the potential of these models in the task, we have made them publicly available.

Tumor-associated mesenchymal stromal cells modulate macrophage phagocytosis in stromal-rich colorectal cancer via PD-1 signaling

CMS4 colorectal cancer (CRC), based on the consensus molecular subtype (CMS), stratifies patients with the poorest disease-free survival rates. It is characterized by a strong mesenchymal stromal cell (MSC) signature, wound healing-like inflammation and therapy resistance. We utilized 2D and 3D in vitro, in vivo, and ex vivo models to assess the impact of inflammation and stromal cells on immunosuppression in CMS4 CRC. RNA sequencing data from untreated stage II/III CRC patients showed enriched TNF-α signatures in CMS1 and CMS4 tumors. Secretome from TNF-α treated cancer cells induced an immunomodulatory and chemotactic phenotype in MSC and cancer-associated fibroblasts (CAFs). Macrophages in CRC tumours migrate and preferentially localise in stromal compartment. Inflammatory CRC secretome enhances expression of PD-L1 and CD47 on both human and murine stromal cells. We demonstrate that TNF-α-induced inflammation in CRC suppresses macrophage phagocytosis via stromal cells. We show that stromal cell-mediated suppression of macrophage phagocytosis is mediated in part through PD-1 signaling. These data suggest that re-stratification of CRC by CMS may reveal patient subsets with microsatellite stable tumors, particularly CMS4-like tumors, that may respond to immunotherapies.

Transcriptomic subtyping of gastrointestinal malignancies

Gastrointestinal (GI) cancers are highly heterogeneous at multiple levels. Tumor heterogeneity can be captured by molecular profiling, such as genetic, epigenetic, proteomic, and transcriptomic classification. Transcriptomic subtyping has the advantage of combining genetic and epigenetic information, cancer cell-intrinsic properties, and the tumor microenvironment (TME). Unsupervised transcriptomic subtyping systems of different GI malignancies have gained interest because they reveal shared biological features across cancers and bear prognostic and predictive value. Importantly, transcriptomic subtypes accurately reflect complex phenotypic states varying not only per tumor region, but also throughout disease progression, with consequences for clinical management. Here, we discuss methodologies of transcriptomic subtyping, proposed taxonomies for GI malignancies, and the challenges posed to clinical implementation, highlighting opportunities for future transcriptomic profiling efforts to optimize clinical impact.

A novel model based on protein post-translational modifications comprising the immune landscape and prediction of colorectal cancer prognosis

Background

Phosphorylation is a critical post-translational modification (PTM) type contributing to colorectal cancer (CRC). The study aimed to construct a nomogram model to predict colon adenocarcinoma (COAD) prognosis based on PTM signatures.

Methods

The Cancer Genome Atlas (TCGA) database has been indexed for COAD patients' RNA sequencing, proteomic data, and clinical details. To find potential PTM prognostic signatures, the least absolute shrinkage and selection operator (LASSO) was deployed. Model validation procedures included the use of the Kaplan-Meier (K-M) method, the receiver operating characteristic (ROC) curve, the area under the curve (AUC), and the decision curve analysis (DCA). Additionally, biological enrichment, tumor immune microenvironment, and chemotherapy were also assessed. To validate the model, CRC cells were used in in vitro experiments using western blotting, proliferation assay, colony formation assay, and flow cytometry.

Results

The LASSO regression analysis identified 8 PTM sites. Based on the median PTM score, patients were classified into low- and high-risk groups. K-M results showed that high-risk patients had worse prognoses (P<0.001). Our model demonstrated powerful effectiveness and predictive value (TCGA whole group: 1-year AUC =0.611, 2-year AUC =0.574, 3-year AUC =0.627). Additionally, high-risk CRC patients were enriched in KRAS signaling pathways (P=0.01), possessed more robust immune escape capacity (P=0.001, and induced cell-cycle arrest of CRC cells (P<0.01).

Conclusions

We established and validated a novel nomogram model related to PTM that can predict prognosis and guide the treatment of COAD.

Converging deep learning and human-observed tumor-adipocyte interaction as a biomarker in colorectal cancer

BACKGROUND

Tumor-Adipose-Feature (TAF) as well as SARIFA (Stroma AReactive Invasion Front Areas) are two histologic features/biomarkers linking tumor-associated adipocytes to poor outcomes in colorectal cancer (CRC) patients. Whereas TAF was identified by deep learning (DL) algorithms, SARIFA was established as a human-observed histopathologic biomarker.

METHODS

To study the overlap between TAF and SARIFA, we performed a systematic pathological review of TAF based on all published image tiles. Additionally, we analyzed the presence/absence of TAF in SARIFA-negative CRC cases to elucidate the biologic and prognostic role of a direct tumor-adipocyte contact. TCGA-CRC gene expression data is investigated to assess the association of FABP4 (fatty-acid binding protein 4) and CD36 (fatty-acid translocase) with both TAF and CRC prognosis.

RESULTS

By investigating the TAF/SARIFA overlap, we show that many TAF patches correspond to the recently described SARIFA-phenomenon. Even though there is a pronounced morphological and biological overlap, there are differences in the concepts. The presence of TAF in SARIFA-negative CRCs is not associated with poor outcomes in this cohort, potentially highlighting the importance of a direct tumor-adipocyte interaction. Upregulation of FABP4 and CD36 gene expression seem both linked to a poor prognosis in CRC.

CONCLUSIONS

By proving the substantial overlap between human-observed SARIFA and DL-based TAF as morphologic biomarkers, we demonstrate that linking DL-based image features to independently developed histopathologic biomarkers is a promising tool in the identification of clinically and biologically meaningful biomarkers. Adipocyte-tumor-cell interactions seem to be crucial in CRC, which should be considered as biomarkers for further investigations.

A consensus molecular subtypes classification strategy for clinical colorectal cancer tissues

Consensus Molecular Subtype (CMS) classification of colorectal cancer (CRC) tissues is complicated by RNA degradation upon formalin-fixed paraffin-embedded (FFPE) preservation. Here, we present an FFPE-curated CMS classifier. The CMSFFPE classifier was developed using genes with a high transcript integrity in FFPE-derived RNA. We evaluated the classification accuracy in two FFPE-RNA datasets with matched fresh-frozen (FF) RNA data, and an FF-derived RNA set. An FFPE-RNA application cohort of metastatic CRC patients was established, partly treated with anti-EGFR therapy. Key characteristics per CMS were assessed. Cross-referenced with matched benchmark FF CMS calls, the CMSFFPE classifier strongly improved classification accuracy in two FFPE datasets compared with the original CMSClassifier (63.6% versus 40.9% and 83.3% versus 66.7%, respectively). We recovered CMS-specific recurrence-free survival patterns (CMS4 versus CMS2: hazard ratio 1.75, 95% CI 1.24-2.46). Key molecular and clinical associations of the CMSs were confirmed. In particular, we demonstrated the predictive value of CMS2 and CMS3 for anti-EGFR therapy response (CMS2&3: odds ratio 5.48, 95% CI 1.10-27.27). The CMSFFPE classifier is an optimized FFPE-curated research tool for CMS classification of clinical CRC samples.

Mining the interpretable prognostic features from pathological image of intrahepatic cholangiocarcinoma using multi-modal deep learning

BACKGROUND

The advances in deep learning-based pathological image analysis have invoked tremendous insights into cancer prognostication. Still, lack of interpretability remains a significant barrier to clinical application.

METHODS

We established an integrative prognostic neural network for intrahepatic cholangiocarcinoma (iCCA), towards a comprehensive evaluation of both architectural and fine-grained information from whole-slide images. Then, leveraging on multi-modal data, we conducted extensive interrogative approaches to the models, to extract and visualize the morphological features that most correlated with clinical outcome and underlying molecular alterations.

RESULTS

The models were developed and optimized on 373 iCCA patients from our center and demonstrated consistent accuracy and robustness on both internal (n = 213) and external (n = 168) cohorts. The occlusion sensitivity map revealed that the distribution of tertiary lymphoid structures, the geometric traits of the invasive margin, the relative composition of tumor parenchyma and stroma, the extent of necrosis, the presence of the disseminated foci, and the tumor-adjacent micro-vessels were the determining architectural features that impacted on prognosis. Quantifiable morphological vector extracted by CellProfiler demonstrated that tumor nuclei from high-risk patients exhibited significant larger size, more distorted shape, with less prominent nuclear envelope and textural contrast. The multi-omics data (n = 187) further revealed key molecular alterations left morphological imprints that could be attended by the network, including glycolysis, hypoxia, apical junction, mTORC1 signaling, and immune infiltration.

CONCLUSIONS

We proposed an interpretable deep-learning framework to gain insights into the biological behavior of iCCA. Most of the significant morphological prognosticators perceived by the network are comprehensible to human minds.

A Pan-Cancer Patient-Derived Xenograft Histology Image Repository with Genomic and Pathologic Annotations Enables Deep Learning Analysis

Patient-derived xenografts (PDX) model human intra- and intertumoral heterogeneity in the context of the intact tissue of immunocompromised mice. Histologic imaging via hematoxylin and eosin (H&E) staining is routinely performed on PDX samples, which could be harnessed for computational analysis. Prior studies of large clinical H&E image repositories have shown that deep learning analysis can identify intercellular and morphologic signals correlated with disease phenotype and therapeutic response. In this study, we developed an extensive, pan-cancer repository of >1,000 PDX and paired parental tumor H&E images. These images, curated from the PDX Development and Trial Centers Research Network Consortium, had a range of associated genomic and transcriptomic data, clinical metadata, pathologic assessments of cell composition, and, in several cases, detailed pathologic annotations of neoplastic, stromal, and necrotic regions. The amenability of these images to deep learning was highlighted through three applications: (i) development of a classifier for neoplastic, stromal, and necrotic regions; (ii) development of a predictor of xenograft-transplant lymphoproliferative disorder; and (iii) application of a published predictor of microsatellite instability. Together, this PDX Development and Trial Centers Research Network image repository provides a valuable resource for controlled digital pathology analysis, both for the evaluation of technical issues and for the development of computational image-based methods that make clinical predictions based on PDX treatment studies. Significance: A pan-cancer repository of >1,000 patient-derived xenograft hematoxylin and eosin-stained images will facilitate cancer biology investigations through histopathologic analysis and contributes important model system data that expand existing human histology repositories.

Magnetic resonance imaging-based radiomics analysis for prediction of treatment response to neoadjuvant chemoradiotherapy and clinical outcome in patients with locally advanced rectal cancer: A large multicentric and validated study

Our study investigated whether magnetic resonance imaging (MRI)-based radiomics features could predict good response (GR) to neoadjuvant chemoradiotherapy (nCRT) and clinical outcome in patients with locally advanced rectal cancer (LARC). Radiomics features were extracted from the T2 weighted (T2W) and Apparent diffusion coefficient (ADC) images of 1070 LARC patients retrospectively and prospectively recruited from three hospitals. To create radiomic models for GR prediction, three classifications were utilized. The radiomic model with the best performance was integrated with important clinical MRI features to create the combined model. Finally, two clinical MRI features and ten radiomic features were chosen for GR prediction. The combined model, constructed with the tumor size, MR-detected extramural venous invasion, and radiomic signature generated by Support Vector Machine (SVM), showed promising discrimination of GR, with area under the curves of 0.799 (95% CI, 0.760-0.838), 0.797 (95% CI, 0.733-0.860), 0.754 (95% CI, 0.678-0.829), and 0.727 (95% CI, 0.641-0.813) in the training and three validation datasets, respectively. Decision curve analysis verified the clinical usefulness. Furthermore, according to Kaplan-Meier curves, patients with a high likelihood of GR as determined by the combined model had better disease-free survival than those with a low probability. This radiomics model was developed based on large-sample size, multicenter datasets, and prospective validation with high radiomics quality score, and also had clinical utility.

Prediction of recurrence risk in endometrial cancer with multimodal deep learning

Predicting distant recurrence of endometrial cancer (EC) is crucial for personalized adjuvant treatment. The current gold standard of combined pathological and molecular profiling is costly, hampering implementation. Here we developed HECTOR (histopathology-based endometrial cancer tailored outcome risk), a multimodal deep learning prognostic model using hematoxylin and eosin-stained, whole-slide images and tumor stage as input, on 2,072 patients from eight EC cohorts including the PORTEC-1/-2/-3 randomized trials. HECTOR demonstrated C-indices in internal (n = 353) and two external (n = 160 and n = 151) test sets of 0.789, 0.828 and 0.815, respectively, outperforming the current gold standard, and identified patients with markedly different outcomes (10-year distant recurrence-free probabilities of 97.0%, 77.7% and 58.1% for HECTOR low-, intermediate- and high-risk groups, respectively, by Kaplan-Meier analysis). HECTOR also predicted adjuvant chemotherapy benefit better than current methods. Morphological and genomic feature extraction identified correlates of HECTOR risk groups, some with therapeutic potential. HECTOR improves on the current gold standard and may help delivery of personalized treatment in EC.

Stratification to Neoadjuvant Radiotherapy in Rectal Cancer by Regimen and Transcriptional Signatures

Response to neoadjuvant radiotherapy (RT) in rectal cancer has been associated with immune and stromal features that are captured by transcriptional signatures. However, how such associations perform across different chemoradiotherapy regimens and within individual consensus molecular subtypes (CMS) and how they affect survival remain unclear. In this study, gene expression and clinical data of pretreatment biopsies from nine cohorts of primary rectal tumors were combined (N = 826). Exploratory analyses were done with transcriptomic signatures for the endpoint of pathologic complete response (pCR), considering treatment regimen or CMS subtype. Relevant findings were tested for overall survival and recurrence-free survival. Immune and stromal signatures were strongly associated with pCR and lack of pCR, respectively, in RT and capecitabine (Cap)/5-fluorouracil (5FU)-treated patients (N = 387), in which the radiosensitivity signature (RSS) showed the strongest association. Upon addition of oxaliplatin (Ox; N = 123), stromal signatures switched direction and showed higher chances to achieve pCR than without Ox (p for interaction 0.02). Among Cap/5FU patients, most signatures performed similarly across CMS subtypes, except cytotoxic lymphocytes that were associated with pCR in CMS1 and CMS4 cases compared with other CMS subtypes (p for interaction 0.04). The only variables associated with survival were pCR and RSS. Although the frequency of pCR across different chemoradiation regimens is relatively similar, our data suggest that response rates may differ depending on the biological landscape of rectal cancer. Response to neoadjuvant RT in stroma-rich tumors may potentially be improved by the addition of Ox. RSS in preoperative biopsies provides predictive information for response specifically to neoadjuvant RT with 5FU.

SIGNIFICANCE

Rectal cancers with stromal features may respond better to RT and 5FU/Cap with the addition of Ox. Within patients not treated with Ox, high levels of cytotoxic lymphocytes associate with response only in immune and stromal tumors. Our analyses provide biological insights about the outcome by different radiotherapy regimens in rectal cancer.

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.

Clinical Challenges of Consensus Molecular Subtype CMS4 Colon Cancer in the Era of Precision Medicine

Over the past decade, our understanding of the diversity of colorectal cancer has expanded significantly, raising hopes of tailoring treatments more precisely for individual patients. A key achievement in this direction was the establishment of the consensus molecular classification, particularly identifying the challenging consensus molecular subtype (CMS) CMS4 associated with poor prognosis. Because of its aggressive nature, extensive research is dedicated to the CMS4 subgroup. Recent years have unveiled molecular and microenvironmental features at the tissue level specific to CMS4 colorectal cancer. This has paved the way for mechanistic studies and the development of preclinical models. Simultaneously, efforts have been made to easily identify patients with CMS4 colorectal cancer. Reassessing clinical trial results through the CMS classification lens has improved our understanding of the therapeutic challenges linked to this subtype. Exploration of the biology of CMS4 colorectal cancer is yielding potential biomarkers and novel treatment approaches. This overview aims to provide insights into the clinico-biological characteristics of the CMS4 subgroup, the molecular pathways driving this subtype, and available diagnostic options. We also emphasize the therapeutic challenges associated with this subtype, offering potential explanations. Finally, we summarize the current tailored treatments for CMS4 colorectal cancer emerging from fundamental and preclinical studies.

Precision Oncology, Artificial Intelligence, and Novel Therapeutic Advancements in the Diagnosis, Prevention, and Treatment of Cancer: Highlights from the 59th Irish Association for Cancer Research (IACR) Annual Conference

Advancements in oncology, especially with the era of precision oncology, is resulting in a paradigm shift in cancer care. Indeed, innovative technologies, such as artificial intelligence, are paving the way towards enhanced diagnosis, prevention, and personalised treatments as well as novel drug discoveries. Despite excellent progress, the emergence of resistant cancers has curtailed both the pace and extent to which we can advance. By combining both their understanding of the fundamental biological mechanisms and technological advancements such as artificial intelligence and data science, cancer researchers are now beginning to address this. Together, this will revolutionise cancer care, by enhancing molecular interventions that may aid cancer prevention, inform clinical decision making, and accelerate the development of novel therapeutic drugs. Here, we will discuss the advances and approaches in both artificial intelligence and precision oncology, presented at the 59th Irish Association for Cancer Research annual conference.

Multiregional transcriptomics identifies congruent consensus subtypes with prognostic value beyond tumor heterogeneity of colorectal cancer

Intra-tumor heterogeneity compromises the clinical value of transcriptomic classifications of colorectal cancer. We investigated the prognostic effect of transcriptomic heterogeneity and the potential for classifications less vulnerable to heterogeneity in a single-hospital series of 1093 tumor samples from 692 patients, including multiregional samples from 98 primary tumors and 35 primary-metastasis sets. We show that intra-tumor heterogeneity of the consensus molecular subtypes (CMS) is frequent and has poor-prognostic associations independently of tumor microenvironment markers. Multiregional transcriptomics uncover cancer cell-intrinsic and low-heterogeneity signals that recapitulate the intrinsic CMSs proposed by single-cell sequencing. Further subclassification identifies congruent CMSs that explain a larger proportion of variation in patient survival than intra-tumor heterogeneity. Plasticity is indicated by discordant intrinsic phenotypes of matched primary and metastatic tumors. We conclude that multiregional sampling reconciles the prognostic power of tumor classifications from single-cell and bulk transcriptomics in the context of intra-tumor heterogeneity, and phenotypic plasticity challenges the reconciliation of primary and metastatic subtypes.

Prediction of Mismatch Repair Status in Endometrial Cancer from Histological Slide Images Using Various Deep Learning-Based Algorithms

The application of deep learning algorithms to predict the molecular profiles of various cancers from digital images of hematoxylin and eosin (H&E)-stained slides has been reported in recent years, mainly for gastric and colon cancers. In this study, we investigated the potential use of H&E-stained endometrial cancer slide images to predict the associated mismatch repair (MMR) status. H&E-stained slide images were collected from 127 cases of the primary lesion of endometrial cancer. After digitization using a Nanozoomer virtual slide scanner (Hamamatsu Photonics), we segmented the scanned images into 5397 tiles of 512 × 512 pixels. The MMR proteins (PMS2, MSH6) were immunohistochemically stained, classified into MMR proficient/deficient, and annotated for each case and tile. We trained several neural networks, including convolutional and attention-based networks, using tiles annotated with the MMR status. Among the tested networks, ResNet50 exhibited the highest area under the receiver operating characteristic curve (AUROC) of 0.91 for predicting the MMR status. The constructed prediction algorithm may be applicable to other molecular profiles and useful for pre-screening before implementing other, more costly genetic profiling tests.

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.

Identification and clinicopathological analysis of potential p73-regulated biomarkers in colorectal cancer via integrative bioinformatics

This study aims to decipher crucial biomarkers regulated by p73 for the early detection of colorectal cancer (CRC) by employing a combination of integrative bioinformatics and expression profiling techniques. The transcriptome profile of HCT116 cell line p53- / - p73+ / + and p53- / - p73 knockdown was performed to identify differentially expressed genes (DEGs). This was corroborated with three CRC tissue expression datasets available in Gene Expression Omnibus. Further analysis involved KEGG and Gene ontology to elucidate the functional roles of DEGs. The protein-protein interaction (PPI) network was constructed using Cytoscape to identify hub genes. Kaplan-Meier (KM) plots along with GEPIA and UALCAN database analysis provided the insights into the prognostic and diagnostic significance of these hub genes. Machine/deep learning algorithms were employed to perform TNM-stage classification. Transcriptome profiling revealed 1289 upregulated and 1897 downregulated genes. When intersected with employed CRC datasets, 284 DEGs were obtained. Comprehensive analysis using gene ontology and KEGG revealed enrichment of the DEGs in metabolic process, fatty acid biosynthesis, etc. The PPI network constructed using these 284 genes assisted in identifying 20 hub genes. Kaplan-Meier, GEPIA, and UALCAN analyses uncovered the clinicopathological relevance of these hub genes. Conclusively, the deep learning model achieved TNM-stage classification accuracy of 0.78 and 0.75 using 284 DEGs and 20 hub genes, respectively. The study represents a pioneer endeavor amalgamating transcriptomics, publicly available tissue datasets, and machine learning to unveil key CRC-associated genes. These genes are found relevant regarding the patients' prognosis and diagnosis. The unveiled biomarkers exhibit robustness in TNM-stage prediction, thereby laying the foundation for future clinical applications and therapeutic interventions in CRC management.

Oral epithelial dysplasia detection and grading in oral leukoplakia using deep learning

BACKGROUND

The grading of oral epithelial dysplasia is often time-consuming for oral pathologists and the results are poorly reproducible between observers. In this study, we aimed to establish an objective, accurate and useful detection and grading system for oral epithelial dysplasia in the whole-slides of oral leukoplakia.

METHODS

Four convolutional neural networks were compared using the image patches from 56 whole-slide of oral leukoplakia labeled by pathologists as the gold standard. Sequentially, feature detection models were trained, validated and tested with 1,000 image patches using the optimal network. Lastly, a comprehensive system named E-MOD-plus was established by combining feature detection models and a multiclass logistic model.

RESULTS

EfficientNet-B0 was selected as the optimal network to build feature detection models. In the internal dataset of whole-slide images, the prediction accuracy of E-MOD-plus was 81.3% (95% confidence interval: 71.4-90.5%) and the area under the receiver operating characteristic curve was 0.793 (95% confidence interval: 0.650 to 0.925); in the external dataset of 229 tissue microarray images, the prediction accuracy was 86.5% (95% confidence interval: 82.4-90.0%) and the area under the receiver operating characteristic curve was 0.669 (95% confidence interval: 0.496 to 0.843).

CONCLUSIONS

E-MOD-plus was objective and accurate in the detection of pathological features as well as the grading of oral epithelial dysplasia, and had potential to assist pathologists in clinical practice.

Image-based consensus molecular subtyping in rectal cancer biopsies and response to neoadjuvant chemoradiotherapy

The development of deep learning (DL) models to predict the consensus molecular subtypes (CMS) from histopathology images (imCMS) is a promising and cost-effective strategy to support patient stratification. Here, we investigate whether imCMS calls generated from whole slide histopathology images (WSIs) of rectal cancer (RC) pre-treatment biopsies are associated with pathological complete response (pCR) to neoadjuvant long course chemoradiotherapy (LCRT) with single agent fluoropyrimidine. DL models were trained to classify WSIs of colorectal cancers stained with hematoxylin and eosin into one of the four CMS classes using a multi-centric dataset of resection and biopsy specimens (n = 1057 WSIs) with paired transcriptional data. Classifiers were tested on a held out RC biopsy cohort (ARISTOTLE) and correlated with pCR to LCRT in an independent dataset merging two RC cohorts (ARISTOTLE, n = 114 and SALZBURG, n = 55 patients). DL models predicted CMS with high classification performance in multiple comparative analyses. In the independent cohorts (ARISTOTLE, SALZBURG), cases with WSIs classified as imCMS1 had a significantly higher likelihood of achieving pCR (OR = 2.69, 95% CI 1.01-7.17, p = 0.048). Conversely, imCMS4 was associated with lack of pCR (OR = 0.25, 95% CI 0.07-0.88, p = 0.031). Classification maps demonstrated pathologist-interpretable associations with high stromal content in imCMS4 cases, associated with poor outcome. No significant association was found in imCMS2 or imCMS3. imCMS classification of pre-treatment biopsies is a fast and inexpensive solution to identify patient groups that could benefit from neoadjuvant LCRT. The significant associations between imCMS1/imCMS4 with pCR suggest the existence of predictive morphological features that could enhance standard pathological assessment.

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.

Immune subtyping of melanoma whole slide images using multiple instance learning

Determining early-stage prognostic markers and stratifying patients for effective treatment are two key challenges for improving outcomes for melanoma patients. Previous studies have used tumour transcriptome data to stratify patients into immune subgroups, which were associated with differential melanoma specific survival and potential predictive biomarkers. However, acquiring transcriptome data is a time-consuming and costly process. Moreover, it is not routinely used in the current clinical workflow. Here, we attempt to overcome this by developing deep learning models to classify gigapixel haematoxylin and eosin (H&E) stained pathology slides, which are well established in clinical workflows, into these immune subgroups. We systematically assess six different multiple instance learning (MIL) frameworks, using five different image resolutions and three different feature extraction methods. We show that pathology-specific self-supervised models using 10x resolution patches generate superior representations for the classification of immune subtypes. In addition, in a primary melanoma dataset, we achieve a mean area under the receiver operating characteristic curve (AUC) of 0.80 for classifying histopathology images into 'high' or 'low immune' subgroups and a mean AUC of 0.82 in an independent TCGA melanoma dataset. Furthermore, we show that these models are able to stratify patients into 'high' and 'low immune' subgroups with significantly different melanoma specific survival outcomes (log rank test, P< 0.005). We anticipate that MIL methods will allow us to find new biomarkers of high importance, act as a tool for clinicians to infer the immune landscape of tumours and stratify patients, without needing to carry out additional expensive genetic tests.

Predicting 5-year recurrence risk in colorectal cancer: development and validation of a histology-based deep learning approach

BACKGROUND

Accurate estimation of the long-term risk of recurrence in patients with non-metastatic colorectal cancer (CRC) is crucial for clinical management. Histology-based deep learning is expected to provide more abundant information for risk stratification.

METHODS

We developed and validated a weakly supervised deep-learning model for predicting 5-year relapse-free survival (RFS) to stratify patients with different risks based on histological images from three hospitals of 614 cases with non-metastatic CRC. A deep prognostic factor (DL-RRS) was established to stratify patients into high and low-risk group. The areas under the curve (AUCs) were calculated to evaluate the performances of models.

RESULTS

Our proposed model achieves the AUCs of 0.833 (95% CI: 0.736-0.905) and 0.715 (95% CI: 0.647-0.776) on validation cohort and external test cohort, respectively. The 5-year RFS rate was 45.7% for high DL-RRS patients, and 82.5% for low DL-RRS patients respectively in the external test cohort (HR: 3.89, 95% CI: 2.51-6.03, P < 0.001). Adjuvant chemotherapy was associated with improved RFS in Stage II patients with high DL-RRS (HR: 0.15, 95% CI: 0.06-0.38, P < 0.001).

CONCLUSIONS

DL-RRS has a good predictive performance of 5-year recurrence risk in CRC, and will better serve the clinical decision-making.

Deep learning in cancer genomics and histopathology

Histopathology and genomic profiling are cornerstones of precision oncology and are routinely obtained for patients with cancer. Traditionally, histopathology slides are manually reviewed by highly trained pathologists. Genomic data, on the other hand, is evaluated by engineered computational pipelines. In both applications, the advent of modern artificial intelligence methods, specifically machine learning (ML) and deep learning (DL), have opened up a fundamentally new way of extracting actionable insights from raw data, which could augment and potentially replace some aspects of traditional evaluation workflows. In this review, we summarize current and emerging applications of DL in histopathology and genomics, including basic diagnostic as well as advanced prognostic tasks. Based on a growing body of evidence, we suggest that DL could be the groundwork for a new kind of workflow in oncology and cancer research. However, we also point out that DL models can have biases and other flaws that users in healthcare and research need to know about, and we propose ways to address them.

A systematic pan-cancer study on deep learning-based prediction of multi-omic biomarkers from routine pathology images

BACKGROUND

The objective of this comprehensive pan-cancer study is to evaluate the potential of deep learning (DL) for molecular profiling of multi-omic biomarkers directly from hematoxylin and eosin (H&E)-stained whole slide images.

METHODS

A total of 12,093 DL models predicting 4031 multi-omic biomarkers across 32 cancer types were trained and validated. The study included a broad range of genetic, transcriptomic, and proteomic biomarkers, as well as established prognostic markers, molecular subtypes, and clinical outcomes.

RESULTS

Here we show that 50% of the models achieve an area under the curve (AUC) of 0.644 or higher. The observed AUC for 25% of the models is at least 0.719 and exceeds 0.834 for the top 5%. Molecular profiling with image-based histomorphological features is generally considered feasible for most of the investigated biomarkers and across different cancer types. The performance appears to be independent of tumor purity, sample size, and class ratio (prevalence), suggesting a degree of inherent predictability in histomorphology.

CONCLUSIONS

The results demonstrate that DL holds promise to predict a wide range of biomarkers across the omics spectrum using only H&E-stained histological slides of solid tumors. This paves the way for accelerating diagnosis and developing more precise treatments for cancer patients.

New clinical trial design in precision medicine: discovery, development and direction

In the era of precision medicine, it has been increasingly recognized that individuals with a certain disease are complex and different from each other. Due to the underestimation of the significant heterogeneity across participants in traditional "one-size-fits-all" trials, patient-centered trials that could provide optimal therapy customization to individuals with specific biomarkers were developed including the basket, umbrella, and platform trial designs under the master protocol framework. In recent years, the successive FDA approval of indications based on biomarker-guided master protocol designs has demonstrated that these new clinical trials are ushering in tremendous opportunities. Despite the rapid increase in the number of basket, umbrella, and platform trials, the current clinical and research understanding of these new trial designs, as compared with traditional trial designs, remains limited. The majority of the research focuses on methodologies, and there is a lack of in-depth insight concerning the underlying biological logic of these new clinical trial designs. Therefore, we provide this comprehensive review of the discovery and development of basket, umbrella, and platform trials and their underlying logic from the perspective of precision medicine. Meanwhile, we discuss future directions on the potential development of these new clinical design in view of the "Precision Pro", "Dynamic Precision", and "Intelligent Precision". This review would assist trial-related researchers to enhance the innovation and feasibility of clinical trial designs by expounding the underlying logic, which be essential to accelerate the progression of precision medicine.

Pathway level subtyping identifies a slow-cycling biological phenotype associated with poor clinical outcomes in colorectal cancer

Molecular stratification using gene-level transcriptional data has identified subtypes with distinctive genotypic and phenotypic traits, as exemplified by the consensus molecular subtypes (CMS) in colorectal cancer (CRC). Here, rather than gene-level data, we make use of gene ontology and biological activation state information for initial molecular class discovery. In doing so, we defined three pathway-derived subtypes (PDS) in CRC: PDS1 tumors, which are canonical/LGR5+ stem-rich, highly proliferative and display good prognosis; PDS2 tumors, which are regenerative/ANXA1+ stem-rich, with elevated stromal and immune tumor microenvironmental lineages; and PDS3 tumors, which represent a previously overlooked slow-cycling subset of tumors within CMS2 with reduced stem populations and increased differentiated lineages, particularly enterocytes and enteroendocrine cells, yet display the worst prognosis in locally advanced disease. These PDS3 phenotypic traits are evident across numerous bulk and single-cell datasets, and demark a series of subtle biological states that are currently under-represented in pre-clinical models and are not identified using existing subtyping classifiers.

Intra-prostatic tumour evolution, steps in metastatic spread and histogenomic associations revealed by integration of multi-region whole-genome sequencing with histopathological features

BACKGROUND

Extension of prostate cancer beyond the primary site by local invasion or nodal metastasis is associated with poor prognosis. Despite significant research on tumour evolution in prostate cancer metastasis, the emergence and evolution of cancer clones at this early stage of expansion and spread are poorly understood. We aimed to delineate the routes of evolution and cancer spread within the prostate and to seminal vesicles and lymph nodes, linking these to histological features that are used in diagnostic risk stratification.

METHODS

We performed whole-genome sequencing on 42 prostate cancer samples from the prostate, seminal vesicles and lymph nodes of five treatment-naive patients with locally advanced disease. We spatially mapped the clonal composition of cancer across the prostate and the routes of spread of cancer cells within the prostate and to seminal vesicles and lymph nodes in each individual by analysing a total of > 19,000 copy number corrected single nucleotide variants.

RESULTS

In each patient, we identified sample locations corresponding to the earliest part of the malignancy. In patient 10, we mapped the spread of cancer from the apex of the prostate to the seminal vesicles and identified specific genomic changes associated with the transformation of adenocarcinoma to amphicrine morphology during this spread. Furthermore, we show that the lymph node metastases in this patient arose from specific cancer clones found at the base of the prostate and the seminal vesicles. In patient 15, we observed increased mutational burden, altered mutational signatures and histological changes associated with whole genome duplication. In all patients in whom histological heterogeneity was observed (4/5), we found that the distinct morphologies were located on separate branches of their respective evolutionary trees.

CONCLUSIONS

Our results link histological transformation with specific genomic alterations and phylogenetic branching. These findings have implications for diagnosis and risk stratification, in addition to providing a rationale for further studies to characterise the genetic changes causally linked to morphological transformation. Our study demonstrates the value of integrating multi-region sequencing with histopathological data to understand tumour evolution and identify mechanisms of prostate cancer spread.

Regression-based Deep-Learning predicts molecular biomarkers from pathology slides

Deep Learning (DL) can predict biomarkers from cancer histopathology. Several clinically approved applications use this technology. Most approaches, however, predict categorical labels, whereas biomarkers are often continuous measurements. We hypothesize that regression-based DL outperforms classification-based DL. Therefore, we develop and evaluate a self-supervised attention-based weakly supervised regression method that predicts continuous biomarkers directly from 11,671 images of patients across nine cancer types. We test our method for multiple clinically and biologically relevant biomarkers: homologous recombination deficiency score, a clinically used pan-cancer biomarker, as well as markers of key biological processes in the tumor microenvironment. Using regression significantly enhances the accuracy of biomarker prediction, while also improving the predictions' correspondence to regions of known clinical relevance over classification. In a large cohort of colorectal cancer patients, regression-based prediction scores provide a higher prognostic value than classification-based scores. Our open-source regression approach offers a promising alternative for continuous biomarker analysis in computational pathology.

Pathogenomics for accurate diagnosis, treatment, prognosis of oncology: a cutting edge overview

The capability to gather heterogeneous data, alongside the increasing power of artificial intelligence to examine it, leading a revolution in harnessing multimodal data in the life sciences. However, most approaches are limited to unimodal data, leaving integrated approaches across modalities relatively underdeveloped in computational pathology. Pathogenomics, as an invasive method to integrate advanced molecular diagnostics from genomic data, morphological information from histopathological imaging, and codified clinical data enable the discovery of new multimodal cancer biomarkers to propel the field of precision oncology in the coming decade. In this perspective, we offer our opinions on synthesizing complementary modalities of data with emerging multimodal artificial intelligence methods in pathogenomics. It includes correlation between the pathological and genomic profile of cancer, fusion of histology, and genomics profile of cancer. We also present challenges, opportunities, and avenues for future work.

Novel biomarker SARIFA in colorectal cancer: highly prognostic, not genetically driven and histologic indicator of a distinct tumor biology

SARIFA (Stroma AReactive Invasion Front Areas) has recently emerged as a promising histopathological biomarker for colon and gastric cancer. To elucidate the underlying tumor biology, we assessed SARIFA-status in tissue specimens from The-Cancer-Genome-Atlas (TCGA) cohorts COAD (colonic adenocarcinoma) and READ (rectal adenocarcinoma). For the final analysis, 207 CRC patients could be included, consisting of 69 SARIFA-positive and 138 SARIFA-negative cases. In this external validation cohort, H&E-based SARIFA-positivity was strongly correlated with unfavorable overall, disease-specific, and progression-free survival, partly outperforming conventional prognostic factors. SARIFA-positivity was not associated with known high-risk genetic profiles, such as BRAF V600E mutations or microsatellite-stable status. Transcriptionally, SARIFA-positive CRCs exhibited an overlap with CRC consensus molecular subtypes CMS1 and CMS4, along with distinct differential gene expression patterns, linked to lipid metabolism and increased stromal cell infiltration scores (SIIS). Gene-expression-based drug sensitivity prediction revealed a differential treatment response in SARIFA-positive CRCs. In conclusion, SARIFA represents the H&E-based counterpart of an aggressive tumor biology, demonstrating a partial overlap with CMS1/4 and also adding a further biological layer related to lipid metabolism. Our findings underscore SARIFA-status as an ideal biomarker for refined patient stratification and novel drug developments, particularly given its cost-effective assessment based on routinely available H&E slides.

Molecular pathological classification of colorectal cancer-an update

Colorectal cancer (CRC) has a broad range of molecular alterations with two major mechanisms of genomic instability (chromosomal instability and microsatellite instability) and has been subclassified into 4 consensus molecular subtypes (CMS) based on bulk RNA sequence data. Here, we update the molecular pathological classification of CRC with an overview of more recent bulk and single-cell RNA data analysis for development of transcriptional classifiers and risk stratification methods, taking into account the marked inter-tumoural and intra-tumoural heterogeneity of CRC. The importance of the stromal and immune components or tumour microenvironment (TME) to prognosis has emerged from these analyses. Attempts to remove the contribution of the tumour microenvironment and reveal neoplastic-specific transcriptional traits involved identification of the CRC intrinsic subtypes (CRIS). The use of immunohistochemistry and digital pathology to implement classification systems are evolving fields. Conventional adenoma versus serrated polyp pathway transcriptomic analysis and characterisation of canonical LGR5+ crypt base columnar stem cell versus ANXA1+ regenerative stem cell phenotypes emerged as key properties for improved understanding of transcriptional signals involved in molecular subclassification of colorectal cancers. Recently, classification by three pathway-derived subtypes (PDS1-3) has been developed, revealing a continuum of intrinsic biology associated with biological, stem cell, histopathological, and clinical attributes.

Robustly federated learning model for identifying high-risk patients with postoperative gastric cancer recurrence

The prediction of patient disease risk via computed tomography (CT) images and artificial intelligence techniques shows great potential. However, training a robust artificial intelligence model typically requires large-scale data support. In practice, the collection of medical data faces obstacles related to privacy protection. Therefore, the present study aims to establish a robust federated learning model to overcome the data island problem and identify high-risk patients with postoperative gastric cancer recurrence in a multicentre, cross-institution setting, thereby enabling robust treatment with significant value. In the present study, we collect data from four independent medical institutions for experimentation. The robust federated learning model algorithm yields area under the receiver operating characteristic curve (AUC) values of 0.710, 0.798, 0.809, and 0.869 across four data centres. Additionally, the effectiveness of the algorithm is evaluated, and both adaptive and common features are identified through analysis.

Artificial Intelligence Applications in the Treatment of Colorectal Cancer: A Narrative Review

Colorectal cancer is the third most prevalent cancer worldwide, and its treatment has been a demanding clinical problem. Beyond traditional surgical therapy and chemotherapy, newly revealed molecular mechanisms diversify therapeutic approaches for colorectal cancer. However, the selection of personalized treatment among multiple treatment options has become another challenge in the era of precision medicine. Artificial intelligence has recently been increasingly investigated in the treatment of colorectal cancer. This narrative review mainly discusses the applications of artificial intelligence in the treatment of colorectal cancer patients. A comprehensive literature search was conducted in MEDLINE, EMBASE, and Web of Science to identify relevant papers, resulting in 49 articles being included. The results showed that, based on different categories of data, artificial intelligence can predict treatment outcomes and essential guidance information of traditional and novel therapies, thus enabling individualized treatment strategy selection for colorectal cancer patients. Some frequently implemented machine learning algorithms and deep learning frameworks have also been employed for long-term prognosis prediction in patients with colorectal cancer. Overall, artificial intelligence shows encouraging results in treatment strategy selection and prognosis evaluation for colorectal cancer patients.

Image-Based Subtype Classification for Glioblastoma Using Deep Learning: Prognostic Significance and Biologic Relevance

PURPOSE

To apply deep learning algorithms to histopathology images, construct image-based subtypes independent of known clinical and molecular classifications for glioblastoma, and produce novel insights into molecular and immune characteristics of the glioblastoma tumor microenvironment.

MATERIALS AND METHODS

Using whole-slide hematoxylin and eosin images from 214 patients with glioblastoma in The Cancer Genome Atlas (TCGA), a fine-tuned convolutional neural network model extracted deep learning features. Biclustering was used to identify subtypes and image feature modules. Prognostic value of image subtypes was assessed via Cox regression on survival outcomes and validated with 189 samples from the Clinical Proteomic Tumor Analysis Consortium (CPTAC) data set. Morphological, molecular, and immune characteristics of glioblastoma image subtypes were analyzed.

RESULTS

Four distinct subtypes and modules (imClust1-4) were identified for the TCGA patients with glioblastoma on the basis of the image feature data. The glioblastoma image subtypes were significantly associated with overall survival (OS; P = .028) and progression-free survival (P = .003). Apparent association was also observed for disease-specific survival (P = .096). imClust2 had the best prognosis for all three survival end points (eg, after 25 months, imClust2 had >7% surviving patients than the other subtypes). Examination of OS in the external validation using the unseen CPTAC data set showed consistent patterns. Multivariable Cox analyses confirmed that the image subtypes carry unique prognostic information independent of known clinical and molecular predictors. Molecular and immune profiling revealed distinct immune compositions of the tumor microenvironment in different image subtypes and may provide biologic explanations for the patterns in patients' outcomes.

CONCLUSION

Our image-based subtype classification on the basis of deep learning models is a novel tool to refine risk stratification in cancers. The image subtypes detected for glioblastoma represent a promising prognostic biomarker with distinct molecular and immune characteristics and may facilitate developing novel, individualized immunotherapies for glioblastoma.

Transcriptomics and proteomics reveal distinct biology for lymph node metastases and tumour deposits in colorectal cancer

Both lymph node metastases (LNMs) and tumour deposits (TDs) are included in colorectal cancer (CRC) staging, although knowledge regarding their biological background is lacking. This study aimed to compare the biology of these prognostic features, which is essential for a better understanding of their role in CRC spread. Spatially resolved transcriptomic analysis using digital spatial profiling was performed on TDs and LNMs from 10 CRC patients using 1,388 RNA targets, for the tumour cells and tumour microenvironment. Shotgun proteomics identified 5,578 proteins in 12 different patients. Differences in RNA and protein expression were analysed, and spatial deconvolution was performed. Image-based consensus molecular subtype (imCMS) analysis was performed on all TDs and LNMs included in the study. Transcriptome and proteome profiles identified distinct clusters for TDs and LNMs in both the tumour and tumour microenvironment segment, with upregulation of matrix remodelling, cell adhesion/motility, and epithelial-mesenchymal transition (EMT) in TDs (all p < 0.05). Spatial deconvolution showed a significantly increased abundance of fibroblasts, macrophages, and regulatory T-cells (p < 0.05) in TDs. Consistent with a higher fibroblast and EMT component, imCMS classified 62% of TDs as poor prognosis subtype CMS4 compared to 36% of LNMs (p < 0.05). Compared to LNMs, TDs have a more invasive state involving a distinct tumour microenvironment and upregulation of EMT, which are reflected in a more frequent histological classification of TDs as CMS4. These results emphasise the heterogeneity of locoregional spread and the fact that TDs should merit more attention both in future research and during staging. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Deep Learning and Colon Cancer Interpretation: Rise of the Machine

The rapidly evolving development of artificial intelligence (AI) has spurred the development of numerous algorithms that augment information obtained from routine pathologic review of hematoxylin and eosin-stained slides. AI tools that predict prognosis and underlying molecular alterations have been the focus of much of the research to date. The results of these studies highlight the tremendous potential of AI to enhance our pathology reports by providing rapid predictions of key features that influence therapy and outcomes.