Real-time classification of tumour and non-tumour tissue in colorectal cancer using diffuse reflectance spectroscopy and neural networks to aid margin assessment.

BACKGROUND: Colorectal cancer is the third most commonly diagnosed malignancy and the second leading cause of mortality worldwide. A positive resection margin following surgery for colorectal cancer is linked with higher rates of local recurrence and poorer survival. The authors investigated diffuse reflectance spectroscopy (DRS) to distinguish tumour and non-tumour tissue in ex-vivo colorectal specimens, to aid margin assessment and provide augmented visual maps to the surgeon in real-time. METHODS: Patients undergoing elective colorectal cancer resection surgery at a London-based hospital were prospectively recruited. A hand-held DRS probe was used on the surface of freshly resected ex-vivo colorectal tissue. Spectral data were acquired for tumour and non-tumour tissue. Binary classification was achieved using conventional machine learning classifiers and a convolutional neural network (CNN), which were evaluated in terms of sensitivity, specificity, accuracy and the area under the curve. RESULTS: A total of 7692 mean spectra were obtained for tumour and non-tumour colorectal tissue. The CNN-based classifier was the best performing machine learning algorithm, when compared to contrastive approaches, for differentiating tumour and non-tumour colorectal tissue, with an overall diagnostic accuracy of 90.8% and area under the curve of 96.8%. Live on-screen classification of tissue type was achieved using a graduated colourmap. CONCLUSION: A high diagnostic accuracy for a DRS probe and tracking system to differentiate ex-vivo tumour and non-tumour colorectal tissue in real-time with on-screen visual feedback was highlighted by this study. Further in-vivo studies are needed to ensure integration into a surgical workflow.

HCCANet: histopathological image grading of colorectal cancer using CNN based on multichannel fusion attention mechanism.

Histopathological image analysis is the gold standard for pathologists to grade colorectal cancers of different differentiation types. However, the diagnosis by pathologists is highly subjective and prone to misdiagnosis. In this study, we constructed a new attention mechanism named MCCBAM based on channel attention mechanism and spatial attention mechanism, and developed a computer-aided diagnosis (CAD) method based on CNN and MCCBAM, called HCCANet. In this study, 630 histopathology images processed with Gaussian filtering denoising were included and gradient-weighted class activation map (Grad-CAM) was used to visualize regions of interest in HCCANet to improve its interpretability. The experimental results show that the proposed HCCANet model outperforms four advanced deep learning (ResNet50, MobileNetV2, Xception, and DenseNet121) and four classical machine learning (KNN, NB, RF, and SVM) techniques, achieved 90.2%, 85%, and 86.7% classification accuracy for colorectal cancers with high, medium, and low differentiation levels, respectively, with an overall accuracy of 87.3% and an average AUC value of 0.9.In addition, the MCCBAM constructed in this study outperforms several commonly used attention mechanisms SAM, SENet, SKNet, Non_Local, CBAM, and BAM on the backbone network. In conclusion, the HCCANet model proposed in this study is feasible for postoperative adjuvant diagnosis and grading of colorectal cancer.

PRKAR2A-derived circular RNAs promote the malignant transformation of colitis and distinguish patients with colitis-associated colorectal cancer.

BACKGROUND: Emerging studies have proved that colonic inflammation caused by refractory inflammatory bowel disease (IBD) can initiate the colitis-associated cancer (CAC), but the transition from inflammation to carcinoma is still largely unknown. METHODS: In this study, mouse colitis and CAC models were established, and the RNA-seq by circRNA microarray was employed to identify the differentially expressed circRNAs and mRNAs in different comparisons (DSS vs. NC and AOM/DSS vs. DSS). The bioinformatics analyses were used to search the common characteristics in mouse colitis and CAC. RESULTS: The K-means clustering algorithm packaged these differential expressed circRNAs into subgroup analysis, and the data strongly implied that mmu_circ_0001109 closely correlated to the pro-inflammatory signals, while mmu_circ_0001845 was significantly associated with the Wnt signalling pathway. Our subsequent data in vivo and in vitro confirmed that mmu_circ_0001109 could exacerbate the colitis by up-regulating the Jak-STAT3 and NF-kappa B signalling pathways, and mmu_circ_0001845 promoted the CAC transformation through the Wnt signalling pathway. By RNA blasting between mice and humans, the human RTEL1- and PRKAR2A-derived circRNAs, which might be considered as homeotic circRNAs of mmu_circ_0001109 and mmu_circ_0001845, respectively, were identified. The clinical data revealed that RTEL1-derived circRNAs had no clinical significance in human IBD and CAC. However, three PRKAR2A-derived circRNAs, which had the high RNA similarities to mmu_circ_0001845, were remarkably up-regulated in CAC tissue samples and promoted the transition from colitis to CAC. CONCLUSIONS: Our results suggested that these human PRKAR2A-derived circRNAs could be novel candidates for distinguishing CAC patients and predicted the prognosis of CAC.

A promising deep learning-assistive algorithm for histopathological screening of colorectal cancer.

Colorectal cancer is one of the most common cancers worldwide, accounting for an annual estimated 1.8 million incident cases. With the increasing number of colonoscopies being performed, colorectal biopsies make up a large proportion of any histopathology laboratory workload. We trained and validated a unique artificial intelligence (AI) deep learning model as an assistive tool to screen for colonic malignancies in colorectal specimens, in order to improve cancer detection and classification; enabling busy pathologists to focus on higher order decision-making tasks. The study cohort consists of Whole Slide Images (WSI) obtained from 294 colorectal specimens. Qritive's unique composite algorithm comprises both a deep learning model based on a Faster Region Based Convolutional Neural Network (Faster-RCNN) architecture for instance segmentation with a ResNet-101 feature extraction backbone that provides glandular segmentation, and a classical machine learning classifier. The initial training used pathologists' annotations on a cohort of 66,191 image tiles extracted from 39 WSIs. A subsequent application of a classical machine learning-based slide classifier sorted the WSIs into 'low risk' (benign, inflammation) and 'high risk' (dysplasia, malignancy) categories. We further trained the composite AI-model's performance on a larger cohort of 105 resections WSIs and then validated our findings on a cohort of 150 biopsies WSIs against the classifications of two independently blinded pathologists. We evaluated the area under the receiver-operator characteristic curve (AUC) and other performance metrics. The AI model achieved an AUC of 0.917 in the validation cohort, with excellent sensitivity (97.4%) in detection of high risk features of dysplasia and malignancy. We demonstrate an unique composite AI-model incorporating both a glandular segmentation deep learning model and a classical machine learning classifier, with excellent sensitivity in picking up high risk colorectal features. As such, AI plays a role as a potential screening tool in assisting busy pathologists by outlining the dysplastic and malignant glands.

The COlorectal NEoplasia Endoscopic Classification to Choose the Treatment classification for identification of large laterally spreading lesions lacking submucosal carcinomas: A prospective study of 663 lesions.

INTRODUCTION: Optical diagnosis is necessary when selecting the resection modality for large superficial colorectal lesions. The COlorectal NEoplasia Endoscopic Classification to Choose the Treatment (CONECCT) encompasses overt (irregular pit or vascular pattern) and covert (macroscopic features) signs of carcinoma in an all-in-one classification using validated criteria. The CONECCT IIC subtype corresponds to adenomas with a high risk of superficial carcinoma that should be resected en bloc with free margins. METHODS: This prospective multicentre study investigated the diagnostic accuracy of the CONECCT classification for predicting submucosal invasion in colorectal lesions >20 mm. Optical diagnosis before en bloc resection by endoscopic submucosal dissection (ESD) was compared with the final histological diagnosis. Diagnostic accuracy for the CONECCT IIC subtype was compared with literature-validated features of concern considered to be risk factors for submucosal invasion (non-granular large spreading tumour [NG LST], macronodule >1 cm, SANO IIIA area, and Paris 0-IIC area). RESULTS: Six hundred 63 lesions removed by ESD were assessed. The en bloc, R0, and curative resection rates were respectively 96%, 85%, and 81%. The CONECCT classification had a sensitivity (Se) of 100%, specificity (Sp) of 26.2%, positive predictive value of 11.6%, and negative predictive value (NPV) of 100% for predicting at least submucosal adenocarcinoma. The sensitivity of CONECCT IIC (100%) to predict submucosal cancer was superior to all other criteria evaluated. COlorectal NEoplasia Endoscopic Classification to Choose the Treatment IIC lesions constituted 11.5% of all submucosal carcinomas. CONCLUSION: The CONECCT classification, which combines covert and overt signs of carcinoma, identifies with very perfect sensitivity (Se 100%, NPV 100%) the 30% of low-risk adenomas in large laterally spreading lesions treatable by piecemeal endoscopic mucosal resection or ESD according to expertise without undertreatment. However, the low specificity of CONECCT leads to a large number of potentially not indicated ESDs for suspected high-risk lesions.

Multi-kingdom microbiota analyses identify bacterial-fungal interactions and biomarkers of colorectal cancer across cohorts.

Despite recent progress in our understanding of the association between the gut microbiome and colorectal cancer (CRC), multi-kingdom gut microbiome dysbiosis in CRC across cohorts is unexplored. We investigated four-kingdom microbiota alterations using CRC metagenomic datasets of 1,368 samples from 8 distinct geographical cohorts. Integrated analysis identified 20 archaeal, 27 bacterial, 20 fungal and 21 viral species for each single-kingdom diagnostic model. However, our data revealed superior diagnostic accuracy for models constructed with multi-kingdom markers, in particular the addition of fungal species. Specifically, 16 multi-kingdom markers including 11 bacterial, 4 fungal and 1 archaeal feature, achieved good performance in diagnosing patients with CRC (area under the receiver operating characteristic curve (AUROC) = 0.83) and maintained accuracy across 3 independent cohorts. Coabundance analysis of the ecological network revealed associations between bacterial and fungal species, such as Talaromyces islandicus and Clostridium saccharobutylicum. Using metagenome shotgun sequencing data, the predictive power of the microbial functional potential was explored and elevated D-amino acid metabolism and butanoate metabolism were observed in CRC. Interestingly, the diagnostic model based on functional EggNOG genes achieved high accuracy (AUROC = 0.86). Collectively, our findings uncovered CRC-associated microbiota common across cohorts and demonstrate the applicability of multi-kingdom and functional markers as CRC diagnostic tools and, potentially, as therapeutic targets for the treatment of CRC.

Resolving the difference between left-sided and right-sided colorectal cancer by single-cell sequencing.

Colorectal cancers (CRCs) exhibit differences in incidence, pathogenesis, molecular pathways, and outcome depending on the location of the tumor. The transcriptomes of 27,927 single human CRC cells from 3 left-sided and 3 right-sided CRC patients were profiled by single-cell RNA-Seq (scRNA-Seq). Right-sided CRC harbors a significant proportion of exhausted CD8+ T cells of a highly migratory nature. One cluster of cells from left-sided CRC exhibiting states preceding exhaustion and a high ratio of preexhausted/exhausted T cells were favorable prognostic markers. Notably, we identified a potentially novel RBP4+NTS+ subpopulation of cancer cells that exclusively expands in left-sided CRC. Tregs from left-sided CRC showed higher levels of immunotherapy-related genes than those from right-sided CRC, indicating that left-sided CRC may have increased responsiveness to immunotherapy. Antibody-dependent cellular phagocytosis (ADCP) and antibody-dependent cellular cytotoxicity (ADCC) induced by M2-like macrophages were more pronounced in left-sided CRC and correlated with a good prognosis in CRC.

Validation of genetic classifiers derived from mouse and human tumors to identify molecular subtypes of colorectal cancer.

Colorectal cancer (CRC) is a leading cause of cancer death in the United States. Standard treatment for advanced-stage CRC for decades has included 5-fluorouracil-based chemotherapy. More recently, targeted therapies for metastatic CRC are being used based on the individual cancer's molecular profile. In the past few years, several different molecular subtype schemes for human CRC have been developed. The molecular subtypes can be distinguished by gene expression signatures and have the potential to be used to guide treatment decisions. However, many subtyping classification methods were developed using mRNA expression levels of hundreds to thousands of genes, making them impractical for clinical use. In this study, we assessed whether an immunohistochemical approach could be used for molecular subtyping of CRCs. We validated two previously published, independent sets of immunohistochemistry classifiers and modified the published methods to improve the accuracy of the scoring methods. In addition, we evaluated whether protein and genetic signatures identified originally in the mouse were linked to clinical outcomes of patients with CRC. We found that low DDAH1 or low GAL3ST2 protein levels in human CRCs correlate with poor patient outcomes. The results of this study have the potential to impact methods for determining the prognosis and therapy selection for patients with CRC.

Genomic and transcriptomic characterization of heterogeneous immune subgroups of microsatellite instability-high colorectal cancers.

BACKGROUND: Colorectal cancers (CRCs) with microsatellite instability-high (MSI-H) are hypermutated tumors and are generally regarded as immunogenic. However, their heterogeneous immune responses and underlying molecular characteristics remain largely unexplained. METHODS: We conducted a retrospective analysis of 73 primary MSI-H CRC tissues to characterize heterogeneous immune subgroups. Based on combined tumor-infiltrating lymphocyte (TIL) immunoscore and tertiary lymphoid structure (TLS) activity, MSI-H CRCs were classified into immune-high, immune-intermediate, and immune-low subgroups. Of these, the immune-high and immune-low subgroups were further analyzed using whole-exome and transcriptome sequencing. RESULTS: We found considerable variations in immune parameters between MSI-H CRCs, and immune subgrouping of MSI-H CRCs was performed accordingly. The TIL densities and TLS activities of immune-low MSI-H CRCs were comparable to those of an immune-low or immune-intermediate subgroup of microsatellite-stable CRCs. There were remarkable differences between immune-high and immune-low MSI-H CRCs, including their pathological features (medullary vs mucinous), genomic alterations (tyrosine kinase fusions vs KRAS mutations), and activated signaling pathways (immune-related vs Wnt and Notch signaling), whereas no significant differences were found in tumor mutational burden (TMB) and neoantigen load. The immune-low MSI-H CRCs were subdivided by the consensus molecular subtype (CMS1 vs CMS3) with different gene expression signatures (mesenchymal/stem-like vs epithelial/goblet-like), suggesting distinct immune evasion mechanisms. Angiogenesis and CD200 were identified as potential therapeutic targets in immune-low CMS1 and CMS3 MSI-H CRCs, respectively. CONCLUSIONS: MSI-H CRCs are immunologically heterogeneous, regardless of TMB. The unusual immune-low MSI-H CRCs are characterized by mucinous histology, KRAS mutations, and Wnt/Notch activation, and can be further divided into distinct gene expression subtypes, including CMS4-like CMS1 and CMS3. Our data provide novel insights into precise immunotherapeutic strategies for subtypes of MSI-H tumors.

Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images.

Machine-assisted pathological recognition has been focused on supervised learning (SL) that suffers from a significant annotation bottleneck. We propose a semi-supervised learning (SSL) method based on the mean teacher architecture using 13,111 whole slide images of colorectal cancer from 8803 subjects from 13 independent centers. SSL (~3150 labeled, ~40,950 unlabeled; ~6300 labeled, ~37,800 unlabeled patches) performs significantly better than the SL. No significant difference is found between SSL (~6300 labeled, ~37,800 unlabeled) and SL (~44,100 labeled) at patch-level diagnoses (area under the curve (AUC): 0.980 ± 0.014 vs. 0.987 ± 0.008, P value = 0.134) and patient-level diagnoses (AUC: 0.974 ± 0.013 vs. 0.980 ± 0.010, P value = 0.117), which is close to human pathologists (average AUC: 0.969). The evaluation on 15,000 lung and 294,912 lymph node images also confirm SSL can achieve similar performance as that of SL with massive annotations. SSL dramatically reduces the annotations, which has great potential to effectively build expert-level pathological artificial intelligence platforms in practice.

The Evolving Role of Consensus Molecular Subtypes: a Step Beyond Inpatient Selection for Treatment of Colorectal Cancer.

OPINION STATEMENT: The heterogenous nature of colorectal cancer (CRC) renders it a major clinical challenge. Increasing genomic understanding of CRC has improved our knowledge of this heterogeneity and the main cancer drivers, with significant improvements in clinical outcomes. Comprehensive molecular characterization has allowed clinicians a more precise range of treatment options based on biomarker selection. Furthermore, this deep molecular understanding likely extends therapeutic options to a larger number of patients. The biological associations of consensus molecular subtypes (CMS) with clinical outcomes in localized CRC have been validated in retrospective clinical trials. The prognostic role of CMS has also been confirmed in the metastatic setting, with CMS2 having the best prognosis, whereas CMS1 tumors are associated with a higher risk of progression and death after chemotherapy. Similarly, according to mesenchymal features and immunosuppressive molecules, CMS1 responds to immunotherapy, whereas CMS4 has a poorer prognosis, suggesting that a CMS1 signature could identify patients who may benefit from immune checkpoint inhibitors regardless of microsatellite instability (MSI) status. The main goal of these comprehensive analyses is to switch from "one marker-one drug" to "multi-marker drug combinations" allowing oncologists to give "the right drug to the right patient." Despite the revealing data from transcriptomic analyses, the high rate of intra-tumoral heterogeneity across the different CMS subgroups limits its incorporation as a predictive biomarker. In clinical practice, when feasible, comprehensive genomic tests should be performed to identify potentially targetable alterations, particularly in RAS/BRAF wild-type, MSI, and right-sided tumors. Furthermore, CMS has not only been associated with clinical outcomes and specific tumor and patient phenotypes but also with specific microbiome patterns. Future steps will include the integration of clinical features, genomics, transcriptomics, and microbiota to select the most accurate biomarkers to identify optimal treatments, improving individual clinical outcomes. In summary, CMS is context specific, identifies a level of heterogeneity beyond standard genomic biomarkers, and offers a means of maximizing personalized therapy.

Evaluation of an Artificial Intelligence-Augmented Digital System for Histologic Classification of Colorectal Polyps.

Importance: Colorectal polyps are common, and their histopathologic classification is used in the planning of follow-up surveillance. Substantial variation has been observed in pathologists' classification of colorectal polyps, and improved assessment by pathologists may be associated with reduced subsequent underuse and overuse of colonoscopy. Objective: To compare standard microscopic assessment with an artificial intelligence (AI)-augmented digital system that annotates regions of interest within digitized polyp tissue and predicts polyp type using a deep learning model to assist pathologists in colorectal polyp classification. Design, Setting, and Participants: In this diagnostic study conducted at a tertiary academic medical center and a community hospital in New Hampshire, 100 slides with colorectal polyp samples were read by 15 pathologists using a microscope and an AI-augmented digital system, with a washout period of at least 12 weeks between use of each modality. The study was conducted from February 10 to July 10, 2020. Main Outcomes and Measures: Accuracy and time of evaluation were used to compare pathologists' performance when a microscope was used with their performance when the AI-augmented digital system was used. Outcomes were compared using paired t tests and mixed-effects models. Results: In assessments of 100 slides with colorectal polyp specimens, use of the AI-augmented digital system significantly improved pathologists' classification accuracy compared with microscopic assessment from 73.9% (95% CI, 71.7%-76.2%) to 80.8% (95% CI, 78.8%-82.8%) (P < .001). The overall difference in the evaluation time per slide between the digital system (mean, 21.7 seconds; 95% CI, 20.8-22.7 seconds) and microscopic examination (mean, 13.0 seconds; 95% CI, 12.4-13.5 seconds) was -8.8 seconds (95% CI, -9.8 to -7.7 seconds), but this difference decreased as pathologists became more familiar and experienced with the digital system; the difference between the time of evaluation on the last set of 20 slides for all pathologists when using the microscope and the digital system was 4.8 seconds (95% CI, 3.0-6.5 seconds). Conclusions and Relevance: In this diagnostic study, an AI-augmented digital system significantly improved the accuracy of pathologic interpretation of colorectal polyps compared with microscopic assessment. If applied broadly to clinical practice, this tool may be associated with decreases in subsequent overuse and underuse of colonoscopy and thus with improved patient outcomes and reduced health care costs.

Identification of immune-related subtypes of colorectal cancer to improve antitumor immunotherapy.

Immunotherapy involving immune checkpoint inhibitors (ICIs) for enhancing immune system activation is promising for tumor management. However, the patients' responses to ICIs are different. Here, we applied a non-negative matrix factorization algorithm to establish a robust immune molecular classification system for colorectal cancer (CRC). We obtained data of 1503 CRC patients (training cohort: 488 from The Cancer Genome Atlas; validation cohort: 1015 from the Gene Expression Omnibus). In the training cohort, 42.8% of patients who exhibited significantly higher immunocyte infiltration and enrichment of immune response-associated signatures were subdivided into immune classes. Within the immune class, 53.1% of patients were associated with a worse overall prognosis and belonged to the immune-suppressed subclass, characterized by the activation of stroma-related signatures, genes, immune-suppressive cells, and signaling. The remaining immune class patients belonged to the immune-activated subclass, which was associated with a better prognosis and response to anti-PD-1 therapy. Immune-related subtypes were associated with different copy number alterations, tumor-infiltrating lymphocyte enrichment, PD-1/PD-L1 expression, mutation landscape, and cancer stemness. These results were validated in patients with microsatellite instable CRC. We described a novel immune-related class of CRC, which may be used for selecting candidate patients with CRC for immunotherapy and tailoring optimal immunotherapeutic treatment.

Comparison of model fit and discriminatory ability of M category as defined by the 7th and 8th editions of the tumor-node-metastasis classification of colorectal cancer and the 9th edition of the Japanese classification.

BACKGROUND: In transitioning from the 7th edition of the tumor-node-metastasis classification (TNM-7) to the 8th edition (TNM-8), colorectal cancer with peritoneal metastasis was newly categorized as M1c. In the 9th edition of the Japanese Classification of colorectal, appendiceal, and anal carcinoma (JPC-9), M1c is further subdivided into M1c1 (without other organ involvement) and M1c2 (with other organ involvement). This study aimed to compare the model fit and discriminatory ability of the M category of these three classification systems, as no study to date has made this comparison. METHODS: The study population consisted of stage IV colorectal cancer patients who were referred to the National Cancer Center Hospital from 2000 to 2017. The Akaike information criterion (AIC), Harrell's concordance index (C-index), and time-dependent receiver operating characteristic (ROC) curves were used to compare the three classification systems. Subgroup analyses, stratified by initial treatment year, were also performed. RESULTS: According to TNM-8, 670 (55%) patients had M1a, 273 (22%) had M1b, and 279 (23%) had M1c (87 M1c1 and 192 M1c2 using JPC-9) tumors. Among the three classification systems, JPC-9 had the lowest AIC value (JPC-9: 10546.3; TNM-7: 10555.9; TNM-8: 10585.5), highest C-index (JPC-9: 0.608; TNM-7: 0.598; TNM-8: 0.599), and superior time-dependent ROC curves throughout the observation period. Subgroup analyses were consistent with these results. CONCLUSIONS: While the revised M category definition did not improve model fit and discriminatory ability from TNM-7 to TNM-8, further subdivision of M1c in JPC-9 improved these parameters. These results support further revisions to M1 subcategories in future editions of the TNM classification system.

Genome-Derived Classification Signature for Ampullary Adenocarcinoma to Improve Clinical Cancer Care.

PURPOSE: The clinical behavior of ampullary adenocarcinoma varies widely. Targeted tumor sequencing may better define biologically distinct subtypes to improve diagnosis and management. EXPERIMENTAL DESIGN: The hidden-genome algorithm, a multilevel meta-feature regression model, was trained on a prospectively sequenced cohort of 3,411 patients (1,001 pancreatic adenocarcinoma, 165 distal bile-duct adenocarcinoma, 2,245 colorectal adenocarcinoma) and subsequently applied to targeted panel DNA-sequencing data from ampullary adenocarcinomas. Genomic classification (i.e., colorectal vs. pancreatic) was correlated with standard histologic classification [i.e., intestinal (INT) vs. pancreatobiliary (PB)] and clinical outcome. RESULTS: Colorectal genomic subtype prediction was primarily influenced by mutations in APC and PIK3CA, tumor mutational burden, and DNA mismatch repair (MMR)-deficiency signature. Pancreatic genomic-subtype prediction was dictated by KRAS gene alterations, particularly KRAS G12D, KRAS G12R, and KRAS G12V. Distal bile-duct adenocarcinoma genomic subtype was most influenced by copy-number gains in the MDM2 gene. Despite high (73%) concordance between immunomorphologic subtype and genomic category, there was significant genomic heterogeneity within both histologic subtypes. Genomic scores with higher colorectal probability were associated with greater survival compared with those with a higher pancreatic probability. CONCLUSIONS: The genomic classifier provides insight into the heterogeneity of ampullary adenocarcinoma and improves stratification, which is dictated by the proportion of colorectal and pancreatic genomic alterations. This approach is reproducible with available molecular testing and obviates subjective histologic interpretation.

Molecular Subtyping Combined with Biological Pathway Analyses to Study Regorafenib Response in Clinically Relevant Mouse Models of Colorectal Cancer.

PURPOSE: Regorafenib (REG) is approved for the treatment of metastatic colorectal cancer, but has modest survival benefit and associated toxicities. Robust predictive/early response biomarkers to aid patient stratification are outstanding. We have exploited biological pathway analyses in a patient-derived xenograft (PDX) trial to study REG response mechanisms and elucidate putative biomarkers. EXPERIMENTAL DESIGN: Molecularly subtyped PDXs were annotated for REG response. Subtyping was based on gene expression (CMS, consensus molecular subtype) and copy-number alteration (CNA). Baseline tumor vascularization, apoptosis, and proliferation signatures were studied to identify predictive biomarkers within subtypes. Phospho-proteomic analysis was used to identify novel classifiers. Supervised RNA sequencing analysis was performed on PDXs that progressed, or did not progress, following REG treatment. RESULTS: Improved REG response was observed in CMS4, although intra-subtype response was variable. Tumor vascularity did not correlate with outcome. In CMS4 tumors, reduced proliferation and higher sensitivity to apoptosis at baseline correlated with response. Reverse phase protein array (RPPA) analysis revealed 4 phospho-proteomic clusters, one of which was enriched with non-progressor models. A classification decision tree trained on RPPA- and CMS-based assignments discriminated non-progressors from progressors with 92% overall accuracy (97% sensitivity, 67% specificity). Supervised RNA sequencing revealed that higher basal EPHA2 expression is associated with REG resistance. CONCLUSIONS: Subtype classification systems represent canonical "termini a quo" (starting points) to support REG biomarker identification, and provide a platform to identify resistance mechanisms and novel contexts of vulnerability. Incorporating functional characterization of biological systems may optimize the biomarker identification process for multitargeted kinase inhibitors.

The Sulfur Microbial Diet and Risk of Colorectal Cancer by Molecular Subtypes and Intratumoral Microbial Species in Adult Men.

INTRODUCTION: We recently described the sulfur microbial diet, a pattern of intake associated with increased gut sulfur-metabolizing bacteria and incidence of distal colorectal cancer (CRC). We assessed whether this risk differed by CRC molecular subtypes or presence of intratumoral microbes involved in CRC pathogenesis (Fusobacterium nucleatum and Bifidobacterium spp.). METHODS: We performed Cox proportional hazards modeling to examine the association between the sulfur microbial diet and incidence of overall and distal CRC by molecular and microbial subtype in the Health Professionals Follow-Up Study (1986-2012). RESULTS: We documented 1,264 incident CRC cases among 48,246 men, approximately 40% of whom had available tissue data. After accounting for multiple hypothesis testing, the relationship between the sulfur microbial diet and CRC incidence did not differ by subtype. However, there was a suggestion of an association by prostaglandin synthase 2 (PTGS2) status with a multivariable adjusted hazard ratio for highest vs lowest tertile of sulfur microbial diet scores of 1.31 (95% confidence interval: 0.99-1.74, Ptrend = 0.07, Pheterogeneity = 0.04) for PTGS2-high CRC. The association of the sulfur microbial diet with distal CRC seemed to differ by the presence of intratumoral Bifidobacterium spp. with an adjusted hazard ratio for highest vs lowest tertile of sulfur microbial diet scores of 1.65 (95% confidence interval: 1.14-2.39, Ptrend = 0.01, Pheterogeneity = 0.03) for Bifidobacterium-negative distal CRC. We observed no apparent heterogeneity by other tested molecular markers. DISCUSSION: Greater long-term adherence to the sulfur microbial diet could be associated with PTGS2-high and Bifidobacterium-negative distal CRC in men. Additional studies are needed to further characterize the role of gut microbial sulfur metabolism and CRC.

Multiclassification of Endoscopic Colonoscopy Images Based on Deep Transfer Learning.

With the continuous improvement of human living standards, dietary habits are constantly changing, which brings various bowel problems. Among them, the morbidity and mortality rates of colorectal cancer have maintained a significant upward trend. In recent years, the application of deep learning in the medical field has become increasingly spread aboard and deep. In a colonoscopy, Artificial Intelligence based on deep learning is mainly used to assist in the detection of colorectal polyps and the classification of colorectal lesions. But when it comes to classification, it can lead to confusion between polyps and other diseases. In order to accurately diagnose various diseases in the intestines and improve the classification accuracy of polyps, this work proposes a multiclassification method for medical colonoscopy images based on deep learning, which mainly classifies the four conditions of polyps, inflammation, tumor, and normal. In view of the relatively small number of data sets, the network firstly trained by transfer learning on ImageNet was used as the pretraining model, and the prior knowledge learned from the source domain learning task was applied to the classification task about intestinal illnesses. Then, we fine-tune the model to make it more suitable for the task of intestinal classification by our data sets. Finally, the model is applied to the multiclassification of medical colonoscopy images. Experimental results show that the method in this work can significantly improve the recognition rate of polyps while ensuring the classification accuracy of other categories, so as to assist the doctor in the diagnosis of surgical resection.

Increasing Embryonic Morphogen Nodal Expression Suggests Malignant Transformation in Colorectal Lesions and as a Potential Marker for CMS4 Subtype of Colorectal Cancer.

Nodal, an embryonic morphogen in TGF-ß family, is related with tumorigenicity and progression in various tumors including colorectal cancer (CRC). However, the difference of Nodal expression between CRC and colorectal polyps has not yet been investigated. Besides, whether Nodal can be used as a marker for consensus molecular subtype classification-4 (CMS4) of CRC is also worth studying. We analyzed Nodal expression in patients of CRC (161), high-grade intraepithelial neoplasia (HGIN, 28) and five types of colorectal polyps (116). The Nodal expression difference among groups and the association between Nodal expression and clinicopathological features were analyzed. Two categories logistic regression model was used to predict the odds ratio (OR) of risk factors for high tumor-stroma percentage (TSP), and ROC curve was used to assess the diagnostic value of Nodal in predicting high TSP in CRC. We found that Nodal expression was significantly elevated in CRC and HGIN (p < 0.0001). The increased expression of Nodal was related with high TSP, mismatch repair-proficient (pMMR) status, lymph node metastasis and advanced AJCC stage (p < 0.05). Besides, Nodal expression was the only risk factor for high TSP (OR = 6.94; p < 0.001), and ROC curve demonstrated that Nodal expression was able to efficiently distinguish high and low TSP. In conclusion, different expression of Nodal between CRC/HGIN and benign lesions is suggestive of a promoting role for Nodal in colorectal tumor progression. Besides, Nodal might also be used as a potential marker for CMS4 subtype of CRC.

Medical costs according to the stages of colorectal cancer: an analysis of health insurance claims in Hachioji, Japan.

BACKGROUND: Although the effect of the early detection of colorectal cancer (CRC) on medical costs needs to be clarified, there are few reports on the actual medical costs of CRC patients in Japan. We aimed to identify medical costs according to CRC stage, using health insurance claims. METHODS: This observational study included CRC patients who had received specific treatment for CRC, which was defined by the procedure code and the claim computer processing system code associated with the treatment of CRC. CRC patients who underwent endoscopic or radical surgical treatment were defined as the curable group and those with palliative treatment, including palliative chemotherapy, as the non-curable group. Total medical costs and medical costs of specific treatments for CRC for 3 years were measured using the claims held by Hachioji City from May 2014 to July 2019. RESULTS: This study included 442 patients in the curable group, including 267 patients who underwent endoscopic treatment, and 175 patients who underwent radical surgical treatment, and 161 patients in the non-curable group. The mean (standard deviation) total medical costs in the curable and non-curable groups were 2,130 (2,494) and 8,279 (5,600) thousand Japanese Yen (JPY), respectively. The mean (standard deviation) medical costs for the specific treatment of CRC in the curable and non-curable groups were 408 (352) and 3,685 (3,479) thousand JPY, respectively. CONCLUSIONS: We clarified the actual medical costs of CRC in curable and non-curable groups. These results suggest the effect of early detection of CRC in reducing medical costs.