Large gastric hamartomatous inverted polyp accompanied by advanced gastric cancer:A case report

BACKGROUND Gastric hamartomatous inverted polyps(GHIPs)are benign polyps of the gastric submucosal layer.Currently there are 52 reported cases in the English literature.According to a literature review,approximately 27%of GHIPs show a coexisting carcinoma.CASE SUMMARY A 66-year-old man was referred to our institution with ulcerative lesions detected on esophagogastroduodenoscopy(EGD)during a regular check-up.Other medical findings were nonspecific.The lesions had borderline histologic features that could not exclude malignancy and were followed up with three EGDs and biopsies at intervals of 3 mo.The latest biopsy was revealed as an adenocarcinoma.A total gastrectomy was performed to remove the tumor.The surgical specimen revealed a 6.9 cm×4.5 cm sized GHIP with a coexisting 1.6 cm sized well-differentiated adenocarcinoma which extended to the muscularis propria.The malignancy did not originate from the GHIP but showed an overlap.CONCLUSION A large GHIP,which was unusually presented as an ulcerative lesion,was surgically removed,and was accompanied by advanced gastric cancer.Regular follow-up and thorough examinations of ulcerative lesions with equivocal biopsy have resulted in appropriate diagnosis and treatment.Therefore,aggressive intervention may be beneficial if GHIP is suspected.

Prediction of clinically actionable genetic alterations from colorectal cancer histopathology images using deep learning

BACKGROUND Identifying genetic mutations in cancer patients have been increasingly important because distinctive mutational patterns can be very informative to determine the optimal therapeutic strategy. Recent studies have shown that deep learning-based molecular cancer subtyping can be performed directly from the standard hematoxylin and eosin(H&E) sections in diverse tumors including colorectal cancers(CRCs). Since H&E-stained tissue slides are ubiquitously available, mutation prediction with the pathology images from cancers can be a time-and cost-effective complementary method for personalized treatment.AIM To predict the frequently occurring actionable mutations from the H&E-stained CRC whole-slide images(WSIs) with deep learning-based classifiers.METHODS A total of 629 CRC patients from The Cancer Genome Atlas(TCGA-COAD and TCGA-READ) and 142 CRC patients from Seoul St. Mary Hospital(SMH) were included. Based on the mutation frequency in TCGA and SMH datasets, we chose APC, KRAS, PIK3CA, SMAD4, and TP53 genes for the study. The classifiers were trained with 360 × 360 pixel patches of tissue images. The receiver operating characteristic(ROC) curves and area under the curves(AUCs) for all the classifiers were presented.RESULTS The AUCs for ROC curves ranged from 0.693 to 0.809 for the TCGA frozen WSIs and from 0.645 to 0.783 for the TCGA formalin-fixed paraffin-embedded WSIs.The prediction performance can be enhanced with the expansion of datasets. When the classifiers were trained with both TCGA and SMH data, the prediction performance was improved.CONCLUSION APC, KRAS, PIK3CA, SMAD4, and TP53 mutations can be predicted from H&E pathology images using deep learning-based classifiers, demonstrating the potential for deep learning-based mutation prediction in the CRC tissue slides.

Novel predictors for lymph node metastasis in submucosal invasive colorectal carcinoma

AIM To evaluate a novel grading system to predict lymph node metastasis(LNM) in patients with submucosal invasive colorectal carcinoma(SICRC).METHODS We analyzed the associations between LNM and various clinicopathological features in 252 patients with SICRC who had undergone radical surgery at the Seoul Saint Mary's hospital between 2000 and 2015.RESULTS LNM was observed in 31 patients(12.3%). The depth and width of the submucosal invasion, lymphatic invasion, tumor budding, and the presence of poorly differentiated clusters(PDCs) were significantly associated with the incidence of LNM. Using multivariate analysis, the receiver operating characteristic curvewas calculated and the area under curve(AUC) was used to compare the ability of the different parameters to identify the risk of LNM. The most powerful clinicopathological parameter for predicting LNM was lymphatic invasion(difference AUC = 0.204), followed by the presence or absence of tumor budding(difference AUC = 0.190), presence of PDCs(difference AUC = 0.172) and tumor budding graded by the Ueno method(difference AUC = 0.128). CONCLUSION Our results indicate that the tumor budding and the depth multiplied by the width measurements of submucosal invasion can provide important information for patients with SICRC.

Prediction of genetic alterations from gastric cancer histopathology images using a fully automated deep learning approach

BACKGROUND Studies correlating specific genetic mutations and treatment response are ongoing to establish an effective treatment strategy for gastric cancer(GC).To facilitate this research,a cost-and time-effective method to analyze the mutational status is necessary.Deep learning(DL)has been successfully applied to analyze hematoxylin and eosin(H and E)-stained tissue slide images.AIM To test the feasibility of DL-based classifiers for the frequently occurring mutations from the H and E-stained GC tissue whole slide images(WSIs).METHODS From the GC dataset of The Cancer Genome Atlas(TCGA-STAD),wildtype/mutation classifiers for CDH1,ERBB2,KRAS,PIK3CA,and TP53 genes were trained on 360×360-pixel patches of tissue images.RESULTS The area under the curve(AUC)for the receiver operating characteristic(ROC)curves ranged from 0.727 to 0.862 for the TCGA frozen WSIs and 0.661 to 0.858 for the TCGA formalin-fixed paraffin-embedded(FFPE)WSIs.The performance of the classifier can be improved by adding new FFPE WSI training dataset from our institute.The classifiers trained for mutation prediction in colorectal cancer completely failed to predict the mutational status in GC,indicating that DL-based mutation classifiers are incompatible between different cancers.CONCLUSION This study concluded that DL could predict genetic mutations in H and E-stained tissue slides when they are trained with appropriate tissue data.