Machine Learning of Histopathological Images Predicts Recurrences of Resected Pancreatic Ductal Adenocarcinoma With Adjuvant Treatment.

OBJECTIVES: Pancreatic ductal adenocarcinoma is an intractable disease with frequent recurrence after resection and adjuvant therapy. The present study aimed to clarify whether artificial intelligence-assisted analysis of histopathological images can predict recurrence in patients with pancreatic ductal adenocarcinoma who underwent resection and adjuvant chemotherapy with tegafur/5-chloro-2,4-dihydroxypyridine/potassium oxonate. MATERIALS AND METHODS: Eighty-nine patients were enrolled in the study. Machine-learning algorithms were applied to 10-billion-scale pixel data of whole-slide histopathological images to generate key features using multiple deep autoencoders. Areas under the curve were calculated from receiver operating characteristic curves using a support vector machine with key features alone and by combining with clinical data (age and carbohydrate antigen 19-9 and carcinoembryonic antigen levels) for predicting recurrence. Supervised learning with pathological annotations was conducted to determine the significant features for predicting recurrence. RESULTS: Areas under the curves obtained were 0.73 (95% confidence interval, 0.59-0.87) by the histopathological data analysis and 0.84 (95% confidence interval, 0.73-0.94) by the combinatorial analysis of histopathological data and clinical data. Supervised learning model demonstrated that poor tumor differentiation was significantly associated with recurrence. CONCLUSIONS: Results indicate that machine learning with the integration of artificial intelligence-driven evaluation of histopathological images and conventional clinical data provides relevant prognostic information for patients with pancreatic ductal adenocarcinoma.

Novel candidate factors predicting the effect of S-1 adjuvant chemotherapy of pancreatic cancer.

The collagen gel droplet-embedded drug sensitivity test (CD-DST) was revealed to be useful for predicting the effect of S-1 adjuvant chemotherapy for pancreatic ductal adenocarcinoma (PDAC). However, collection of an adequate number of PDAC cells is difficult due to the surrounding fibroblasts. Thus, the aim of this study was to discover novel biomarkers to predict chemosensitivity based on the CD-DST results. Proteomics analysis was performed using liquid chromatography tandem mass spectrometry (LC-MS/MS). Candidate proteins were validated in patients with 5-FU CD-DST results via immunohistochemistry (IHC). The relationships between the candidate proteins and the effect of the adjuvant S-1 were investigated via IHC. Among the 2696 proteins extracted by LC-MS/MS, C1TC and SAHH could accurately predict the CD-DST results. Recurrence-free survival (RFS) was significantly improved in the IHC-positive group compared with the IHC-negative group in both factors. The negative group did not show a significant difference from the group that did not receive S-1. The double-positive group was associated with significantly prolonged RFS compared to the no adjuvant chemotherapy group. C1TC and SAHH have been shown to be useful biomarkers for predicting 5-FU sensitivity as a substitute for the CD-DST in adjuvant chemotherapy for PDAC.