Abstract 82MO
Background
Histology whole-slide images contains crucial information of patients' risk. In this study, we aimed to develop a fully automated approach for stratifying colorectal cancer (CRC) patients’ risk of mortality by applying deep learning convolutional neural networks to histology whole-slide images.
Methods
We developed deep learning model of two-stage for stratifying CRC's survival risk. First a tumor differentiation classifier was trained on expert annotations to generate probability maps and a predictor index for tumor differentiation. Survival times and aforementioned maps were used to train a Cox neural network that predicts overall survival. Three CRC datasets were used including 2 public datasets from The Cancer Genome Atlas (TCGA); TCGA-COAD was used for model training, TCGA-READ and a local institutional dataset were used for validation.
Results
The accuracy of predicting tumor differentiation achieved to 85% (AUCs 0.983, 0.963, 0.963 and 0.981 for low, medium, high grades, and normal tissue, respectively) in validation set of TCGA-COAD. The patient specific score that predicted by Cox survival CNN networks showed it;s moderate discrimination ability with c-index of 0.65 in validation set. The score can also be combined with clinical factors (age, gender and TNM staging) as a powerful prediction model to stratify CCR's risk. The combined Cox model archieved c-indices of 0.77 and 0.79 in two independent validation sets. C-indices of the model in two validation sets were 0.72 and 0.75 without deep learning based pathological score.
Conclusions
In this study, we proved that the deep learning based psthological scores were added factor beyongd normal clinical factors of sex, age and TNM staging and significantly enhanced the prediction performance of these factors. This study demonstrates that deep learning can provide a meaningful reference for tumor differentiation grading and patient risk evaluation for pathologists.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
Fudan University Shanghai Cancer Center.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
80MO - Gut microbiome analysis for predicting neoadjuvant chemoradiotherapy response in locally advanced rectal cancer patients
Presenter: Yuxi Yi
Session: Mini oral session on Gastrointestinal tumours 2
Resources:
Abstract
Slides
Webcast
81MO - Clinical experience of a personalized and tumour-informed circulating tumour DNA assay for minimal residual disease detection in oligometastatic colorectal cancer patients
Presenter: Stacey Cohen
Session: Mini oral session on Gastrointestinal tumours 2
Resources:
Abstract
Slides
Webcast
83MO - AMG 510, a novel small molecule inhibitor of KRAS(G12C), for patients (pts) with advanced gastrointestinal (GI) cancers: Results from the CodeBreaK100 phase I trial
Presenter: Timothy Price
Session: Mini oral session on Gastrointestinal tumours 2
Resources:
Abstract
Slides
Webcast
84MO - A phase II, multicenter, open-label study of trastuzumab deruxtecan (T-DXd; DS-8201) in patients with HER2-expressing metastatic colorectal cancer (mCRC): DESTINY-CRC01
Presenter: Takayuki Yoshino
Session: Mini oral session on Gastrointestinal tumours 2
Resources:
Abstract
Slides
Webcast
85MO - Management of adverse events associated with encorafenib plus cetuximab in patients with BRAF V600E mutant metastatic colorectal cancer (BEACON CRC Study)
Presenter: Chang-Fang Chiu
Session: Mini oral session on Gastrointestinal tumours 2
Resources:
Abstract
Slides
Webcast
Invited Discussant abstracts 80MO, 81MO and 82MO
Presenter: Dawn Qing Qing Chong
Session: Mini oral session on Gastrointestinal tumours 2
Resources:
Slides
Webcast
Invited Discussant abstracts 83MO, 84MO and 85MO
Presenter: Julien Taieb
Session: Mini oral session on Gastrointestinal tumours 2
Resources:
Slides
Webcast
LIVE Q&A
Presenter: Julien Taieb
Session: Mini oral session on Gastrointestinal tumours 2
Resources:
Webcast
LIVE Q&A
Presenter: Julien Taieb
Session: Mini oral session on Gastrointestinal tumours 2
Resources:
Webcast