Noninvasive Computed Tomography–Based Deep Learning Model Predicts In Vitro Chemosensitivity Assay Results in Pancreatic Cancer
Taishu Kanda, Taiichi Wakiya, Keinosuke Ishido, Norihisa Kimura, Hayato Nagase, Eri Yoshida, Junichi Nakagawa, Masashi Matsuzaka, Takenori Niioka, Yoshihiro Sasaki, Kenichi Hakamada- Endocrinology
- Hepatology
- Endocrinology, Diabetes and Metabolism
- Internal Medicine
Objectives
We aimed to predict in vitro chemosensitivity assay results from computed tomography (CT) images by applying deep learning (DL) to optimize chemotherapy for pancreatic ductal adenocarcinoma (PDAC).
Materials and Methods
Preoperative enhanced abdominal CT images and the histoculture drug response assay (HDRA) results were collected from 33 PDAC patients undergoing surgery. Deep learning was performed using CT images of both the HDRA-positive and HDRA-negative groups. We trimmed small patches from the entire tumor area. We established various prediction labels for HDRA results with 5-fluorouracil (FU), gemcitabine (GEM), and paclitaxel (PTX). We built a predictive model using a residual convolutional neural network and used 3-fold cross-validation.
Results
Of the 33 patients, effective response to FU, GEM, and PTX by HDRA was observed in 19 (57.6%), 11 (33.3%), and 23 (88.5%) patients, respectively. The average accuracy and the area under the receiver operating characteristic curve (AUC) of the model for predicting the effective response to FU were 93.4% and 0.979, respectively. In the prediction of GEM, the models demonstrated high accuracy (92.8%) and AUC (0.969). Likewise, the model for predicting response to PTX had a high performance (accuracy, 95.9%; AUC, 0.979).
Conclusions
Our CT patch–based DL model exhibited high predictive performance in projecting HDRA results. Our study suggests that the DL approach could possibly provide a noninvasive means for the optimization of chemotherapy.