Deep learning-based radiomic features for improving neoadjuvant chemoradiation response prediction in locally advanced rectal cancer
- 24 February 2020
- journal article
- research article
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 65 (7), 075001
- https://doi.org/10.1088/1361-6560/ab7970
Abstract
Purpose: Radiomic features achieve promising results in cancer diagnosis and treatment response prediction. The goal of this study is to compare the handcrafted, or explicitly designed, radiomic features and deep learning (DL)-based radiomic features extracted from pre-treatment diffusion-weighted magnetic resonance images (DWIs) for predicting neoadjuvant chemoradiation treatment (nCRT) response in patients with locally advanced rectal cancer (LARC). Materials and methods: 43 patients receiving nCRT were included. All patients underwent DWIs before nCRT and total mesorectal excision surgery after nCRT. Gross tumor volume (GTV) contours were drawn by an experienced radiation oncologist on DWIs. The patient-cohort was split into the responder group (n=22) and the non-responder group (n=21) based on the post-nCRT response assessed by postoperative pathology, MRI or colonoscopy. Handcrafted and DL-based features were extracted from the apparent diffusion coefficient (ADC) map of the DWI using conventional computer-aided diagnosis methods and a pre-trained convolution neural network, respectively. Least absolute shrinkage and selection operator (LASSO)-logistic regression models were constructed using extracted features for predicting treatment response. The model performance was evaluated with repeated 20 times stratified 4-fold cross-validation using receiver operating characteristic (ROC) curves and compared using the corrected resampled t-test. Results: The model built with handcrafted features achieved the mean area under the ROC curve (AUC) of 0.64, while the one built with DL-based features yielded the mean AUC of 0.73. The corrected resampled t-test on AUC showed P-value < 0.05. Conclusion: DL-based features extracted from pre-treatment DWIs achieved significantly better classification performance compared with handcrafted features for predicting nCRT response in LARC patients.Keywords
This publication has 29 references indexed in Scilit:
- Deep learningNature, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Comparison of Tumor Regression Grade Systems for Locally Advanced Rectal Cancer After Multimodality TreatmentJNCI Journal of the National Cancer Institute, 2014
- EURECCA colorectal: Multidisciplinary management: European consensus conference colon & rectumEuropean Journal of Cancer, 2013
- Apparent diffusion coefficient for evaluating tumour response to neoadjuvant chemoradiation therapy for locally advanced rectal cancerEuropean Radiology, 2010
- Long-term outcome in patients with a pathological complete response after chemoradiation for rectal cancer: a pooled analysis of individual patient dataThe Lancet Oncology, 2010
- Estimating classification error rate: Repeated cross-validation, repeated hold-out and bootstrapComputational Statistics & Data Analysis, 2009
- Genome-wide association analysis by lasso penalized logistic regressionBioinformatics, 2009
- Pathologic stage is most prognostic of disease‐free survival in locally advanced rectal cancer patients after preoperative chemoradiationCancer, 2008
- Preoperative Radiotherapy Combined with Total Mesorectal Excision for Resectable Rectal CancerThe New England Journal of Medicine, 2001