Machine learning for prediction of chemoradiation therapy response in rectal cancer using pre-treatment and mid-radiation multi-parametric MRI

• Published in: Magnetic resonance imaging Vol. 61; pp. 33 - 40
• Main Authors: Shi, Liming, Zhang, Yang, Nie, Ke, Sun, Xiaonan, Niu, Tianye, Yue, Ning, Kwong, Tiffany, Chang, Peter, Chow, Daniel, Chen, Jeon-Hor, Su, Min-Ying
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Inc 01.09.2019
• Subjects: Chemoradiotherapy - methods; Contrast Media; Convolutional neural network; Diffusion Magnetic Resonance Imaging - methods; Female; Humans; Image Enhancement - methods; Locally advanced rectal cancer; Machine Learning; Male; Middle Aged; Multi-parametric MRI; Multiparametric Magnetic Resonance Imaging - methods; Neoadjuvant chemoradiation therapy; Predictive Value of Tests; Radiomics; Rectal Neoplasms - diagnostic imaging; Rectal Neoplasms - pathology; Rectal Neoplasms - therapy; Rectum - diagnostic imaging; Rectum - pathology; Reproducibility of Results; Treatment Outcome; Tumor Burden; Neoadjuvant chemoradiation therapy; Multi-parametric MRI; Locally advanced rectal cancer; Convolutional neural network; Radiomics
• ISSN: 0730-725X; 1873-5894
• DOI: 10.1016/j.mri.2019.05.003

To predict the neoadjuvant chemoradiation therapy (CRT) response in patients with locally advanced rectal cancer (LARC) using radiomics and deep learning based on pre-treatment MRI and a mid-radiation follow-up MRI taken 3–4 weeks after the start of CRT. A total of 51 patients were included, 45 with pre-treatment, 41 with mid-radiation therapy (RT), and 35 with both MRI sets. The multi-parametric MRI protocol included T2, diffusion weighted imaging (DWI) with b-values of 0 and 800 s/mm2, and dynamic-contrast-enhanced (DCE) MRI. After completing CRT and surgery, the specimen was examined to determine the pathological response based on the tumor regression grade. The tumor ROI was manually drawn on the post-contrast image and mapped to other sequences. The total tumor volume and mean apparent diffusion coefficient (ADC) were measured. Radiomics using GLCM texture and histogram parameters, and deep learning using a convolutional neural network (CNN), were performed to differentiate pathologic complete response (pCR) vs. non-pCR, and good response (GR) vs. non-GR. Tumor volume decreased and ADC increased significantly in the mid-RT MRI compared to the pre-treatment MRI. For predicting pCR vs. non-pCR, combining ROI and radiomics features achieved an AUC of 0.80 for pre-treatment, 0.82 for mid-RT, and 0.86 for both MRI together. For predicting GR vs. non-GR, the AUC was 0.91 for pre-treatment, 0.92 for mid-RT, and 0.93 for both MRI together. In deep learning using CNN, combining pre-treatment and mid-RT MRI achieved a higher accuracy compared to using either dataset alone, with AUC of 0.83 for predicting pCR vs. non-pCR. Radiomics based on pre-treatment and early follow-up multi-parametric MRI in LARC patients receiving CRT could extract comprehensive quantitative information to predict final pathologic response.