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

Liming Shi, Yang Zhang, Ke Nie, Xiaonan Sun, Tianye Niu, Ning Yue, Tiffany Kwong, Peter Chang, Daniel Chow, Jeon Hor Chen, Min Ying Su

Research output: Contribution to journalArticle

Abstract

Purpose: 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. Methods: 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. Results: 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. Conclusion: 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.

Original languageEnglish (US)
Pages (from-to)33-40
Number of pages8
JournalMagnetic Resonance Imaging
Volume61
DOIs
StatePublished - Sep 1 2019

Fingerprint

Rectal Neoplasms
Magnetic resonance imaging
Learning systems
Radiation
Radiotherapy
Tumors
Area Under Curve
Therapeutics
Learning
Tumor Burden
Machine Learning
Neural networks
Neoadjuvant Therapy
Surgery
Neoplasms
Textures
Imaging techniques

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Radiology Nuclear Medicine and imaging
  • Biomedical Engineering

Keywords

  • Convolutional neural network
  • Locally advanced rectal cancer
  • Multi-parametric MRI
  • Neoadjuvant chemoradiation therapy
  • Radiomics

Cite this

Shi, Liming ; Zhang, Yang ; Nie, Ke ; Sun, Xiaonan ; Niu, Tianye ; Yue, Ning ; Kwong, Tiffany ; Chang, Peter ; Chow, Daniel ; Chen, Jeon Hor ; Su, Min Ying. / Machine learning for prediction of chemoradiation therapy response in rectal cancer using pre-treatment and mid-radiation multi-parametric MRI. In: Magnetic Resonance Imaging. 2019 ; Vol. 61. pp. 33-40.
@article{0c4d8c5e71fd4c0b9111ae616739951b,
title = "Machine learning for prediction of chemoradiation therapy response in rectal cancer using pre-treatment and mid-radiation multi-parametric MRI",
abstract = "Purpose: 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. Methods: 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. Results: 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. Conclusion: 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.",
keywords = "Convolutional neural network, Locally advanced rectal cancer, Multi-parametric MRI, Neoadjuvant chemoradiation therapy, Radiomics",
author = "Liming Shi and Yang Zhang and Ke Nie and Xiaonan Sun and Tianye Niu and Ning Yue and Tiffany Kwong and Peter Chang and Daniel Chow and Chen, {Jeon Hor} and Su, {Min Ying}",
year = "2019",
month = "9",
day = "1",
doi = "https://doi.org/10.1016/j.mri.2019.05.003",
language = "English (US)",
volume = "61",
pages = "33--40",
journal = "Magnetic Resonance Imaging",
issn = "0730-725X",
publisher = "Elsevier Inc.",

}

Machine learning for prediction of chemoradiation therapy response in rectal cancer using pre-treatment and mid-radiation multi-parametric MRI. / Shi, Liming; Zhang, Yang; Nie, Ke; Sun, Xiaonan; Niu, Tianye; Yue, Ning; Kwong, Tiffany; Chang, Peter; Chow, Daniel; Chen, Jeon Hor; Su, Min Ying.

In: Magnetic Resonance Imaging, Vol. 61, 01.09.2019, p. 33-40.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine learning for prediction of chemoradiation therapy response in rectal cancer using pre-treatment and mid-radiation multi-parametric MRI

AU - Shi, Liming

AU - Zhang, Yang

AU - Nie, Ke

AU - Sun, Xiaonan

AU - Niu, Tianye

AU - Yue, Ning

AU - Kwong, Tiffany

AU - Chang, Peter

AU - Chow, Daniel

AU - Chen, Jeon Hor

AU - Su, Min Ying

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Purpose: 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. Methods: 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. Results: 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. Conclusion: 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.

AB - Purpose: 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. Methods: 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. Results: 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. Conclusion: 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.

KW - Convolutional neural network

KW - Locally advanced rectal cancer

KW - Multi-parametric MRI

KW - Neoadjuvant chemoradiation therapy

KW - Radiomics

UR - http://www.scopus.com/inward/record.url?scp=85065922214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065922214&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.mri.2019.05.003

DO - https://doi.org/10.1016/j.mri.2019.05.003

M3 - Article

VL - 61

SP - 33

EP - 40

JO - Magnetic Resonance Imaging

JF - Magnetic Resonance Imaging

SN - 0730-725X

ER -