Prediction of Neoadjuvant Chemoradiotherapy Response in Rectal Cancer with Metric Learning Using Pretreatment 18F-Fluorodeoxyglucose Positron Emission Tomography

Kuo-Chen Wu; Shang-Wen Chen; Te-Chun Hsieh; Kuo-Yang Yen; Kin-Man Law; Yu-Chieh Kuo; Ruey-Feng Chang; Chia-Hung Kao

doi:10.3390/cancers13246350

Prediction of Neoadjuvant Chemoradiotherapy Response in Rectal Cancer with Metric Learning Using Pretreatment 18F-Fluorodeoxyglucose Positron Emission Tomography

Cancers (Basel). 2021 Dec 17;13(24):6350. doi: 10.3390/cancers13246350.

Authors

Kuo-Chen Wu^{1

2}, Shang-Wen Chen^{2

3

4

5}, Te-Chun Hsieh^{6

7}, Kuo-Yang Yen^{6

7}, Kin-Man Law^{2

8}, Yu-Chieh Kuo², Ruey-Feng Chang^{1

2

9}, Chia-Hung Kao^{2

6

10

11}

Affiliations

¹ Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei 106, Taiwan.
² Center of Augmented Intelligence in Healthcare, China Medical University Hospital, Taichung 404, Taiwan.
³ School of Medicine, College of Medicine, China Medical University, Taichung 404, Taiwan.
⁴ School of Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan.
⁵ Department of Radiation Oncology, China Medical University Hospital, Taichung 404, Taiwan.
⁶ Department of Nuclear Medicine and PET Center, China Medical University Hospital, Taichung 404, Taiwan.
⁷ Department of Biomedical Imaging and Radiological Science, China Medical University, Taichung 404, Taiwan.
⁸ Department of Computer Science and Engineering, National Chung Hsing University, Taichung 402, Taiwan.
⁹ Department of Computer Science and Information Engineering, National Taiwan University, Taipei 106, Taiwan.
¹⁰ Graduate Institute of Biomedical Sciences, School of Medicine, College of Medicine, China Medical University, Taichung 404, Taiwan.
¹¹ Department of Bioinformatics and Medical Engineering, Asia University, Taichung 413, Taiwan.

Abstract

Objectives: Neoadjuvant chemoradiotherapy (NCRT) followed by surgery is the mainstay of treatment for patients with locally advanced rectal cancer. Based on baseline 18F-fluorodeoxyglucose ([18F]-FDG)-positron emission tomography (PET)/computed tomography (CT), a new artificial intelligence model using metric learning (ML) was introduced to predict responses to NCRT.

Patients and methods: This study used the data of 236 patients with newly diagnosed rectal cancer; the data of 202 and 34 patients were for training and validation, respectively. All patients received pretreatment [18F]FDG-PET/CT, NCRT, and surgery. The treatment response was scored by Dworak tumor regression grade (TRG); TRG3 and TRG4 indicated favorable responses. The model employed ML combined with the Uniform Manifold Approximation and Projection for dimensionality reduction. A receiver operating characteristic (ROC) curve analysis was performed to assess the model's predictive performance.

Results: In the training cohort, 115 patients (57%) achieved TRG3 or TRG4 responses. The area under the ROC curve was 0.96 for the prediction of a favorable response. The sensitivity, specificity, and accuracy were 98.3%, 96.5%, and 97.5%, respectively. The sensitivity, specificity, and accuracy for the validation cohort were 95.0%, 100%, and 98.8%, respectively.

Conclusions: The new ML model presented herein was used to determined that baseline 18F[FDG]-PET/CT images could predict a favorable response to NCRT in patients with rectal cancer. External validation is required to verify the model's predictive value.

Keywords: 18F-fluorodeoxyglucose positron emission tomography/computed tomography; metric learning; neoadjuvant chemoradiotherapy; rectal cancer.