Whole slide imaging-based deep learning to predict the treatment response of patients with non-small cell lung cancer

Yuteng Pan; Wei Sheng; Liting Shi; Di Jing; Wei Jiang; Jyh-Cheng Chen; Haiyan Wang; Jianfeng Qiu

doi:10.21037/qims-22-1098

Whole slide imaging-based deep learning to predict the treatment response of patients with non-small cell lung cancer

Quant Imaging Med Surg. 2023 Jun 1;13(6):3547-3555. doi: 10.21037/qims-22-1098. Epub 2023 Apr 6.

Authors

Yuteng Pan^#^{1

2}, Wei Sheng^#³, Liting Shi², Di Jing⁴, Wei Jiang⁵, Jyh-Cheng Chen^{6

7}, Haiyan Wang^#⁸, Jianfeng Qiu^#²

Affiliations

¹ Medical Science and Technology Innovation Center, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, China.
² Medical Engineering and Technology Research Center, School of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Tai'an, China.
³ Department of Radiation Oncology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China.
⁴ Department of Oncology, National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha, China.
⁵ Department of Radiotherapy, Yantai Yuhuangding Hospital, Qingdao University School of Medicine, Yantai, China.
⁶ Department of Biomedical Imaging and Radiological Sciences National Yang-Ming Chiao-Tung University, Taipei.
⁷ Department of Biomedical Imaging and Radiological Science, China Medical University, Taichung.
⁸ Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China.

^# Contributed equally.

Abstract

Background: This study developed and validated a deep learning (DL) model based on whole slide imaging (WSI) for predicting the treatment response to chemotherapy and radiotherapy (CRT) among patients with non-small cell lung cancer (NSCLC).

Methods: We collected the WSI of 120 nonsurgical patients with NSCLC treated with CRT from three hospitals in China. Based on the processed WSI, two DL models were established: a tissue classification model which was used to select tumor-tiles, and another model which predicted the treatment response of the patients based on the tumor-tiles (predicting the treatment response of each tile). A voting method was employed, by which the label of tiles with the greatest quantity from 1 patient would be used as the label of the patient.

Results: The tissue classification model had a great performance (accuracy in the training set/internal validation set =0.966/0.956). Based on 181,875 tumor-tiles selected by the tissue classification model, the model for predicting the treatment response demonstrated strong predictive ability (accuracy of patient-level prediction in the internal validation set/external validation set 1/external validation set 2 =0.786/0.742/0.737).

Conclusions: A DL model was constructed based on WSI to predict the treatment response of patients with NSCLC. This model can help doctors to formulate personalized CRT plans and improve treatment outcomes.

Keywords: Non-small cell lung cancer (NSCLC); chemotherapy and radiotherapy (CRT); deep learning (DL); treatment response; whole slide imaging (WSI).