Your browser doesn't support javascript.
loading
Prediction of Neoadjuvant Chemoradiotherapy Response in Rectal Cancer Patients Using Harmonized Radiomics of Multcenter 18F-FDG-PET Image.
Ju, Hye-Min; Yang, Jingyu; Park, Jung-Mi; Choi, Joon-Ho; Song, Hyejin; Kim, Byung-Il; Shin, Ui-Sup; Moon, Sun Mi; Cho, Sangsik; Woo, Sang-Keun.
  • Ju HM; Radiological and Medico-Oncological Sciences, University of Science and Technology, Daejeon 34113, Republic of Korea.
  • Yang J; Division of Applied RI, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea.
  • Park JM; Division of Applied RI, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea.
  • Choi JH; Department of Nuclear Medicine, Soonchunhyang University Bucheon Hospital, Bucheon 14584, Republic of Korea.
  • Song H; Department of Nuclear Medicine, Soonchunhyang University Bucheon Hospital, Bucheon 14584, Republic of Korea.
  • Kim BI; Division of Applied RI, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea.
  • Shin US; Department of Nuclear Medicine, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea.
  • Moon SM; Department of Surgery, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea.
  • Cho S; Department of Surgery, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea.
  • Woo SK; Department of Surgery, Korea Institute of Radiological and Medical Sciences, Seoul 07812, Republic of Korea.
Cancers (Basel) ; 15(23)2023 Nov 30.
Article en En | MEDLINE | ID: mdl-38067368
ABSTRACT
We developed machine and deep learning models to predict chemoradiotherapy in rectal cancer using 18F-FDG PET images and harmonized image features extracted from 18F-FDG PET/CT images. Patients diagnosed with pathologic T-stage III rectal cancer with a tumor size > 2 cm were treated with neoadjuvant chemoradiotherapy. Patients with rectal cancer were divided into an internal dataset (n = 116) and an external dataset obtained from a separate institution (n = 40), which were used in the model. AUC was calculated to select image features associated with radiochemotherapy response. In the external test, the machine-learning signature extracted from 18F-FDG PET image features achieved the highest accuracy and AUC value of 0.875 and 0.896. The harmonized first-order radiomics model had a higher efficiency with accuracy and an AUC of 0.771 than the second-order model in the external test. The deep learning model using the balanced dataset showed an accuracy of 0.867 in the internal test but an accuracy of 0.557 in the external test. Deep-learning models using 18F-FDG PET images must be harmonized to demonstrate reproducibility with external data. Harmonized 18F-FDG PET image features as an element of machine learning could help predict chemoradiotherapy responses in external tests with reproducibility.
Palabras clave