Predicting response to neoadjuvant chemotherapy for colorectal liver metastasis using deep learning on prechemotherapy cross-sectional imaging.

Autor: Davis JMK; Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA., Niazi MKK; Center for Artificial Intelligence Research and the Clinical Image Analysis Lab, Wake Forest University School of Medicine, Winston-Salem, North Carolina, USA., Ricker AB; Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA., Tavolara TE; Center for Artificial Intelligence Research and the Clinical Image Analysis Lab, Wake Forest University School of Medicine, Winston-Salem, North Carolina, USA., Robinson JN; Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA., Annanurov B; Center for Artificial Intelligence Research and the Clinical Image Analysis Lab, Wake Forest University School of Medicine, Winston-Salem, North Carolina, USA., Smith K; Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA., Mantha R; Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA., Hwang J; Department of Medical Oncology, Atrium Health Carolinas Medical Center, Levine Cancer Institute, Charlotte, North Carolina, USA., Shrestha R; Department of Radiology, Atrium Health, Charlotte, North Carolina, USA., Iannitti DA; Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA., Martinie JB; Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA., Baker EH; Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA., Gurcan MN; Center for Artificial Intelligence Research and the Clinical Image Analysis Lab, Wake Forest University School of Medicine, Winston-Salem, North Carolina, USA., Vrochides D; Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA.
Jazyk: angličtina
Zdroj: Journal of surgical oncology [J Surg Oncol] 2024 Jul; Vol. 130 (1), pp. 93-101. Date of Electronic Publication: 2024 May 07.
DOI: 10.1002/jso.27673
Abstrakt: Background and Objectives: Deep learning models (DLMs) are applied across domains of health sciences to generate meaningful predictions. DLMs make use of neural networks to generate predictions from discrete data inputs. This study employs DLM on prechemotherapy cross-sectional imaging to predict patients' response to neoadjuvant chemotherapy.
Methods: Adult patients with colorectal liver metastasis who underwent surgery after neoadjuvant chemotherapy were included. A DLM was trained on computed tomography images using attention-based multiple-instance learning. A logistic regression model incorporating clinical parameters of the Fong clinical risk score was used for comparison. Both model performances were benchmarked against the Response Evaluation Criteria in Solid Tumors criteria. A receiver operating curve was created and resulting area under the curve (AUC) was determined.
Results: Ninety-five patients were included, with 33,619 images available for study inclusion. Ninety-five percent of patients underwent 5-fluorouracil-based chemotherapy with oxaliplatin and/or irinotecan. Sixty percent of the patients were categorized as chemotherapy responders (30% reduction in tumor diameter). The DLM had an AUC of 0.77. The AUC for the clinical model was 0.41.
Conclusions: Image-based DLM for prediction of response to neoadjuvant chemotherapy in patients with colorectal cancer liver metastases was superior to a clinical-based model. These results demonstrate potential to identify nonresponders to chemotherapy and guide select patients toward earlier curative resection.
(© 2024 The Authors. Journal of Surgical Oncology published by Wiley Periodicals LLC.)
Databáze: MEDLINE
Externí odkaz: