Predicting response to neoadjuvant chemotherapy for colorectal liver metastasis using deep learning on prechemotherapy cross‐sectional imaging
Journal of Surgical Oncology · 2024
DOI: 10.1002/jso.27673 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Surgical Oncology, 2024. Verfasst von Joshua M K Davis und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA. Hauptthemen laut MEDLINE: Colorectal Neoplasms, Liver Neoplasms, Deep Learning, Neoadjuvant Therapy. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Atrium Health Department of Surgery Grant.
Themen: Onkologische Pflege
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Surgery, Atrium Health Carolinas Medical Center, Charlotte, North Carolina, USA.
- Center for Artificial Intelligence Research and the Clinical Image Analysis Lab, Wake Forest University School of Medicine, Winston-Salem, North Carolina, USA.
- Department of Medical Oncology, Atrium Health Carolinas Medical Center, Levine Cancer Institute, Charlotte, North Carolina, USA.
- Department of Radiology, Atrium Health, Charlotte, North Carolina, USA.
Förderung
- Atrium Health Department of Surgery Grant
Zitieren
APA
Davis, J. M. K., Niazi, M. K. K., Ricker, A. B., Tavolara, T. E., Robinson, J. N., Annanurov, B., Smith, K., Mantha, R., Hwang, J., Shrestha, R., Iannitti, D. A., Martinie, J. B., Baker, E. H., Gurcan, M. N., & Vrochides, D. (2024). Predicting response to neoadjuvant chemotherapy for colorectal liver metastasis using deep learning on prechemotherapy cross‐sectional imaging. Journal of Surgical Oncology. https://doi.org/10.1002/jso.27673
Vancouver
Davis JMK, Niazi MKK, Ricker AB, Tavolara TE, Robinson JN, Annanurov B, et al. Predicting response to neoadjuvant chemotherapy for colorectal liver metastasis using deep learning on prechemotherapy cross‐sectional imaging. Journal of Surgical Oncology. 2024. doi:10.1002/jso.27673
BibTeX
@article{Davis2024,
author = {Davis, Joshua M K and Niazi, Muhammad Khalid Khan and Ricker, Ansley B and Tavolara, Thomas E and Robinson, Jordan N and Annanurov, Bayram and Smith, Kaylee and Mantha, Rohit and Hwang, Jimmy and Shrestha, Ruchi and Iannitti, David A and Martinie, John B and Baker, Erin H and Gurcan, Metin N and Vrochides, Dionisios},
title = {Predicting response to neoadjuvant chemotherapy for colorectal liver metastasis using deep learning on prechemotherapy cross‐sectional imaging},
journal = {Journal of Surgical Oncology},
year = {2024},
doi = {10.1002/jso.27673}
}
EUVIMED