Detailed Abstract
[Poster Presentation 13 - Liver (Liver Disease/Surgery)]
[LV PP 13-S2] Deep-learning Model Based on Contrast-enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma
Masahiko KINOSHITA 1, Daiju UEDA 2, Toshimasa MATSUMOTO 2, Hiroji SHINKAWA 1, Akira YAMAMOTO 3, Masatsugu SHIBA 4, Takuma OKADA 1, Naoki TANI 1, Kenjiro KIMURA 1, Go OHIRA 1, Kohei NISHIO 1, Takeaki ISHIZAWA 1
1 Department of Hepato-Biliary-Pancreatic Surgery, Osaka Metropolitan University Graduate School of Medicine, JAPAN, 2 Smart Life Science Lab, Center for Health Science Innovation, Osaka Metropolitan University , JAPAN, 3 Department of Diagnostic And Interventional Radiology, Osaka Metropolitan University Graduate School of Medicine, JAPAN, 4 Department of Biofunctional Analysis, Osaka Metropolitan University Graduate School of Medicine, JAPAN
Background : We aimed to develop the deep-learning (DL) predictive model for postoperative early recurrence (within 2 years) of hepatocellular carcinoma (HCC) based on contrast-enhanced computed tomography (CECT) imaging.
Methods : This study included 543 patients who underwent initial hepatectomy for HCC and were randomly classified into training, validation, and test datasets at a ratio of 8:1:1. Several clinical variables and arterial CECT images were used to create predictive models for early recurrence. Artificial intelligence models were implemented using convolutional neural networks and multilayer perceptron as a classifier. Further, the Youden index was used to discriminate between high- and low-risk groups. The importance values of each explanatory variable for early recurrence were calculated using permutation importance.
Results : The DL predictive model for postoperative early recurrence was developed with the area under the curve value of 0.71 (test datasets) and 0.73 (validation datasets). Postoperative early recurrence incidences in the high- and low-risk groups were 73% and 30%, respectively (P = 0.0057). Permutation importance demonstrated that among explanatory variables, the variable with the highest importance value was CECT imaging analysis.
Conclusions : We developed a DL model to predict postoperative early HCC recurrence. DL-based analysis is effective for determining the treatment strategies in patients with HCC.
Methods : This study included 543 patients who underwent initial hepatectomy for HCC and were randomly classified into training, validation, and test datasets at a ratio of 8:1:1. Several clinical variables and arterial CECT images were used to create predictive models for early recurrence. Artificial intelligence models were implemented using convolutional neural networks and multilayer perceptron as a classifier. Further, the Youden index was used to discriminate between high- and low-risk groups. The importance values of each explanatory variable for early recurrence were calculated using permutation importance.
Results : The DL predictive model for postoperative early recurrence was developed with the area under the curve value of 0.71 (test datasets) and 0.73 (validation datasets). Postoperative early recurrence incidences in the high- and low-risk groups were 73% and 30%, respectively (P = 0.0057). Permutation importance demonstrated that among explanatory variables, the variable with the highest importance value was CECT imaging analysis.
Conclusions : We developed a DL model to predict postoperative early HCC recurrence. DL-based analysis is effective for determining the treatment strategies in patients with HCC.
SESSION
Poster Presentation 13
Zone G 3/22/2024 2:50 PM - 3:40 PM