Cargando…

Deep Learning Model Based on Contrast-Enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma

SIMPLE SUMMARY: Patients with postoperative early recurrence of hepatocellular carcinoma within 2 years are at high risk for poor prognosis, and identifying high-risk patients with postoperative early recurrence is becoming increasingly important in the clinical practice for hepatocellular carcinoma...

Descripción completa

Detalles Bibliográficos
Autores principales: Kinoshita, Masahiko, Ueda, Daiju, Matsumoto, Toshimasa, Shinkawa, Hiroji, Yamamoto, Akira, Shiba, Masatsugu, Okada, Takuma, Tani, Naoki, Tanaka, Shogo, Kimura, Kenjiro, Ohira, Go, Nishio, Kohei, Tauchi, Jun, Kubo, Shoji, Ishizawa, Takeaki
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10092973/
https://www.ncbi.nlm.nih.gov/pubmed/37046801
http://dx.doi.org/10.3390/cancers15072140
_version_ 1785023473638178816
author Kinoshita, Masahiko
Ueda, Daiju
Matsumoto, Toshimasa
Shinkawa, Hiroji
Yamamoto, Akira
Shiba, Masatsugu
Okada, Takuma
Tani, Naoki
Tanaka, Shogo
Kimura, Kenjiro
Ohira, Go
Nishio, Kohei
Tauchi, Jun
Kubo, Shoji
Ishizawa, Takeaki
author_facet Kinoshita, Masahiko
Ueda, Daiju
Matsumoto, Toshimasa
Shinkawa, Hiroji
Yamamoto, Akira
Shiba, Masatsugu
Okada, Takuma
Tani, Naoki
Tanaka, Shogo
Kimura, Kenjiro
Ohira, Go
Nishio, Kohei
Tauchi, Jun
Kubo, Shoji
Ishizawa, Takeaki
author_sort Kinoshita, Masahiko
collection PubMed
description SIMPLE SUMMARY: Patients with postoperative early recurrence of hepatocellular carcinoma within 2 years are at high risk for poor prognosis, and identifying high-risk patients with postoperative early recurrence is becoming increasingly important in the clinical practice for hepatocellular carcinoma. However, preoperatively predicting the early recurrence remains difficult. Thus, we developed a deep learning model that accurately predicts early postoperative hepatocellular carcinoma recurrence; in addition, the contrast-enhanced computed tomography imaging analysis was the most important factor to predict early hepatocellular carcinoma recurrence in clinical variables of the current deep learning model. Guiding the treatment strategy for patients with hepatocellular carcinoma may be possible using contrast-enhanced computed tomography images by utilizing the deep learning method. ABSTRACT: 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. 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. Furthermore, 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. The DL predictive model for postoperative early recurrence was developed with the area under the curve values 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 the explanatory variables, the variable with the highest importance value was CECT imaging analysis. 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.
format Online
Article
Text
id pubmed-10092973
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100929732023-04-13 Deep Learning Model Based on Contrast-Enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma Kinoshita, Masahiko Ueda, Daiju Matsumoto, Toshimasa Shinkawa, Hiroji Yamamoto, Akira Shiba, Masatsugu Okada, Takuma Tani, Naoki Tanaka, Shogo Kimura, Kenjiro Ohira, Go Nishio, Kohei Tauchi, Jun Kubo, Shoji Ishizawa, Takeaki Cancers (Basel) Article SIMPLE SUMMARY: Patients with postoperative early recurrence of hepatocellular carcinoma within 2 years are at high risk for poor prognosis, and identifying high-risk patients with postoperative early recurrence is becoming increasingly important in the clinical practice for hepatocellular carcinoma. However, preoperatively predicting the early recurrence remains difficult. Thus, we developed a deep learning model that accurately predicts early postoperative hepatocellular carcinoma recurrence; in addition, the contrast-enhanced computed tomography imaging analysis was the most important factor to predict early hepatocellular carcinoma recurrence in clinical variables of the current deep learning model. Guiding the treatment strategy for patients with hepatocellular carcinoma may be possible using contrast-enhanced computed tomography images by utilizing the deep learning method. ABSTRACT: 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. 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. Furthermore, 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. The DL predictive model for postoperative early recurrence was developed with the area under the curve values 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 the explanatory variables, the variable with the highest importance value was CECT imaging analysis. 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. MDPI 2023-04-04 /pmc/articles/PMC10092973/ /pubmed/37046801 http://dx.doi.org/10.3390/cancers15072140 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kinoshita, Masahiko
Ueda, Daiju
Matsumoto, Toshimasa
Shinkawa, Hiroji
Yamamoto, Akira
Shiba, Masatsugu
Okada, Takuma
Tani, Naoki
Tanaka, Shogo
Kimura, Kenjiro
Ohira, Go
Nishio, Kohei
Tauchi, Jun
Kubo, Shoji
Ishizawa, Takeaki
Deep Learning Model Based on Contrast-Enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma
title Deep Learning Model Based on Contrast-Enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma
title_full Deep Learning Model Based on Contrast-Enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma
title_fullStr Deep Learning Model Based on Contrast-Enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma
title_full_unstemmed Deep Learning Model Based on Contrast-Enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma
title_short Deep Learning Model Based on Contrast-Enhanced Computed Tomography Imaging to Predict Postoperative Early Recurrence after the Curative Resection of a Solitary Hepatocellular Carcinoma
title_sort deep learning model based on contrast-enhanced computed tomography imaging to predict postoperative early recurrence after the curative resection of a solitary hepatocellular carcinoma
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10092973/
https://www.ncbi.nlm.nih.gov/pubmed/37046801
http://dx.doi.org/10.3390/cancers15072140
work_keys_str_mv AT kinoshitamasahiko deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT uedadaiju deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT matsumototoshimasa deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT shinkawahiroji deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT yamamotoakira deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT shibamasatsugu deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT okadatakuma deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT taninaoki deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT tanakashogo deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT kimurakenjiro deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT ohirago deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT nishiokohei deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT tauchijun deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT kuboshoji deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma
AT ishizawatakeaki deeplearningmodelbasedoncontrastenhancedcomputedtomographyimagingtopredictpostoperativeearlyrecurrenceafterthecurativeresectionofasolitaryhepatocellularcarcinoma