Deep Learning Model With Convolutional Neural Network for Detecting and Segmenting Hepatocellular Carcinoma in CT: A Preliminary Study.

Autor:	Duc VT; Department of Diagnostic Imaging, University Medical Center, Ho Chi Minh City, VNM., Chien PC; Department of Diagnostic Imaging, University Medical Center, Ho Chi Minh City, VNM., Huyen LDM; Department of Diagnostic Imaging, University Medical Center, Ho Chi Minh City, VNM., Chau TLM; Department of Diagnostic Imaging, University Medical Center, Ho Chi Minh City, VNM., Chanh NDT; Department of Artificial Intelligence - Computer Vision, Vinbrain Company, Hanoi, VNM., Soan DTM; Department of Model Development, Vinbrain Company, Hanoi, VNM., Huyen HC; Department of Model Development, Vinbrain Company, Hanoi, VNM., Thanh HM; Department of of Model Development, Vinbrain Company, Hanoi, VNM., Hy LNG; Department of Medical Imaging, University of Medicine and Pharmacy at Ho Chi Minh City, Ho Chi Minh City, VNM., Nam NH; Department of Medical Imaging, University of Medicine and Pharmacy at Ho Chi Minh City, Ho Chi Minh City, VNM., Uyen MTT; Department of Diagnostic Imaging, Tu Du Hospital, Ho Chi Minh City, VNM., Nhi LHH; Department of Radiology, Vinmec Healthcare System, Ho Chi Minh City, VNM., Minh LHN; Faculty of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City, Ho Chi Minh City, VNM.
Jazyk:	angličtina
Zdroj:	Cureus [Cureus] 2022 Jan 17; Vol. 14 (1), pp. e21347. Date of Electronic Publication: 2022 Jan 17 (Print Publication: 2022).
DOI:	10.7759/cureus.21347
Abstrakt:	Introduction Hepatocellular carcinoma (HCC) is one of the most common malignancies in the world. Early detection and accurate diagnosis of HCC play an important role in patient management. This study aimed to develop a convolutional neural network-based model to identify and segment HCC lesions utilizing dynamic contrast agent-enhanced computed tomography (CT). Methods This retrospective study used CT image sets of histopathology-confirmed hepatocellular carcinoma over three phases (arterial, venous, and delayed). The proposed convolutional neural network (CNN) segmentation method was based on the U-Net architecture and trained using the domain adaptation technique. The proposed method was evaluated using 115 liver masses of 110 patients (87 men and 23 women; mean age, 56.9 years ± 11.9 (SD); mean mass size, 6.0 cm ± 3.6). The sensitivity for identifying HCC of the model and Dice score for segmentation of liver masses between radiologists and the CNN model were calculated for the test set. Results The sensitivity for HCC identification of the model was 100%. The median Dice score for HCC segmenting between radiologists and the CNN model was 0.81 for the test set. Conclusion Deep learning with CNN had high performance in the identification and segmentation of HCC on dynamic CT. Competing Interests: The authors have declared that no competing interests exist. (Copyright © 2022, Duc et al.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu