» Articles » PMID: 38532511

A Hierarchical Fusion Strategy of Deep Learning Networks for Detection and Segmentation of Hepatocellular Carcinoma from Computed Tomography Images

Overview
Journal Cancer Imaging
Publisher Springer Nature
Specialties Oncology
Radiology
Date 2024 Mar 27
PMID 38532511
Authors
Affiliations
Soon will be listed here.
Abstract

Background: Automatic segmentation of hepatocellular carcinoma (HCC) on computed tomography (CT) scans is in urgent need to assist diagnosis and radiomics analysis. The aim of this study is to develop a deep learning based network to detect HCC from dynamic CT images.

Methods: Dynamic CT images of 595 patients with HCC were used. Tumors in dynamic CT images were labeled by radiologists. Patients were randomly divided into training, validation and test sets in a ratio of 5:2:3, respectively. We developed a hierarchical fusion strategy of deep learning networks (HFS-Net). Global dice, sensitivity, precision and F1-score were used to measure performance of the HFS-Net model.

Results: The 2D DenseU-Net using dynamic CT images was more effective for segmenting small tumors, whereas the 2D U-Net using portal venous phase images was more effective for segmenting large tumors. The HFS-Net model performed better, compared with the single-strategy deep learning models in segmenting small and large tumors. In the test set, the HFS-Net model achieved good performance in identifying HCC on dynamic CT images with global dice of 82.8%. The overall sensitivity, precision and F1-score were 84.3%, 75.5% and 79.6% per slice, respectively, and 92.2%, 93.2% and 92.7% per patient, respectively. The sensitivity in tumors < 2 cm, 2-3, 3-5 cm and > 5 cm were 72.7%, 92.9%, 94.2% and 100% per patient, respectively.

Conclusions: The HFS-Net model achieved good performance in the detection and segmentation of HCC from dynamic CT images, which may support radiologic diagnosis and facilitate automatic radiomics analysis.

Citing Articles

Diagnostic Performance of Deep Learning Applications in Hepatocellular Carcinoma Detection Using Computed Tomography Imaging.

Sahin E, Tatar O, Ulutas M, Guler S, Simsek T, Turgay N Turk J Gastroenterol. 2025; 36(2):124-130.

PMID: 39760649 PMC: 11851832. DOI: 10.5152/tjg.2024.24538.


Vascular liver segmentation: a narrative review on methods and new insights brought by artificial intelligence.

Chierici A, Lareyre F, Salucki B, Iannelli A, Delingette H, Raffort J J Int Med Res. 2024; 52(9):3000605241263170.

PMID: 39291427 PMC: 11418557. DOI: 10.1177/03000605241263170.


Artificial intelligence techniques in liver cancer.

Wang L, Fatemi M, Alizad A Front Oncol. 2024; 14:1415859.

PMID: 39290245 PMC: 11405163. DOI: 10.3389/fonc.2024.1415859.


The evolution and revolution of artificial intelligence in hepatology: From current applications to future paradigms.

Simsek C Hepatol Forum. 2024; 5(3):97-99.

PMID: 39006141 PMC: 11237248. DOI: 10.14744/hf.2024.2024.ed0001.

References
1.
Chlebus G, Schenk A, Moltz J, van Ginneken B, Hahn H, Meine H . Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing. Sci Rep. 2018; 8(1):15497. PMC: 6195599. DOI: 10.1038/s41598-018-33860-7. View

2.
Roberts L, Sirlin C, Zaiem F, Almasri J, Prokop L, Heimbach J . Imaging for the diagnosis of hepatocellular carcinoma: A systematic review and meta-analysis. Hepatology. 2017; 67(1):401-421. DOI: 10.1002/hep.29487. View

3.
Chen L, Song H, Wang C, Cui Y, Yang J, Hu X . Liver tumor segmentation in CT volumes using an adversarial densely connected network. BMC Bioinformatics. 2019; 20(Suppl 16):587. PMC: 6886252. DOI: 10.1186/s12859-019-3069-x. View

4.
Anter A, Hassenian A . CT liver tumor segmentation hybrid approach using neutrosophic sets, fast fuzzy c-means and adaptive watershed algorithm. Artif Intell Med. 2018; 97:105-117. DOI: 10.1016/j.artmed.2018.11.007. View

5.
Li X, Chen H, Qi X, Dou Q, Fu C, Heng P . H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes. IEEE Trans Med Imaging. 2018; 37(12):2663-2674. DOI: 10.1109/TMI.2018.2845918. View