HCA-DAN: Hierarchical Class-aware Domain Adaptive Network for Gastric Tumor Segmentation in 3D CT Images

Overview

Journal Cancer Imaging

Publisher Springer Nature

Specialties Oncology
Radiology

Date 2024 May 22

PMID 38773670

Authors

Ning Yuan

Yongtao Zhang

Kuan Lv

Yiyao Liu

Aocai Yang

Pianpian Hu

Hongwei Yu

Xiaowei Han

Xing Guo

Junfeng Li

Tianfu Wang

Baiying Lei

Guolin Ma

Affiliations

Soon will be listed here.

Abstract

Background: Accurate segmentation of gastric tumors from CT scans provides useful image information for guiding the diagnosis and treatment of gastric cancer. However, automated gastric tumor segmentation from 3D CT images faces several challenges. The large variation of anisotropic spatial resolution limits the ability of 3D convolutional neural networks (CNNs) to learn features from different views. The background texture of gastric tumor is complex, and its size, shape and intensity distribution are highly variable, which makes it more difficult for deep learning methods to capture the boundary. In particular, while multi-center datasets increase sample size and representation ability, they suffer from inter-center heterogeneity.

Methods: In this study, we propose a new cross-center 3D tumor segmentation method named Hierarchical Class-Aware Domain Adaptive Network (HCA-DAN), which includes a new 3D neural network that efficiently bridges an Anisotropic neural network and a Transformer (AsTr) for extracting multi-scale context features from the CT images with anisotropic resolution, and a hierarchical class-aware domain alignment (HCADA) module for adaptively aligning multi-scale context features across two domains by integrating a class attention map with class-specific information. We evaluate the proposed method on an in-house CT image dataset collected from four medical centers and validate its segmentation performance in both in-center and cross-center test scenarios.

Results: Our baseline segmentation network (i.e., AsTr) achieves best results compared to other 3D segmentation models, with a mean dice similarity coefficient (DSC) of 59.26%, 55.97%, 48.83% and 67.28% in four in-center test tasks, and with a DSC of 56.42%, 55.94%, 46.54% and 60.62% in four cross-center test tasks. In addition, the proposed cross-center segmentation network (i.e., HCA-DAN) obtains excellent results compared to other unsupervised domain adaptation methods, with a DSC of 58.36%, 56.72%, 49.25%, and 62.20% in four cross-center test tasks.

Conclusions: Comprehensive experimental results demonstrate that the proposed method outperforms compared methods on this multi-center database and is promising for routine clinical workflows.

Citing Articles

Next-Gen Medical Imaging: U-Net Evolution and the Rise of Transformers.

Zhang C, Deng X, Ling S Sensors (Basel). 2024; 24(14).

PMID: 39066065 PMC: 11280776. DOI: 10.3390/s24144668.

References

Dong D, Tang L, Li Z, Fang M, Gao J, Shan X . Development and validation of an individualized nomogram to identify occult peritoneal metastasis in patients with advanced gastric cancer. Ann Oncol. 2019; 30(3):431-438. PMC: 6442651. DOI: 10.1093/annonc/mdz001. View

Yasaka K, Akai H, Abe O, Kiryu S . Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study. Radiology. 2017; 286(3):887-896. DOI: 10.1148/radiol.2017170706. View

Ajani J, DAmico T, Almhanna K, Bentrem D, Chao J, Das P . Gastric Cancer, Version 3.2016, NCCN Clinical Practice Guidelines in Oncology. J Natl Compr Canc Netw. 2016; 14(10):1286-1312. DOI: 10.6004/jnccn.2016.0137. View

Heller N, Isensee F, Maier-Hein K, Hou X, Xie C, Li F . The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge. Med Image Anal. 2020; 67:101821. PMC: 7734203. DOI: 10.1016/j.media.2020.101821. View

Wang Y, Liu W, Yu Y, Liu J, Jiang L, Xue H . Prediction of the Depth of Tumor Invasion in Gastric Cancer: Potential Role of CT Radiomics. Acad Radiol. 2019; 27(8):1077-1084. DOI: 10.1016/j.acra.2019.10.020. View

Meng L, Dong D, Chen X, Fang M, Wang R, Li J . 2D and 3D CT Radiomic Features Performance Comparison in Characterization of Gastric Cancer: A Multi-Center Study. IEEE J Biomed Health Inform. 2020; 25(3):755-763. DOI: 10.1109/JBHI.2020.3002805. View

Li H, Liu B, Zhang Y, Fu C, Han X, Du L . 3D IFPN: Improved Feature Pyramid Network for Automatic Segmentation of Gastric Tumor. Front Oncol. 2021; 11:618496. PMC: 8173118. DOI: 10.3389/fonc.2021.618496. View

Jiang Y, Wang W, Chen C, Zhang X, Zha X, Lv W . Radiomics Signature on Computed Tomography Imaging: Association With Lymph Node Metastasis in Patients With Gastric Cancer. Front Oncol. 2019; 9:340. PMC: 6498894. DOI: 10.3389/fonc.2019.00340. View

Isensee F, Jaeger P, Kohl S, Petersen J, Maier-Hein K . nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2020; 18(2):203-211. DOI: 10.1038/s41592-020-01008-z. View

10.

Gibson E, Giganti F, Hu Y, Bonmati E, Bandula S, Gurusamy K . Automatic Multi-Organ Segmentation on Abdominal CT With Dense V-Networks. IEEE Trans Med Imaging. 2018; 37(8):1822-1834. PMC: 6076994. DOI: 10.1109/TMI.2018.2806309. View

11.

Coburn N, Cosby R, Klein L, Knight G, Malthaner R, Mamazza J . Staging and surgical approaches in gastric cancer: A systematic review. Cancer Treat Rev. 2017; 63:104-115. DOI: 10.1016/j.ctrv.2017.12.006. View

12.

Jiang Y, Chen C, Xie J, Wang W, Zha X, Lv W . Radiomics signature of computed tomography imaging for prediction of survival and chemotherapeutic benefits in gastric cancer. EBioMedicine. 2018; 36:171-182. PMC: 6197796. DOI: 10.1016/j.ebiom.2018.09.007. View

13.

Bray F, Ferlay J, Soerjomataram I, Siegel R, Torre L, Jemal A . Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018; 68(6):394-424. DOI: 10.3322/caac.21492. View

14.

Feng Q, Liu C, Qi L, Sun S, Song Y, Yang G . An Intelligent Clinical Decision Support System for Preoperative Prediction of Lymph Node Metastasis in Gastric Cancer. J Am Coll Radiol. 2019; 16(7):952-960. DOI: 10.1016/j.jacr.2018.12.017. View

15.

Wang Y, Liu W, Yu Y, Liu J, Xue H, Qi Y . CT radiomics nomogram for the preoperative prediction of lymph node metastasis in gastric cancer. Eur Radiol. 2019; 30(2):976-986. DOI: 10.1007/s00330-019-06398-z. View

16.

Guan H, Liu M . Domain Adaptation for Medical Image Analysis: A Survey. IEEE Trans Biomed Eng. 2021; 69(3):1173-1185. PMC: 9011180. DOI: 10.1109/TBME.2021.3117407. View

17.

Si K, Xue Y, Yu X, Zhu X, Li Q, Gong W . Fully end-to-end deep-learning-based diagnosis of pancreatic tumors. Theranostics. 2021; 11(4):1982-1990. PMC: 7778580. DOI: 10.7150/thno.52508. View

18.

Lutnick B, Ginley B, Govind D, McGarry S, LaViolette P, Yacoub R . An integrated iterative annotation technique for easing neural network training in medical image analysis. Nat Mach Intell. 2019; 1(2):112-119. PMC: 6557463. DOI: 10.1038/s42256-019-0018-3. View

19.

Litjens G, Kooi T, Bejnordi B, Setio A, Ciompi F, Ghafoorian M . A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42:60-88. DOI: 10.1016/j.media.2017.07.005. View

20.

Zhang Y, Li H, Du J, Qin J, Wang T, Chen Y . 3D Multi-Attention Guided Multi-Task Learning Network for Automatic Gastric Tumor Segmentation and Lymph Node Classification. IEEE Trans Med Imaging. 2021; 40(6):1618-1631. DOI: 10.1109/TMI.2021.3062902. View