Dual Segmentation Models for Poorly and Well-differentiated Hepatocellular Carcinoma Using Two-step Transfer Deep Learning on Dynamic Contrast-enhanced CT Images

Overview

Journal Phys Eng Sci Med

Publisher Springer

Specialty Biomedical Engineering

Date 2022 Dec 5

PMID 36469246

Authors

Noriyuki Nagami

Hidetaka Arimura

Junichi Nojiri

Cui Yunhao

Kenta Ninomiya

Manabu Ogata

Mitsutoshi Oishi

Keiichi Ohira

Shigetoshi Kitamura

Hiroyuki Irie

Affiliations

Soon will be listed here.

Abstract

The aim of this study was to develop dual segmentation models for poorly and well-differentiated hepatocellular carcinoma (HCC), using two-step transfer learning (TSTL) based on dynamic contrast-enhanced (DCE) computed tomography (CT) images. From 2013 to 2019, DCE-CT images of 128 patients with 80 poorly differentiated and 48 well-differentiated HCCs were selected at our hospital. In the first transfer learning (TL) step, a pre-trained segmentation model with 192 CT images of lung cancer patients was retrained as a poorly differentiated HCC model. In the second TL step, a well-differentiated HCC model was built from a poorly differentiated HCC model. The average three-dimensional Dice's similarity coefficient (3D-DSC) and 95th-percentile of the Hausdorff distance (95% HD) were mainly employed to evaluate the segmentation accuracy, based on a nested fourfold cross-validation test. The DSC denotes the degree of regional similarity between the HCC reference regions and the regions estimated using the proposed models. The 95% HD is defined as the 95th-percentile of the maximum measures of how far two subsets of a metric space are from each other. The average 3D-DSC and 95% HD were 0.849 ± 0.078 and 1.98 ± 0.71 mm, respectively, for poorly differentiated HCC regions, and 0.811 ± 0.089 and 2.01 ± 0.84 mm, respectively, for well-differentiated HCC regions. The average 3D-DSC for both regions was 1.2 times superior to that calculated without the TSTL. The proposed model using TSTL from the lung cancer dataset showed the potential to segment poorly and well-differentiated HCC regions on DCE-CT images.

References

Sung H, Ferlay J, Siegel R, Laversanne M, Soerjomataram I, Jemal A . Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021; 71(3):209-249. DOI: 10.3322/caac.21660. View

Villanueva A . Hepatocellular Carcinoma. N Engl J Med. 2019; 380(15):1450-1462. DOI: 10.1056/NEJMra1713263. View

Kim E, Viatour P . Hepatocellular carcinoma: old friends and new tricks. Exp Mol Med. 2020; 52(12):1898-1907. PMC: 8080814. DOI: 10.1038/s12276-020-00527-1. View

Tarhan N, Hatipoglu T, Ercan E, Bener M, Keles G, Basaran C . Correlation of dynamic multidetector CT findings with pathological grades of hepatocellular carcinoma. Diagn Interv Radiol. 2011; 17(4):328-33. DOI: 10.4261/1305-3825.DIR.2682-09.3. View

Chen W, Zhang T, Xu L, Zhao L, Liu H, Gu L . Radiomics Analysis of Contrast-Enhanced CT for Hepatocellular Carcinoma Grading. Front Oncol. 2021; 11:660509. PMC: 8212783. DOI: 10.3389/fonc.2021.660509. View

Perez-Saborido B, de los Galanes S, Meneu-Diaz J, Jimenez Romero C, Moreno Elola-Olaso A, Fundora Suarez Y . Tumor recurrence after liver transplantation for hepatocellular carcinoma: recurrence pathway and prognostic factors. Transplant Proc. 2007; 39(7):2304-7. DOI: 10.1016/j.transproceed.2007.06.059. View

Shinkawa H, Tanaka S, Kabata D, Takemura S, Amano R, Kimura K . The Prognostic Impact of Tumor Differentiation on Recurrence and Survival after Resection of Hepatocellular Carcinoma Is Dependent on Tumor Size. Liver Cancer. 2021; 10(5):461-472. PMC: 8527909. DOI: 10.1159/000517992. View

Kim Y, Kim J, Yoon W, Kang M, Lee I, Kim T . Interobserver variability in gross tumor volume delineation for hepatocellular carcinoma : Results of Korean Radiation Oncology Group 1207 study. Strahlenther Onkol. 2016; 192(10):714-21. DOI: 10.1007/s00066-016-1028-2. 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

10.

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

11.

Qayyum A, Lalande A, Meriaudeau F . Automatic segmentation of tumors and affected organs in the abdomen using a 3D hybrid model for computed tomography imaging. Comput Biol Med. 2020; 127:104097. DOI: 10.1016/j.compbiomed.2020.104097. View

12.

Alirr O . Deep learning and level set approach for liver and tumor segmentation from CT scans. J Appl Clin Med Phys. 2020; 21(10):200-209. PMC: 7592966. DOI: 10.1002/acm2.13003. View

13.

Cui Y, Arimura H, Nakano R, Yoshitake T, Shioyama Y, Yabuuchi H . Automated approach for segmenting gross tumor volumes for lung cancer stereotactic body radiation therapy using CT-based dense V-networks. J Radiat Res. 2021; 62(2):346-355. PMC: 7948852. DOI: 10.1093/jrr/rraa132. View

14.

Chen X, Sun S, Bai N, Han K, Liu Q, Yao S . A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy. Radiother Oncol. 2021; 160:175-184. DOI: 10.1016/j.radonc.2021.04.019. View

15.

Taha A, Hanbury A . Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging. 2015; 15:29. PMC: 4533825. DOI: 10.1186/s12880-015-0068-x. View

16.

Landis J, Koch G . The measurement of observer agreement for categorical data. Biometrics. 1977; 33(1):159-74. View

17.

Yamada A, Oyama K, Fujita S, Yoshizawa E, Ichinohe F, Komatsu D . Dynamic contrast-enhanced computed tomography diagnosis of primary liver cancers using transfer learning of pretrained convolutional neural networks: Is registration of multiphasic images necessary?. Int J Comput Assist Radiol Surg. 2019; 14(8):1295-1301. DOI: 10.1007/s11548-019-01987-1. View

18.

Chlap P, Min H, Vandenberg N, Dowling J, Holloway L, Haworth A . A review of medical image data augmentation techniques for deep learning applications. J Med Imaging Radiat Oncol. 2021; 65(5):545-563. DOI: 10.1111/1754-9485.13261. View

19.

Gibson E, Li W, Sudre C, Fidon L, Shakir D, Wang G . NiftyNet: a deep-learning platform for medical imaging. Comput Methods Programs Biomed. 2018; 158:113-122. PMC: 5869052. DOI: 10.1016/j.cmpb.2018.01.025. View

20.

Liu Z, Liu F, Chen W, Liu X, Hou X, Shen J . Automatic Segmentation of Clinical Target Volumes for Post-Modified Radical Mastectomy Radiotherapy Using Convolutional Neural Networks. Front Oncol. 2021; 10:581347. PMC: 7921705. DOI: 10.3389/fonc.2020.581347. View