Precise ablation zone segmentation on CT images after liver cancer ablation using semi‐automatic CNN‐based segmentation

Quoc Anh Le1, Xuan Loc Pham2, Theo van Walsum3, Hang Viet Dao4,5, Tuan Linh Le6, Daniel Franklin7, Adriaan Moelker3, Ha Vu Le1,2, Nguyen Linh-Trung1, Luu Manh Ha1,3,2
1AVITECH, VNU University of Engineering and Technology, Hanoi, Vietnam
2FET, VNU University of Engineering and Technology, Hanoi, Vietnam
3Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, The Netherlands
4Internal Medicine Faculty, Hanoi Medical University, Hanoi, Vietnam
5The Institute of Gastroenterology and Hepatology Hanoi Vietnam
6Diagnostic Imaging and Interventional Radiology Center, Hanoi Medical University Hospital, Hanoi, Vietnam
7School of Electrical and Data Engineering, University of Technology Sydney, Sydney, Australia

Tóm tắt

AbstractBackground

Ablation zone segmentation in contrast‐enhanced computed tomography (CECT) images enables the quantitative assessment of treatment success in the ablation of liver lesions. However, fully automatic liver ablation zone segmentation in CT images still remains challenging, such as low accuracy and time‐consuming manual refinement of the incorrect regions.

Purpose

Therefore, in this study, we developed a semi‐automatic technique to address the remaining drawbacks and improve the accuracy of the liver ablation zone segmentation in the CT images.

Methods

Our approach uses a combination of a CNN‐based automatic segmentation method and an interactive CNN‐based segmentation method. First, automatic segmentation is applied for coarse ablation zone segmentation in the whole CT image. Human experts then visually validate the segmentation results. If there are errors in the coarse segmentation, local corrections can be performed on each slice via an interactive CNN‐based segmentation method. The models were trained and the proposed method was evaluated using two internal datasets of post‐interventional CECT images ( = 22, = 145; 62 patients in total) and then further tested using an external benchmark dataset ( = 12; 10 patients).

Results

To evaluate the accuracy of the proposed approach, we used Dice similarity coefficient (DSC), average symmetric surface distance (ASSD), Hausdorff distance (HD), and volume difference (VD). The quantitative evaluation results show that the proposed approach obtained mean DSC, ASSD, HD, and VD scores of 94.0%, 0.4 mm, 8.4 mm, 0.02, respectively, on the internal dataset, and 87.8%, 0.9 mm, 9.5 mm, and −0.03, respectively, on the benchmark dataset. We also compared the performance of the proposed approach to that of five well‐known segmentation methods; the proposed semi‐automatic method achieved state‐of‐the‐art performance on ablation segmentation accuracy, and on average, 2 min are required to correct the segmentation. Furthermore, we found that the accuracy of the proposed method on the benchmark dataset is comparable to that of manual segmentation by human experts ( = 0.55, ‐test).

Conclusions

The proposed semi‐automatic CNN‐based segmentation method can be used to effectively segment the ablation zones, increasing the value of CECT for an assessment of treatment success. For reproducibility, the trained models, source code, and demonstration tool are publicly available at https://github.com/lqanh11/Interactive_AblationZone_Segmentation.

Từ khóa


Tài liệu tham khảo

10.1002/ijc.33767

10.1016/j.jhep.2022.08.021

10.1002/hep.28961

10.1097/MD.0000000000022703

Li D, 2014, Minimally invasive local therapies for liver cancer, Cancer Biol Med, 11, 217

10.2147/OTT.S204340

Yu Z, 2021, Comparison of ultrasound guided versus CT guided radiofrequency ablation on liver function, serum PIVKA‐II, AFP levels and recurrence in patients with primary hepatocellular carcinoma, Am J Transl Res, 13, 6881

10.1016/j.ejrad.2010.09.019

Antoch G, 2005, Assessment of liver tissue after radiofrequency ablation: findings with different imaging procedures, J Nucl Med, 46, 520

10.1097/RCT.0000000000000562

10.1016/j.media.2022.102680

10.1038/srep15373

10.1002/mp.14623

10.3389/fonc.2021.669437

10.3389/fonc.2022.886517

RonnebergerO FischerP BroxT.U‐Net: convolutional networks for biomedical image segmentation. In:Medical Image Computing and Computer‐Assisted Intervention–MICCAI 2015: 18th International Conference Munich Germany October 5‐9 2015 Proceedings Part III 18.Springer;2015:234‐241.

XuW LiuH WangX QianY.Liver segmentation in CT based on ResUNet with 3D probabilistic and geometric post process. In:2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP) IEEE;2019:685‐689.

10.1109/TMI.2018.2845918

10.1038/s41592-020-01008-z

DosovitskiyA BeyerL KolesnikovA et al.An image is worth 16 × 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929;2020.

HatamizadehA TangY NathV et al.UNETR: Transformers for 3D medical image segmentation. In:Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2022:574‐584.

ChenJ LuY YuQ et al.TransUNet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306;2021.

XieY ZhangJ ShenC XiaY.CoTr: efficiently bridging CNN and transformer for 3D medical image segmentation. In:Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference Strasbourg France September 27–October 1 2021 Proceedings Part III 24.Springer;2021:171‐180.

10.1016/j.cmpb.2019.105102

10.1016/S0734-189X(85)90153-7

10.1109/83.902291

10.1145/1015706.1015720

10.1016/j.media.2012.06.002

10.1109/TSMC.1979.4310076

10.1023/A:1007979827043

10.1109/TMI.2016.2621185

LinD DaiJ JiaJ HeK SunJ.ScribbleSup: scribble‐supervised convolutional networks for semantic segmentation. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:3159‐3167.

10.1109/TPAMI.2018.2840695

10.1109/TMI.2018.2791721

10.1016/j.media.2021.102102

10.1002/mp.16120

SofiiukK PetrovIA KonushinA.Reviving iterative training with mask guidance for interactive segmentation. In:2022 IEEE International Conference on Image Processing (ICIP).IEEE;2022:3141‐3145.

ÇiçekÖ AbdulkadirA LienkampSS BroxT RonnebergerO.3D U‐Net: learning dense volumetric segmentation from sparse annotation. In:Medical Image Computing and Computer‐Assisted Intervention–MICCAI 2016: 19th International Conference Athens Greece October 17‐21 2016 Proceedings Part II 19.Springer;2016;424‐432.

10.1038/s42256-019-0057-9

BenensonR PopovS FerrariV.Large‐scale interactive object segmentation with human annotators. In:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:11700‐11709.

10.1118/1.4927790

IsenseeF PetersenJ KleinA et al.nnU‐Net: self‐adapting framework for U‐Net‐based medical image segmentation. arXiv preprint arXiv:1809.10486;2018.

CardosoMJ LiW BrownR et al.MONAI: An open‐source framework for deep learning in healthcare. arXiv preprint arXiv:2211.02701;2022.

LinT‐Y MaireM BelongieS et al.Microsoft COCO: common objects in context. In:Computer Vision–ECCV 2014: 13th European Conference Zurich Switzerland September 6‐12 2014 Proceedings Part V 13.Springer;2014:740‐755.

GuptaA DollarP GirshickR.LVIS: A dataset for large vocabulary instance segmentation. In:Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:5356‐5364.

10.1148/radiol.221373

Diaz‐PintoA AlleS NathV et al.MONAI label: a framework for AI‐assisted interactive labeling of 3D medical images. arXiv preprint arXiv:2203.12362;2022.

10.1634/theoncologist.2018-0337

YushkevichPA GaoY GerigG.ITK‐SNAP: an interactive tool for semi‐automatic segmentation of multi‐modality biomedical images. In:2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).IEEE;2016:3342‐3345.

KikinisR PieperSD VosburghKG.3D Slicer: a platform for subject‐specific image analysis visualization and clinical support. In:Intraoperative Imaging and Image‐Guided Therapy.Springer;2013:277‐289.

10.1016/j.media.2017.07.005

10.1016/j.media.2022.102444

10.1016/j.eswa.2023.122742

10.1038/s41467-024-44824-z