Page 53 - 《中国医疗器械杂志》2025年第2期

Chinese Journal of Medical Instrumentation 2025 年 第49卷 第2期

综 合 评 述

Computer Society, 2013: 1-8. estimation network[J]. Comput Biol Med, 2023, 164:
[4] OKADA Y, KOISHI T, USHIKI S, et al. A fast stereo 107305 .
matching algorithm for 3D reconstruction of internal [17] EDWARDS P J E, PSYCHOGYIOS D, SPEIDEL S, et
organs in laparoscopic surgery[C]// Proceedings of the al. SERV-CT: a disparity dataset from cone-beam CT for
Medical Imaging 2008 Conference. Bellingham, WA: validation of endoscopic 3D reconstruction[J]. Med
SPIE Press, 2008: 846-853. Image Anal, 2022, 76: 102302 .
[5] STOYANOV D, DARZI A, YANG G Z, et al. Real-time [18] YE M L, JOHNS E, HANDA A, et al. Self-supervised
stereo reconstruction in robotically assisted minimally Siamese learning on stereo image pairs for depth
invasive surgery[C]// Proceedings of the 13th International estimation in robotic surgery[EB/OL]. arXiv preprint,
Conference on Medical Image Computing and Computer- arXiv, 1705.08260(2017-05-17)[2024-05-30]. https://arxiv.
Assisted Intervention. Berlin, Germany: Springer-Verlag, org/abs/1705.08260.
2010: 275-282. [19] BARDOZZO F, COLLINS T, FORGIONE A, et al.
[6] 陆明军. 双目医用内窥镜立体匹配技术的研究 [D]. 合 StaSiS-Net: a stacked and siamese disparity estimation
肥: 合肥工业大学, 2021. network for depth reconstruction in modern 3D
[7] WEI G D, SHI W L, FENG G Y, et al. An automatic and laparoscopy[J]. Med Image Anal, 2022, 77: 102380.
robust visual SLAM method for intra-abdominal [20] YANG Z X, SIMON R, LINTE C A. Disparity
environment reconstruction[J]. JACIII, 2023, 27(6): refinement framework for learning-based stereo matching
1216-1229. methods in cross-domain setting for laparoscopic
[8] JIANG Y C, DONG Z H, MAI S P. Robust cost volume images[J]. J Med Imaging (Bellingham), 2023, 10(4):
generation method for dense stereo matching in 045001 .
endoscopic scenarios[J]. Sensors (Basel), 2023, 23(7): [21] WEI R F, LI B, MO H J, et al. Stereo dense scene
3427. reconstruction and accurate localization for learning-
[9] ZHANG X H, JI X Q, WANG J C, et al. Renal surface based navigation of laparoscope in minimally invasive
reconstruction and segmentation for image-guided surgery[J]. IEEE Trans Biomed Eng, 2023, 70(2): 488-
surgical navigation of laparoscopic partial nephrec- 500.
tomy[J]. Biomed Eng Lett, 2023, 13(2): 165-174. [22] ZHANG G, HUANG Z W, LIN J Z, et al. A 3D
[10] SHI H K, WANG Z W, ZHOU Y, et al. Bidirectional reconstruction based on an unsupervised domain adaptive
semi-supervised dual-branch CNN for robust 3D for binocular endoscopy[J]. Front Physiol, 2022, 13:
reconstruction of stereo endoscopic images via adaptive 994343.
cross and parallel supervisions[J]. IEEE Trans Med [23] CHEN L, TANG W, JOHN N W, et al. De-smokeGCN:
Imaging, 2023, 42(11): 3269-3282. generative cooperative networks for joint surgical smoke
[11] YANG Z Y, DAI J, PAN J J. 3D reconstruction from detection and removal[J]. IEEE Trans Med Imaging,
endoscopy images: a survey[J]. Comput Biol Med, 2024, 2020, 39(5): 1615-1625.
175: 108546. [24] LUO H L, WANG C C, DUAN X G, et al. Unsupervised
[12] XU H F, ZHANG J Y. AANet: adaptive aggregation learning of depth estimation from imperfect rectified
network for efficient stereo matching[C]// Proceedings of stereo laparoscopic images[J]. Comput Biol Med, 2022,
the 2020 IEEE/CVF Conference on Computer Vision and 140: 105109.
Pattern Recognition. Los Alamitos, CA: IEEE Computer [25] YANG Z X, SIMON R, LI Y M, et al. Dense depth
Society, 2020: 1956-1965. estimation from stereo endoscopy videos using
[13] TANKOVICH V, HÄNE C, ZHANG Y D, et al. HITNet: unsupervised optical flow methods[C]// Proceedings of
hierarchical iterative tile refinement network for real-time the 25th Conference on Medical Image Understanding
stereo matching[C]// Proceedings of the 2021 IEEE/CVF and Analysis. Berlin, Germany: Springer-Verlag, 2021:
Conference on Computer Vision and Pattern Recognition. 337-349.
Los Alamitos, CA: IEEE Computer Society, 2021: [26] YANG B, XU S Y, CHEN H R, et al. Reconstruct
14357-14367. dynamic soft-tissue with stereo endoscope based on a
[14] XU G W, CHENG J D, GUO P, et al. Attention single-layer network[J]. IEEE Trans Image Process, 2022,
concatenation volume for accurate and efficient stereo 31: 5828-5840.
matching[C]// Proceedings of the 2022 IEEE/CVF [27] HE K M, ZHANG X Y, REN S Q, et al. Deep residual
Conference on Computer Vision and Pattern Recognition. learning for image recognition[C]// Proceedings of the
Los Alamitos, CA: IEEE Computer Society, 2022: 2016 IEEE Conference on Computer Vision and Pattern
12971-12980. Recognition. New York, NY: IEEE, 2016: 770-778.
[15] WANG X Z, NIE Y F, LU S P, et al. Deep convolutional [28] XU K, CHEN Z Y, JIA F C. Unsupervised binocular
network for stereo depth mapping in binocular depth prediction network for laparoscopic surgery[J].
endoscopy[J]. IEEE Access, 2020, 8: 73241-73249. Comput Assist Surg (Abingdon), 2019, 24: 30-35.
[16] WANG X Z, NIE Y F, REN W Q, et al. Multi-scale, [29] YANG H T, KAHRS L A. Real-time coarse-to-fine depth
multi-dimensional binocular endoscopic image depth estimation on stereo endoscopic images with self-

167