浏览全部资源
扫码关注微信
收稿日期：2024-12-06，
修回日期：2025-04-02，
录用日期：2025-04-09，
网络出版日期：2025-04-09，
移动端阅览
目的
2
光声层析成像（photoacoustic tomography，PAT）是一种多物理场耦合的新型成像技术。目前，主流PAT应用是在图像重建后进行图像分割和目标识别，重建中存在物理模型不合理假设、噪声和数据不完备等问题，直接影响后续分割精度。为了解决这一问题，本文提出一种联合图像重建和分割的深度学习框架。
方法
2
将图像重建和分割两个任务结合起来，充分利用二者之间的关联：在分割过程中，将重建结果作为先验知识，更好地恢复和保留目标的形状和边界；分割结果又为重建提供约束和引导，使得重建结果更贴近真实目标，从而同步完成PAT图像重建和分割。
结果
2
仿真、仿体和在体实验结果表明，与两步法相比，采用所提方法重建图像的结构相似度指标可提高约10.01%，峰值信噪比可提高约12.15%，图像分割的DICE指标可提高约13.27%，Jaccard指数可提高约6.08%，平均表面对称距离可提高约16.55%。与其他联合重建与分割方法相比，重建图像的结构相似度可提高约3.65%，峰值信噪比可提高约4.96%；图像分割的DICE指标可提高约2.73%，Jaccard指数提高约3.85%，平均表面对称距离提高约5.99%。
结论
2
本文方法通过实现PAT图像的联合重建与分割，有效减少了重建误差积累对于分割精度的影响，提高了PAT的成像质量和分割精度，展现出良好的应用前景。
Objective
2
Photoacoustic tomography （PAT） is an emerging imaging technique that combines optical contrast with acoustic resolution， demonstrating great potential in the field of biomedical applications in recent years. Its non-invasive nature， high contrast， and high resolution make it an important tool in medical diagnosis and research. However， due to limitations in the imaging principles and the complexity of biological tissues， photoacoustic images often suffer from issues such as blurring， artifacts， and low contrast， which restrict their accuracy and reliability in clinical applications. Improving image quality is crucial for further advancement of PAT technology. Current research generally treats image reconstruction and segmentation as two separate steps. First， the inverse problem is solved to reconstruct a two-dimensional or three-dimensional image from the photoacoustic signals collected by the ultrasonic detectors， achieving the "signal-to-image" conversion. Then， regions of interest （such as specific tissues or structures） are segmented or identified from the reconstructed images， achieving the "image-to-feature" conversion. This decoupled processing framework shows significant limitations in practical applications. In the image reconstruction phase， errors inevitably arise due to inaccuracy of the physical model， unreasonable assumptions （such as the acoustically homogeneous medium and constant speed of sound）， noise interference， and incomplete data acquisition. These errors accumulate in subsequent segmentation and target recognition tasks， significantly reducing the accuracy of automated analysis. This， in turn， limits the potential of PAT in fields such as precision medicine and real-time diagnosis. To address this issue， this paper proposes an end-to-end deep learning framework that innovatively integrates image reconstruction and segmentation tasks into a unified network. Through the interaction and collaborative optimization between these two tasks， the framework fully leverages their potential correlations to significantly improve the overall quality of PAT images and achieve higher accuracy in image segmentation.
Method
2
This paper presents an end-to-end joint reconstruction and segmentation deep learning framework， aimed at enhancing the quality of PAT image reconstruction and segmentation accuracy through iterative optimization. The framework consists of two core modules： the reconstruction module and the segmentation module. The reconstruction module is used to generate an initial image using deep neural networks while minimizing reconstruction errors caused by factors such as incomplete physical models or noises.The segmentation module performs further image processing based on the reconstruction module， with its task being the precise segmentation of the regions of interest. To capture the details of the target regions in the image， the segmentation module adopts a context-aware mechanism， combining both global and local features of the image. Specifically， the segmentation module employs a hybrid architecture that combines fully convolutional networks （FCN） and DenseNet. The encoder-decoder structure of the FCN enables pixel-level classification and extracts both low-level and high-level features from the image， while DenseNet enhances the utilization of information from previous layers through dense connections， improving feature representation capability. The combination of FCN and DenseNet allows the segmentation module to better process complex image information and achieve higher precision semantic segmentation. The key aspect of the framework is the establishment of a bidirectional feedback mechanism between the reconstruction and segmentation modules， creating a deep collaboration loop. In this mechanism， the output of the segmentation module serves as a constraint that guides the reconstruction module to refine the restoration of the target region， while the image provided by the reconstruction module offers important prior information to the segmentation module， further optimizing the segmentation of the target regions. Through this bidirectional feedback， the two modules promote each other during the iterative process， continuously improving the accuracy of both reconstruction and segmentation. In each iteration， the reconstruction module corrects reconstruction errors with the feedback from the segmentation module， while the segmentation module extracts more accurate features from the progressively optimized reconstructed image， thereby improving segmentation precision. Unlike traditional methods， this framework avoids the issue of accumulation of errors due to independent tasks through deep collaboration. In conventional approaches， image reconstruction and segmentation are typically processed separately， which leads to a lack of information sharing between the two tasks and ultimately affects the overall accuracy of the results. On the contrary， the proposed framework optimizes both modules jointly， ensuring that the output of each module provides higher-quality input for the next， thus ensuring synchronized improvement of both reconstruction and segmentation tasks. Ultimately， through multiple iterations， this deep integration of information not only significantly enhances image clarity， but also substantially improves segmentation accuracy.
Result
2
To validate the effectiveness of the proposed method， a series of simulation experiments， phantom studies， and in vivo experiments were conducted. The experimental results demonstrate significant advantages over the two-step scheme in both image reconstruction and segmentation tasks. In simulation experiments， the proposed method improved the structural similarity index （SSIM） of the reconstructed images by up to 10.01% and the peak signal-to-noise ratio （PSNR） by up to 12.15%. In segmentation tasks， the DICE coefficient and the Jaccard index improved by up to 13.27% and 6.08%， respectively， while the average symmetric surface distance （ASSD） was reduced by up to 16.55%. In phantom experiments， the method showed robust performance even in complex scenarios （such as heterogeneous media and variable speed of sound）. Compared with other joint reconstruction and segmentation methods， the SSIM and PSNR of the reconstructed images can be improved by approximately 3.65% and 4.96%， respectively； the DICE， Jaccard index， and ASSD for image segmentation can be improved by about 2.73%， 3.85%， and 5.99%， respectively. Further in vivo experiments validated the applicability of this method in real-world biological imaging. In tumor detection and vascular imaging tasks， the images generated by the proposed method exhibited sharp boundaries， accurate shapes， and significantly improved segmentation integrity of the target regions， exceeding traditional methods， and showing strong robustness and generalizability.
Conclusion
2
This paper proposes an end-to-end deep learning framework that jointly performs image reconstruction and segmentation tasks， effectively solving the critical issue of error accumulation in traditional two-step methods. Compared to existing approaches， the proposed method better restores the shape and boundaries of the target region， reduces information loss and blurring， and demonstrates significant performance improvements in simulation， phantom， and in vivo experiments. The study shows that the proposed method has significant theoretical importance and demonstrates great potential in practical applications. Future research will further explore the application potential of this framework in real-time processing and large-scale datasets to promote the clinical translation of PAT into medical diagnosis and treatment.
ALRFOU K and ZHAO T . 2024 . GCxt-UNet： Efficient network for medical image segmentation ［EB/OL］.［ 2024-06-09 ］. https://a-rxiv.org/pdf/2406.05891.pdf https://a-rxiv.org/pdf/2406.05891.pdf
ANTHOLZER S ， HALTMEIER M and SCHWAB J . 2019 . Deep learning for photoacoustic tomography from sparse data . Inverse Problems in Science and Engineering ， 27 （ 7 ）： 987 - 1005 ［ DOI： 10.1080/17415977.2018.1518444 http://dx.doi.org/10.1080/17415977.2018.1518444 ］
ARRIDGE S ， BEARD P ， BETCKE M ， COX B ， HUYNH N ， LUCKA 1 F， OGUNLADE O and ZHANG E . 2016. Accelerated high-resolution photoacoustic tomography via compressed sensing . Physics in Medicine and Biology， 61 （ 24 ）： 8908 - 8940 ［DOI 10.1088/1361-6560/61/24/8908 http://dx.doi.org/10.1088/1361-6560/61/24/8908 ］
BADRINARAYANAN V ， KENDALL A and CIPOLLA R . 2017 . SegNet： A deep convolutional encoder-decoder architecture for image segmentation . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 39 （ 12 ）： 2481 - 2495 ［ DOI： 10.1109/TPAMI.2016.2644615 http://dx.doi.org/10.1109/TPAMI.2016.2644615 ］
BAL G and UHLMANN G . 2010 . Inverse diffusion theory of ph-otoacoustics . Inverse Problems ， 26 （ 8 ）： 085010 ［ DOI： 10.1088/0266-5611/26/8/085010 http://dx.doi.org/10.1088/0266-5611/26/8/085010 ］
BOINK Y E ， MANOHAR S and BRUNE C . 2020 . A partially-learned algorithm for joint photo-acoustic reconstruction and segmentation . IEEE Transactions on Medical Imaging ， 39 （ 1 ）： 129 - 139 ［ DOI： 10.1109/TMI.2019.2922026 http://dx.doi.org/10.1109/TMI.2019.2922026 ］
CHLIS N K ， KARLAS A ， FASOULA N A ， KALLMAYER M ， ECKSTEIN H H ， THEIS F ， NTZIACHRISTOS V and MARR C . 2020 . A sparse deep learning approach for automatic segmentation of human vasculature in multispectral optoacoustic tomography . Photoacoustics ， 20 ： 100203 ［ DOI： 10.1016/j.pacs.2020.100203 http://dx.doi.org/10.1016/j.pacs.2020.100203 ］
CORONA V ， BENNING M ， EHRHARDT M J ， GLADDEN L F ， MAIR R ， RECI A ， SEDERMAN A J ， REICHELT S and SCHONLIEB C B . 2019 . Enhancing joint reconstruction and segmentation with non-convex Bregman iteration . Inverse Problems ， 35 （ 5 ）： 055001 ［ DOI： 10.1088/1361-6420/ab0b77 http://dx.doi.org/10.1088/1361-6420/ab0b77 ］
COX B T and BEARD P C . 2005 . Fast calculation of pulsed photoacoustic fields in fluids using k-space methods . Journal of the Acoustical Society of America ， 117 （ 6 ）： 3616 - 3627 ［ DOI： 10.1121/1.1920227 http://dx.doi.org/10.1121/1.1920227 ］
DEY S ， SAHA S ， FENG B T ， FENG ， CUI M ， DELISLE L ， LEONG O ， WANG L V and BOUMAN K L . 2024 . Score-based diffusion models for photoacoustic tomography image reconstruction ［EB/OL］.［ 2024-03-30 ］. https://arxiv.org/pdf/2404.00471.pdf https://arxiv.org/pdf/2404.00471.pdf
FARNIA P ， MOHAMMADI M ， NAJAFZADEH E ， ALIMOHAMADI M ， MAKKIABADI B and AHMADIAN A . 2020 . High-quality photoacoustic image reconstruction based on deep convolutional neural network： towards intra-operative photoacoustic imaging . Biomedical Physics and Engineering Express ， 6 （ 4 ）： 045019 ［ DOI： 10.1088/2057-1976/ab9a10 http://dx.doi.org/10.1088/2057-1976/ab9a10 ］
GUO M ， LAN H ， YANG C ， and GAO F . 2022 . AS-Net： fast photoacoustic reconstruction with multi-feature fusion from sparse data . IEEE Transactions on Computational Imaging ， 8 ： 215 - 223 ［ DOI： 10.1109/tci.2022.3155379 http://dx.doi.org/10.1109/tci.2022.3155379 ］
HAKIMNEJAD H ， AZIMIFAR Z and GOSHTASBI N . 2024 . DensePANet： An improved generative adversarial network for photoacoustic tomography image reconstruction from sparse data ［EB/OL］.［ 2024-04-19 ］. https://arxiv.org/abs/2404.13101.pdf https://arxiv.org/abs/2404.13101.pdf
HEIMANN T and MEINZER H P . 2009 . Statistical shape models for 3D medical image segmentation： A review . Medical Image Analysis ， 13 （ 4 ）： 543 - 563 ［ DOI： 10.1016/j.media.2009.05.004 http://dx.doi.org/10.1016/j.media.2009.05.004 ］
ISENSEE F ， JAEGER P F ， KOHL S A A ， PETERSEN J and MAIER H K H . 2021 . nnU-Net： a self-configuring method for deep learning-based biomedical image segmentation . Nature Methods ， 18 （ 2 ）： 203 - 211 ［ DOI： 10.1038/s41592-020-01008-z http://dx.doi.org/10.1038/s41592-020-01008-z ］
JADON S . SemSegLoss： A python package of loss functions for semantic segmentation . Software Impacts ， 2021 ， 9 ： 100078 ［ DOI： 10.1016/j.simpa.2021.100078 http://dx.doi.org/10.1016/j.simpa.2021.100078 ］
JOSEPH F K ， ARORA A ， KANCHARLA P ， SINGH M K A ， STEENBERGEN W and CHANNAPPAYYA S S . 2021 . Generative adversarial network based photoacoustic image reconstruction from bandlimited and limited-view data // Proceedings of SPIE International Conference on Photons Plus Ultrasound： Imaging and Sensing . Onlion ： SPIE： 1164235-1-1164235 - 6 ［ DOI： 10.1117/12.2577750 http://dx.doi.org/10.1117/12.2577750 ］
LAFCI B ， MERCEP E ， MORSCHER S ， BEN X L and RAZANSKY D . 2020 . Efficient segmentation of multi-modal optoacoustic and ultrasound images using convolutional neural networks // Proceedings of SPIE International Conference on Photons Plus Ultrasound： Imaging and Sensing. San Francisco： SPIE：112402N-1-112402N-6 ［ DOI： 10.1117/12.2543970 http://dx.doi.org/10.1117/12.2543970 ］
LAFCI B ， MERCEP E ， MORSCHER S ， BEN X L and RAZANSKY D . 2021 . Deep learning for automatic segmentation of hybrid optoacoustic ultrasound （OPUS） images . IEEE Transactions on Ultrasonics， Ferroelectrics， and Frequency Control ， 68 （ 3 ）： 688 - 696 ［ DOI： 10.1109/TUFFC.2020.3022324 http://dx.doi.org/10.1109/TUFFC.2020.3022324 ］
LALONDE R ， XU Z Y ， IRMAKCI I ， JAIN S and BAGCI U . 2021 . Capsules for biomedical image segmentation . Medical Image Analysis ， 68 ： 101889 ［ DOI： 10.1016/j.media.2020.101889 http://dx.doi.org/10.1016/j.media.2020.101889 ］
LI J ， GUO S W ， MENG X ， LAI Z C and HAN S K . 2022 . DPG-Net： Densely progressive-growing network for point cloud completion . Neurocomputing ， 491 ： 1 - 13 ［ DOI： 10.1016/j.neucom.2022.03.060 http://dx.doi.org/10.1016/j.neucom.2022.03.060 ］
LIU F Y ， GONG X J ， WANG L V ， GUAN J J ， SONG L and MENG J . 2019 . Dictionary learning sparse-sampling reconstruction method for in-vivo 3D photoacoustic computed tomography . Biomedical Optics Express ， 10 （ 4 ）： 1660 - 1677 ［ DOI： 10.1364/BOE.10.001660 http://dx.doi.org/10.1364/BOE.10.001660 ］
LU T ， CHEN T ， GAO F ， SUN B ， NTZIACHRISTOS V and LI J . 2021 . LV-GAN： A deep learning approach for limited-view optoacoustic imaging based on hybrid datasets . Journal of Biophotonics ， 14 ： e 202000325 ［ DOI： 10.1002/jbio.202000325 http://dx.doi.org/10.1002/jbio.202000325 ］
LU X M . 2021 . Research and Quantitative Analysis of 3D Segmentation of Vascular Photoacoustic Images Based on the Hessian Matrix . Guizhou ： Guizhou University
卢学敏 . 2021 . 基于Hessian矩阵的血管光声图像三维分割研究及量化分析 . 贵州 ： 贵州大学
LUNGU G F ， LI M L ， XIE X Y ， W LV and STOICA G . 2007 . In vivo imaging and characterization of hypoxia-induced ne-ovascularization and tumor invasion . International Journal of Oncology ， 30 （ 1 ）： 45 - 54 ［ DOI： 10.3892/ijo.30.1.45 http://dx.doi.org/10.3892/ijo.30.1.45 ］
LY C D ， NGUYEN V T ， VO T H ， MONDAL S ， PARK S ， CHOI J ， VU T T H ， KIM C S and OH J . 2022 . Full-view in vivo skin and blood vessels profile segmentation in photoacoustic imaging based on deep learning . Photoacoustics ， 25 ： 100310 ［ DOI： 10.1016/j.pacs.2021.100310 http://dx.doi.org/10.1016/j.pacs.2021.100310 ］
MA J ， LI F and WANG B . 2024 . U-Mamba： Enhancing long-range dependency for biomedical image segmentation ［EB/OL］.［ 2024-01-09 ］. https://arxiv.org/pdf/2401.04722.pdf https://arxiv.org/pdf/2401.04722.pdf
MADHUMATHY P and PANDEY R . 2022 . Deep learning based photoacoustic imaging for non-invasive imaging . Multimedia Tools and Applications ， 81 ： 7501 – 7518 ［ DOI： 10.1007/s11042-022-11903-6 http://dx.doi.org/10.1007/s11042-022-11903-6 ］
MANDAL S ， VISWANATH P S ， YESHASWINI N ， BEN X L and RAZANSKY D . 2015 . Multiscale edge detection and parametric shape modeling for boundary delineation in optoacoustic images // Proceedings of IEEE 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society （EMBC） . Milan ， IEEE ： 707 - 710 ［ DOI： 10.1109/EMBC.2015.7318460 http://dx.doi.org/10.1109/EMBC.2015.7318460 ］
OH J T ， LI M L ， ZHANG H F ， Maslov K ， Stoica G and Wang L V . 2006 . Three-dimensional imaging of skin melanoma in vivo by dual-wavelength photoacoustic microscopy . Journal of Biomedical Optics ， 11 （ 3 ）： 034032 ［ DOI： 10.1117/1.2210907 http://dx.doi.org/10.1117/1.2210907 ］
PALTAUF G ， VIATOR J A ， PRAHL S A ， and Jacques S L . 2002 . Iterative reconstruction algorithm for optoacoustic imaging . The Journal of the Acoustical Society of America ， 112 （ 4 ）： 1536 - 1544 ［ DOI： 10.1121/1.1501898 http://dx.doi.org/10.1121/1.1501898 ］
PENG D ， ZHAI C ， ZHANG Y and GUAN H . 2023 . High-resolution optical remote sensing image change detection based on dense connection and attention feature fusion network . The Photogrammetric Record ， 38 （ 184 ）： 498 - 519 ［ DOI： 10.1111/phor.12462 http://dx.doi.org/10.1111/phor.12462 ］
POUDEL J ， YANG L and ANASTASIO M A . 2019 . A survey of computational frameworks for solving the acoustic inverse problem in three-dimensional photoacoustic computed tomography . Physics in Medicine and Biology ， 64 （ 14 ）： 14 TR 01 ［ DOI： 10.1088/1361-6560/ab2017 http://dx.doi.org/10.1088/1361-6560/ab2017 ］
STABIN M G ， PETERSON T E ， HOLBURN G E and EMMONS M A . 2006 . Voxel-based mouse and rat models for internal dose calculations . The Journal of Nuclear Medicine ， 47 （ 4 ）： 655 - 659 .
SUN M C . 2023 . Research on Photoacoustic Tomography Image Enhancement and Tissue Calibration Methods . Baoding ： North China Electric Power University
孙美晨 . 2023 . 光声层析图像增强与组织标定方法研究 . 保定 ： 华北电力大学
SUN M J ， LI C ， CHEN N B ， ZHAO H X ， MA L Y LIU C B ， SHEN Y ， LIN R and GONG X J . 2020 . Full three-dimensional segmentation and quantification of tumor vessels for photoacoustic images . Photoacoustics ， 20 ： 100212 ［ DOI： 10.1016/j.pacs.2020.100212 http://dx.doi.org/10.1016/j.pacs.2020.100212 ］
SUN W and WANG R . 2018 . Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM . IEEE Geoscience and Remote Sensing Letters ， 15 （ 3 ）： 474 - 478 ［ DOI： 10.1109/LGRS.2018.2795531 http://dx.doi.org/10.1109/LGRS.2018.2795531 ］
SUN Z and SUN L S . 2021 . Simultaneous reconstruction of opti-cal absorption property and speed of sound in intravascular photoacoustic tomography . Inverse Problems in Science and Engineering ， 29 （ 12 ）： 1764 - 1788 ［ DOI： 10.1080/17415977.2021.1879805 http://dx.doi.org/10.1080/17415977.2021.1879805 ］
SUN Z and YAN X Y . 2020 . A deep learning method for limited-view intravascular photoacoustic image reconstruction . Journal of Medical Imaging and Health Informatics ， 10 （ 11 ）： 2707 - 2713 ［ DOI： 10.1166/jmihi.2020.3204 http://dx.doi.org/10.1166/jmihi.2020.3204 ］
SUN Z and YAN X Y . 2020 . Image reconstruction based on compressed sensing for sparse-data endoscopic photoacoustic tomography . Computers in Biology and Medicine ， 116 ： 103587 ［ DOI： 10.1016/j.compbiomed.2019.103587 http://dx.doi.org/10.1016/j.compbiomed.2019.103587 ］
SUN Z ， WANG X Y and YAN X Y . 2021 . An iterative gradient convolutional neural network and its application in endoscopic photoacoustic image formation from incomplete acoustic measurement . Neural Computing and Applications ， 33 ： 8555 - 8574 ［ DOI： 10.1007/s00521-020-05607-x http://dx.doi.org/10.1007/s00521-020-05607-x ］
TONG J ， DONG Y W ， SUN Y C . 1989 . The relationship between nonlinear acoustic parameters B/A and tissue sound speed and composition . Chinese Journal of Biomedical Engineering ， 8 （ 3 ）： 190 - 195
仝杰 ， 董彦武 ， 孙永臣 . 1989 . 非线性声参量B/A与组织声速及组份的关系 . 中国生物医学工程学报 ， 8 （ 3 ）： 190 - 195
XU M H and WANG L V . 2005 . Universal back-projection algorithm for photoacoustic computed tomography . Physical Review E ， 71 ： 016706 ［ DOI： 10.1117/12.589146 http://dx.doi.org/10.1117/12.589146 ］
XU M H ， XU Y and WANG L V . 2003 . Time-domain reconstruction algorithms and numerical simulations for thermoacoustic tomography in various geometries . IEEE Transactions on Biomedical Engineering ， 50 （ 9 ）： 1086 - 1099 ［ DOI： 10.1109/TBME.2003.816081 http://dx.doi.org/10.1109/TBME.2003.816081 ］
YANG C C ， LAN H R ， GAO F and GAO F . 2021 . Review of deep learning for photoacoustic imaging . Photoacoustics ， 21 ： 100215 ［ DOI： 10.1016/j.pacs.2020.100215 http://dx.doi.org/10.1016/j.pacs.2020.100215 ］
YANG L ， PARK S ， ANIS F ， SU R ， A A and ANASTASIO A . 2019 . Analysis of the use of unmatched backward operators in iterative image reconstruction with application to three-dimensional optoacoustic tomography . IEEE Transactions on Computational Imaging ， 5 （ 3 ）： 437 – 449 ［ DOI： 10.1109/TCI.2019.2895217 http://dx.doi.org/10.1109/TCI.2019.2895217 ］
YAO J J and WANG L V . 2018 . Recent progress in photoacoustic molecular imaging . Current Opinion in Chemical Biology ， 45 ： 104 - 112 ［ DOI： 10.1016/j.cbpa.2018.03.016 http://dx.doi.org/10.1016/j.cbpa.2018.03.016 ］
YAO J ， XIA J ， MASLOV K I ， NASIRIAVANAKI M ， TSYTSAR-EV V ， DEMCHENKO A V and WANG L V . 2013 . Nonin-vasive photoacoustic computed tomography of mouse brain metabolism in vivo . NeuroImage ， 64 ： 257 - 266 ［ DOI： 10.1016/j.neuroimage.2012.08.054 http://dx.doi.org/10.1016/j.neuroimage.2012.08.054 ］
Zhang X F ， Zhang S ， Zhang D H and Liu R . 2023 . Group Attention-based Medical Image Segmentation Model . Journal of Image andGraphics ， 28 （ 10 ）： 3231 - 3242
张学峰 ， 张胜 ， 张冬晖 ， 刘瑞 . 2023 . 引入分组注意力的医学图像分割模型 . 中国图象图形学报 ， 28 （ 10 ）： 3231 - 3242 ［ DOI： 10. 11834/jig. 220748 http://dx.doi.org/10.11834/jig.220748 ］
ZHAO H ， WANG G S ， LIN R ， GONG X J ， SONG L ， LI T ， WANG W J ， ZHANG K Y ， QIAN X Q ， ZHANG X X ， LI L ， LIU Z C and LIU C B . 2018 . Three-dimensional hessian matrix-based quantitative vascular imaging of rat iris with optical-resolution photoacoustic microscopy in vivo . Journal of Biomedical Optics ， 23 （ 4 ）： 046006 ［ DOI： 10.1117/1.JBO.23.4.046006 http://dx.doi.org/10.1117/1.JBO.23.4.046006 ］
ZHAO Y Q ， WANG X H ， WANG X F and SHILH F Y . 2014 . Retinal vessels segmentation based on level set and region growing . Pattern Recognition ， 47 （ 7 ）： 2437 - 2446 ［ DOI： 10.1016/j.patcog.2014.01.006 http://dx.doi.org/10.1016/j.patcog.2014.01.006 ］
Zhou T ， Dong Y L ， Huo B Q ， Liu S and Ma Z J . 2021 . U-net and its applications in medical image segmentation： a review . Journal ofImage and Graphic ， 26 （ 09 ）： 2058 - 2077
周涛 ， 董雅丽 ， 霍兵强 ， 刘珊 ， 马宗军 . 2021 . U-Net网络医学图像分割应用综述 . 中国图象图形学报 ， 26 （ 09 ）： 2058 - 2077 . ［ DOI： 10.11834/JIG.200704 http://dx.doi.org/10.11834/JIG.200704 ］
相关文章
相关作者
相关机构
京公网安备11010802024621