计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 241100152-7.doi: 10.11896/jsjkx.241100152
王宝会1, 杜辉2, 张远1
WANG Baohui1, DU Hui2, ZHANG Yuan1
摘要： 在临床实践中,下肢骨畸形是骨科医疗中常见且治疗难度较大的病症,医生通常依赖正侧位X光片进行负重位畸形程度判断,但这一过程高度依赖医生的专业程度与经验水平。虽然CT三维摄片技术存在,但患者在拍摄CT时需要平躺,与站立负重位的差异导致其无法很好地满足诊断要求。因此,创建更为直观和准确的下肢骨畸形模型展示至关重要。这样不仅可以简化医生的工作,还能提高诊断的准确性,帮助他们制定更有效的治疗方案。因此,提出了基于PSSobel-X2CTGAN的模型,在原模型的基础上对reshape模块加入了Transformer机制,另外在数据集的准备中使用了CycleGAN来进行数据增强。在原论文的数据集上进行验证,实验结果清晰地表明,该模型在CT-PELVIC和SKI10数据集上的结构相似值分别达到了79.51%和56.32%,而原模型的值仅为77.49%和49.53%,展示了其显著的改进和提升。
中图分类号:
| [1]YE R W,WANG B H.Research on Lower Limb X-ray 3D Reconstruction Algorithm Based on Generative Adversarial Network[J].Computer Science,2024,51(S2):232-238. [2]SHEPP L A,VARDI Y.Maximum Likelihood Reconstructionfor Emission Tomography[J].IEEE Transactions on Medical Imaging,1983,1:113-122. [3]LUSTIG M,DONOHO D L,PAULY J M.Sparse MRI:The application of compressed sensing for rapid MR imaging[J].Magnetic Resonance in Medicine,2007,58(6):1182-1195. [4]HERMAN G T.Fundamentals of Computerized Tomography:Image Reconstruction from Projections[C]//Advances in Pattern Recognition.2009. [5]LAMECKER H,WENCKEBACH T H,HEGE H.Atlas-based 3D-Shape Reconstruction from X-Ray Images[C]//18th International Conference on Pattern Recognition(ICPR’06).2006:371-374. [6]SERRADELL E,ROMERO A,LETA R,et al.Simultaneouscorrespondence and non-rigid 3D reconstruction of the coronary tree from single X-ray images[C]//2011 International Confe-rence on Computer Vision.2011:850- 857. [7]EIGEN D,PUHRSCH C,FERGUS R.Depth Map Prediction from a Single Image using a Multi-Scale Deep Network[C]//NIPS.2014. [8]HENZLER P,RASCHE V,ROPINSKI T,et al.Single-imageTomography:3D Volumes from 2D X-Rays[J].arXiv:1710.04867,2017. [9]YING X,GUO H,MA K,et al.X2CT-GAN:Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).2019:10611-10620. [10]WÜRFL T,GHESU F C,CHRISTLEIN V,et al.Deep Learning Computed Tomography[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.2016. [11]MAGNOR M A,KINDLMANN G L,DURIC N,et al.Con-strained inverse volume rendering for planetary nebulae[J].IEEE Visualization,2004,2004:83-90. [12]SHI W,CABALLERO J,HUSZÁR F,et al.Real-Time SingleImage and Video Super- Resolution Using an Efficient Sub-Pixel Convolutional Neural Network[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2016:1874-1883. [13]MAO X,LI Q,XIE H,et al.Least Squares Generative Adversarial Networks[C]//2017 IEEE International Conference on Computer Vision(ICCV).2016:2813-2821. [14]YU B,ZHOU L,WANG L,et al.Ea-GANs:Edge-Aware Ge-nerative Adversarial Networks for Cross-Modality MR Image Synthesis[J]IEEE Transactions on Medical Imaging,2019,38:1750-1762. [15]BAHNER M L,DEBUS J,ZABEL A,et al.Digitally reconstructed radiographs from abdominal CT scans as a new tool for radiotherapy planning[J].Investigative Radiology,1999,34(10):643-647. [16]LIU P,HAN H,DU Y,et al.Deep learning to segment pelvic bones:large-scale CT datasets and baseline models[J].International Journal of Computer Assisted Radiology and Surgery,2020,16:749-756. [17]HEIMANN T,MORRISON B,STYNER M A,et al.Segmentation of Knee Images:A Grand Challenge[C]//MICCAI Workshop on Medical Image Analysis for the Clinic.2010:207-214. [18]CARION N,MASSA F,SYNNAEVE G,et al.End-to-end object detection with transformers[C]//European Conference on Computer Vision.Springer,2020:213-222. [19]CHEN H,GU J,ZHANG Z.Attention in attention network for image super-resolution[J].arXiv:2104.09497,2021. [20]ZHU J,PARK T,ISOLA P,et al.Unpaired Image-to-ImageTranslation Using Cycle-Consistent Adversarial Networks[C]//IEEE International Conference on Computer Vision(ICCV).2017:2242-2251. |
|
||
首页