优化医学影像三维渲染可视化效果：技术综述

doi:10.11996/JG.j.2095-302X.2024050879

图学学报 ›› 2024, Vol. 45 ›› Issue (5): 879-891.DOI: 10.11996/JG.j.2095-302X.2024050879

优化医学影像三维渲染可视化效果：技术综述

许丹丹¹^,²(), 崔勇³, 张世倩¹^,², 刘雨聪²^,⁴, 林予松²^,⁴()

1.郑州大学计算机与人工智能学院，河南郑州 450001
2.郑州大学互联网医疗与健康服务河南省协同创新中心，河南郑州 450052
3.郑州轻工业大学计算机科学与技术学院，河南郑州 450002
4.郑州大学网络空间安全学院，河南郑州 450002

收稿日期:2024-04-24 修回日期:2024-07-25 出版日期:2024-10-31 发布日期:2024-10-31
通讯作者:林予松(1973-)，男，教授，博士。主要研究方向为医学图像处理。E-mail：yslin@ha.edu.cn
第一作者:许丹丹(1993-)，女，硕士研究生。主要研究方向为医学影像三维可视化。E-mail：ddxu@ha.edu.cn
基金资助:
国家自然科学基金面上项目(81772009);郑州市协同创新重大专项项目(20XTZX05015)

Optimizing the visual effects of 3D rendering in medical imaging: a technical review

XU Dandan¹^,²(), CUI Yong³, ZHANG Shiqian¹^,², LIU Yucong²^,⁴, LIN Yusong²^,⁴()

1. School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou Henan 450001, China
2. Collaborative Innovation Center for Internet Healthcare, Zhengzhou University, Zhengzhou Henan 450052, China
3. School of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou Henan 450002, China
4. School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou Henan 450002, China

Received:2024-04-24 Revised:2024-07-25 Published:2024-10-31 Online:2024-10-31
Contact: LIN Yusong (1973-), professor, Ph.D. His main research interest covers medical image processing. E-mail：yslin@ha.edu.cn
First author：XU Dandan (1993-), master student. Her main research interest covers 3D visualization of medical images. E-mail：ddxu@ha.edu.cn
Supported by:
National Natural Science Foundation of China(81772009);Collaborative Innovation Major Project of Zhengzhou(20XTZX05015)

摘要/Abstract

摘要：

医学成像学是医学领域的一个重要分支，目前最常见的医学成像方式主要包括：磁共振成像、计算机断层扫描、超声成像、X射线、正电子发射断层扫描等。医学影像是通过各种成像技术获取信息实体，医学影像三维渲染是医学成像领域使用的一种可视化技术，对于可视化解剖结构、精准诊疗、手术规划等具有重要意义。分析医学影像三维渲染技术在可视化效果优化的研究现状，首先介绍了2种基础的三维渲染技术，然后从优化技术和框架两方面入手，介绍当前三维渲染可视化的优化研究，比较不同技术的特点、使用环境以及优缺点，为相关研究人员选择不同的技术提供参考，最后从主观和客观两方面介绍如何评价三维渲染的可视化效果。讨论了在技术发展过程中，存在引入的算法复杂度高、渲染效率降低、算法实时性差的问题，并思考解决这些问题的方法，探讨优化三维渲染可视化效果的未来发展方向。

关键词: 医学影像, 三维渲染, 传递函数, 光线投射, 全局照明, 深度学习

Abstract:

Medical imaging is a critical field in medicine, utilizing techniques such as magnetic resonance imaging (MRI), computed tomography (CT) scans, ultrasound (US), X-rays, and positron emission tomography (PET) scans. These medical images are generated through various imaging techniques. In this context, 3D rendering has emerged as a pivotal visualization tool that plays a significant role in visualizing anatomical structures, enabling accurate diagnosis, effective treatment planning, and precise surgical interventions. This analysis examined the current state of research on optimizing visualization effects in 3D rendering technology within medical imaging. First, two fundamental 3D rendering techniques were introduced, providing a foundation for understanding the technological landscape. Following this, the discussion examined recent advancements in visualization optimization, focusing on two main areas: technical optimization and framework optimization. Technical optimization involved refining algorithms and methods to improve image quality and rendering speed. Framework optimization, on the other hand, focused on the integration of rendering technologies into broader software systems to enhance performance and usability. A comparative analysis of various optimization techniques was presented, highlighting their characteristics, application scenarios, and respective strengths and weaknesses. This comparison served as a reference for researchers and practitioners in selecting appropriate techniques for their specific needs. Evaluating the effectiveness of 3D rendering was another crucial aspect covered in this analysis. Both subjective and objective evaluation methods were explored to provide a comprehensive assessment of visualization quality. The analysis also discussed potential challenges posed by technological advancements, such as increased algorithm complexity, decreased rendering efficiency, and suboptimal real-time performance, as well as exploring potential solutions. Future directions for optimizing 3D rendering and visualization effects were explored.

Key words: medical imaging, three-dimensional rendering, transfer function, ray casting, global illumination, deep learning

中图分类号:

许丹丹, 崔勇, 张世倩, 刘雨聪, 林予松. 优化医学影像三维渲染可视化效果：技术综述[J]. 图学学报, 2024, 45(5): 879-891.

XU Dandan, CUI Yong, ZHANG Shiqian, LIU Yucong, LIN Yusong. Optimizing the visual effects of 3D rendering in medical imaging: a technical review[J]. Journal of Graphics, 2024, 45(5): 879-891.

图/表 14

图1 三维医学渲染中使用的CT图像序列[4]

Fig. 1 The CT images sequence used in 3D medical rendering[4]

图2 X射线设备及医学影像数据集的可视化图像((a)临床干预中的X射线C臂系统；(b) C形臂几何形态的旋转自由度；(c)使用X射线C臂系统获取的三维数据集[5])

Fig. 2 Visualization of X-ray equipment and medical image datasets ((a) The X-ray C-arm system in a clinical intervention; (b) The degrees of rotational freedom of the C-arm geometry; (c) A 3D data set, acquired using the X-ray C-arm system[5])

图3 结构总览图

Fig. 3 Structural overview diagram

表1 2种基础三维渲染技术对比表

Table 1 Comparison table of two basic 3D rendering techniques

渲染技术	特点	使用场景	优点	缺点
等值面渲染	基于等值面提取，显示特定数值的体素	显示解剖结构或病变表面	有助于表面形状分析	难以处理复杂的内部结构
直接体绘制	直接对体数据进行渲染，无需将数据转换为其他几何形状	可视化体数据内部结构	呈现内部细节，对密集数据集表现较好	可能产生视觉混淆，不适用于强调表面特征

图4 行进立方体[12]

Fig. 4 Marching cube[12]

图5 交互式探索的多细节级别渲染((a)在原始数据集中以全图像分辨率渲染等值面；(b)在原始数据集中以1/4图像分辨率渲染等值面，并升级到全图像分辨率；(c)在每个维度分辨率减半且经过低通滤波的数据集中以全图像分辨率渲染等值面[14])

Fig. 5 Level of detail rendering for interactive exploration ((a) Rendering of isosurfaces in the original datasets at full image resolution; (b) Rendering the isosurfaces in the original datasets at 1/4 the image resolution and upscaling to full image resolution; (c) Rendering the isosurfaces in the low-pass filtered and down-sampled datasets with half the resolution in each dimension at full image resolution[14])

图6 直接体绘制流程概览

Fig. 6 Overview of direct volume rendering pipeline

图7 直接体绘制采样步骤

Fig. 7 Sampling steps of direct volume rendering

表2 优化三维渲染可视化效果技术对比表

Table 2 Comparison table of 3D rendering visualization effect optimization technology

渲染技术	特点	使用场景	优点	缺点
传递函数	体数据映射到图像属性	强调特定范围或结构	提供用户控制，优化可视化效果	调整参数需要一定专业知识
光线投射	跟踪光线路径计算颜色和亮度	处理非平面表面和实体	速度快	未考虑复杂光照
全局照明	模拟光的多次反射和折射	需要高度真实感的场景	光影效果逼真	计算复杂度高，实时性差
环境光遮蔽	不直接计算光线路径或分布，基于局部情况模拟阴影效果	实时性要求高、细节要求不那么精确的场景	计算效率高，适用性广	可能产生不真实的阴影，对细节的呈现不够精确
深度学习	灵活，选择度高	用于多种渲染任务	高质量渲染	计算成本高，训练复杂

图8 脊柱和骨盆多发创伤性骨折的非增强三维CT图像((a)-(b) CR和VR均显示肋骨、腰椎横突、骶骨和耻骨多发性骨折[61])

Fig. 8 Non-enhanced 3-D CT images of multiple traumatic fractures of the spine and pelvis ((a)-(b) Both CR and VR demonstrate multiple fractures of the ribs, lumbal transverse processes, sacrum, and pubic bones[61])

图9 结合定向环境光遮挡和阴影生成获得的结果 ((a)盆景；(b)背包；(c)膝盖CT；(d)脚。左侧是具有定向遮挡的发射和吸收照明模型；右侧添加了Blinn-Phong阴影[63])

Fig. 9 Achieved results combining directional ambient occlusion and shadow generation ((a) Bonsai; (b) Backpack; (c) CT-Knee; (d) Foot. On the left, emission and absorption illumination model with directional occlusion; On the right, shadows with Blinn-Phong shading are added[63])

图10 使用自动微分重建传递函数((a)初始化传递函数渲染的图像；(b)重建传递函数渲染生成的图像；(c)参考图像)

Fig. 10 Reconstruct transfer functions with automatic differentiation ((a) Image rendered with the initialized transfer function; (b) Image rendered with the reconstructed transfer function; (c) Reference image)

图11 系统架构和工作流程[89]

Fig. 11 System architecture and workflow[89]

表3 优化三维渲染可视化效果的方法对比

Table 3 Comparison of methods for optimizing 3D rendering visual effects

方法	任务	数据集	SSIM	PSNR/dB
路径追踪^[50]	全局照明	Backpack	0.997	49.663
路径追踪^[50]	全局照明	Wrasse	0.998	53.545
DVAO^[65]	环境光遮挡	Chameleon	0.866	-
GAN+cGAN^[67]	模拟全局照明	Deep illumination	0.968	34.170
DNN^[81]	图像合成	CT-chest	-	24.900
可微分渲染^[86]	TF优化	CT-chest	0.990	36.700
可微分渲染^[86]	TF优化	Tooth	0.988	34.800

参考文献 92

[1]	RITTER F, BOSKAMP T, HOMEYER A, et al. Medical image analysis[J]. IEEE Pulse, 2011, 2(6): 60-70. DOI PMID
[2]	KRUPINSKI E A, JIANG Y L. Anniversary paper: evaluation of medical imaging systems[J]. Medical Physics, 2008, 35(2): 645-659. DOI PMID
[3]	BEYER T, BAILEY D L, BIRK U J, et al. Medical physics and imaging-a timely perspective[J]. Frontiers in Physics, 2021, 9: 634693.
[4]	VISUTSAK P. Marching cubes and histogram pyramids for 3d medical visualization[J]. Journal of Imaging, 2020, 6(9): 88.
[5]	RUIJTERS D. Dynamic resolution in GPU-accelerated volume rendering to autostereoscopic multiview lenticular displays[J]. EURASIP Journal on Advances in Signal Processing, 2008, 2009: 843753.
[6]	STREEB D, EL-ASSADY M, KEIM D A, et al. Why visualize? Arguments for visual support in decision making[J]. IEEE Computer Graphics and Applications, 2021, 41(2): 17-22.
[7]	COMANICIU D, ENGEL K, GEORGESCU B, et al. Shaping the future through innovations: from medical imaging to precision medicine[J]. Medical Image Analysis, 2016, 33: 19-26. DOI PMID
[8]	陈志坚, 俞建达, 池小斌, 等. 三维可视化技术在腹腔镜肝巨大肿瘤切除中的应用价值[J]. 中华肝脏外科手术学电子杂志, 2024, 13(3): 302-307.
	CHEN Z J, YU J D, CHI X B, et al. Application value of three-dimensional visualization technology in laparoscopic resection of huge liver tumors[J]. Chinese Journal of Hepatic Surgery (Electronic Edition), 2024, 13(3): 302-307 (in Chinese).
[9]	YUAN Q, CHEN X M, ZHAI J, et al. Application of 3D modeling and fusion technology of medical image data in image teaching[J]. BMC Medical Education, 2021, 21(1): 184.
[10]	ZHANG Y, FENG H B, ZHAO Y, et al. Exploring the application of the artificial-intelligence-integrated platform 3D Slicer in medical imaging education[J]. Diagnostics, 2024, 14(2): 146.
[11]	COLL D M, HERTS B R, DAVROS W J, et al. Preoperative use of 3D volume rendering to demonstrate renal tumors and renal anatomy[J]. Radiographics, 2000, 20(2): 431-438. PMID
[12]	LORENSEN W E, CLINE H E. Marching cubes: a high resolution 3D surface construction algorithm[M]//WOLFE R. Seminal Graphics: Pioneering Efforts That Shaped The Field. New York: ACM, 1998: 347-353.
[13]	VAN GELDER A, WILHELMS J. Topological considerations in isosurface generation[J]. ACM Transactions on Graphics (TOG), 1994, 13(4): 337-375.
[14]	WEISS S, CHU M Y, THUEREY N, et al. Volumetric isosurface rendering with deep learning-based super-resolution[J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27(6): 3064-3078.
[15]	DREBIN R A, CARPENTER L, HANRAHAN P. Volume rendering[J]. ACM SIGGRAPH Computer Graphics, 1988, 22(4): 65-74.
[16]	JUNG Y, KIM J, BI L, et al. A direct volume rendering visualization approach for serial PET-CT scans that preserves anatomical consistency[J]. International Journal of Computer Assisted Radiology and Surgery, 2019, 14(5): 733-744. DOI PMID
[17]	CABRAL D, RAMTOHUL P, FRADINHO A C, et al. Volume rendering of deep retinal age-related microvascular anomalies[J]. Ophthalmology Retina, 2022, 6(12): 1185-1193.
[18]	IGLESIAS-GUITIAN J A, MANE P, MOON B. Real-time denoising of volumetric path tracing for direct volume rendering[J]. IEEE Transactions on Visualization and Computer Graphics, 2022, 28(7): 2734-2747.
[19]	IŞIK M, MULLIA K, FISHER M, et al. Interactive Monte Carlo denoising using affinity of neural features[J]. ACM Transactions on Graphics (TOG), 2021, 40(4): 37.
[20]	LI Y H, SANG X Z, XING S J, et al. Real-time volume data three-dimensional display with a modified single-pass multiview rendering method[J]. Optical Engineering, 2020, 59(10): 102412.
[21]	ATHAWALE T M, MA B, SAKHAEE E, et al. Direct volume rendering with nonparametric models of uncertainty[J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27(2): 1797-1807.
[22]	WEISS J, NAVAB N. Deep direct volume rendering: Learning visual feature mappings from exemplary images[EB/OL]. [2023-11-12]. https://arxiv.org/abs/2106.05429.
[23]	LJUNG P, KRÜGER J, GROLLER E, et al. State of the art in transfer functions for direct volume rendering[J]. Computer Graphics Forum, 2016, 35(3): 669-691.
[24]	KHAN N M, KSANTINI R, GUAN L. A novel image-centric approach toward direct volume rendering[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2018, 9(4): 42.
[25]	CAI L L, NGUYEN B P, CHUI C K, et al. A two-level clustering approach for multidimensional transfer function specification in volume visualization[J]. The Visual Computer, 2017, 33(2): 163-177.
[26]	MA J, MUAD Y A, CHEN J J. Visualization of medical volume data based on improved k-means clustering and segmentation rules[J]. IEEE Access, 2021, 9: 100498-100512.
[27]	JUNG Y, KIM J, KUMAR A, et al. Feature of interest-based direct volume rendering using contextual saliency-driven ray profile analysis[J]. Computer Graphics Forum, 2018, 37(6): 5-19.
[28]	LUNDSTRÖM C, LJUNG P, YNNERMAN A. Extending and simplifying transfer function design in medical volume rendering using local histograms[C]// The 7th Joint Eurographics/IEEE VGTC Conference on Visualization. Goslar: Eurographics Association, 2005: 263-270.
[29]	LAN Y S, DING Y M, LUO X, et al. A clustering based transfer function for volume rendering using gray-gradient mode histogram[J]. IEEE Access, 2019, 7: 80737-80747.
[30]	SALHI M, KSANTINI R, ZOUARI B. A real-time image-centric transfer function design based on incremental classification[J]. Journal of Real-Time Image Processing, 2022, 19(1): 185-203.
[31]	KIM S, JANG Y, KIM S E. Image-based TF colorization with CNN for direct volume rendering[J]. IEEE Access, 2021, 9: 124281-124294.
[32]	AN H, KIM J, SHENG B, et al. A transfer function optimization using visual saliency for region of interest-based direct volume rendering[J]. Displays, 2023, 80: 102531.
[33]	MA B, ENTEZARI A. Volumetric feature-based classification and visibility analysis for transfer function design[J]. IEEE Transactions on Visualization and Computer Graphics, 2018, 24(12): 3253-3267.
[34]	JUNG Y Y, KONG J, KIM J. A transfer function design using a knowledge database based on deep image and primitive intensity profile features retrieval[EB/OL]. [2023-11-12]. https://www.sciopen.com/article/10.1007/s11390-024-3419-7.
[35]	WEISS S, WESTERMANN R. Differentiable direct volume rendering[J]. IEEE Transactions on Visualization and Computer Graphics, 2022, 28(1): 562-572.
[36]	NEUHAUSER C, WESTERMANN R. Transfer function optimization for comparative volume rendering[EB/OL]. [2023-06-09]. https://arxiv.org/abs/2306.05885.
[37]	KANG J, LEE J, SHIN Y G, et al. Depth-of-field rendering using progressive lens sampling in direct volume rendering[J]. IEEE Access, 2020, 8: 93335-93345.
[38]	KRAFT V, LINK F, SCHENK A, et al. Adaptive illumination sampling for direct volume rendering[C]// The 37th Computer Graphics International Conference. Cham: Springer, 2020: 107-118.
[39]	王芳, 秦磊华. 基于BRDF和GPU并行计算的全局光照实时渲染[J]. 图学学报, 2016, 37(5): 583-591. DOI
	Wang F, Qin L H. Global illumination real-time rendering based on BRDF and GPU parallel computing[J]. Journal of Graphics, 2016, 37(5): 583-591 (in Chinese).
[40]	徐翔, 吴小龙, 陈子凌, 等. 大规模三维场景光线追踪渲染方法综述[J/OL]. 计算机辅助设计与图形学学报, 2024: 1-17. (2024-04-17) [2024-07-24]. http://kns.cnki.net/kcms/detail/11.2925.tp.20240415.1158.002.html.
	Xu X, Wu X L, Chen Z L, et al. A survey of ray tracing rendering of large-scale scenes[J/OL]. Journal of Computer-Aided Design & Computer Graphics, 2024: 1-17. (2024-04-17) [2024-07-24]. http://kns.cnki.net/kcms/detail/11.2925.tp.20240415.1158.002.html (in Chinese).
[41]	HOFMANN N, MARTSCHINKE J, ENGEL K, et al. Neural denoising for path tracing of medical volumetric data[J]. Proceedings of the ACM on Computer Graphics and Interactive Techniques, 2020, 3(2): 13.
[42]	MYKHAYLOV P, VYATKIN S, CHEKHMESTRUK R, et al. Interactive volume rendering method using a 3D texture[C]// 2021 11th International Conference on Advanced Computer Information Technologies. New York: IEEE Press, 2021: 182-187.
[43]	SEO W, PARK S, IHM I. Efficient ray tracing of large 3D scenes for mobile distributed computing environments[J]. Sensors, 2022, 22(2): 491.
[44]	ZELLMANN S, SCHULZE J P, LANG U. Binned k-d tree construction for sparse volume data on multi-core and GPU systems[J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27(3): 1904-1915.
[45]	ZHOU J, WEN D S. Research on ray tracing algorithm and acceleration techniques using KD-tree[C]// 2021 6th International Conference on Intelligent Computing and Signal Processing. New York: IEEE Press, 2021: 107-110.
[46]	MARTSCHINKE J, HARTNAGEL S, KEINERT B, et al. Adaptive temporal sampling for volumetric path tracing of medical data[J]. Computer Graphics Forum, 2019, 38(4): 67-76. DOI
[47]	HUO Y C, YOON S E. A survey on deep learning-based Monte Carlo denoising[J]. Computational Visual Media, 2021, 7(2): 169-185.
[48]	DENISOVA E, MANETTI L, BOCCHI L, et al. AR²T: advanced realistic rendering technique for biomedical volumes[C]// The 26th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2023: 347-357.
[49]	ŠMAJDEK U, LESAR Ž, MAROLT M, et al. Combined volume and surface rendering with global illumination caching[J]. The Visual Computer, 2024, 40(4): 2491-2503.
[50]	YUAN Y L, YANG J Z, SUN Q, et al. Cinematic volume rendering algorithm based on multiple lights photon mapping[J]. Multimedia Tools and Applications, 2024, 83(2): 5799-5812.
[51]	SOYER P. Cinematic rendering: when virtuality comes true[J]. Diagnostic and Interventional Imaging, 2019, 100(9): 465-466. DOI PMID
[52]	RECHT H S, WEISBERG E M, FISHMAN E K. 3D CT cinematic rendering of pediatric thoracic vascular anomalies[J]. European Journal of Radiology Open, 2023, 10: 100485.
[53]	PRESTON S, LIU J, EISENBEIS L, et al. 3D CT urethrography with cinematic rendering (3DUG): a new modality for evaluation of complex urethral anatomy and assessment of the postoperative phalloplasty urethra[J]. Urology, 2023, 174: 212-217.
[54]	FUKUMOTO W, KITERA N, MITANI H, et al. Global illumination rendering versus volume rendering for the forensic evaluation of stab wounds using computed tomography[J]. Scientific Reports, 2022, 12(1): 2452. DOI PMID
[55]	PACHOWSKY M L, MORF H, SIMON D, et al. Cinematic rendering in rheumatic diseases—Photorealistic depiction of pathologies improves disease understanding for patients[J]. Frontiers in Medicine, 2022, 9: 946106.
[56]	HU R, ZHANG X Y, LIU J, et al. Clinical application of cinematic rendering in maxillofacial fractures[J]. International Journal of Oral and Maxillofacial Surgery, 2022, 51(12): 1562-1569.
[57]	刘键, 程新歌, 胡容, 等. CT电影渲染技术用于膝关节粉碎性骨折[J]. 中国医学影像技术, 2022, 38(9): 1391-1394.
	LIU J, CHENG X G, HU R, et al. CT cinematic rendering technique for comminuted fractures of knee joint[J]. Chinese Journal of Medical Imaging Technology, 2022, 38(9): 1391-1394 (in Chinese).
[58]	JAVED A A, YOUNG R W C, HABIB J R, et al. Cinematic rendering: novel tool for improving pancreatic cancer surgical planning[J]. Current Problems in Diagnostic Radiology, 2022, 51(6): 878-883. DOI PMID
[59]	AL KHALIFAH A, ZIMMERMAN S L, FISHMAN E K. Visualization of acute aortic injury with cinematic rendering[J]. Emergency Radiology, 2022, 29(6): 1043-1048.
[60]	STEFFEN T, WINKLHOFER S, STARZ F, et al. Three-dimensional perception of cinematic rendering versus conventional volume rendering using CT and CBCT data of the facial skeleton[J]. Annals of Anatomy-Anatomischer Anzeiger, 2022, 241: 151905.
[61]	DAPPA E, HIGASHIGAITO K, FORNARO J, et al. Cinematic rendering-an alternative to volume rendering for 3D computed tomography imaging[J]. Insights Into Imaging, 2016, 7(6): 849-856.
[62]	ABBAS F, MALAH M, BABAHENINI M C. Attentional conditional generative adversarial network for ambient occlusion approximation[C]// The 2nd International Conference on Intelligent Systems and Pattern Recognition. Cham: Springer, 2022: 349-361.
[63]	CAMPAGNOLO L Q, CELES W. Interactive directional ambient occlusion and shadow computations for volume ray casting[J]. Computers & Graphics, 2019, 84: 66-76.
[64]	GAUTRON P. Real-time ray-traced ambient occlusion of complex scenes using spatial hashing[C]// Special Interest Group on Computer Graphics and Interactive Techniques Conference Talks. New York: ACM, 2020: 5.
[65]	ENGEL D, ROPINSKI T. Deep volumetric ambient occlusion[J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27(2): 1268-1278.
[66]	REN L, SONG Y. AOGAN: a generative adversarial network for screen space ambient occlusion[J]. Computational Visual Media, 2022, 8(3): 483-494.
[67]	ABBAS F, MALAH M, BABAHENINI M C. Approximating global illumination with ambient occlusion and environment light via generative adversarial networks[J]. Pattern Recognition Letters, 2023, 166: 209-217.
[68]	SINGH S P, WANG L P, GUPTA S, et al. 3D deep learning on medical images: a review[J]. Sensors, 2020, 20(18): 5097.
[69]	ESTEVA A, CHOU K, YEUNG S, et al. Deep learning-enabled medical computer vision[J]. NPJ Digital Medicine, 2021, 4(1): 5. DOI PMID
[70]	JAVAN R, MOSTAGHNI N. AI-powered hyperrealism: next step in cinematic rendering?[J]. Radiology, 2024, 310(1): e231971.
[71]	ALTAF F, ISLAM S M S, AKHTAR N, et al. Going deep in medical image analysis: concepts, methods, challenges, and future directions[J]. IEEE Access, 2019, 7: 99540-99572.
[72]	PANAYIDES A S, AMINI A, FILIPOVIC N D, et al. AI in medical imaging informatics: current challenges and future directions[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 24(7): 1837-1857. DOI PMID
[73]	WANG C L, HAN J. DL4SciVis: a state-of-the-art survey on deep learning for scientific visualization[J]. IEEE Transactions on Visualization and Computer Graphics, 2023, 29(8): 3714-3733.
[74]	王稚儒, 常远, 鲁鹏, 等. 神经辐射场加速算法综述[J]. 图学学报, 2024, 45(1): 1-13. DOI
	WANG Z R, CHANG Y, LU P, et al. A review on neural radiance fields acceleration[J]. Journal of Graphics, 2024, 45(1): 1-13 (in Chinese). DOI
[75]	李洪安, 郑峭雪, 陶若霖, 等. 基于深度学习的图像超分辨率研究综述[J]. 图学学报, 2023, 44(1): 1-15. DOI
	LI H A, ZHENG Q X, TAO R L, et al. Review of image super-resolutionbased on deep learning[J]. Journal of Graphics, 2023, 44(1): 1-15 (in Chinese).
[76]	常远, 盖孟. 基于神经辐射场的视点合成算法综述[J]. 图学学报, 2021, 42(3): 376-384.
	CHANG Y, GAI M. A review on neural radiance fields based view synthesis[J]. Journal of Graphics, 2021, 42(3): 376-384 (in Chinese).
[77]	BERGER M, LI J X, LEVINE J A. A generative model for volume rendering[J]. IEEE Transactions on Visualization and Computer Graphics, 2019, 25(4): 1636-1650.
[78]	KAZEMINIA S, BAUR C, KUIJPER A, et al. GANs for medical image analysis[J]. Artificial Intelligence in Medicine, 2020, 109: 101938.
[79]	XIE N, LU Y F, LIU C. Web3D client-enhanced global illumination via GAN for health visualization[J]. IEEE Access, 2020, 8: 13270-13281.
[80]	LIU C, SONG H L, FANG T, et al. Web-cloud collaborative mobile online 3D rendering system[EB/OL]. [2023-11-13]. http://downloads.hindawi.com/journals/scn/2022/4748946.pdf.
[81]	HONG F, LIU C, YUAN X R. DNN-VolVis: interactive volume visualization supported by deep neural network[C]// 2019 IEEE Pacific Visualization Symposium. New York: IEEE Press, 2019: 282-291.
[82]	FUJIOKA T, YASHIMA Y, OYAMA J, et al. Deep-learning approach with convolutional neural network for classification of maximum intensity projections of dynamic contrast-enhanced breast magnetic resonance imaging[J]. Magnetic Resonance Imaging, 2021, 75: 1-8. DOI PMID
[83]	KATO H, BEKER D, MORARIU M, et al. Differentiable rendering: a survey[EB/OL]. [2023-11-13]. https://arxiv.org/abs/2006.12057.
[84]	NIEMEYER M, MESCHEDER L, OECHSLE M, et al. Differentiable volumetric rendering: Learning implicit 3D representations without 3D supervision[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2020: 3501-3512.
[85]	COLE F, GENOVA K, SUD A, et al. Differentiable surface rendering via non-differentiable sampling[C]// 2021 IEEE/CVF International Conference on Computer Vision. New York: IEEE Press, 2021: 6068-6077.
[86]	PAN B, LU J Y, LI H X, et al. Differentiable design galleries: a differentiable approach to explore the design space of transfer functions[J]. IEEE Transactions on Visualization and Computer Graphics, 2024, 30(1): 1369-1379.
[87]	SINGH A, SENGUPTA S, LAKSHMINARAYANAN V. Explainable deep learning models in medical image analysis[J]. Journal of Imaging, 2020, 6(6): 52.
[88]	VAN DER VELDEN B H M, KUIJF H J, GILHUIJS K G A, et al. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis[J]. Medical Image Analysis, 2022, 79: 102470.
[89]	LIU L J, WANG L Z, HUANG Q S, et al. An efficient architecture for medical high-resolution images transmission in mobile telemedicine systems[J]. Computer Methods and Programs in Biomedicine, 2020, 187: 105088.
[90]	LAMBRU C, MOLDOVEANU F, MORAR A, et al. A framework for learning and rapid implementation of real-time global illumination methods[J]. Applied Sciences, 2022, 12(11): 5654.
[91]	ZHENG Q H, WANG J H, SHEN Y, et al. Adaptive resource allocation based on scoring mechanism and priority for 3D rendering[C]// 2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting. New York: IEEE Press, 2023: 1-5.
[92]	FU Z P, ZHOU J, XU W P, et al. GPU and VPU enabled virtual mobile infrastructure for 3-D image rendering and its application in telemedicine[J]. IEEE Internet of Things Journal, 2024, 11(5): 7724-7738.

优化医学影像三维渲染可视化效果：技术综述

Optimizing the visual effects of 3D rendering in medical imaging: a technical review

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 92

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李琼 , 考月英 , 张莹 , 徐沛 . 面向无人机航拍图像的目标检测研究综述[J]. 图学学报, 2024, 45(6): 1145-1164.
[2]	刘灿锋, 孙浩, 东辉. 结合 Transformer 与 Kolmogorov Arnold 网络的分子扩增时序预测研究[J]. 图学学报, 2024, 45(6): 1256-1265.
[3]	宋思程, 陈辰, 李晨辉, 王长波. 基于密度图多目标追踪的时空数据可视化[J]. 图学学报, 2024, 45(6): 1289-1300.
[4]	王宗继, 刘云飞, 陆峰. Cloud Sphere: 一种基于渐进式变形自编码的三维模型表征方法[J]. 图学学报, 2024, 45(6): 1375-1388.
[5]	胡凤阔, 叶兰, 谭显峰, 张钦展, 胡志新, 方清, 王磊, 满孝锋. 一种基于改进YOLOv8的轻量化路面病害检测算法[J]. 图学学报, 2024, 45(5): 892-900.
[6]	刘义艳, 郝婷楠, 贺晨, 常英杰. 基于DBBR-YOLO的光伏电池表面缺陷检测[J]. 图学学报, 2024, 45(5): 913-921.
[7]	翟永杰, 李佳蔚, 陈年昊, 王乾铭, 王新颖. 融合改进Transformer的车辆部件检测方法[J]. 图学学报, 2024, 45(5): 930-940.
[8]	姜晓恒, 段金忠, 卢洋, 崔丽莎, 徐明亮. 融合先验知识推理的表面缺陷检测[J]. 图学学报, 2024, 45(5): 957-967.
[9]	熊超, 王云艳, 罗雨浩. 特征对齐与上下文引导的多视图三维重建[J]. 图学学报, 2024, 45(5): 1008-1016.
[10]	胡欣, 常娅姝, 秦皓, 肖剑, 程鸿亮. 基于改进YOLOv8和GMM图像点集匹配的双目测距方法[J]. 图学学报, 2024, 45(4): 714-725.
[11]	牛为华, 郭迅. 基于改进YOLOv8的船舰遥感图像旋转目标检测算法[J]. 图学学报, 2024, 45(4): 726-735.
[12]	李滔, 胡婷, 武丹丹. 结合金字塔结构和注意力机制的单目深度估计[J]. 图学学报, 2024, 45(3): 454-463.
[13]	朱光辉, 缪君, 胡宏利, 申基, 杜荣华. 基于自增强注意力机制的室内单图像分段平面三维重建[J]. 图学学报, 2024, 45(3): 464-471.
[14]	王稚儒, 常远, 鲁鹏, 潘成伟. 神经辐射场加速算法综述[J]. 图学学报, 2024, 45(1): 1-13.
[15]	王欣雨, 刘慧, 朱积成, 盛玉瑞, 张彩明. 基于高低频特征分解的深度多模态医学图像融合网络[J]. 图学学报, 2024, 45(1): 65-77.