讲在前面
这部分是PART I和PART II。
论文目录
PART I
Optical Imaging(光学影像) | 概要 |
---|---|
1.Enhancing OCT Signal by Fusion of GANs: Improving Statistical Power of Glaucoma Clinical Trials 通过GAN融合增强OCT信号:提高青光眼临床试验的统计能力 |
|
2.A Deep Reinforcement Learning Framework for Frame-by-Frame Plaque Tracking on Intravascular Optical Coherence Tomography Image 用于血管内光学相干断层扫描图像的逐帧斑块跟踪的深度强化学习框架 |
|
3.Multi-index Optic Disc Quantification via MultiTask Ensemble Learning 通过多任务集成学习进行多指标光盘定量 |
|
4.Retinal Abnormalities Recognition Using Regional Multitask Learning 使用区域多任务学习的视网膜异常识别 |
|
5.Unifying Structure Analysis and Surrogate-Driven Function Regression for Glaucoma OCT Image Screening 青光眼OCT图像筛选的统一结构分析和替代驱动功能回归 |
|
6.Evaluation of Retinal Image Quality Assessment Networks in Different Color-Spaces 不同色彩空间中视网膜图像质量评估网络的评估 |
|
7.3D Surface-Based Geometric and Topological Quantification of Retinal Microvasculature in OCT-Angiography via Reeb Analysis 基于Reeb分析的OCT血管造影术中视网膜微血管的3D基于表面的几何和拓扑定量 |
肝内胆管癌、迁移学习 |
8.Limited-Angle Diffuse Optical Tomography Image Reconstruction Using Deep Learning 深度学习的有限角度漫射光学层析成像图像重建 |
开源代码、unet改进 |
9.Data-Driven Enhancement of Blurry Retinal Images via Generative Adversarial Networks 通过生成对抗网络进行数据驱动的模糊视网膜图像增强 |
神经影像 |
10.Dual Encoding U-Net for Retinal Vessel Segmentation 视网膜血管分割的双重编码U-Net |
增加数据多样性以提高模型泛化能力的反向操作,让模型忘记新加入的数据 |
11.A Deep Learning Design for Improving Topology Coherence in Blood Vessel Segmentation 改善血管分割中拓扑一致性的深度学习设计 |
皮肤影像、解决过拟合的一种网络、软硬标签 |
12.Boundary and Entropy-Driven Adversarial Learning for Fundus Image Segmentation 边界和熵驱动的对抗学习用于眼底图像分割 |
数据增强的方式 |
13.Unsupervised Ensemble Strategy for Retinal Vessel Segmentation 视网膜血管分割的无监督合并策略 |
小病种的分类方案 |
14.Fully Convolutional Boundary Regression for Retina OCT Segmentation 视网膜OCT分割的全卷积边界回归 |
开源代码、语义分割、CT/MRI/X等模态、自监督 |
15.PM-Net: Pyramid Multi-label Network for Joint Optic Disc and Cup Segmentation PM-Net:金字塔多标签网络,用于联合光盘和杯分割 |
胶囊网络、分类、病灶定位、CheXpert和RSNA肺炎数据集 |
16.Biological Age Estimated from Retinal Imaging: A Novel Biomarker of Aging 从视网膜成像估计生物年龄:生物年龄的新型标志 |
联合仿真框架、应对模型无法满足所有厂商CT影响的问题 |
17.Task Adaptive Metric Space for Medium-Shot Medical Image Classification 中等自适应医学图像分类的任务自适应度量空间 |
疾病诊断和分类、不忘旧知识学习新知识 |
18.Two-Stream CNN with Loose Pair Training for Multi-modal AMD Categorization 带有松散对训练的两流CNN用于多模式AMD分类 |
标签优化、监督学习 |
19.Deep Multi-label Classification in Affine Subspaces 仿射子空间中的深度多标签分类 |
神经图像 |
20.Multi-scale Microaneurysms Segmentation Using Embedding Triplet Loss 嵌入Triplet Loss的多尺度微动脉瘤分割 |
BraTs 2018、关节形状 |
21.A Divide-and-Conquer Approach Towards Understanding Deep Networks 一种理解深度网络的分而治之方法 |
注意力、食道癌 |
22.Multiclass Segmentation as Multitask Learning for Drusen Segmentation in Retinal Optical Coherence Tomography 视网膜光学相干断层扫描中玻璃疣分割的多类分割作为多任务学习 |
注意力、气管分割 |
23.Active Appearance Model Induced Generative Adversarial Network for Controlled Data Augmentation 用于受控数据增强的主动外观模型诱导的生成对抗网络 |
注意力、骨头 |
24.Biomarker Localization by Combining CNN Classifier and Generative Adversarial Network 结合CNN分类器和生成对抗网络进行生物标记定位 |
器官分割前的定位、注意力、胸部CT数据集、肾脏KiTS19 |
25.Probabilistic Atlases to Enforce Topological Constraints 概率图集可增强拓扑约束 |
高阶注意力、REFUGE和Drishti-GS1数据集、用于血管分割的DRIVE和用于肺分割的LUNA |
26.Synapse-Aware Skeleton Generation for Neural Circuits 用于神经回路的突触感知骨架生成 |
开源代码、不同器官细胞核语义分割、MoNuSAC 2020数据集 |
27.Seeing Under the Cover: A Physics Guided Learning Approach for In-bed Pose Estimation 幕后观察:对卧床姿势估计的物理指导学习方法 |
模型解释技术、黑盒可视化技术 |
28.EDA-Net: Dense Aggregation of Deep and Shallow Information Achieves Quantitative Photoacoustic Blood Oxygenation Imaging Deep in Human Breast EDA-Net:深层和浅层信息的密集聚集实现了人体乳房深处的定量光声血氧充氧成像 |
模型解释 |
29.Fused Detection of Retinal Biomarkers in OCT Volumes 对OCT中的视网膜生物标志进行混融合侦测 |
开源代码、胶囊网络 |
30.Vessel-Net: Retinal Vessel Segmentation Under Multi-path Supervision Vessel-Net:多路径监测下的视网膜血管分割 |
开源代码、医学图像检索系统 |
31.Ki-GAN: Knowledge Infusion Generative Adversarial Network for Photoacoustic Image Reconstruction In Vivo Ki-GAN:知识注入生成对抗网络,用于体内光声图像重建 |
数据与模型之间的关系解释 |
32.Uncertainty Guided Semi-supervised Segmentation of Retinal Layers in OCT Images OCT图像中不确定性指导的视网膜层半监督分割 |
模型解释技术 |
Endoscopy(内镜检查) | 概要 |
---|---|
33.Triple ANet: Adaptive Abnormal-aware Attention Network for WCE Image Classification Triple ANet:用于WCE图像分类的自适应异常感知注意力网络 |
劣质(损坏)注释修复 |
34.Selective Feature Aggregation Network with Area-Boundary Constraints for Polyp Segmentation 用于息肉分割的具有区域边界约束选择性特征聚合网络 |
UNet改进、边界位置和小组织上效果好 |
35.Deep Sequential Mosaicking of Fetoscopic Videos 胎镜检查视频的深度序列拼接 |
稀有疾病的诊断和分类、ISIC 2018皮肤病灶分类数据 |
36.Landmark-Guided Deformable Image Registration for Supervised Autonomous Robotic Tumor Resection 具有里程碑意义的可指导自主性肿瘤切除的可变形图像配准 |
脑细胞分类、解决新数据加入模型从头训练的问题 |
37.Multi-view Learning with Feature Level Fusion for Cervical Dysplasia Diagnosis |