基于深度学习的医疗影像论文汇总（Deep Learning Papers on Medical Image Analysis）

2017 年 10 月 21 日 AI研习社 周康

本文摘自知乎专栏AI医疗影像进阶之路，原文作者Shadi Albarqouni，译者为周康。

看到好东西，怎么能不分享呢。

第一次在知乎翻译，由于水平有限（不是谦虚的那种有限，是真的有限），有不准确的地方还望包涵，最重要的是，还望大佬们多多指正！

Background

To the best of our knowledge, this is the first list of deep learning papers on medical applications. There are couple of lists for deep learning papers in general, or computer vision, for example Awesome Deep Learning Papers（http://t.cn/R5GgRIi）. In this list, I try to classify the papers based on their deep learning techniques and learning methodology. I believe this list could be a good starting point for DL researchers on Medical Applications.

这是第一个基于深度学习的医疗影像论文汇总。github上还有一些基于深度学习的计算机视觉论文汇总，比如Awesome Deep Vision（http://t.cn/RLvTzjn）；以及一些不限于应用的深度学习论文汇总，比如Awesome Deep Learning Papers（http://t.cn/R5GgRIi）。在这个汇总里，我会尽量根据不同的深度学习技术（deep learning techniques）和学习方法（learning methodology）去分类。

Criteria

1，A list of top deep learning papers published since 2015.
2，Papers are collected from peer-reviewed journals and high reputed conferences. However, it may have recent papers on arXiv.
3，A meta-data is required along with the paper, i.e. Deep Learning technique, Imaging Modality, Area of Interest, Clinical Database (DB).

自2015年起，顶会顶刊上的深度学习论文;
同行评议的期刊和知名度较高的会议，以及最近的arXiv（arXiv:CV & PR：http://t.cn/RWAEJSI）论文。

医疗论文期刊/会议：

Medical Image Analysis (MedIA)（http://t.cn/RWAEWNJ）
IEEE Transaction on Medical Imaging (IEEE-TMI)（https://ieee-tmi.org/）
IEEE Transaction on Biomedical Engineering (IEEE-TBME)（https://tbme.embs.org/）

PS：暑假师兄做的work投到了TBME，最近我接着师兄的work继续做。我们的任务是Kaggle比赛的糖尿病视网膜病变检测（Diabetic Retinopathy Detection ）。

IEEE Journal of Biomedical and Health Informatics (IEEE-JBHI)（http://t.cn/RWAnkiL）
International Journal on Computer Assisted Radiology and Surgery (IJCARS)（http://t.cn/zOTPHNL）
International Conference on Information Processing in Medical Imaging (IPMI)
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
International Conference on Information Processing in Computer-Assisted Interventions (IPCAI)
IEEE International Symposium on Biomedical Imaging (ISBI)

Shortcuts

3.1，深度学习技术：

NN: Neural Networks
MLP: Multilayer Perceptron
RBM: Restricted Boltzmann Machine
SAE: Stacked Auto-Encoders
CAE: Convolutional Auto-Encoders
CNN: Convolutional Neural Networks
RNN: Recurrent Neural Networks
LSTM: Long Short Term Memory
M-CNN: Multi-Scale/View/Stream CNN
FCN: Fully Convolutional Networks

3.2，成像方式：

US: Ultrasound
MR/MRI: Magnetic Resonance Imaging
PET: Positron Emission Tomography
MG: Mammography
CT: Computed Tompgraphy
H&E: Hematoxylin & Eosin Histology Images
RGB: Optical Images

4.1，Deep Learning Techniques

AutoEncoders/ Stacked AutoEncoders（http://t.cn/RWAuKrS）
Convolutional Neural Networks（http://t.cn/RWAuHGU）
Recurrent Neural Networks（http://t.cn/RWAu119）
Generative Adversarial Networks（http://t.cn/RWA3v8q）

4.2，Medical Applications

Annotation（http://t.cn/RWA3fHN）
Classification（http://t.cn/RWA39G5）
Detection/ Localization（http://t.cn/RWA3lOL）
Segmentation（http://t.cn/RWA3RoL）
Registration（http://t.cn/RWA3dJZ）
Regression（http://t.cn/RWA1Ply）
Other tasks（http://t.cn/RWA12NV）

Deep Learning Techniques

5.1，Auto-Encoders/ Stacked Auto-Encoders

5.2，Convolutional Neural Networks

AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images（http://t.cn/RWA1lmT）
Fast Convolutional Neural Network Training Using Selective Data Sampling: Application to Hemorrhage Detection in Color Fundus Images（http://t.cn/RWA1Rma）

5.3，Recurrent Neural Networks

5.4，Generative Adversarial Networks

Medical Applications

Annotation

Deep learning of feature representation with multiple instance learning for medical image analysis（http://t.cn/RWA1FkV）
AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images （http://t.cn/RWABUT7）

Classification

Multi-scale Convolutional Neural Networks for Lung Nodule Classification（http://t.cn/RWADf0A）
Predicting Alzheimer's disease: a neuroimaging study with 3D convolutional neural networks （http://t.cn/RWADSK4）
Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep Learning （http://t.cn/RWADYxw）
Quantifying Radiographic Knee Osteoarthritis Severity using Deep Convolutional Neural Networks （http://t.cn/RWADk5G）
A Deep Semantic Mobile Application for Thyroid Cytopathology （http://t.cn/RWAko5r）
Alzheimer's Disease Diagnostics by a Deeply Supervised Adaptable 3D Convolutional Network （http://t.cn/RWAkcoj）
Multi-resolution-tract CNN with hybrid pretrained and skin-lesion trained layers （http://t.cn/RWAkWVF）
Towards Automated Melanoma Screening: Exploring Transfer Learning Schemes （http://t.cn/RWAkEnF）
Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks （http://t.cn/RWAF7qb）
3D Deep Learning for Multi-modal Imaging-Guided Survival Time Prediction of Brain Tumor Patients （http://t.cn/RWAkkPX）
Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans （http://t.cn/RWAFyHc）
Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring （http://t.cn/RWAFILN）
Spectral Graph Convolutions for Population-based Disease Prediction （http://t.cn/RWAFohq）
SurvivalNet: Predicting patient survival from diffusion weighted magnetic resonance images using cascaded fully convolutional and 3D convolutional neural networks （http://t.cn/RWAFYuV）

Detection / Localization

3D Deep Learning for Efficient and Robust Landmark Detection in Volumetric Data （http://t.cn/RWAstTB）
Standard Plane Localization in Fetal Ultrasound via Domain Transferred Deep Neural Networks （http://t.cn/RWAs6xr）
Automated anatomical landmark detection ondistal femur surface using convolutional neural network （http://t.cn/RWAsYbY）
Automatic Fetal Ultrasound Standard Plane Detection Using Knowledge Transferred Recurrent Neural Networks （http://t.cn/RWAsn1T）
Regressing Heatmaps for Multiple Landmark Localization using CNNs （http://t.cn/RW2vv2L）
An artificial agent for anatomical landmark detection in medical images （http://t.cn/RW2vy2P）
Real-time Standard Scan Plane Detection and Localisation in Fetal Ultrasound using Fully Convolutional Neural Networks （http://t.cn/RW2vft1）
Recognizing end-diastole and end-systole frames via deep temporal regression network （http://t.cn/RW2vrQW）
Improving Computer-Aided Detection Using Convolutional Neural Networks and Random View Aggregation Neural Networks （http://t.cn/RW2vrQW）
Automated detection of pulmonary nodules in PET/CT images: Ensemble false-positive reduction using a convolutional neural network technique Neural Networks （http://t.cn/RW2hTcw）
Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks （http://t.cn/RW2Pu8C）
Self-Transfer Learning for Fully Weakly Supervised Lesion Localization （http://t.cn/RW27xd4）
Fast Convolutional Neural Network Training Using Selective Data Sampling: Application to Hemorrhage Detection in Color Fundus Images （http://t.cn/RWA1Rma）

Segmentation

Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation （http://t.cn/RW27lTz）
Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields （http://t.cn/RW27n2Y）
Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks （http://t.cn/RibGTxx）
SurvivalNet: Predicting patient survival from diffusion weighted magnetic resonance images using cascaded fully convolutional and 3D convolutional neural networks （http://t.cn/RWAFYuV）
q-Space Deep Learning: Twelve-Fold Shorter and Model-Free Diffusion MRI （http://t.cn/RW2zfRN）(Section II.B.2)

Registration

An Artificial Agent for Robust Image Registration （http://t.cn/RW2zWw4）

Regression

Automated anatomical landmark detection ondistal femur surface using convolutional neural network （http://t.cn/RWAsYbY）
q-Space Deep Learning: Twelve-Fold Shorter and Model-Free Diffusion MRI （http://t.cn/RW2zfRN）(Section II.B.1）