深度学习-计算机视觉(CV)-医学图像分割

前言

记录一下研究生阶段的研究方向(医学图像分割)所看的论文以及所使用的数据集资源.

每日会对内容进行更新补充！

---

一、论文

1. 15篇CV领域经典论文

(1)Receptive fields, binocular interaction and functional architecture in the cat's visual cortex

(2)Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position

(3) Gradient-based learning applied to document recognition

(4) Reducing the dimensionality of data with neural networks

(5) ImageNet Classification with Deep Convolutional Neural Networks

(6)Visualizing and understanding convolutional networks

(7) Very Deep Convolutional Networks for Large-Scale Image Recognition

(8) Network in network

(9) Going deeper with convolutions

(10) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

(11) Deep Residual Learning for Image Recognition

(12) Xception: Deep Learning With Depthwise Separable Convolutions

(13) DenseNet: Implementing Efficient ConvNet Descriptor Pyramids

(14) Mobilenets: Efficient convolutional neural networks for mobile vision applications

(15) Learning Transferable Architectures for Scalable Image Recognition

2.图像分割方向值得关注的模型及论文

(1)ViT : An image is worth 16x16 words: Transformers for image recognition at scale

(2)SwinUnter: Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis

(3)DAU-Net : DAU-Net: A Regression Cell Counting Method

(4)TransBTS : TransBTS: Multimodal Brain Tumor Segmentation Using Transformer

(5)TransUNet:TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

(6)SegFormer : SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

(7)SegNet : SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

(8) MultiResUNet : MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentation

(9)RRUnet : A Dense U-Net with Cross-Layer Intersection for Detection and Localization of Image Forgery

(10)UNet++ : UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation

(11)UNet 3+ : UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation

(12)SegGAN : Semantic Segmentation using Adversarial Networks

(13)FCN : Fully Convolutional Networks for Semantic Segmentation

(14)Attention-UNet : Attention U-Net: Learning Where to Look for the Pancreas

(15)V-Net : V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

(16) nn-UNet : nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation

3.扩散模型相关

(1)开山之作**:Deep Unsupervised Learning using Nonequilibrium Thermodynamics**

(2)DDPM : Denoising Diffusion Probabilistic Models

(3)IDDPM : Improved Denoising Diffusion Probabilistic Models

(4)生成能力超越GAN : Diffusion Models Beat GANs on Image Synthesis

(5)CLASSIFIER-FREE DIFFUSION GUIDANCE

(6)DDIM : Denoising Diffusion Implicit Models

(7)Score-Based Generative Modeling through Stochastic Differential Equations

(8)DELL E 2 : Hierarchical Text-Conditional Image Generation with CLIP Latents

(9)GLIDE:GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

(10)DIFFUSION MODELS IN MEDICAL IMAGING: A COMPREHENSIVE SURVEY

(11) Understanding Diffusion Models: A Unified Perspective

4.扩散模型+图像分割

(1) Can Segmentation Models Be Trained with Fully Synthetically Generated Data?

(2) Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation

(3) SegDiff : SegDiff: Image Segmentation with Diffusion Probabilistic Models

(4) MedSegDiff : MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model

(5) Label-Efficient Semantic Segmentation with Diffusion Models

(6) Accelerating diffusion models via pre-segmentation diffusion sampling for medical image segmentation

(7) Object Segmentation Without Labels with Large-Scale Generative Models

(8)Diffusion Models for Implicit Image Segmentation Ensembles

(9) MedSegDiff-V2: Diffusion-Based Medical Image Segmentation with Transformer

(10) Ambiguous Medical Image Segmentation Using Diffusion Models

(11) DENOISING DIFFUSION MEDICAL MODELS

(12) Stochastic Segmentation with Conditional Categorical Diffusion Models

(13) DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change Detection

(14)Denoising Pretraining for Semantic Segmentation

(15) Diffusion models as plug-and-play priors

(16) Brain tumor segmentation using synthetic MR images - A comparison of GANs and diffusion models

(17) Diff-UNet : Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation

(18) DermoSegDiff : DermoSegDiff: A Boundary-Aware Segmentation Diffusion Model for Skin Lesion Delineation

(19) Certification of Deep Learning Models for Medical Image Segmentation

(20) Diffusion models in medical imaging: A comprehensive survey

(21) Stochastic Segmentation with Conditional Categorical Diffusion Models

(22) One-Shot Unsupervised Domain Adaptation With Personalized Diffusion Models

(23) Mutual Graph Learning Network and Diffusion Probabilistic Model-based Medical Image Segmentation

(24) Diffusion and Multi-Domain Adaptation Methods for Eosinophil Segmentation

(25) Analysing Diffusion Segmentation for Medical Images

(26) Polyp-DDPM: Diffusion-Based Semantic Polyp Synthesis for Enhanced Segmentation

(27) Surf-CDM: Score-Based Surface Cold-Diffusion Model for Medical Image Segmentation

(28) Masked Diffusion as Self-supervised Representation Learner

(29) Robust semi-supervised segmentation with timestep ensembling diffusion models

(30) A 3D Generative Model of Pathological Multi-modal MR Images and Segmentations

(31) Introducing Shape Prior Module in Diffusion Model for Medical Image Segmentation

(32) [Pre-training with Diffusion Models for Dental Radiography Segmentation]( "Pre-training with Diffusion Models for Dental Radiography Segmentation")

(33) LSegDiff: A Latent Diffusion Model for Medical Image Segmentation

待补充 。。。。。。

二、数据集

1. BraTS

年份	总病例数	训练集病例数	验证集病例数	测试集病例数
2012	50	35	无	15
2013	60	35	无	25
2014	238	200	无	38
2015	274	200	无	74
2016	391	200	无	191
2017	477	285	46	146
2018	542	285	66	191
2019	626	335	125	166
2020	660	369	125	166
2021	2040	1251	219	570

注：点击年份可以直接跳转到相关数据集界面。

2.MSD Task01 (BraTS)

论文：The Medical Segmentation Decathlon

数据集：Task01

3.MSD Tsk03 (LiTS2017)

数据集：LiTS

4. Cityscapes

数据集：Cityscapes

---

待更，之后预计更新图像分割中Transformer方向和Diffusion Models方向的论文。还有一些自己用到的其他数据集，如LiTS等。