近期更新计划
主题是关于视网膜眼底图像的增强与分割
有关FA（荧光素血管造影），因其在分割中不宜于应用（数据集不够好）故不会再进行更新，Review（R）也不会进行论文总结。
11月
Dr-SAM: An End-to-End Framework for Vascular Segmentation, Diameter Estimation, and Anomaly Detection on Angiography Images.
FS-MedSAM2: Exploring the Potential of SAM2 for Few-Shot Medical Image Segmentation without Fine-tuning
Fundus2Angio: A Conditional GAN Architecture for Generating Fluorescein Angiography Images from Retinal Fundus Photography
GlanceSeg: Real-time microangioma lesion segmentation with gaze map-guided foundation model for early detection of diabetic retinopathy
LeSAM: Adapt Segment Anything Model for Medical Lesion Segmentation
R：Segment Anything Model (SAM) for Medical Image Segmentation: A Preliminary Review
R：A review of optic disc and optic cup segmentation based on fundus images
MAFE-Net: retinal vessel segmentation based on a multiple attention-guided fusion mechanism and ensemble learning network
（MAF-Net: Multiple attention-guided fusion network for fundus vascular image segmentation）
FA:Deep learning segmentation of non‑perfusion area from color fundus images and AI‑generated fluorescein angiography
FA: Multiple‑ResNet GAN: An enhanced high‑resolution image generation method for translation from fundus structure image to fluorescein angiography
Applications of Deep Learning in Fundus Images: A Review
Efficient and Robust Medical Image Segmentation Using Lightweight ViT-Tiny based SAM and Model Quantization 论文需要大修
FA:Translation of Color Fundus Photography into Fluorescein Angiography Using Deep Learning for Enhanced Diabetic Retinopathy Screening
FA:Fundus to Fluorescein Angiography Video Generation as a Retinal Generative Foundation Model （Running title: Fundus2Video as a Foundation Model ）
FA:A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs
12月：
CLASS A:
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation
Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Dr-SAM: U-Shape Structure Segment Anything Model for Generalizable Medical Image Segmentation
DS-TransUNet: Dual Swin Transformer U-Net for Medical Image Segmentation
Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes
One-Prompt to Segment All Medical Images
SAMedOCT: Adapting Segment Anything Model (SAM) for Retinal OCT
TriSAM: Tri-Plane SAM for zero-shot cortical blood vessel segmentation in VEM images
CLASS B:
AutoProSAM:AutomatedPromptingSAMfor3DMulti-OrganSegmentation
Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts
SAM-SP: Self-Prompting Makes SAM Great Again
SAM-U: Multi-box prompts triggered uncertainty estimation for reliable SAM in medical image
Self-Prompting Large Vision Models for Few-Shot Medical Image Segmentation
TP-DRSeg: Improving Diabetic Retinopathy Lesion Segmentation with Explicit Text-Prompts Assisted SAM
CLASS C:
EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction
EfficientViT-SAM:AcceleratedSegmentAnythingModel WithoutAccuracyLoss
Lite-SAM Is Actually What You Need for Segment Everything
MedficientSAM: A Robust Medical Segmentation Model with Optimized Inference Pipeline for Limited Clinical Settings