Medical Image Segmentation Architectures

Transformer-based Architectures

• PVTFormer – CT Liver Segmentation via PVT-based Encoding and Refined Decoding (ISBI 2024)
• MDNet – Multi-Decoder Network for Abdominal CT Organs Segmentation (2024)
• TransNetR – Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing (MIDL 2023)
• TransRUPNet – Improved Out-of-Distribution Generalization in Polyp Segmentation

CNN-based Architectures

• DoubleUNet – Deep Convolutional Network for Medical Image Segmentation
• ResUNet++ – Advanced Architecture for Medical Image Segmentation
• ResUNet++ + CRF + TTA – Comprehensive Polyp Segmentation Study
• ColonSegNet – Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy
• NanoNet – Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy
• DDANet – Dual Decoder Attention Network for Automatic Polyp Segmentation
• LightLayers – Parameter Efficient Dense and Convolutional Layers for Classification

Attention-based & Hybrid Models

• PNS-Net – Progressively Normalized Self-Attention Network for Video Polyp Segmentation
• UNet – U-Net Architecture for Surgical Image Segmentation (ROBUST-MIS Challenge)

Code & Papers

Source code for these architectures is available on my GitHub page.

Corresponding publications can be found on Google Scholar.