Ultrasound Image Segmentation

Ultrasound image segmentation aims to automatically identify and delineate anatomical structures and lesions within ultrasound images, facilitating faster and more accurate diagnoses. Current research heavily utilizes convolutional neural networks (CNNs), often incorporating architectures like U-Net and its variants, along with transformer-based models and the Segment Anything Model (SAM), adapted and enhanced for the unique challenges of ultrasound imagery (e.g., low contrast, noise). These advancements hold significant promise for improving diagnostic accuracy, reducing workload for medical professionals, and enabling new applications in areas such as robotic-assisted procedures and quantitative image analysis.

Papers

August 18, 2023

Can ultrasound confidence maps predict sonographers' labeling variability?
Vanessa Gonzalez Duque, Leonhard Zirus, Yordanka Velikova, Nassir Navab, Diana Mateus
Deep Learning Ultrasound Image Segmentation Confidence Map Ultrasound Dataset

August 14, 2023

CEmb-SAM: Segment Anything Model with Condition Embedding for Joint Learning from Heterogeneous Datasets
Dongik Shin, Beomsuk Kim, Seungjun Baek
Segment Anything Model Joint Learning Medical Image Segmentation Task Robust Segmentation Heterogeneous Datasets Ultrasound Image Segmentation

May 30, 2023

Multi-source adversarial transfer learning for ultrasound image segmentation with limited similarity
Yifu Zhang, Hongru Li, Tao Yang, Rui Tao, Zhengyuan Liu, Shimeng Shi, Jiansong Zhang, Ning Ma, Wujin Feng, Zhanhu Zhang, Xinyu Zhang
Transfer Learning Multi Source Ultrasound Image Segmentation Adversarial Transfer

May 16, 2023

Multi-Level Global Context Cross Consistency Model for Semi-Supervised Ultrasound Image Segmentation with Diffusion Model
Fenghe Tang, Jianrui Ding, Lingtao Wang, Min Xian, Chunping Ning
Diffusion Model Semi Supervised Learning Segmentation Network Ultrasound Image Segmentation Context Perturbation Context Consistency

March 22, 2023

MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization
Yuan Bi, Zhongliang Jiang, Ricarda Clarenbach, Reza Ghotbi, Angelos Karlas, Nassir Navab
Medical Image Segmentation Domain Generalization Ultrasound Image Segmentation Anatomical Landmark Domain Invariant Encoder Independent Segmentation

February 22, 2023

Slim U-Net: Efficient Anatomical Feature Preserving U-net Architecture for Ultrasound Image Segmentation
Deepak Raina, Kashish Verma, SH Chandrashekhara, Subir Kumar Saha
U Net Segmentation Network Segmentation Accuracy Ultrasound Image Segmentation Soft Robotic Bladder

November 8, 2022

Infant hip screening using multi-class ultrasound scan segmentation
Andrew Stamper, Abhinav Singh, James McCouat, Irina Voiculescu
Deep Learning Algorithm Ultrasound Image Segmentation

October 24, 2022

CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network
Fenghe Tang, Lingtao Wang, Chunping Ning, Min Xian, Jianrui Ding
Medical Image Segmentation Multi Scale U Net Segmentation Network Hybrid Convolutional Ultrasound Image Segmentation Cognition and Memory Unit

September 15, 2022

Rethinking the Unpretentious U-net for Medical Ultrasound Image Segmentation
Gongping Chen, Lei Li, JianXun Zhang, Yu Dai
U Net Breast Ultrasound Ultrasound Image Segmentation Breast Tumor Segmentation Nagoya University

August 9, 2022

Automatic Ultrasound Image Segmentation of Supraclavicular Nerve Using Dilated U-Net Deep Learning Architecture
Mizuki Miyatake, Subhash Nerella, David Simpson, Natalia Pawlowicz, Sarah Stern, Patrick Tighe, Parisa Rashidi
Ultrasound Image Segmentation Brachial Plexus Nerve Identification

Ultrasound Image Segmentation

Papers

Can ultrasound confidence maps predict sonographers' labeling variability?

CEmb-SAM: Segment Anything Model with Condition Embedding for Joint Learning from Heterogeneous Datasets

Multi-source adversarial transfer learning for ultrasound image segmentation with limited similarity

Multi-Level Global Context Cross Consistency Model for Semi-Supervised Ultrasound Image Segmentation with Diffusion Model

MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization

Slim U-Net: Efficient Anatomical Feature Preserving U-net Architecture for Ultrasound Image Segmentation

Infant hip screening using multi-class ultrasound scan segmentation

CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network

Rethinking the Unpretentious U-net for Medical Ultrasound Image Segmentation

Automatic Ultrasound Image Segmentation of Supraclavicular Nerve Using Dilated U-Net Deep Learning Architecture