Ultrasound Contrastive Learning

Ultrasound contrastive learning leverages the inherent temporal and spatial relationships within ultrasound video sequences to learn robust image representations from unlabeled data, addressing the scarcity of annotated medical images. Current research focuses on optimizing the selection and weighting of image pairs for contrastive learning, exploring methods like using proximal frames within videos and meta-learning approaches to improve semantic consistency. These advancements aim to improve the accuracy of deep learning models for various ultrasound-based diagnostic tasks, such as COVID-19 detection and cancer classification, ultimately enhancing the efficiency and accessibility of medical imaging analysis.

Papers

March 12, 2024

Intra-video Positive Pairs in Self-Supervised Learning for Ultrasound
Blake VanBerlo, Alexander Wong, Jesse Hoey, Robert Arntfield
Self Supervised Learning Self Supervised B Mode Intra Video Positive Pair Ultrasound Contrastive Learning

June 28, 2023

Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasound
Xinfeng Li, Junning Ze, Chen Yan, Yushi Cheng, Xiaoyu Ji, Wenyuan Xu
Adversarial Example Speaker Recognition System Physical Backdoor Attack Ultrasound Contrastive Learning

December 8, 2022

Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning
Yixiong Chen, Chunhui Zhang, Chris H. Q. Ding, Li Liu
Contrastive Learning Supervised ImageNet Ultrasound Image Contrastive Meta Learning Ultrasound Contrastive Learning

July 12, 2022

NEC: Speaker Selective Cancellation via Neural Enhanced Ultrasound Shadowing
Hanqing Guo, Chenning Li, Lingkun Li, Zhichao Cao, Qiben Yan, Li Xiao
Speaker Independent Ear Microphone Ultrasound Contrastive Learning

April 29, 2022

COVID-Net US-X: Enhanced Deep Neural Network for Detection of COVID-19 Patient Cases from Convex Ultrasound Imaging Through Extended Linear-Convex Ultrasound Augmentation Learning
E. Zhixuan Zeng, Adrian Florea, Alexander Wong
Neural Network Convex Set Decision Support System COVID 19 Case Point of Care Ultrasound Contrastive Learning

Ultrasound Contrastive Learning

Papers

Intra-video Positive Pairs in Self-Supervised Learning for Ultrasound

Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasound

Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning

NEC: Speaker Selective Cancellation via Neural Enhanced Ultrasound Shadowing

COVID-Net US-X: Enhanced Deep Neural Network for Detection of COVID-19 Patient Cases from Convex Ultrasound Imaging Through Extended Linear-Convex Ultrasound Augmentation Learning