Masked Video Modeling with Correlation-aware Contrastive Learning for Breast Cancer Diagnosis in Ultrasound

08/21/2022
by   Zehui Lin, et al.
0

Breast cancer is one of the leading causes of cancer deaths in women. As the primary output of breast screening, breast ultrasound (US) video contains exclusive dynamic information for cancer diagnosis. However, training models for video analysis is non-trivial as it requires a voluminous dataset which is also expensive to annotate. Furthermore, the diagnosis of breast lesion faces unique challenges such as inter-class similarity and intra-class variation. In this paper, we propose a pioneering approach that directly utilizes US videos in computer-aided breast cancer diagnosis. It leverages masked video modeling as pretraning to reduce reliance on dataset size and detailed annotations. Moreover, a correlation-aware contrastive loss is developed to facilitate the identifying of the internal and external relationship between benign and malignant lesions. Experimental results show that our proposed approach achieved promising classification performance and can outperform other state-of-the-art methods.

READ FULL TEXT

page 2

page 3

page 8

research
05/17/2022

HoVer-Trans: Anatomy-aware HoVer-Transformer for ROI-free Breast Cancer Diagnosis in Ultrasound Images

Ultrasonography is an important routine examination for breast cancer di...
research
11/08/2021

BRACS: A Dataset for BReAst Carcinoma Subtyping in H E Histology Images

Breast cancer is the most commonly diagnosed cancer and registers the hi...
research
12/29/2020

COIN: Contrastive Identifier Network for Breast Mass Diagnosis in Mammography

Computer-aided breast cancer diagnosis in mammography is a challenging p...
research
06/29/2023

SimPLe: Similarity-Aware Propagation Learning for Weakly-Supervised Breast Cancer Segmentation in DCE-MRI

Breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) pl...
research
07/28/2021

AI assisted method for efficiently generating breast ultrasound screening reports

Ultrasound is the preferred choice for early screening of dense breast c...
research
11/15/2017

End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design

We develop an end-to-end training algorithm for whole-image breast cance...
research
08/04/2023

Computational modeling to determine the physical characteristics of biological tissues for medical diagnosis

Timely diagnosis of breast cancer is an important task. This type of bre...

Please sign up or login with your details

Forgot password? Click here to reset