Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network

Bryar Shareef, Min Xian, Aleksandar Vakanski, Haotian Wang
8/4/2023
eess.IVcs.CVcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Capturing global contextual information plays a critical role in breast ultrasound (BUS) image classification. Although convolutional neural networks (CNNs) have demonstrated reliable performance in tumor classification, they have inherent limitations for modeling global and long-range dependencies due to the localized nature of convolution operations. Vision Transformers have an improved capability of capturing global contextual information but may distort the local image patterns due to the tokenization operations. In this study, we proposed a hybrid multitask deep neural network called Hybrid-MT-ESTAN, designed to perform BUS tumor classification and segmentation using a hybrid architecture composed of CNNs and Swin Transformer components. The proposed approach was compared to nine BUS classification methods and evaluated using seven quantitative metrics on a dataset of 3,320 BUS images. The results indicate that Hybrid-MT-ESTAN achieved the highest accuracy, sensitivity, and F1 score of 82.7%, 86.4%, and 86.0%, respectively.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Novel Channel Boosted Residual CNN-Transformer with Regional-Boundary Learning for Breast Cancer Detection

87% match2025

Interpretable Deep Transfer Learning for Breast Ultrasound Cancer Detection: A Multi-Dataset Study

86% match2025

Multimodal Deep Learning for Phyllodes Tumor Classification from Ultrasound and Clinical Data

85% match2025

AResNet-ViT: A Hybrid CNN-Transformer Network for Benign and Malignant Breast Nodule Classification in Ultrasound Images

84% match2024

Comparative Analysis of Vision Transformers and Convolutional Neural Networks for Medical Image Classification

83% match2025

Leveraging Transformers to Improve Breast Cancer Classification and Risk Assessment with Multi-modal and Longitudinal Data

83% match2023

Cite this paper

@article{shareef2023breast,
  title  = {Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network},
  author = {Bryar Shareef and Min Xian and Aleksandar Vakanski and Haotian Wang},
  year   = {2023},
  eprint = {2308.02101},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.02101v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.02101.svg)](https://codeofpaper.com/paper/2308.02101)

Discussion