Literature DB >> 33714900

Semi-supervised GAN-based Radiomics Model for Data Augmentation in Breast Ultrasound Mass Classification.

Ting Pang1, Jeannie Hsiu Ding Wong2, Wei Lin Ng3, Chee Seng Chan4.   

Abstract

BACKGROUND AND
OBJECTIVE: The capability of deep learning radiomics (DLR) to extract high-level medical imaging features has promoted the use of computer-aided diagnosis of breast mass detected on ultrasound. Recently, generative adversarial network (GAN) has aided in tackling a general issue in DLR, i.e., obtaining a sufficient number of medical images. However, GAN methods require a pair of input and labeled images, which require an exhaustive human annotation process that is very time-consuming. The aim of this paper is to develop a radiomics model based on a semi-supervised GAN method to perform data augmentation in breast ultrasound images.
METHODS: A total of 1447 ultrasound images, including 767 benign masses and 680 malignant masses were acquired from a tertiary hospital. A semi-supervised GAN model was developed to augment the breast ultrasound images. The synthesized images were subsequently used to classify breast masses using a convolutional neural network (CNN). The model was validated using a 5-fold cross-validation method.
RESULTS: The proposed GAN architecture generated high-quality breast ultrasound images, verified by two experienced radiologists. The improved performance of semi-supervised learning increased the quality of the synthetic data produced in comparison to the baseline method. We achieved more accurate breast mass classification results (accuracy 90.41%, sensitivity 87.94%, specificity 85.86%) with our synthetic data augmentation compared to other state-of-the-art methods.
CONCLUSION: The proposed radiomics model has demonstrated a promising potential to synthesize and classify breast masses on ultrasound in a semi-supervised manner.
Copyright © 2021 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Breast cancer classification; Data augmentation; Deep learning radiomics; Generative adversarial network; Semi-supervised learning; Ultrasound imaging

Year:  2021        PMID: 33714900     DOI: 10.1016/j.cmpb.2021.106018

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   5.428


  8 in total

1.  Predicting Breast Tumor Malignancy Using Deep ConvNeXt Radiomics and Quality-Based Score Pooling in Ultrasound Sequences.

Authors:  Mohamed A Hassanien; Vivek Kumar Singh; Domenec Puig; Mohamed Abdel-Nasser
Journal:  Diagnostics (Basel)       Date:  2022-04-22

2.  Generative Adversarial Networks to Improve Fetal Brain Fine-Grained Plane Classification.

Authors:  Alberto Montero; Elisenda Bonet-Carne; Xavier Paolo Burgos-Artizzu
Journal:  Sensors (Basel)       Date:  2021-11-29       Impact factor: 3.576

3.  Breast Cancer Classification from Ultrasound Images Using Probability-Based Optimal Deep Learning Feature Fusion.

Authors:  Kiran Jabeen; Muhammad Attique Khan; Majed Alhaisoni; Usman Tariq; Yu-Dong Zhang; Ameer Hamza; Artūras Mickus; Robertas Damaševičius
Journal:  Sensors (Basel)       Date:  2022-01-21       Impact factor: 3.576

Review 4.  Deep Learning With Radiomics for Disease Diagnosis and Treatment: Challenges and Potential.

Authors:  Xingping Zhang; Yanchun Zhang; Guijuan Zhang; Xingting Qiu; Wenjun Tan; Xiaoxia Yin; Liefa Liao
Journal:  Front Oncol       Date:  2022-02-17       Impact factor: 6.244

5.  A quantization assisted U-Net study with ICA and deep features fusion for breast cancer identification using ultrasonic data.

Authors:  Talha Meraj; Wael Alosaimi; Bader Alouffi; Hafiz Tayyab Rauf; Swarn Avinash Kumar; Robertas Damaševičius; Hashem Alyami
Journal:  PeerJ Comput Sci       Date:  2021-12-16

6.  Augmentation-Consistent Clustering Network for Diabetic Retinopathy Grading with Fewer Annotations.

Authors:  Guanghua Zhang; Keran Li; Zhixian Chen; Li Sun; Jianwei Zhang; Xueping Pan
Journal:  J Healthc Eng       Date:  2022-03-28       Impact factor: 2.682

7.  Cyclic GAN Model to Classify Breast Cancer Data for Pathological Healthcare Task.

Authors:  Pooja Chopra; N Junath; Sitesh Kumar Singh; Shakir Khan; R Sugumar; Mithun Bhowmick
Journal:  Biomed Res Int       Date:  2022-07-21       Impact factor: 3.246

8.  Synthetic MRI improves radiomics-based glioblastoma survival prediction.

Authors:  Elisa Moya-Sáez; Rafael Navarro-González; Santiago Cepeda; Ángel Pérez-Núñez; Rodrigo de Luis-García; Santiago Aja-Fernández; Carlos Alberola-López
Journal:  NMR Biomed       Date:  2022-05-21       Impact factor: 4.478

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.