Adapting the pre-trained convolutional neural networks to improve the anomaly detection and classification in mammographic images
Open Access
- 9 September 2023
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 13 (1) , 1-16
Abstract
Mortality from breast cancer (BC) is among the top causes of cancer death in women. BC can be effectively treated when diagnosed early, improving the likelihood that a patient will survive. BC masses and calcification clusters must be identified by mammography in order to prevent disease effects and commence therapy at an early stage. A mammography misinterpretation may result in an unnecessary biopsy of the false-positive results, lowering the patient’s odds of survival. This study intends to improve breast mass detection and identification in order to provide better therapy and reduce mortality risk. A new deep-learning (DL) model based on a combination of transfer-learning (TL) and long short-term memory (LSTM) is proposed in this study to adequately facilitate the automatic detection and diagnosis of the BC suspicious region using the 80–20 method. Since DL designs are modelled to be problem-specific, TL applies the knowledge gained during the solution of one problem to another relevant problem. In the presented model, the learning features from the pre-trained networks such as the squeezeNet and DenseNet are extracted and transferred with the features that have been extracted from the INbreast dataset. To measure the proposed model performance, we selected accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) as our metrics of choice. The classification of mammographic data using the suggested model yielded overall accuracy, sensitivity, specificity, precision, and AUC values of 99.236%, 98.8%, 99.1%, 96%, and 0.998, respectively, demonstrating the model’s efficacy in detecting breast tumors.Keywords
Funding Information
- Linköping University
This publication has 56 references indexed in Scilit:
- Convolutional neural network improvement for breast cancer classificationExpert Systems with Applications, 2019
- Transfer learning based deep CNN for segmentation and detection of mitoses in breast cancer histopathological imagesMicroscopy, 2019
- Transfer learning based histopathologic image classification for breast cancer detectionHealth Information Science and Systems, 2018
- Improve the Performance of Transfer Learning Without Fine-Tuning Using Dissimilarity-Based Multi-view Learning for Breast Cancer Histology Images2018
- Breast cancer detection in mammograms using convolutional neural network2018
- Breast mass lesion classification in mammograms by transfer learning2017
- DeepCAD: A Computer-Aided Diagnosis System for Mammographic Masses Using Deep Invariant FeaturesComputers, 2016
- A Region Based Convolutional Network for Tumor Detection and Classification in Breast Mammography2016
- INbreastAcademic Radiology, 2012
- BARRIERS TO BREAST CANCER SCREENING: AN INTEGRATIVE REVIEWHealth Care for Women International, 2000