Fusion of transfer learning models with LSTM for detection of breast cancer using ultrasound images

• Published in: Computers in biology and medicine Vol. 169; p. 107914
• Main Authors: Lanjewar, Madhusudan G., Panchbhai, Kamini G., Patle, Lalchand B.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.02.2024; Elsevier Limited
• Subjects: Accuracy; Algorithms; Area Under Curve; Breast cancer; Breast Neoplasms; Correlation coefficients; Datasets; Disease; Female; Gradient-weighted class activation mapping (Grad-CAM); Humans; Internal Medicine; Learning; Long short-term memory LSTM; Machine Learning; Magnetic resonance imaging; Mammography; Mathematical analysis; Methods; MobileNetV2; Other; Performance evaluation; Risk factors; SMOTETomek; Statistical analysis; Statistical methods; Transfer learning; Ultrasonic imaging; Ultrasonography; Ultrasound; Ultrasound images; VGG16; Womens health; MobileNetV2; VGG16; Ultrasound images; Breast cancer; Long short-term memory LSTM; SMOTETomek; Gradient-weighted class activation mapping (Grad-CAM)
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107914

Breast Cancer (BC) is one of the top reasons for fatality in women worldwide. As a result, timely identification is critical for successful therapy and excellent survival rates. Transfer Learning (TL) approaches have recently shown promise in aiding in the early recognition of BC. In this work, three TL models, MobileNetV2, ResNet50, and VGG16, were combined with LSTM to extract the features from Ultrasound Images (USIs). Furthermore, the Synthetic Minority Over-sampling Technique (SMOTE) with Tomek (SMOTETomek) was employed to balance the extracted features. The proposed method with VGG16 achieved an F1 score of 99.0 %, Matthews Correlation Coefficient (MCC) and Kappa Coefficient of 98.9 % with an Area Under Curve (AUC) of 1.0. The K-fold method was applied for cross-validation and achieved an average F1 score of 96 %. Moreover, the Gradient-weighted Class Activation Mapping (Grad-CAM) method was applied for visualization, and the Local Interpretable Model-agnostic Explanations (LIME) method was applied for interpretability. The Normal Approximation Interval (NAI) and bootstrapping methods were used to calculate Confidence Intervals (CIs). The proposed method achieved a Lower CI (LCI), Upper CI (UCI), and Mean CI (MCI) of 96.50 %, 99.75 %, and 98.13 %, respectively, with the NAI, while 95 % LCI of 93.81 %, an UCI of 96.00 %, and a bootstrap mean of 94.90 % with the bootstrap method. Furthermore, the performance of the six state-of-the-art (SOTA) TL models, such as Xception, NASNetMobile, InceptionResNetV2, MobileNetV2, ResNet50, and VGG16, were compared with the proposed method. •Transfer Learning with LSTM was proposed.•Data imabalancing method was used to enhance the performance.•VGG16-LSTM achieved an F1 score of 99 % with an AUC of 1.•The lower CI, higher CI, and mean CI of 96.50 %, 99.75 %, and 98.13 %, respectively.