What question did this study set out to answer?

This research aims to evaluate the effectiveness of deep learning models for breast cancer detection using infrared thermography.

March 14, 20260 citationsOpen Access

Cross-Validation Deep Learning for Breast Cancer Detection Using DMR-IR Infrared Images

RMRenata dos Santos MeloUniversidade Federal de Uberlândia HFHenrique FernandesUniversidade Federal de Uberlândia ABAndré Ricardo BackesUniversidade Federal de São Carlos

Key Points

This research aims to evaluate the effectiveness of deep learning models for breast cancer detection using infrared thermography.
Utilized DMR-IR thermal images for analysis.
Assessed five pre-trained Convolutional Neural Networks (CNNs).
Implemented 5-fold cross-validation for performance evaluation.
Trained models on images from three anatomical views: frontal, lateral 90°, and lateral 45°.
Aggregated five images per patient for model training.
ResNet50 achieved the highest accuracy at 92.79%.
Precision reached 95.00%, indicating high correctness in positive identifications.
Specificity was recorded at 98.67%, showcasing the model's ability to correctly identify non-cancerous cases.
Sensitivity amounted to 72.00%, reflecting the true positive rate of the model.
F1-score of 79.43% highlights a balance between precision and recall.

Abstract

Breast cancer detection is a global health priority. While traditional methods have limitations, infrared thermography offers a promising, non-invasive alternative by detecting subtle thermal changes that can indicate tumors. This paper assessed five pre-trained Convolutional Neural Networks (CNNs) for breast cancer detection using DMR-IR thermal images, employing a 5-fold cross-validation. Among the tested models, ResNet50 achieved the best overall performance, with the highest average accuracy (92.79%), precision (95.00%), specificity (98.67%), sensitivity (72.00%), and F1-score (79.43%). The model was trained using raw thermal images from three anatomical views (frontal, lateral 90°, and lateral 45°), totaling five images per patient, an approach still uncommon in the literature. These results highlight ResNet50's strong potential for reliable and clinically applicable breast cancer detection using thermography.

AIに質問

Bookmark

View Full Paper