1. Evaluating Recalibrating AI Models for Breast Cancer Diagnosis in a New Context: Insights from Transfer Learning, Image Enhancement and High-Quality Training Data Integration.
- Author
-
Jiang, Zhengqiang, Gandomkar, Ziba, Trieu, Phuong Dung, Tavakoli Taba, Seyedamir, Barron, Melissa L., Obeidy, Peyman, and Lewis, Sarah J.
- Subjects
- *
BREAST tumor diagnosis , *DEEP learning , *ARTIFICIAL intelligence , *MAMMOGRAMS , *CONTRAST media , *CANCER patients , *DIAGNOSTIC imaging , *DECISION making , *PREDICTION models - Abstract
Simple Summary: Breast cancer is one of the leading causes of cancer-related death in women. The early detection of breast cancer with screening mammograms plays a pivotal role in reducing mortality rates. Although population-based double-reading screening mammograms have reduced mortality by over 31% in women with breast cancer in Europe, continuing this program is difficult due to the shortage of radiologists. Artificial intelligence (AI) is an emerging technology that has provided promising results in medical imaging for disease detection. This study investigates the performance of AI models on an Australian mammographic database, demonstrating how transfer learning from a USA mammographic database to an Australian one, contrast enhancement on mammographic images and the quality of training data according to radiologists' concordance can improve breast cancer diagnosis. Our proposed methodology offers a more efficacious approach for AI to contribute to radiologists' decision making when interpreting mammography images. This paper investigates the adaptability of four state-of-the-art artificial intelligence (AI) models to the Australian mammographic context through transfer learning, explores the impact of image enhancement on model performance and analyses the relationship between AI outputs and histopathological features for clinical relevance and accuracy assessment. A total of 1712 screening mammograms (n = 856 cancer cases and n = 856 matched normal cases) were used in this study. The 856 cases with cancer lesions were annotated by two expert radiologists and the level of concordance between their annotations was used to establish two sets: a 'high-concordances subset' with 99% agreement of cancer location and an 'entire dataset' with all cases included. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of Globally aware Multiple Instance Classifier (GMIC), Global-Local Activation Maps (GLAM), I&H and End2End AI models, both in the pretrained and transfer learning modes, with and without applying the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The four AI models with and without transfer learning in the high-concordance subset outperformed those in the entire dataset. Applying the CLAHE algorithm to mammograms improved the performance of the AI models. In the high-concordance subset with the transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by the GLAM model (0.909), I&H (0.893) and End2End (0.875). There were significant differences (p < 0.05) in the performances of the four AI models between the high-concordance subset and the entire dataset. The AI models demonstrated significant differences in malignancy probability concerning different tumour size categories in mammograms. The performance of AI models was affected by several factors such as concordance classification, image enhancement and transfer learning. Mammograms with a strong concordance with radiologists' annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF