PreprintArticleVersion 2Preserved in Portico This version is not peer-reviewed
Evaluating Recalibrating AI Models for Breast Cancer Diagnosis in a New Context: Insights from Transfer Learning, Image Enhancement and High Quality Training Data Integration
Version 1
: Received: 10 December 2023 / Approved: 11 December 2023 / Online: 11 December 2023 (11:05:38 CET)
Version 2
: Received: 11 December 2023 / Approved: 12 December 2023 / Online: 12 December 2023 (15:13:32 CET)
Jiang, Z.; Gandomkar, Z.; Trieu, P.D.Y.; Tavakoli Taba, S.; Barron, M.L.; Obeidy, P.; Lewis, S.J. Evaluating Recalibrating AI Models for Breast Cancer Diagnosis in a New Context: Insights from Transfer Learning, Image Enhancement and High-Quality Training Data Integration. Cancers2024, 16, 322.
Jiang, Z.; Gandomkar, Z.; Trieu, P.D.Y.; Tavakoli Taba, S.; Barron, M.L.; Obeidy, P.; Lewis, S.J. Evaluating Recalibrating AI Models for Breast Cancer Diagnosis in a New Context: Insights from Transfer Learning, Image Enhancement and High-Quality Training Data Integration. Cancers 2024, 16, 322.
Jiang, Z.; Gandomkar, Z.; Trieu, P.D.Y.; Tavakoli Taba, S.; Barron, M.L.; Obeidy, P.; Lewis, S.J. Evaluating Recalibrating AI Models for Breast Cancer Diagnosis in a New Context: Insights from Transfer Learning, Image Enhancement and High-Quality Training Data Integration. Cancers2024, 16, 322.
Jiang, Z.; Gandomkar, Z.; Trieu, P.D.Y.; Tavakoli Taba, S.; Barron, M.L.; Obeidy, P.; Lewis, S.J. Evaluating Recalibrating AI Models for Breast Cancer Diagnosis in a New Context: Insights from Transfer Learning, Image Enhancement and High-Quality Training Data Integration. Cancers 2024, 16, 322.
Abstract
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 image subsets. 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 pre-trained 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 transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by 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 high-concordance subset and 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 strong concordance of radiologists’ annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models.
Keywords
Artificial Intelligence; Deep Learning; Radiologists’ Concordance; Image enhancement; Mammography; Saliency Maps; Transfer Learning
Subject
Public Health and Healthcare, Public Health and Health Services
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
,
,
,
,
*
Commenter: Zhengqiang Jiang
Commenter's Conflict of Interests: Author
Funding: This work was funded by the National Breast Cancer Foundation (NBCF) Australia.