Interpretable Breast Cancer Risk Stratification Using Statistical Feature Engineering on Thermal Images
- Title
- Interpretable Breast Cancer Risk Stratification Using Statistical Feature Engineering on Thermal Images
- Creator
- Hazra, Chandrima; Jayan, Mini; Saleema, J.S.
- Description
- This research solves the black box problem of AI implementation in imaging by introducing a transparent, statistically grounded approach to breast cancer risk stratification via infrared thermography without compromising performance. Using the public DMR-IR dataset, statistical feature engineering was applied to training data by extracting first- and second-order statistical features. After ensuring non-normality with a Shapiro-Wilk test, feature significance was established with the Mann-Whitney U test. LASSO regularization selected the five most predictive features: mean, standard deviation, kurtosis, correlation, and energy. To counteract class imbalance, SMOTE was applied, and two machine learning modelslogistic regression and random forest (classifier)were trained on the balanced data and then evaluated on an unseen test dataset. Reporting an AUC of 0.98 over logistic regressions 0.96 reflects stringent statistical feature engineering and great generalization, creating a strong and interpretable model for breast cancer diagnosis in thermal images, and instills more clinical confidence in AI-based diagnostic systems. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
- Source
- Lecture Notes in Computer Science;Volume;16308 LNCS;pp.65-79
- Date
- 01-01-2026
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Subject
- Breast Cancer; Infrared Thermography; Interpretable AI; LASSO; Machine Learning; SMOTE; Statistical Feature Engineering
- Coverage
- Hazra C., Department of Statistics and Data Science, Christ (Deemed to be University), Karnataka, Bangalore, India; Jayan M., Department of Statistics and Data Science, Christ (Deemed to be University), Karnataka, Bangalore, India; Saleema J.S., Department of Statistics and Data Science, Christ (Deemed to be University), Karnataka, Bangalore, India
- Rights
- Restricted Access; Hardcopy may be available in the library
- Relation
- ISSN: 3029743; ISBN: 978-303210989-7;
- Format
- online
- Language
- English
- Type
- Conference paper
Collection
Citation
Hazra, Chandrima; Jayan, Mini; Saleema, J.S., “Interpretable Breast Cancer Risk Stratification Using Statistical Feature Engineering on Thermal Images,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/25375.