Interpretable Diagnosis of Pulmonary Emphysema on Low-Dose CT Using ResNet Embeddings

Sarsembayeva T. Mansurova M. Oshibayeva A. Serebryakov S.
January 2026 Multidisciplinary Digital Publishing Institute (MDPI)

Journal of Imaging
2026 #12 Issue 1

Accurate and interpretable detection of pulmonary emphysema on low-dose computed tomography (LDCT) remains a critical challenge for large-scale screening and population health studies. This work proposes a quality-controlled and interpretable deep learning pipeline for emphysema assessment using ResNet-152 embeddings. The pipeline integrates automated lung segmentation, quality-control filtering, and extraction of 2048-dimensional embeddings from mid-lung patches, followed by analysis using logistic regression, LASSO, and recursive feature elimination (RFE). The embeddings are further fused with quantitative CT (QCT) markers, including %LAA, Perc15, and total lung volume (TLV), to enhance robustness and interpretability. Bootstrapped validation demonstrates strong diagnostic performance (ROC-AUC = 0.996, PR-AUC = 0.962, balanced accuracy = 0.931) with low computational cost. The proposed approach shows that ResNet embeddings pretrained on CT data can be effectively reused without retraining for emphysema characterization, providing a reproducible and explainable framework suitable as a research and screening-support framework for population-level LDCT analysis.

deep learning , emphysema , explainable AI , feature embeddings , low-dose CT , ResNet , weak supervision

Text of the article Перейти на текст статьи

Faculty of Information Technologies and Artificial Intelligence, Department of Artificial Intelligence and Big Data, Al-Farabi Kazakh National University, Almaty, 050040, Kazakhstan
Faculty of Medicine, Department of Public Health and Scientific Research, Khoja Akhmet Yassawi International Kazakh-Turkish University, Turkistan, 161200, Kazakhstan
Smart Parking Technologies Ltd., Almaty, 010000, Kazakhstan

Faculty of Information Technologies and Artificial Intelligence
Faculty of Medicine
Smart Parking Technologies Ltd.

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026