Conference proceeding
Optimized feature selection of nodular and peri‑nodular radiomics for lung cancer risk prediction with ensemble artificial neural networks
Vol.13926, pp.139261Y-139261Y-5
Progress in Biomedical Optics and Imaging
04/02/2026
DOI: 10.1117/12.3085592
Abstract
Lung cancer is responsible for 22% of all cancer related deaths, highlighting the need for screening high-risk individuals using Low Dose Computed Tomography (LDCT) to enhance early detection. Around 97% of nodules identified during lung cancer screening are benign, meaning there is a need for effective tools to differentiate malignant from benign cases. Additionally, incorrectly flagging nodules as suspicious during evaluation of LDCT images can lead to downstream complications from repeated imaging, invasive biopsy, and overall stress to the patient. We hypothesized that a machine learning method utilizing quantitative features extracted from the nodule and surrounding parenchymal tissue of LDCT images can assist in classifying nodule malignancy. Our approach explores predictive performance of ensembles of Artificial Neural Networks trained on important radiomic features using LASSO, ELASTICNET, and MRMRE feature selection methods.
Details
- Title: Subtitle
- Optimized feature selection of nodular and peri‑nodular radiomics for lung cancer risk prediction with ensemble artificial neural networks
- Creators
- Kevin Knoernschild - University of IowaKimberly E. Schroeder - University of IowaJacob Kitzmann - University of IowaChrissy Lusk - Karmanos Cancer Institute (United States)Christine Neslund-Dudas - Henry Ford Health SystemAnn G. Schwartz - Karmanos Cancer Institute (United States)Jessica C. Sieren - University of Iowa
- Contributors
- Axel Wismüller (Editor) - University of RochesterThomas M. Deserno (Editor) - Peter L. Reichertz Institut für Medizinische Informatik (Germany)
- Resource Type
- Conference proceeding
- Publication Details
- Vol.13926, pp.139261Y-139261Y-5
- Series
- Progress in Biomedical Optics and Imaging
- DOI
- 10.1117/12.3085592
- ISSN
- 1605-7422
- Publisher
- SPIE
- Grant note
- National Institute of Health: U01CA80098, U01CA79778 National Cancer Institute: R01CA141769, P30CA022453 Herrick Foundation
This work was funded by the National Institute of Health (R01CA267820). The authors thank the researchers and study participants from National Lung Screening Trial, which was also funded by the National Institute of Health (U01CA80098, U01CA79778) and the INHALE study, funded by National Cancer Institute (R01CA141769, P30CA022453 Epidemiology Research Core) and the Herrick Foundation.
- Language
- English
- Date published
- 04/02/2026
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology
- Record Identifier
- 9985157514402771
Metrics
8 Record Views