Journal article
Machine learning approach for distinguishing malignant and benign lung nodules utilizing standardized perinodular parenchymal features from CT
Medical physics (Lancaster), Vol.46(7), pp.3207-3216
07/2019
DOI: 10.1002/mp.13592
PMCID: PMC6945763
PMID: 31087332
Abstract
Computed tomography (CT) is an effective method for detecting and characterizing lung nodules in vivo. With the growing use of chest CT, the detection frequency of lung nodules is increasing. Noninvasive methods to distinguish malignant from benign nodules have the potential to decrease the clinical burden, risk, and cost involved in follow-up procedures on the large number of false-positive lesions detected. This study examined the benefit of including perinodular parenchymal features in machine learning (ML) tools for pulmonary nodule assessment.
Lung nodule cases with pathology confirmed diagnosis (74 malignant, 289 benign) were used to extract quantitative imaging characteristics from computed tomography scans of the nodule and perinodular parenchyma tissue. A ML tool development pipeline was employed using k-medoids clustering and information theory to determine efficient predictor sets for different amounts of parenchyma inclusion and build an artificial neural network classifier. The resulting ML tool was validated using an independent cohort (50 malignant, 50 benign).
The inclusion of parenchymal imaging features improved the performance of the ML tool over exclusively nodular features (P < 0.01). The best performing ML tool included features derived from nodule diameter-based surrounding parenchyma tissue quartile bands. We demonstrate similar high-performance values on the independent validation cohort (AUC-ROC = 0.965). A comparison using the independent validation cohort with the Fleischner pulmonary nodule follow-up guidelines demonstrated a theoretical reduction in recommended follow-up imaging and procedures.
Radiomic features extracted from the parenchyma surrounding lung nodules contain valid signals with spatial relevance for the task of lung cancer risk classification. Through standardization of feature extraction regions from the parenchyma, ML tool validation performance of 100% sensitivity and 96% specificity was achieved.
Details
- Title: Subtitle
- Machine learning approach for distinguishing malignant and benign lung nodules utilizing standardized perinodular parenchymal features from CT
- Creators
- Johanna Uthoff - University of IowaMatthew J Stephens - University of CincinnatiJohn D Jr Newell - Department of Radiology, University of Iowa, Iowa City, IA, 52242, USAEric A Hoffman - University of IowaJared Larson - University of IowaNicholas Koehn - University of IowaFrank A De Stefano - University of IowaChrissy M Lusk - Karmanos Cancer InstituteAngela S Wenzlaff - Karmanos Cancer InstituteDonovan Watza - Karmanos Cancer InstituteChristine Neslund-Dudas - Department of Public Health Sciences Henry Ford Health System Detroit MI 48202USALaurie L Carr - Department of Medicine National Jewish Health DenverCO 80206USADavid A Lynch - Department of Radiology National Jewish Health Denver CO 80206USAAnn G Schwartz - Karmanos Cancer InstituteJessica C Sieren - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Medical physics (Lancaster), Vol.46(7), pp.3207-3216
- DOI
- 10.1002/mp.13592
- PMID
- 31087332
- PMCID
- PMC6945763
- ISSN
- 0094-2405
- eISSN
- 2473-4209
- Grant note
- NCI P30 CA086862 / Holden Comprehensive Cancer Center P30 ES005605 / NIEHS NIH HHS U01 HL089856 / NHLBI NIH HHS U01 HL089897 / NHLBI NIH HHS Herrick Foundation P30 CA022453 / NCI NIH HHS R01 CA141769 / NCI NIH HHS NCT00608764 / COPDGene study R01CA141769 / INHALE P30CA022453 / INHALE P30 CA086862 / NCI NIH HHS HHSN26120130011I / National Cancer Institute, Health and Human Services
- Language
- English
- Date published
- 07/2019
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology; Internal Medicine
- Record Identifier
- 9984318816402771
Metrics
11 Record Views