Rajesh P Shah1,2, Heather M Selby1,3, Pritam Mukherjee3, Shefali Verma4, Peiyi Xie3,5, Qinmei Xu3,6, Millie Das1,7, Sachin Malik1,2, Olivier Gevaert3, Sandy Napel2. 1. Veterans Affairs Palo Alto Health Care System, Palo Alto, CA. 2. Department of Radiology, Stanford University, Stanford, CA. 3. Department of Medicine, Center for Biomedical Informatics Research (BMIR), Stanford University, Stanford, CA. 4. Palo Alto Veterans Institute for Research, Palo Alto, CA. 5. Present address: Department of Radiology, The Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong, China. 6. Present address: Department of Medical Imaging, Jinling Hospital, Nanjing University School of Medicine, Nanjing, Jiangsu, China. 7. Department of Medicine-Oncology, Stanford University, Stanford, CA.
Abstract
PURPOSE: Small-cell lung cancer (SCLC) is the deadliest form of lung cancer, partly because of its short doubling time. Delays in imaging identification and diagnosis of nodules create a risk for stage migration. The purpose of our study was to determine if a machine learning radiomics model can detect SCLC on computed tomography (CT) among all nodules at least 1 cm in size. MATERIALS AND METHODS: Computed tomography scans from a single institution were selected and resampled to 1 × 1 × 1 mm. Studies were divided into SCLC and other scans comprising benign, adenocarcinoma, and squamous cell carcinoma that were segregated into group A (noncontrast scans) and group B (contrast-enhanced scans). Four machine learning classification models, support vector classifier, random forest (RF), XGBoost, and logistic regression, were used to generate radiomic models using 59 quantitative first-order and texture Imaging Biomarker Standardization Initiative compliant PyRadiomics features, which were found to be robust between two segmenters with minimum Redundancy Maximum Relevance feature selection within each leave-one-out-cross-validation to avoid overfitting. The performance was evaluated using a receiver operating characteristic curve. A final model was created using the RF classifier and aggregate minimum Redundancy Maximum Relevance to determine feature importance. RESULTS: A total of 103 studies were included in the analysis. The area under the receiver operating characteristic curve for RF, support vector classifier, XGBoost, and logistic regression was 0.81, 0.77, 0.84, and 0.84 in group A, and 0.88, 0.87, 0.85, and 0.81 in group B, respectively. Nine radiomic features in group A and 14 radiomic features in group B were predictive of SCLC. Six radiomic features overlapped between groups A and B. CONCLUSION: A machine learning radiomics model may help differentiate SCLC from other lung lesions.
PURPOSE: Small-cell lung cancer (SCLC) is the deadliest form of lung cancer, partly because of its short doubling time. Delays in imaging identification and diagnosis of nodules create a risk for stage migration. The purpose of our study was to determine if a machine learning radiomics model can detect SCLC on computed tomography (CT) among all nodules at least 1 cm in size. MATERIALS AND METHODS: Computed tomography scans from a single institution were selected and resampled to 1 × 1 × 1 mm. Studies were divided into SCLC and other scans comprising benign, adenocarcinoma, and squamous cell carcinoma that were segregated into group A (noncontrast scans) and group B (contrast-enhanced scans). Four machine learning classification models, support vector classifier, random forest (RF), XGBoost, and logistic regression, were used to generate radiomic models using 59 quantitative first-order and texture Imaging Biomarker Standardization Initiative compliant PyRadiomics features, which were found to be robust between two segmenters with minimum Redundancy Maximum Relevance feature selection within each leave-one-out-cross-validation to avoid overfitting. The performance was evaluated using a receiver operating characteristic curve. A final model was created using the RF classifier and aggregate minimum Redundancy Maximum Relevance to determine feature importance. RESULTS: A total of 103 studies were included in the analysis. The area under the receiver operating characteristic curve for RF, support vector classifier, XGBoost, and logistic regression was 0.81, 0.77, 0.84, and 0.84 in group A, and 0.88, 0.87, 0.85, and 0.81 in group B, respectively. Nine radiomic features in group A and 14 radiomic features in group B were predictive of SCLC. Six radiomic features overlapped between groups A and B. CONCLUSION: A machine learning radiomics model may help differentiate SCLC from other lung lesions.
Authors: Paul A Yushkevich; Joseph Piven; Heather Cody Hazlett; Rachel Gimpel Smith; Sean Ho; James C Gee; Guido Gerig Journal: Neuroimage Date: 2006-03-20 Impact factor: 6.556
Authors: John H M Austin; Rowena Yip; Belinda M D'Souza; David F Yankelevitz; Claudia I Henschke Journal: Lung Cancer Date: 2011-12-20 Impact factor: 5.705
Authors: Satomi Odani; Israel T Agaku; Corinne M Graffunder; Michael A Tynan; Brian S Armour Journal: MMWR Morb Mortal Wkly Rep Date: 2018-01-12 Impact factor: 17.586
Authors: Hugo J W L Aerts; Emmanuel Rios Velazquez; Ralph T H Leijenaar; Chintan Parmar; Patrick Grossmann; Sara Carvalho; Sara Cavalho; Johan Bussink; René Monshouwer; Benjamin Haibe-Kains; Derek Rietveld; Frank Hoebers; Michelle M Rietbergen; C René Leemans; Andre Dekker; John Quackenbush; Robert J Gillies; Philippe Lambin Journal: Nat Commun Date: 2014-06-03 Impact factor: 14.919
Authors: Melissa M Chen; Admir Terzic; Anton S Becker; Jason M Johnson; Carol C Wu; Max Wintermark; Christoph Wald; Jia Wu Journal: Eur J Radiol Open Date: 2022-09-29