1. Lung tumor segmentation methods: Impact on the uncertainty of radiomics features for non-small cell lung cancer
- Author
-
Constance A. Owens, David Fuentes, Jing Li, Christine B. Peterson, Jinzhong Yang, Dennis S. Mackin, Eugene J. Koay, Mohammad Salehpour, Laurence E. Court, Chad Tang, and Wen Yu
- Subjects
Research Validity ,Lung Neoplasms ,Medical Doctors ,Computer science ,Health Care Providers ,lcsh:Medicine ,Lung and Intrathoracic Tumors ,Diagnostic Radiology ,030218 nuclear medicine & medical imaging ,0302 clinical medicine ,Radiomics ,Carcinoma, Non-Small-Cell Lung ,Medicine and Health Sciences ,Image Processing, Computer-Assisted ,Segmentation ,Medical Personnel ,lcsh:Science ,Tomography ,Reliability (statistics) ,Observer Variation ,Multidisciplinary ,Radiology and Imaging ,Uncertainty ,Software Engineering ,Research Assessment ,Reproducibility ,Professions ,Oncology ,Feature (computer vision) ,030220 oncology & carcinogenesis ,Engineering and Technology ,medicine.symptom ,Research Article ,Computer and Information Sciences ,Similarity (geometry) ,Imaging Techniques ,Neuroimaging ,Image processing ,Radiation ,Research and Analysis Methods ,Lesion ,03 medical and health sciences ,Diagnostic Medicine ,Physicians ,Carcinoma ,medicine ,Humans ,Lung cancer ,Software Tools ,business.industry ,lcsh:R ,Cancers and Neoplasms ,Biology and Life Sciences ,Pattern recognition ,medicine.disease ,Computed Axial Tomography ,Non-Small Cell Lung Cancer ,Health Care ,People and Places ,lcsh:Q ,Population Groupings ,Lung tumor ,Artificial intelligence ,Secondary Lung Tumors ,Tomography, X-Ray Computed ,business ,Software ,Neuroscience - Abstract
Purpose To evaluate the uncertainty of radiomics features from contrast-enhanced breath-hold helical CT scans of non-small cell lung cancer for both manual and semi-automatic segmentation due to intra-observer, inter-observer, and inter-software reliability. Methods Three radiation oncologists manually delineated lung tumors twice from 10 CT scans using two software tools (3D-Slicer and MIM Maestro). Additionally, three observers without formal clinical training were instructed to use two semi-automatic segmentation tools, Lesion Sizing Toolkit (LSTK) and GrowCut, to delineate the same tumor volumes. The accuracy of the semi-automatic contours was assessed by comparison with physician manual contours using Dice similarity coefficients and Hausdorff distances. Eighty-three radiomics features were calculated for each delineated tumor contour. Informative features were identified based on their dynamic range and correlation to other features. Feature reliability was then evaluated using intra-class correlation coefficients (ICC). Feature range was used to evaluate the uncertainty of the segmentation methods. Results From the initial set of 83 features, 40 radiomics features were found to be informative, and these 40 features were used in the subsequent analyses. For both intra-observer and inter-observer reliability, LSTK had higher reliability than GrowCut and the two manual segmentation tools. All observers achieved consistently high ICC values when using LSTK, but the ICC value varied greatly for each observer when using GrowCut and the manual segmentation tools. For inter-software reliability, features were not reproducible across the software tools for either manual or semi-automatic segmentation methods. Additionally, no feature category was found to be more reproducible than another feature category. Feature ranges of LSTK contours were smaller than those of manual contours for all features. Conclusion Radiomics features extracted from LSTK contours were highly reliable across and among observers. With semi-automatic segmentation tools, observers without formal clinical training were comparable to physicians in evaluating tumor segmentation.
- Published
- 2018