Differentiation of pulmonary sclerosing pneumocytoma from solid malignant pulmonary nodules by radiomic analysis on multiphasic CT

Abstract

Purpose To investigate the diagnostic value and feasibility of radiomics‐based texture analysis in differentiating pulmonary sclerosing pneumocytoma (PSP) from solid malignant pulmonary nodules (SMPN) on single‐ and three‐phase computed tomography (CT) images. Materials and Methods A total of 25 PSP patients and 35 SMPN patients with pathologically confirmed results were retrospectively included in this study. For each patient, the tumor regions were manually labeled in images acquired at the noncontrast phase (NCP), arterial phase (AP), and venous phase (VP). The least absolute shrinkage and selection operator (LASSO) method was used to select the most useful predictive features extracted from the CT images. The predictive models that discriminate PSP from SMPN based on single‐phase CT images (NCP, AP, and VP) or three‐phase CT images (Combined model) were developed and validated through fivefold cross‐validation using a logistic regression classifier. Model performance was evaluated using receiver operating characteristic (ROC) analysis. The predictive performance was also compared between the Combined model and human readers. Results Four, five, and five features were selected from NCP, AP, and VP CT images for the development of radiomic models, respectively. The NCP, AP, and VP models exhibited areas under the curve (AUCs) of 0.748 (95% confidence interval [CI], 0.620–0.852), 0.749 (95% CI, 0.620–0.852), and 0.790 (95% CI, 0.665–0.884) in the validation dataset, respectively. The Combined model based on three‐phase CT images outperformed the NCP, AP, and VP models (all p < 0.05), yielding an AUC of 0.882 (95% CI, 0.773–0.951) in the validation dataset. The Combined model displayed noninferior performance compared to two senior radiologists; however, it outperformed two junior radiologists (p = 0.004 and 0.001, respectively). Conclusion The Combined model based on radiomic features extracted from three‐phase CT images achieved radiologist‐level performance and could be used as promising noninvasive tool to differentiate PSP from SMPN.

Neural network-based model for evaluating inert nodules and volume doubling time in T1 lung adenocarcinoma: a nested case−control study

“…Heuvelmans et al. ( 13 ) found that in the baseline screening of the Nelson test, all malignant, fast-growing pulmonary nodules referred after 3-month follow-up CT had a VDT ≤ 232 days. Lowering the cut off VDT may reduce false-positive referrals.…”

“…With the continuous development of deep learning, the clinical application of artificial intelligence pulmonary nodule diagnosis assistant systems is becoming increasingly mature. In many studies, such systems have been shown to provide good effectiveness in assisting the detection of pulmonary nodules (12)(13)(14). Some researchers have studied the effect of nodule volume-doubling time on nodules (15-19), while others have explored the growth rate of pulmonary nodules and the natural history of invasive adenocarcinoma (20-22).…”

Feature selection methods and predictive models in CT lung cancer radiomics

“…Typically, these studies are interested in determining malignancy, specific gene expression or phenotyping, or segmentation. 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 ,…”

“…Classification studies create a model that can stratify a cohort into distinct bins determined by the study. Typically, these studies are interested in determining malignancy, specific gene expression or phenotyping, or segmentation 23–99 . Prognostics studies create models that score individual cases along a sliding scale.…”

Measuring the bias of incorrect application of feature selection when using cross-validation in radiomics

“…Unfortunately, sometimes illustrations of the radiomics pipeline are simplified and make the impression that feature selection is a preprocessing step before modeling applied to the whole data and that cross-validation is only part of the model selection [3,12,16]. Similarly, it is not always clear whether studies that use cross-validation but not an explicit validation set have applied feature selection incorrectly or whether it is just misleadingly described [17][18][19][20][21][22][23][24][25][26][27][28][29]. In fact, only a few studies describe their methodology in full [6].…”