Performance of alternative manual and automated deep learning segmentation techniques for the prediction of benign and malignant lung nodules

作者：Heather M. Selby, Pritam Mukherjee, Christopher Parham, Sachin B. Malik, Olivier Gevaert, Sandy Napel, Rajesh P. Shah · 发表于：Journal of medical imaging · 年份：2023 · DOI：10.1117/1.jmi.10.4.044006 · 被引用次数：1 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Lung Cancer Diagnosis and Treatment、Advanced Radiotherapy Techniques

PurposeWe aim to evaluate the performance of radiomic biopsy (RB), best-fit bounding box (BB), and a deep-learning-based segmentation method called no-new-U-Net (nnU-Net), compared to the standard full manual (FM) segmentation method for predicting benign and malignant lung nodules using a computed tomography (CT) radiomic machine learning model.Materials and MethodsA total of 188 CT scans of lung nodules from 2 institutions were used for our study. One radiologist identified and delineated all 188 lung nodules, whereas a second radiologist segmented a subset (n = 20) of these nodules. Both radiologists employed FM and RB segmentation methods. BB segmentations were generated computationally from the FM segmentations. The nnU-Net, a deep-learning-based segmentation method, performed automatic nodule detection and segmentation. The time radiologists took to perform segmentations was recorded. Radiomic features were extracted from each segmentation method, and models to predict benign and malignant lung nodules were developed. The Kruskal–Wallis and DeLong tests were used to compare segmentation times and areas under the curve (AUC), respectively.ResultsFor the delineation of the FM, RB, and BB segmentations, the two radiologists required a median time (IQR) of 113 (54 to 251.5), 21 (9.25 to 38), and 16 (12 to 64.25) s, respectively (p = 0.04). In dataset 1, the mean AUC (95% CI) of the FM, RB, BB, and nnU-Net model were 0.964 (0.96 to 0.968), 0.985 (0.983 to 0.987), 0.961 (0.95...