Affiliations 1 Southeast University, Laboratory of Image Science and Technology, Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing, Centre de Recherche en Information Biomédicale Sino-français (CRIBs), Nanjing, 210096, P.R. China. 2 Department of Radiation Oncology Physics and Technology, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, 250117, China. 3 Shandong Key Laboratory of Digital Medicine and Computer Assisted Surgery, The Affiliated Hospital of Qingdao University, Qingdao, 266000, P.R. China.
Background: Radiomics has been considered an imaging marker for capturing quantitative image information . The introduction of radiomics to image segmentation is desirable but challenging. Purpose: This study aims to develop and validate a radiomics-based framework for image segmentation . Methods: RFIS is designed using features extracted from volume created by sliding window . The 53 svfeatures are extracted from 11 phantom series. Outliers in the svfeature datasets are detected by isolation ...更多
Background: Radiomics has been considered an imaging marker for capturing quantitative image information . The introduction of radiomics to image segmentation is desirable but challenging. Purpose: This study aims to develop and validate a radiomics-based framework for image segmentation . Methods: RFIS is designed using features extracted from volume created by sliding window . The 53 svfeatures are extracted from 11 phantom series. Outliers in the svfeature datasets are detected by isolation forest and specified as the mean value. The percentage coefficient of variation is calculated to evaluate the reproducibility of svfeatures. RFIS is constructed and applied to the gross target volume segmentation from the peritumoral region to assess its feasibility. The 127 lung cancer images are enrolled. The test-retest method, correlation matrix, and Mann-Whitney U test are used to select non-redundant svfeatures of statistical significance from the reproducible svfeatures. The synthetic minority over-sampling technique is utilized to balance the minority group in the training sets. The support vector machine is employed for RFIS construction, which is tuned in the training set using ten-fold stratified cross-validation and then evaluated in the test sets. The swvolumes with the consistent classification results are grouped and merged. Mode filtering is performed to remove very small subvolumes and create relatively large regions of completely uniform character. In addition, RFIS performance is evaluated by the area under the receiver operating characteristic curve , accuracy, sensitivity, specificity, and dice similarity coefficient . Results: 30249 phantom and 145008 patient image swvolumes were analyzed. 49 svfeatures represented excellent reproducibility. 45 features included five categories that passed test-retest analysis. 13 svfeatures svfeatures were selected for RFIS construction. RFIS showed an average sensitivity of 0.848, a specificity of 0.821, an accuracy of 83.48% , and an AUC of 0.906 with cross-validation. The sensitivity, specificity, accuracy and AUC were equal to 0.762, 0.840, 82.29% , and 0.877 in the test set, respectively. GTV was segmented by grouping and merging swvolume with identical classification results. The mean DSC after mode filtering was 0.707±0.093 in the training sets and 0.688±0.072 in the test sets. Conclusion: Reproducible svfeatures can capture the differences in QII among swvolumes. RFIS can be applied to swvolume classification, which achieves image segmentation by grouping and merging the swvolume with similar QII. This article is protected by copyright. All rights reserved.收起
