PDF
Full
Outline
Objective To investigate the diagnostic value of magnetic resonance imaging (MRI)-based intratumoral and peritumoral radiomics of prostate cancer (PCa) for bone metastases. Methods A total of 211 patients diagnosed with PCa by biopsy pathology at Gansu Provincial People's Hospital from January 2018 to January 2023 were retrospectively analyzed. These patients were randomly divided into a training set (n=147) and a validation set (n=64) in a 7:3 ratio. Regions of interest (ROIs) were delineated from the patients' T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient imaging (ADC) sequences to extract radiomic features. Z-score (normalization) and the LASSO algorithm were used for feature dimensionality reduction, selection, and construction. A predictive model was then built using a logistic regression (LR) machine learning classifier. The receiver operating characteristic (ROC) curve was plotted, and the area under the curve (AUC) was calculated to assess the model's performance. Calibration curves and decision curves (DCA) were plotted to evaluate the model's fit and clinical net benefit. Results Radiomic features were extracted from the tumor and peritumoral regions in each patient's T2WI, DWI, and ADC images, with a total of 312 features from each region. The LASSO regression model ultimately identified 10 intratumoral radiomic features closely related to bone metastasis, including 2 T2 sequence features, 7 DWI features, and 1 ADC sequence feature; and 9 peritumoral radiomic features, including 4 T2 sequence features, 3 DWI features, and 2 ADC sequence features. The predictive model based on intratumoral radiomic features achieved an AUC of 0.845 (95%CI 0.747-0.943), while the predictive model based on peritumoral radiomic features had an AUC of 0.818 (95%CI 0.716-0.919). A combined nomogram model incorporating intratumoral features, peritumoral radiomic features, and clinical features (including Gleason score, total prostate specific antigen, and body mass index) yielded an AUC of 0.936 (95%CI 0.902-0.970). Calibration curves indicated that the combined model had good fit, and DCA demonstrated that the combined model provided better clinical net benefit. Conclusions Peritumoral radiomics has excellent predictive value for bone metastasis in newly diagnosed PCa. Combining with intratumoral radiomics features and clinical features, it significantly enhances the predictive capability of the model.
PDF
179
79
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
