Machine learning pipeline for automated segmentation and classification of complicated cystic renal masses on MRI: comparison with radiologists' assessments.
Authors
Affiliations (12)
Affiliations (12)
- Department of Radiology, First Medical Center of Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.
- University of Chinese Academy of Sciences, 19 (A) Yuquan Road, Shijingshan District, Beijing, 100049, China.
- Department of Radiology, Yantai Yuhuangding Hospital, 20 Yuhuangding East Road, Zhifu District, 264000, Shandong Province, China.
- Department of Pathology, First Medical Center of Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.
- Department of Medical Imaging, Beijing Huairou Hospital, 9 Courtyard, Yongtai North Street, Huairou District, Beijing, 101400, China.
- Department of Radiology, Second Medical Center of Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.
- Department of Innovative Medical Research, Hospital Management Institute, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.
- Department of Urology, Third Medical Center of Chinese PLA General Hospital, 39 Yongding Road, Haidian District, Beijing, 100089, China.
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, 95 Yongan Road, Xicheng District, Beijing, 100050, China.
- Radiology Department, Peking University First Hospital, 8 Xishiku Street, Xicheng District, Beijing, 100034, China.
- University of Chinese Academy of Sciences, 19 (A) Yuquan Road, Shijingshan District, Beijing, 100049, China. [email protected].
- Department of Radiology, First Medical Center of Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China. [email protected].
Abstract
To develop and validate a machine learning (ML)-based pipeline for automated segmentation and classification of complicated cystic renal masses (cCRMs) on MRI. This multicenter retrospective study enrolled 275 patients (median age, 48 years; 85 females) with pathologically confirmed 275 cCRMs (203 malignant) who underwent renal MRI from January 2013 to December 2023. cCRMs from one institution were used as a training set (n = 215), while those from the other three institutions served as a test set (n = 60). 3D V-Net and random forest algorithms were employed for segmentation and classification, respectively. Segmentation and classification performance was evaluated using the Dice similarity coefficient (DSC) and the area under the curve (AUC), respectively. Two junior and two senior radiologists independently classified cCRMs in the test set into Bosniak categories II-IV based on the Bosniak classification, version 2019. In the test set, the ML pipeline achieved DSC of 0.718 for cCRMs (n = 60) on excretory phase images. Additionally, classification performance of the ML pipeline (AUC = 0.835, 95% confidence interval [CI]: 0.717-0.919) significantly surpassed the junior radiologists (0.835 vs. 0.641, P = 0.042) and matched the senior radiologists (0.835 vs. 0.799, P = 0.684). The ML pipeline demonstrates expert-level diagnostic accuracy for automated segmentation and classification of cCRMs, potentially mitigating interobserver variability while maintaining robust performance across multicenter institutional data.