Scholarlink

Background <p>To develop and test the performance of a fully automated system for classifying renal tumor subtypes via deep machine learning for automated segmentation and classification.</p> Materials and methods <p>The model was developed using computed tomography (CT) images of pathologically proven renal tumors collected from a prospective cohort at a medical center between March 2016 and December 2020. A total of 561 renal tumors were included: 233 clear cell renal cell carcinomas (RCCs), 82 papillary RCCs, 74 chromophobe RCCs, and 172 angiomyolipomas. Renal tumor masks manually drawn on contrast-enhanced CT images were used to develop a 3D U-Net-based deep learning model for fully automated tumor segmentation. After segmentation, the entire classification pipeline, including feature extraction and subtype classification, was conducted without any manual intervention. Both conventional radiological features (Hounsfield units, HUs) and radiomic features extracted from areas predicted by the deep learning models were used to develop an algorithm for classifying renal tumor subtypes via a random forest classifier. The performance of the segmentation model was evaluated using the Dice similarity coefficient, while the classification model was assessed based on accuracy, sensitivity, and specificity.</p> Results <p>For tumors larger than 4&#xa0;cm, the Dice similarity coefficient (DSC) for automated segmentation was 0.83, while for tumors smaller than 4&#xa0;cm, the DSC was 0.65. The classification accuracy (ACC) for distinguishing RCC subtypes was 0.77 for tumors larger than 4&#xa0;cm and 0.68 for tumors smaller than 4&#xa0;cm. Additionally, the accuracy for benign versus malignant classification was 0.85.</p> Conclusions <p>Our automatic segmentation and classifier model showed promising results for renal tumor segmentation and classification.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Fully automated segmentation and classification of renal tumors on CT scans via machine learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年1月29日

查看全文
  • Jang Hee Han,
  • Byung Woo Kim,
  • Taek Min Kim,
  • Ji Yeon Ko,
  • Seung Jae Choi,
  • Minho Kang,
  • Sang Youn Kim,
  • Jeong Yeon Cho,
  • Ja Hyeon Ku,
  • Cheol Kwak,
  • Young-Gon Kim,
  • Chang Wook Jeong

摘要

Background

To develop and test the performance of a fully automated system for classifying renal tumor subtypes via deep machine learning for automated segmentation and classification.

Materials and methods

The model was developed using computed tomography (CT) images of pathologically proven renal tumors collected from a prospective cohort at a medical center between March 2016 and December 2020. A total of 561 renal tumors were included: 233 clear cell renal cell carcinomas (RCCs), 82 papillary RCCs, 74 chromophobe RCCs, and 172 angiomyolipomas. Renal tumor masks manually drawn on contrast-enhanced CT images were used to develop a 3D U-Net-based deep learning model for fully automated tumor segmentation. After segmentation, the entire classification pipeline, including feature extraction and subtype classification, was conducted without any manual intervention. Both conventional radiological features (Hounsfield units, HUs) and radiomic features extracted from areas predicted by the deep learning models were used to develop an algorithm for classifying renal tumor subtypes via a random forest classifier. The performance of the segmentation model was evaluated using the Dice similarity coefficient, while the classification model was assessed based on accuracy, sensitivity, and specificity.

Results

For tumors larger than 4 cm, the Dice similarity coefficient (DSC) for automated segmentation was 0.83, while for tumors smaller than 4 cm, the DSC was 0.65. The classification accuracy (ACC) for distinguishing RCC subtypes was 0.77 for tumors larger than 4 cm and 0.68 for tumors smaller than 4 cm. Additionally, the accuracy for benign versus malignant classification was 0.85.

Conclusions

Our automatic segmentation and classifier model showed promising results for renal tumor segmentation and classification.