人工智能
计算机科学
分割
深度学习
机器学习
算法
作者
Katharina Hoebel,Christopher P. Bridge,Sara Ahmed,Oluwatosin O. Akintola,Caroline D. Chung,Raymond Y. Huang,Jason Michael Johnson,Albert Eusik Kim,K. Ina Ly,Ken Chang,Jay Patel,Marco C. Pinho,Tracy T. Batchelor,Bruce Robert Rosen,Elizabeth Robins Gerstner,Jayashree Kalpathy–Cramer
出处
期刊:Radiology
[Radiological Society of North America]
日期:2023-11-22
卷期号:6 (1): e220231-e220231
被引量:19
摘要
Purpose To present results from a literature survey on practices in deep learning segmentation algorithm evaluation and perform a study on expert quality perception of brain tumor segmentation. Materials and Methods A total of 180 articles reporting on brain tumor segmentation algorithms were surveyed for the reported quality evaluation. Additionally, ratings of segmentation quality on a four-point scale were collected from medical professionals for 60 brain tumor segmentation cases. Results Of the surveyed articles, Dice score, sensitivity, and Hausdorff distance were the most popular metrics to report segmentation performance. Notably, only 2.8% of the articles included clinical experts’ evaluation of segmentation quality. The experimental results revealed a low interrater agreement (Krippendorff α, 0.34) in experts’ segmentation quality perception. Furthermore, the correlations between the ratings and commonly used quantitative quality metrics were low (Kendall tau between Dice score and mean rating, 0.23; Kendall tau between Hausdorff distance and mean rating, 0.51), with large variability among the experts. Conclusion The results demonstrate that quality ratings are prone to variability due to the ambiguity of tumor boundaries and individual perceptual differences, and existing metrics do not capture the clinical perception of segmentation quality. Keywords: Brain Tumor Segmentation, Deep Learning Algorithms, Glioblastoma, Cancer, Machine Learning Clinical trial registration nos. NCT 00756106 and NCT 00662506 Supplemental material is available for this article. © RSNA, 2023
科研通智能强力驱动
Strongly Powered by AbleSci AI