Peking University Fourth School of Clinical Medicine, Beijing, China.
Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, China.
Eur Radiol. 2024 May;34(5):2849-2860. doi: 10.1007/s00330-023-10308-9. Epub 2023 Oct 18.
To develop an automatic computer-based method that can help clinicians in assessing spine growth potential based on EOS radiographs.
We developed a deep learning-based (DL) algorithm that can mimic the human judgment process to automatically determine spine growth potential and the Risser sign based on full-length spine EOS radiographs. A total of 3383 EOS cases were collected and used for the training and test of the algorithm. Subsequently, the completed DL algorithm underwent clinical validation on an additional 440 cases and was compared to the evaluations of four clinicians.
Regarding the Risser sign, the weighted kappa value of our DL algorithm was 0.933, while that of the four clinicians ranged from 0.909 to 0.930. In the assessment of spine growth potential, the kappa value of our DL algorithm was 0.944, while the kappa values of the four clinicians were 0.916, 0.934, 0.911, and 0.920, respectively. Furthermore, our DL algorithm obtained a slightly higher accuracy (0.973) and Youden index (0.952) compared to the best values achieved by the four clinicians. In addition, the speed of our DL algorithm was 15.2 ± 0.3 s/40 cases, much faster than the inference speeds of the clinicians, ranging from 177.2 ± 28.0 s/40 cases to 241.2 ± 64.1 s/40 cases.
Our algorithm demonstrated comparable or even better performance compared to clinicians in assessing spine growth potential. This stable, efficient, and convenient algorithm seems to be a promising approach to assist doctors in clinical practice and deserves further study.
This method has the ability to quickly ascertain the spine growth potential based on EOS radiographs, and it holds promise to provide assistance to busy doctors in certain clinical scenarios.
• In the clinic, there is no available computer-based method that can automatically assess spine growth potential. • We developed a deep learning-based method that could automatically ascertain spine growth potential. • Compared with the results of the clinicians, our algorithm got comparable results.
开发一种基于计算机的自动方法，帮助临床医生根据 EOS 射线照片评估脊柱生长潜力。
我们开发了一种基于深度学习（DL）的算法，可以模拟人类判断过程，自动根据全长脊柱 EOS 射线照片确定脊柱生长潜力和 Risser 征。共收集了 3383 例 EOS 病例用于算法的训练和测试。随后，该完成的 DL 算法在另外 440 例病例上进行了临床验证，并与 4 位临床医生的评估进行了比较。
在 Risser 征方面，我们的 DL 算法的加权kappa 值为 0.933，而 4 位临床医生的范围为 0.909 至 0.930。在评估脊柱生长潜力方面，我们的 DL 算法的 kappa 值为 0.944，而 4 位临床医生的 kappa 值分别为 0.916、0.934、0.911 和 0.920。此外，我们的 DL 算法的准确性（0.973）和 Youden 指数（0.952）略高于 4 位临床医生的最佳值。此外，我们的 DL 算法的速度为 15.2 ± 0.3 s/40 例，明显快于临床医生的推理速度，范围为 177.2 ± 28.0 s/40 例至 241.2 ± 64.1 s/40 例。
与临床医生评估脊柱生长潜力相比，我们的算法表现出相当或更好的性能。这种稳定、高效、方便的算法似乎是一种有前途的方法，可以帮助医生在临床实践中，并值得进一步研究。
该方法能够快速确定 EOS 射线照片的脊柱生长潜力，有望在某些临床情况下为忙碌的医生提供帮助。
在临床上，没有可用的基于计算机的方法可以自动评估脊柱生长潜力。
我们开发了一种基于深度学习的方法，可以自动确定脊柱生长潜力。
与临床医生的结果相比，我们的算法得到了相当的结果。
