Zeleznik Roman, Weiss Jakob, Taron Jana, Guthier Christian, Bitterman Danielle S, Hancox Cindy, Kann Benjamin H, Kim Daniel W, Punglia Rinaa S, Bredfeldt Jeremy, Foldyna Borek, Eslami Parastou, Lu Michael T, Hoffmann Udo, Mak Raymond, Aerts Hugo J W L
Artificial Intelligence in Medicine (AIM) Program, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
NPJ Digit Med. 2021 Mar 5;4(1):43. doi: 10.1038/s41746-021-00416-5.
Although artificial intelligence algorithms are often developed and applied for narrow tasks, their implementation in other medical settings could help to improve patient care. Here we assess whether a deep-learning system for volumetric heart segmentation on computed tomography (CT) scans developed in cardiovascular radiology can optimize treatment planning in radiation oncology. The system was trained using multi-center data (n = 858) with manual heart segmentations provided by cardiovascular radiologists. Validation of the system was performed in an independent real-world dataset of 5677 breast cancer patients treated with radiation therapy at the Dana-Farber/Brigham and Women's Cancer Center between 2008-2018. In a subset of 20 patients, the performance of the system was compared to eight radiation oncology experts by assessing segmentation time, agreement between experts, and accuracy with and without deep-learning assistance. To compare the performance to segmentations used in the clinic, concordance and failures (defined as Dice < 0.85) of the system were evaluated in the entire dataset. The system was successfully applied without retraining. With deep-learning assistance, segmentation time significantly decreased (4.0 min [IQR 3.1-5.0] vs. 2.0 min [IQR 1.3-3.5]; p < 0.001), and agreement increased (Dice 0.95 [IQR = 0.02]; vs. 0.97 [IQR = 0.02], p < 0.001). Expert accuracy was similar with and without deep-learning assistance (Dice 0.92 [IQR = 0.02] vs. 0.92 [IQR = 0.02]; p = 0.48), and not significantly different from deep-learning-only segmentations (Dice 0.92 [IQR = 0.02]; p ≥ 0.1). In comparison to real-world data, the system showed high concordance (Dice 0.89 [IQR = 0.06]) across 5677 patients and a significantly lower failure rate (p < 0.001). These results suggest that deep-learning algorithms can successfully be applied across medical specialties and improve clinical care beyond the original field of interest.
尽管人工智能算法通常是为狭义任务而开发和应用的，但它们在其他医疗环境中的应用有助于改善患者护理。在此，我们评估心血管放射学中开发的用于计算机断层扫描（CT）扫描的心脏容积分割深度学习系统是否能优化放射肿瘤学的治疗计划。该系统使用多中心数据（n = 858）进行训练，这些数据带有心血管放射科医生提供的手动心脏分割。该系统在达纳 - 法伯/布莱根妇女癌症中心2008年至2018年接受放射治疗的5677例乳腺癌患者的独立真实世界数据集中进行了验证。在20例患者的子集中，通过评估分割时间、专家之间的一致性以及有无深度学习辅助时的准确性，将该系统的性能与八位放射肿瘤学专家进行了比较。为了将该性能与临床中使用的分割进行比较，在整个数据集中评估了该系统的一致性和失败情况（定义为Dice < 0.85）。该系统无需重新训练即可成功应用。在深度学习辅助下，分割时间显著缩短（4.0分钟[IQR 3.1 - 5.0]对2.0分钟[IQR 1.3 - 3.5]；p < 0.001），一致性提高（Dice 0.95[IQR = 0.02]对0.97[IQR = 0.02]，p < 0.001）。有无深度学习辅助时专家的准确性相似（Dice 0.92[IQR = 0.02]对0.92[IQR = 0.02]；p = 0.48），且与仅使用深度学习的分割无显著差异（Dice 0.92[IQR = 0.02]；p ≥ 0.1）。与真实世界数据相比，该系统在5677例患者中显示出高度一致性（Dice 0.89[IQR = 0.06]）且失败率显著更低（p < 0.001）。这些结果表明，深度学习算法可以成功应用于不同医学专业，并在超出原始感兴趣领域的范围内改善临床护理。
