Department of Radiology, Isala, Zwolle, the Netherlands; Imaging & Oncology Division, University Medical Center Utrecht, Utrecht, the Netherlands.
Imaging & Oncology Division, University Medical Center Utrecht, Utrecht, the Netherlands.
Eur J Radiol. 2024 Sep;178:111602. doi: 10.1016/j.ejrad.2024.111602. Epub 2024 Jul 3.
The non-perfused volume divided by total fibroid load (NPV/TFL) is a predictive outcome parameter for MRI-guided high-intensity focused ultrasound (MR-HIFU) treatments of uterine fibroids, which is related to long-term symptom relief. In current clinical practice, the MR-HIFU outcome parameters are typically determined by visual inspection, so an automated computer-aided method could facilitate objective outcome quantification. The objective of this study was to develop and evaluate a deep learning-based segmentation algorithm for volume measurements of the uterus, uterine fibroids, and NPVs in MRI in order to automatically quantify the NPV/TFL.
A segmentation pipeline was developed and evaluated using expert manual segmentations of MRI scans of 115 uterine fibroid patients, screened for and/or undergoing MR-HIFU treatment. The pipeline contained three separate neural networks, one per target structure. The first step in the pipeline was uterus segmentation from contrast-enhanced (CE)-T1w scans. This segmentation was subsequently used to remove non-uterus background tissue for NPV and fibroid segmentation. In the following step, NPVs were segmented from uterus-only CE-T1w scans. Finally, fibroids were segmented from uterus-only T2w scans. The segmentations were used to calculate the volume for each structure. Reliability and agreement between manual and automatic segmentations, volumes, and NPV/TFLs were assessed.
For treatment scans, the Dice similarity coefficients (DSC) between the manually and automatically obtained segmentations were 0.90 (uterus), 0.84 (NPV) and 0.74 (fibroid). Intraclass correlation coefficients (ICC) were 1.00 [0.99, 1.00] (uterus), 0.99 [0.98, 1.00] (NPV) and 0.98 [0.95, 0.99] (fibroid) between manually and automatically derived volumes. For manually and automatically derived NPV/TFLs, the mean difference was 5% [-41%, 51%] (ICC: 0.66 [0.32, 0.85]).
The algorithm presented in this study automatically calculates uterus volume, fibroid load, and NPVs, which could lead to more objective outcome quantification after MR-HIFU treatments of uterine fibroids in comparison to visual inspection. When robustness has been ascertained in a future study, this tool may eventually be employed in clinical practice to automatically measure the NPV/TFL after MR-HIFU procedures of uterine fibroids.
非灌注体积与肌瘤总负荷比（NPV/TFL）是 MRI 引导高强度聚焦超声（MR-HIFU）治疗子宫肌瘤的预测结果参数，与长期症状缓解相关。在当前的临床实践中，MR-HIFU 结果参数通常通过目视检查确定，因此自动化的计算机辅助方法可以促进客观的结果量化。本研究的目的是开发和评估一种基于深度学习的分割算法，用于测量 MRI 中子宫、子宫肌瘤和 NPV 的体积，以便自动量化 NPV/TFL。
使用 115 名接受过 MR-HIFU 治疗的子宫纤维瘤患者的 MRI 扫描的专家手动分割来开发和评估分割管道。该管道包含三个独立的神经网络，每个目标结构一个。管道的第一步是从对比增强（CE）-T1w 扫描中分割子宫。然后，此分割用于去除 NPV 和肌瘤分割的非子宫背景组织。在下一步中，从仅包含子宫的 CE-T1w 扫描中分割 NPV。最后，从仅包含 T2w 的子宫扫描中分割肌瘤。分割用于计算每个结构的体积。评估了手动和自动分割、体积和 NPV/TFL 之间的可靠性和一致性。
对于治疗扫描，手动和自动分割之间的 Dice 相似系数（DSC）分别为 0.90（子宫）、0.84（NPV）和 0.74（肌瘤）。手动和自动获得的体积之间的组内相关系数（ICC）分别为 1.00[0.99，1.00]（子宫）、0.99[0.98，1.00]（NPV）和 0.98[0.95，0.99]（肌瘤）。手动和自动获得的 NPV/TFL 之间的平均差异为 5%[-41%，51%]（ICC：0.66[0.32，0.85]）。
本研究中提出的算法可自动计算子宫体积、肌瘤负荷和 NPV，与目视检查相比，这可能导致在 MRI 引导高强度聚焦超声治疗子宫肌瘤后进行更客观的结果量化。在未来的研究中确定了稳健性后，该工具最终可能会在临床实践中用于自动测量 MRI 引导高强度聚焦超声治疗子宫肌瘤后的 NPV/TFL。
