Abstract：
BACKGROUND: 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.
METHODS: 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.
RESULTS: 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]).
CONCLUSIONS: 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.
METHODS: 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.
RESULTS: 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]).
CONCLUSIONS: 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.
摘要：
背景：非灌注体积除以总肌瘤负荷（NPV/TFL）是MRI引导的高强度聚焦超声（MR-HIFU）治疗子宫肌瘤的预测结果参数，这与长期症状缓解有关。在目前的临床实践中，MR-HIFU结果参数通常通过目视检查确定，因此，一种自动化的计算机辅助方法可以促进客观结果的量化。这项研究的目的是开发和评估一种基于深度学习的子宫体积测量分割算法，子宫肌瘤,和MRI中的NPV，以便自动量化NPV/TFL。
方法：对115例子宫肌瘤患者进行MRI扫描的专家手动分割，开发并评估了分割管道，筛查和/或接受MR-HIFU治疗。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。该分割随后用于去除非子宫背景组织以进行NPV和纤维瘤分割。在接下来的步骤中，NPV从仅子宫CE-T1w扫描中分割。最后,根据仅子宫的T2w扫描对肌瘤进行分割。分割用于计算每个结构的体积。手动和自动分割之间的可靠性和协议，卷,和NPV/TFL进行评估。
结果：对于治疗扫描，手动和自动获得的切分之间的骰子相似系数（DSC）为0.90（子宫），0.84（净现值）和0.74（肌瘤）。组内相关系数（ICC）为1.00[0.99，1.00]（子宫），手动和自动导出体积之间的0.99[0.98,1.00](NPV)和0.98[0.95,0.99](纤维瘤)。对于手动和自动导出的NPV/TFL，平均差异为5%[-41%，51%](ICC：0.66[0.32，0.85])。
结论：本研究中提出的算法自动计算子宫体积，肌瘤负荷，和NPV，与目视检查相比，这可能导致MR-HIFU治疗子宫肌瘤后更客观的结果量化。当在未来的研究中确定了稳健性时，该工具最终可用于临床实践,在子宫肌瘤MR-HIFU手术后自动测量NPV/TFL.
方法：对115例子宫肌瘤患者进行MRI扫描的专家手动分割，开发并评估了分割管道，筛查和/或接受MR-HIFU治疗。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。该分割随后用于去除非子宫背景组织以进行NPV和纤维瘤分割。在接下来的步骤中，NPV从仅子宫CE-T1w扫描中分割。最后,根据仅子宫的T2w扫描对肌瘤进行分割。分割用于计算每个结构的体积。手动和自动分割之间的可靠性和协议，卷,和NPV/TFL进行评估。
结果：对于治疗扫描，手动和自动获得的切分之间的骰子相似系数（DSC）为0.90（子宫），0.84（净现值）和0.74（肌瘤）。组内相关系数（ICC）为1.00[0.99，1.00]（子宫），手动和自动导出体积之间的0.99[0.98,1.00](NPV)和0.98[0.95,0.99](纤维瘤)。对于手动和自动导出的NPV/TFL，平均差异为5%[-41%，51%](ICC：0.66[0.32，0.85])。
结论：本研究中提出的算法自动计算子宫体积，肌瘤负荷，和NPV，与目视检查相比，这可能导致MR-HIFU治疗子宫肌瘤后更客观的结果量化。当在未来的研究中确定了稳健性时，该工具最终可用于临床实践,在子宫肌瘤MR-HIFU手术后自动测量NPV/TFL.
