文献速递前列腺癌

深度学习预测根治性前列腺切除术难度:一种新的评估方案

Deep Learning for Predicting Difficulty in Radical Prostatectomy: A Novel Evaluation Scheme.
PubMed 文献 · Urology · 2025-01-13

本研究通过两阶段深度学习方法从术前磁共振成像中探索评估根治性前列腺切除术难度的新指标,在来自两个真实队列的290例腹腔镜和机器人辅助根治性前列腺切除术患者中验证了该流程和指标。研究发现前列腺体积、盆腔与前列腺空间关系等系数与估计失血量和手术时间具有统计学显著性,整个流程在外部数据集上验证结果一致。

要点

  • 两阶段深度学习方法可从前列腺MRI中自动分割前列腺和骨盆并定位15个解剖标志点。
  • 描述盆腔-前列腺空间约束的指标与根治性前列腺切除术的失血量和手术时间显著相关。
  • 孤立的骨盆测量指标对手术结局影响极小。

核心结论

  • 两阶段解剖标志点定位方法可行,描述盆腔-前列腺空间约束的指标显著影响根治性前列腺切除术的手术难度,导致失血量增加和手术时间延长,而孤立的骨盆测量对手术结局影响极小。

研究设计与样本

  • 研究纳入来自两个真实队列的290例接受腹腔镜和机器人辅助根治性前列腺切除术的患者,采用两阶段深度学习方法,训练nnUNet_v2自适应模型分割前列腺和骨盆,并使用改进的PointNet网络基于高斯热图间接回归15个解剖标志点。

主要发现

  • 两阶段流程取得良好的分割和标志点定位结果,平均验证Dice系数为0.8641,达到毫米级精度。
  • 前列腺体积(PV)、ρ、PT、PAP、AG、PSD1、PSD2、πρ2/ISTA、AG+PG、AG×PG、PSD2×ρ和PAP/(AG+PG)与估计失血量(EBL)的系数具有统计学显著性。
  • PSD2和PSD2×ρ与手术时间的系数具有统计学显著性。
  • 整个流程在外部数据集上验证,结果一致。

关键数值与推荐

  • 原文未报告具体的阈值、推荐等级或给药方案。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: To explore new metrics for assessing radical prostatectomy difficulty through a two-stage deep learning method from preoperative magnetic resonance imaging. METHODS: The procedure and metrics were validated through 290 patients consisting of laparoscopic and robot-assisted radical prostatectomy procedures from two real cohorts. The nnUNet_v2 adaptive model was trained to perform accurate segmentation of the prostate and pelvis. A modified network PointNet was used for indirectly regressing 15 anatomical landmarks based on Gaussian heatmaps. Novel metrics proposed in this study that characterized the spatial relationship between the prostate and pelvis were included to evaluate the surgical difficulty. RESULTS: The two-stage process achieved decent segmentation and landmark localization results with the mean validation dice of 0.8641 and millimeter-level accuracy. We found the coefficients of PV, ρ, PT, PAP, AG, PSD1, PSD2, πρ2/ISTA, AG+PG, AG×PG, PSD2×ρ, and PAP/(AG+PG) with Estimated Blood Loss and PSD2, PSD2×ρ with Operation Time, respectively, with statistic significant, which provides possibilities for assessing surgical difficulty evaluation. The entire pipeline had been validated on the external dataset, and the results were consistent. CONCLUSION: The two-stage anatomical landmark localization approach is feasible. Indicators describing pelvic-prostate spatial constraints significantly impact surgical difficulty in radical prostatectomy, leading to increased blood loss and longer operation times, while isolated pelvic measurements have minimal effect on surgical outcomes.

来源:Urology,查看原文。版权归原作者所有。

引用

  1. Mei H, Wang Z, Zheng Q, et al. Deep Learning for Predicting Difficulty in Radical Prostatectomy: A Novel Evaluation Scheme. Urology. 2025. PMID: 39814211. doi:10.1016/j.urology.2025.01.028

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。