Gade Marius, Nguyen Kevin Mekhaphan, Gedde Sol, Fernandez-Quilez Alvaro
Department of Electrical Engineering and Computer Science, University of Stavanger, Stavanger, Norway.
Stavanger Medical Imaging Laboratory (SMIL), Department of Radiology, Stavanger University Hospital, Stavanger, Norway.
Insights Imaging. 2024 Nov 29;15(1):286. doi: 10.1186/s13244-024-01863-w.
To estimate the uncertainty of a deep learning (DL)-based prostate segmentation algorithm through conformal prediction (CP) and to assess its effect on the calculation of the prostate volume (PV) in patients at risk of prostate cancer (PC).
Three-hundred seventy-seven multi-center 3-Tesla axial T2-weighted exams from biopsied males (66.64 7.47 years) at risk of PC were retrospectively included in the study. Assessment of PV based on PI-RADS 2.1 ellipsoid formula ( ) was available for included patients. Prostate segmentations were obtained from a DL model and used to calculate the PV ( ). CP was applied at a confidence level of 85% to flag unreliable pixel segmentations of the DL model. Subsequently, the PV ( ) was calculated when disregarding uncertain pixel segmentations. Agreement between and was evaluated against the reference standard . Intraclass correlation coefficient (ICC) and Bland-Altman plots were used to assess the agreement. The relative volume difference (RVD) was used to evaluate the PV calculation accuracy, and the Wilcoxon Signed-Rank Test was used to assess statistical differences. A p-value < 0.05 was considered statistically significant.
Conformal prediction significantly reduced RVD when compared to the DL algorithm (RVD = - 2.81 8.85 and RVD = -8.01 11.50). showed a significantly larger agreement than when using the reference standard (mean difference (95% limits of agreement) : 1.27 mL (- 13.64; 16.17 mL) : 6.07 mL (- 14.29; 26.42 mL)), with an excellent ICC ( : 0.97 (95% CI: 0.97 to 0.98)).
Uncertainty quantification through CP increases the accuracy and reliability of DL-based PV assessment in patients at risk of PC.
Conformal prediction can flag uncertain pixel predictions of DL-based prostate MRI segmentation at a desired confidence level, increasing the reliability and safety of prostate volume assessment in patients at risk of prostate cancer.
Conformal prediction can flag uncertain pixel predictions of prostate segmentations at a user-defined confidence level. Deep learning with conformal prediction shows high accuracy in prostate volumetric assessment. Agreement between automatic and ellipsoid-derived volume was significantly larger with conformal prediction.
通过共形预测（CP）评估基于深度学习（DL）的前列腺分割算法的不确定性，并评估其对前列腺癌（PC）风险患者前列腺体积（PV）计算的影响。
本研究回顾性纳入了377例有PC风险的接受活检男性（年龄66.64±7.47岁）的多中心3特斯拉轴向T2加权检查。纳入患者可根据PI-RADS 2.1椭球公式（ ）进行PV评估。从DL模型获得前列腺分割结果并用于计算PV（ ）。以85%的置信水平应用CP来标记DL模型中不可靠的像素分割。随后，在忽略不确定像素分割的情况下计算PV（ ）。将 与 的一致性与参考标准 进行比较评估。使用组内相关系数（ICC）和Bland-Altman图评估一致性。使用相对体积差异（RVD）评估PV计算准确性，并使用Wilcoxon符号秩检验评估统计学差异。p值<0.05被认为具有统计学意义。
与DL算法相比，共形预测显著降低了RVD（RVD = -2.81±8.85和RVD = -8.01±11.50）。当使用参考标准 时， 显示出比 显著更大的一致性（平均差异（95%一致性界限） ：1.27 mL（-13.64；16.17 mL） ：6.07 mL（-14.29；26.42 mL）），ICC极佳（ ：0.97（95% CI：0.97至0.98））。
通过CP进行不确定性量化可提高PC风险患者基于DL的PV评估的准确性和可靠性。
共形预测可以在所需的置信水平下标记基于DL的前列腺MRI分割中不确定的像素预测，提高前列腺癌风险患者前列腺体积评估的可靠性和安全性。
共形预测可以在用户定义的置信水平下标记前列腺分割中不确定的像素预测。具有共形预测的深度学习在前列腺体积评估中显示出高精度。共形预测下自动分割体积与椭球衍生体积之间的一致性显著更大。
