Gundogdu Batuhan, Chatterjee Aritrick, Medved Milica, Bagci Ulas, Karczmar Gregory S, Oto Aytekin
Department of Radiology, University of Chicago, 5801 S Ellis Ave, Chicago, IL 60637.
Sanford J. Grossman Center of Excellence in Prostate Imaging and Image Guided Therapy, University of Chicago, Chicago, Ill.
Radiol Artif Intell. 2025 Mar;7(2):e240167. doi: 10.1148/ryai.240167.
Purpose To evaluate the performance of Physics-Informed Autoencoder (PIA), a self-supervised deep learning model, in measuring tissue-based biomarkers for prostate cancer (PCa) using hybrid multidimensional MRI. Materials and Methods This retrospective study introduces PIA, an emerging self-supervised deep learning model that integrates a three-compartment diffusion-relaxation model with hybrid multidimensional MRI. PIA was trained to encode the biophysical model into a deep neural network to predict measurements of tissue-specific biomarkers for PCa without extensive training data requirements. Comprehensive in silico and in vivo experiments, using histopathology measurements as the reference standard, were conducted to validate the model's efficacy in comparison to the traditional nonlinear least squares (NLLS) algorithm. PIA's robustness to noise was tested in in silico experiments with varying signal-to-noise ratio (SNR) conditions, and in vivo performance for estimating volume fractions was evaluated in 21 patients (mean age, 60 years ± 6.6 [SD]; all male) with PCa (71 regions of interest). Evaluation metrics included the intraclass correlation coefficient (ICC) and Pearson correlation coefficient. Results PIA predicted the reference standard tissue parameters with high accuracy, outperforming conventional NLLS methods, especially under noisy conditions ( = 0.80 vs 0.65, < .001 for epithelium volume at SNR of 20:1). In in vivo validation, PIA's noninvasive volume fraction estimates matched quantitative histology (ICC, 0.94, 0.85, and 0.92 for epithelium, stroma, and lumen compartments, respectively; < .001 for all). PIA's measurements strongly correlated with PCa aggressiveness ( = 0.75, < .001). Furthermore, PIA ran 10 000 faster than NLLS (0.18 second vs 40 minutes per image). Conclusion PIA provided accurate prostate tissue biomarker measurements from MRI data with better robustness to noise and computational efficiency compared with the NLLS algorithm. The results demonstrate the potential of PIA as an accurate, noninvasive, and explainable artificial intelligence method for PCa detection. Prostate, Stacked Auto-Encoders, Tissue Characterization, MR-Diffusion-weighted Imaging ©RSNA, 2025 See also commentary by Adams and Bressem in this issue.
目的 评估物理信息自动编码器（PIA）这一自监督深度学习模型，在使用混合多维磁共振成像（MRI）测量前列腺癌（PCa）基于组织的生物标志物方面的性能。材料与方法 这项回顾性研究引入了PIA，这是一种新兴的自监督深度学习模型，它将三室扩散 - 弛豫模型与混合多维MRI相结合。PIA经过训练，将生物物理模型编码到深度神经网络中，以预测PCa组织特异性生物标志物的测量值，而无需大量训练数据。使用组织病理学测量作为参考标准，进行了全面的计算机模拟和体内实验，以验证该模型与传统非线性最小二乘法（NLLS）算法相比的有效性。在不同信噪比（SNR）条件的计算机模拟实验中测试了PIA对噪声的鲁棒性，并在21例（平均年龄60岁±6.6[标准差]；均为男性）PCa患者（71个感兴趣区域）中评估了其在体内估计体积分数的性能。评估指标包括组内相关系数（ICC）和皮尔逊相关系数。结果 PIA以高精度预测了参考标准组织参数，优于传统的NLLS方法，尤其是在噪声条件下（在SNR为20:1时，上皮体积的ICC为0.80，而NLLS为0.65，P<0.001）。在体内验证中，PIA的无创体积分数估计与定量组织学结果相符（上皮、基质和管腔室的ICC分别为0.94、0.85和0.92；均P<0.001）。PIA的测量结果与PCa侵袭性密切相关（r = 0.75，P<0.001）。此外，PIA的运行速度比NLLS快10000倍（每张图像0.18秒对40分钟）。结论 与NLLS算法相比，PIA能从MRI数据中准确测量前列腺组织生物标志物，对噪声具有更好的鲁棒性和计算效率。结果证明了PIA作为一种用于PCa检测的准确、无创且可解释的人工智能方法的潜力。前列腺、堆叠自动编码器、组织表征、磁共振扩散加权成像 ©RSNA，2025 另见本期Adams和Bressem的评论。
