MRI is increasingly being used in the diagnosis of prostate cancer (PCa), with diffusion MRI (dMRI) playing an integral role. When combined with computational models, dMRI can estimate microstructural information such as cell size. Conventionally, such models are fit with a nonlinear least squares (NLLS) curve fitting approach, associated with a high computational cost. Supervised deep neural networks (DNNs) are an efficient alternative, however their performance is significantly affected by the underlying distribution of the synthetic training data. Self-supervised learning is an attractive alternative, where instead of using a separate training dataset, the network learns the features of the input data itself. This approach has only been applied to fitting of trivial dMRI models thus far. Here, we introduce a self-supervised DNN to estimate the parameters of the VERDICT (Vascular, Extracellular and Restricted DIffusion for Cytometry in Tumours) model for prostate. We demonstrate, for the first time, fitting of a complex three-compartment biophysical model with machine learning without the requirement of explicit training labels. We compare the estimation performance to baseline NLLS and supervised DNN methods, observing improvement in estimation accuracy and reduction in bias with respect to ground truth values. Our approach also achieves a higher confidence level for discrimination between cancerous and benign prostate tissue in comparison to the other methods on a dataset of 20 PCa patients, indicating potential for accurate tumour characterisation.

翻译：MRI在前列腺癌（PCa）诊断中的应用日益广泛，其中弥散加权成像（dMRI）发挥着关键作用。通过与计算模型相结合，dMRI能够估算细胞尺寸等微观结构信息。传统上，此类模型采用非线性最小二乘（NLLS）曲线拟合方法，但该方法计算成本较高。监督式深度神经网络（DNN）是一种高效的替代方案，但其性能显著受限于合成训练数据的潜在分布。自监督学习作为更具吸引力的替代方案，其网络无需独立训练数据集，而是直接从输入数据中学习特征。然而，该方法目前仅被应用于简单dMRI模型的参数拟合。本文首次提出将自监督DNN应用于前列腺VERDICT（肿瘤细胞计数的血管、细胞外及受限弥散模型）模型的参数估计，实现了复杂三室生物物理模型在无显式训练标签条件下的机器学习拟合。我们将参数估计性能与基线NLLS方法和监督式DNN方法进行比较，结果表明：本文方法在估算精度上有所提升且系统偏差更小。通过对20例PCa患者数据集的分析，该方法在区分癌性与良性前列腺组织方面获得了更高的置信度，显示出准确表征肿瘤的潜力。