Wilson’s disease (WD) is caused by copper accumulation in the brain and liver, and if not treated early, can lead to severe disability and death. WD has shown white matter hyperintensity (WMH) in the brain magnetic resonance scans (MRI) scans, but the diagnosis is challenging due to (i) subtle intensity changes and (ii) weak training MRI when using artificial intelligence (AI). Design and validate seven types of high-performing AI-based computer-aided design (CADx) systems consisting of 3D optimized classification, and characterization of WD against controls. We propose a “conventional deep convolution neural network” (cDCNN) and an “improved DCNN” (iDCNN) where rectified linear unit (ReLU) activation function was modified ensuring “differentiable at zero.” Three-dimensional optimization was achieved by recording accuracy while changing the CNN layers and augmentation by several folds. WD was characterized using (i) CNN-based feature map strength and (ii) Bispectrum strengths of pixels having higher probabilities of WD. We further computed the (a) area under the curve (AUC), (b) diagnostic odds ratio (DOR), (c) reliability, and (d) stability and (e) benchmarking. Optimal results were achieved using 9 layers of CNN, with 4-fold augmentation. iDCNN yields superior performance compared to cDCNN with accuracy and AUC of 98.28 ± 1.55, 0.99 (p < 0.0001), and 97.19 ± 2.53%, 0.984 (p < 0.0001), respectively. DOR of iDCNN outperformed cDCNN fourfold. iDCNN also outperformed (a) transfer learning–based “Inception V3” paradigm by 11.92% and (b) four types of “conventional machine learning–based systems”: k-NN, decision tree, support vector machine, and random forest by 55.13%, 28.36%, 15.35%, and 14.11%, respectively. The AI-based systems can potentially be useful in the early WD diagnosis.

威尔森氏病 (WD) 是由大脑和肝脏中的铜积累引起的，如果不及早治疗，会导致严重的残疾和死亡。WD 在脑磁共振扫描 (MRI) 扫描中显示出白质高信号 (WMH)，但由于 (i) 细微的强度变化和 (ii) 使用人工智能 (AI) 时的 MRI 训练较弱，因此诊断具有挑战性。设计和验证七种基于 AI 的高性能计算机辅助设计 (CADx) 系统，包括 3D 优化分类和对照控制的 WD 表征。我们提出了一个“传统的深度卷积神经网络”（cDCNN）和一个“改进的 DCNN”（iDCNN），其中修正了修正线性单元（ReLU）激活函数以确保“在零处可微”。3D 优化是通过记录精度同时改变 CNN 层和数倍增强来实现的。WD 使用 (i) 基于 CNN 的特征图强度和 (ii) 具有更高 WD 概率的像素的双谱强度来表征。我们进一步计算了 (a) 曲线下面积 (AUC)、(b) 诊断优势比 (DOR)、(c) 可靠性和 (d) 稳定性和 (e) 基准测试。使用 9 层 CNN 和 4 倍增强实现了最佳结果。与 cDCNN 相比，iDCNN 具有更高的性能，准确度和 AUC 为 98.28 ± 1.55, 0.99 ( (c) 可靠性，以及 (d) 稳定性和 (e) 基准测试。使用 9 层 CNN 和 4 倍增强实现了最佳结果。与 cDCNN 相比，iDCNN 具有更高的性能，准确度和 AUC 为 98.28 ± 1.55, 0.99 ( (c) 可靠性，以及 (d) 稳定性和 (e) 基准测试。使用 9 层 CNN 和 4 倍增强实现了最佳结果。与 cDCNN 相比，iDCNN 具有更高的性能，准确度和 AUC 为 98.28 ± 1.55, 0.99 (p < 0.0001) 和 97.19 ± 2.53%、0.984 ( p < 0.0001)。iDCNN 的 DOR 比 cDCNN 好四倍。iDCNN 的表现也优于 (a) 基于迁移学习的“Inception V3”范式 11.92% 和 (b) 四种“基于传统机器学习的系统”：k- NN、决策树、支持向量机和随机森林 55.13 %、28.36%、15.35% 和 14.11%。基于 AI 的系统可能有助于早期 WD 诊断。