Hosseini Mahboube Sadat, Aghamiri Seyed Mahmoud Reza, Fatemi Ardekani Ali, BagheriMofidi Seyed Mehdi, Safari Mojtaba
Department of Medical Radiation Engineering, Shahid Beheshti University, Tehran, 1983969411, Iran.
Department of Physics, Jackson State University, Jackson, MS, USA.
J Imaging Inform Med. 2025 Feb;38(1):587-601. doi: 10.1007/s10278-024-01171-1. Epub 2024 Jul 30.
Geometric distortions in brain MRI images arising from susceptibility artifacts at air-tissue interfaces pose a significant challenge for high-precision radiation therapy modalities like stereotactic radiosurgery, necessitating sub-millimeter accuracy. To achieve this goal, we developed AutoCorNN, an unsupervised physics-aware deep-learning model for correcting geometric distortions. Two publicly available datasets, the MPI-Leipzig Mind-Brain-Body with 318 subjects, and the Vestibular Schwannoma-SEG dataset, encompassing 242 patients were utilized. AutoCorNN integrates two 2D convolutional encoder-decoder neural networks with the forward physical model of MRI signal generation to predict undistorted MR and field map images from distorted MR input. The network is trained in an unsupervised manner by minimizing the mean absolute error between the measured and estimated k-space data, without requiring ground truth images during training or deployment. The model was evaluated on vestibular schwannoma cases. AutoCorNN achieved a peak signal-to-noise ratio (PSNR) of 41.35 ± 0.02 dB, a root mean square error (RMSE) of 0.02 ± 0.003, and a structural similarity index (SSIM) of 0.99 ± 0.02 outperforming uncorrected and B0-mapping correction methods. Geometric distortions of about 1.6 mm were observed at the air-tissue interfaces at the air canal and nasal cavity borders. Geometrically, distortion correction increased the target volume from 3.12 ± 0.52 cc to 3.84 ± 0.54 cc. Dosimetrically, AutoCorNN improved target coverage (0.96 ± 0.01 to 0.97 ± 0.02), conformity index (0.92 ± 0.03 to 0.94 ± 0.03), and reduced dose gradients outside the target. AutoCorNN achieves accurate geometric distortion correction comparable to conventional iterative methods while offering substantial computational acceleration, enabling precise target delineation and conformal dose delivery for improved radiation therapy outcomes.
在气-组织界面处由磁化率伪影引起的脑磁共振成像（MRI）图像几何畸变，对立体定向放射外科等高精度放射治疗方式构成了重大挑战，这需要亚毫米级的精度。为实现这一目标，我们开发了AutoCorNN，这是一种用于校正几何畸变的无监督物理感知深度学习模型。使用了两个公开可用的数据集，即包含318名受试者的MPI-莱比锡脑-身数据集，以及涵盖242名患者的前庭神经鞘瘤-SEG数据集。AutoCorNN将两个二维卷积编码器-解码器神经网络与MRI信号生成的正向物理模型相结合，以从失真的MR输入预测未失真的MR和场图图像。该网络通过最小化测量的和估计的k空间数据之间的平均绝对误差，以无监督方式进行训练，在训练或部署期间不需要真实图像。该模型在前庭神经鞘瘤病例上进行了评估。AutoCorNN实现了41.35±0.02dB的峰值信噪比（PSNR）、0.02±0.003的均方根误差（RMSE）以及0.99±0.02的结构相似性指数（SSIM），优于未校正和B0映射校正方法。在气道和鼻腔边界的气-组织界面处观察到约1.6毫米的几何畸变。从几何角度来看，畸变校正使靶体积从3.12±0.52立方厘米增加到3.84±0.54立方厘米。在剂量学方面，AutoCorNN改善了靶区覆盖（从0.96±0.01到0.97±0.02）、适形指数（从0.92±0.03到0.94±0.03），并降低了靶区外的剂量梯度。AutoCorNN实现了与传统迭代方法相当的精确几何畸变校正，同时提供了显著的计算加速，能够实现精确的靶区勾画和适形剂量递送，以改善放射治疗效果。
