Channarayapatna Srinivasa Arvind, Bhat Seema S, Baduwal Dikendra, Sim Zheng Ting Jordan, Patil Shamshekhar S, Amarapur Ashwin, Prakash K N Bhanu
Bioinformatics Institute, Agency for Science, Technology and Research (A*STAR), 30 Biopolis Street, #07-01 Matrix, Singapore, 138671, Republic of Singapore.
Aikenist Technologies Pvt. Ltd, 10th Main Road, 22nd Cross Rd, 3rd Block East, Jayanagar, Bengaluru, Karnataka, 560011, India.
Radiol Phys Technol. 2025 Aug 8. doi: 10.1007/s12194-025-00938-7.
Clinical magnetic resonance imaging (MRI) is a high-resolution tool widely used for detailed anatomical imaging. However, prolonged scan times often lead to motion artefacts and patient discomfort. Fast acquisition techniques can reduce scan times but often produce noisy, low-contrast images, compromising segmentation accuracy essential for diagnosis and treatment planning. To address these limitations, we developed an end-to-end framework that incorporates BIDS-based data organiser and anonymizer, a GAN-based MR image enhancement model (GAN-MRI), AssemblyNet for brain region segmentation, and an attention-residual U-Net with Guided loss for abdominal and thigh segmentation. Thirty brain scans (5,400 slices) and 32 abdominal (1,920 slices) and 55 thigh scans (2,200 slices) acquired from multiple MRI scanners (GE, Siemens, Toshiba) underwent evaluation. Image quality improved significantly, with SNR and CNR for brain scans increasing from 28.44 to 42.92 (p < 0.001) and 11.88 to 18.03 (p < 0.001), respectively. Abdominal scans exhibited SNR increases from 35.30 to 50.24 (p < 0.001) and CNR from 10,290.93 to 93,767.22 (p < 0.001). Double-blind evaluations highlighted improved visualisations of anatomical structures and bias field correction. Segmentation performance improved substantially in the thigh (muscle: + 21%, IMAT: + 9%) and abdominal regions (SSAT: + 1%, DSAT: + 2%, VAT: + 12%), while brain segmentation metrics remained largely stable, reflecting the robustness of the baseline model. Proposed framework is designed to handle data from multiple anatomies with variations from different MRI scanners and centres by enhancing MRI scan and improving segmentation accuracy, diagnostic precision and treatment planning while reducing scan times and maintaining patient comfort.
临床磁共振成像（MRI）是一种广泛用于详细解剖成像的高分辨率工具。然而，延长扫描时间往往会导致运动伪影和患者不适。快速采集技术可以减少扫描时间，但通常会产生噪声大、对比度低的图像，从而影响诊断和治疗规划所需的分割精度。为了解决这些局限性，我们开发了一个端到端框架，该框架包含基于BIDS的数据整理器和匿名化器、基于生成对抗网络（GAN）的MR图像增强模型（GAN-MRI）、用于脑区分割的AssemblyNet以及用于腹部和大腿分割的带有引导损失的注意力残差U-Net。对从多台MRI扫描仪（GE、西门子、东芝）获取的30例脑部扫描（5400层）、32例腹部扫描（1920层）和55例大腿扫描（2200层）进行了评估。图像质量显著提高，脑部扫描的信噪比（SNR）和对比噪声比（CNR）分别从28.44提高到42.92（p < 0.001）和从11.88提高到18.03（p < 0.001）。腹部扫描的SNR从35.30提高到50.24（p < 0.001），CNR从10290.93提高到93767.22（p < 0.001）。双盲评估突出了解剖结构可视化的改善和偏置场校正。大腿（肌肉：+21%，IMAT：+9%）和腹部区域（SSAT：+1%，DSAT：+2%，VAT：+12%）的分割性能有显著提高，而脑部分割指标基本保持稳定，这反映了基线模型的稳健性。所提出的框架旨在通过增强MRI扫描并提高分割精度、诊断精度和治疗规划，同时减少扫描时间并保持患者舒适度，来处理来自不同MRI扫描仪和中心的具有差异的多个解剖部位的数据。
