Porter Valerie A, Hobson Brad A, D'Almeida Alita J, Bales Karen L, Lein Pamela J, Chaudhari Abhijit J
Department of Biomedical Engineering, University of California, Davis, One Shields Ave, Davis, CA, USA; Department of Radiology, University of California, Davis, One Shields Ave, Davis, CA, USA.
Department of Biomedical Engineering, University of California, Davis, One Shields Ave, Davis, CA, USA; Center for Molecular and Genomic Imaging, University of California, Davis, One Shields Ave, Davis, CA, USA.
Comput Biol Med. 2025 Sep;195:110569. doi: 10.1016/j.compbiomed.2025.110569. Epub 2025 Jun 20.
Automated whole-brain delineation (WBD) techniques often struggle to generalize across pre-clinical studies due to variations in animal models, magnetic resonance imaging (MRI) scanners, and tissue contrasts. We developed a 3D U-Net neural network for WBD pre-trained on organophosphate intoxication (OPI) rat brain MRI scans. We used transfer learning (TL) to adapt this OPI-pretrained network to other animal models: rat model of Alzheimer's disease (AD), mouse model of tetramethylenedisulfotetramine (TETS) intoxication, and titi monkey model of social bonding.
We assessed an OPI-pretrained 3D U-Net across animal models under three conditions: (1) direct application to each dataset; (2) utilizing TL; and (3) training disease-specific U-Net models. For each condition, training dataset size (TDS) was optimized, and output WBDs were compared to manual segmentations for accuracy.
The OPI-pretrained 3D U-Net (TDS = 100) achieved the best accuracy [median[min-max]] for the test OPI dataset with a Dice coefficient (DC) = [0.987 [0.977-0.992]] and Hausdorff distance (HD) = [0.86 [0.55-1.27]]mm. TL improved generalization across all models [AD (TDS = 40): DC = 0.987 [0.977-0.992] and HD = 0.72 [0.54-1.00]mm; TETS (TDS = 10): DC = 0.992 [0.984-0.993] and HD = 0.40 [0.31-0.50]mm; Monkey (TDS = 8): DC = 0.977 [0.968-0.979] and HD = 3.03 [2.19-3.91]mm], showing performance comparable to disease-specific networks.
The OPI-pretrained 3D U-Net with TL achieved accuracy comparable to disease-specific networks with reduced training data (TDS ≤ 40 scans) across all models. Future work will focus on developing a multi-region delineation pipeline for pre-clinical MRI brain data, utilizing the proposed WBD as an initial step.
由于动物模型、磁共振成像（MRI）扫描仪和组织对比度的差异，自动化全脑勾勒（WBD）技术在临床前研究中往往难以推广。我们开发了一种3D U-Net神经网络，用于在有机磷中毒（OPI）大鼠脑MRI扫描上进行预训练的WBD。我们使用迁移学习（TL）将这个OPI预训练网络应用于其他动物模型：阿尔茨海默病（AD）大鼠模型、毒鼠强（TETS）中毒小鼠模型和社会联结绒猴模型。
我们在三种情况下评估了一个OPI预训练的3D U-Net在不同动物模型上的表现：（1）直接应用于每个数据集；（2）利用迁移学习；（3）训练针对特定疾病的U-Net模型。对于每种情况，优化训练数据集大小（TDS），并将输出的WBD与手动分割结果进行准确性比较。
OPI预训练的3D U-Net（TDS = 100）在测试OPI数据集上达到了最佳准确性[中位数[最小值 - 最大值]]，骰子系数（DC）= [0.987 [0.977 - 0.992]]，豪斯多夫距离（HD）= [0.86 [0.55 - 1.27]]mm。迁移学习提高了在所有模型上的泛化能力[AD（TDS = 40）：DC = 0.987 [0.977 - 0.992]，HD = 0.72 [0.54 - 1.00]mm；TETS（TDS = 10）：DC = 0.992 [0.984 - 0.993]，HD = 0.40 [0.31 - 0.50]mm；猴子（TDS = 8）：DC = 0.977 [0.968 - 0.979]，HD = 3.03 [2.19 - 3.91]mm]，表现与针对特定疾病的网络相当。
带有迁移学习的OPI预训练3D U-Net在所有模型上使用减少的训练数据（TDS≤40次扫描）达到了与针对特定疾病的网络相当的准确性。未来的工作将集中于利用所提出的WBD作为初始步骤，为临床前MRI脑数据开发一个多区域勾勒流程。
