Yoo Sang Kyun, Kim Tae Hyung, Kim Jin Sung, Ahn Sung Soo, Kim Eui Hyun, Sung Wonmo, Kim Hojin, Yoon Hong In
Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Korea.
Medical Physics and Biomedical Engineering Lab (MPBEL), Yonsei University College of Medicine, Seoul, Korea.
Yonsei Med J. 2025 Aug;66(8):502-510. doi: 10.3349/ymj.2024.0198.
Black-blood (BB) magnetic resonance images (MRI) offer superior image contrast for the detection and segmentation of brain metastases (BMs). This study investigated the efficacy and accuracy of deep learning (DL) architectures and post-processing for BMs detection and segmentation with BB images.
The BB images of 50 patients were collect to train (40) and test (10) the DL model. To ensure consistency, we implemented piecewise linear histogram matching for intensity normalization and resampling. Modified U-Net, including combination with generative adversarial network (GAN), was applied to enhance the segmentation performance. The U-Net-based networks generated bounding boxes indicating regions of interest, which were then processed in a post-processing using the Segment Anything Model (SAM). We quantitatively assessed the three U-Net-based models and their post-processed counterparts in terms of lesion-wise sensitivity (LWS), patient-wise dice similarity coefficient (DSC), and average false-positive rate (FPR).
The modified U-Net with GAN yielded a patient-wise DSC of 0.853 and a LWS of 89.19%, which outperformed the standard U-Net (patient-wise DSC of 0.815) and modified U-Net only (patient-wise DSC of 0.846). Combining GAN architecture with modified U-Net also reduced the FPR, less than 1 on average. Post-processing with SAM further did not affect LWS and FPR, but effectively enhanced the patient-wise DSC by 2%-3% for the U-Net-based models.
The modifications to standard U-Net notably improves the detection and segmentation of BMs in BB images, and applying SAM as post-processing can further enhance the precision of segmentation results.
黑血（BB）磁共振成像（MRI）在脑转移瘤（BMs）的检测和分割方面具有卓越的图像对比度。本研究探讨了深度学习（DL）架构及后处理在利用BB图像检测和分割BMs方面的有效性和准确性。
收集50例患者的BB图像用于训练（40例）和测试（10例）DL模型。为确保一致性，我们实施了分段线性直方图匹配以进行强度归一化和重采样。应用改进的U-Net，包括与生成对抗网络（GAN）相结合，以提高分割性能。基于U-Net的网络生成指示感兴趣区域的边界框，然后使用分割一切模型（SAM）进行后处理。我们从病灶敏感性（LWS）、患者层面的骰子相似系数（DSC）和平均假阳性率（FPR）方面对三种基于U-Net的模型及其后处理后的模型进行了定量评估。
带有GAN的改进U-Net患者层面的DSC为0.853，LWS为89.19%，优于标准U-Net（患者层面的DSC为0.815）和仅改进的U-Net（患者层面的DSC为0.846）。将GAN架构与改进的U-Net相结合还降低了FPR，平均小于1。使用SAM进行后处理进一步未影响LWS和FPR，但对于基于U-Net的模型有效地将患者层面的DSC提高了2%-3%。
对标准U-Net的改进显著提高了BB图像中BMs的检测和分割，并且应用SAM作为后处理可以进一步提高分割结果的精度。
