This study addresses challenges in fetal magnetic resonance imaging (MRI) related to motion artifacts, maternal respiration, and hardware limitations. To enhance MRI quality, we employ deep learning techniques, specif...This study addresses challenges in fetal magnetic resonance imaging (MRI) related to motion artifacts, maternal respiration, and hardware limitations. To enhance MRI quality, we employ deep learning techniques, specifically utilizing Cycle GAN. Synthetic pairs of images, simulating artifacts in fetal MRI, are generated to train the model. Our primary contribution is the use of Cycle GAN for fetal MRI restoration, augmented by artificially corrupted data. We compare three approaches (supervised Cycle GAN, Pix2Pix, and Mobile Unet) for artifact removal. Experimental results demonstrate that the proposed supervised Cycle GAN effectively removes artifacts while preserving image details, as validated through Structural Similarity Index Measure (SSIM) and normalized Mean Absolute Error (MAE). The method proves comparable to alternatives but avoids the generation of spurious regions, which is crucial for medical accuracy.展开更多
目的探讨乳腺肿瘤的多参数MRI特征(T_(2)-WI、ADC值和DCE)以及乳腺密度和背景实质增强(BPE)特征在不同乳腺癌(BC)分子亚型中的差异,以期为临床诊断提供重要参考。方法本研究为回顾性研究,纳入344例患者。所有患者均接受了多参数乳房MRI(...目的探讨乳腺肿瘤的多参数MRI特征(T_(2)-WI、ADC值和DCE)以及乳腺密度和背景实质增强(BPE)特征在不同乳腺癌(BC)分子亚型中的差异,以期为临床诊断提供重要参考。方法本研究为回顾性研究,纳入344例患者。所有患者均接受了多参数乳房MRI(T_(2)WI、ADC和DCE序列),并根据最新的BIRADS提取特征,使用ROI之间的类内系数(ICC)来评估读者间协议。结果研究人群分为:luminal A 89例(26%),luminal B HER2阳性39例(11.5%),luminal B HER2阴性168例(48.5%),三阴性(TNBC)41例(12%),HER2富集7例(2%)。Luminal内A肿瘤与特殊的组织学类型、最小的肿瘤大小和持续的动力学曲线相关(P均<0.05)。Luminal B HER2阴性肿瘤与最低ADC值相关(0.77×10^(-3)mm^(2)/s^(2)),其预测BC分子亚型的准确性为0.583。TNBC与不对称和中度/显著BPE,圆形/椭圆形肿块,边缘受限和边缘增强相关(P均<0.05)。HER2富集的BC与最大肿瘤大小相关(平均37.28mm,p值=0.02)。结论BC分子亚型与T_(2)WI、ADC和DCE MRI特征相关,ADC有助于预测luminal B HER2阴性病例。展开更多
文摘This study addresses challenges in fetal magnetic resonance imaging (MRI) related to motion artifacts, maternal respiration, and hardware limitations. To enhance MRI quality, we employ deep learning techniques, specifically utilizing Cycle GAN. Synthetic pairs of images, simulating artifacts in fetal MRI, are generated to train the model. Our primary contribution is the use of Cycle GAN for fetal MRI restoration, augmented by artificially corrupted data. We compare three approaches (supervised Cycle GAN, Pix2Pix, and Mobile Unet) for artifact removal. Experimental results demonstrate that the proposed supervised Cycle GAN effectively removes artifacts while preserving image details, as validated through Structural Similarity Index Measure (SSIM) and normalized Mean Absolute Error (MAE). The method proves comparable to alternatives but avoids the generation of spurious regions, which is crucial for medical accuracy.
文摘目的探讨乳腺肿瘤的多参数MRI特征(T_(2)-WI、ADC值和DCE)以及乳腺密度和背景实质增强(BPE)特征在不同乳腺癌(BC)分子亚型中的差异,以期为临床诊断提供重要参考。方法本研究为回顾性研究,纳入344例患者。所有患者均接受了多参数乳房MRI(T_(2)WI、ADC和DCE序列),并根据最新的BIRADS提取特征,使用ROI之间的类内系数(ICC)来评估读者间协议。结果研究人群分为:luminal A 89例(26%),luminal B HER2阳性39例(11.5%),luminal B HER2阴性168例(48.5%),三阴性(TNBC)41例(12%),HER2富集7例(2%)。Luminal内A肿瘤与特殊的组织学类型、最小的肿瘤大小和持续的动力学曲线相关(P均<0.05)。Luminal B HER2阴性肿瘤与最低ADC值相关(0.77×10^(-3)mm^(2)/s^(2)),其预测BC分子亚型的准确性为0.583。TNBC与不对称和中度/显著BPE,圆形/椭圆形肿块,边缘受限和边缘增强相关(P均<0.05)。HER2富集的BC与最大肿瘤大小相关(平均37.28mm,p值=0.02)。结论BC分子亚型与T_(2)WI、ADC和DCE MRI特征相关,ADC有助于预测luminal B HER2阴性病例。
