Synthesizing the First Phase of Dynamic Sequences of Breast MRI for Enhanced Lesion Identification.
Synthesizing the First Phase of Dynamic Sequences of Breast MRI for Enhanced Lesion Identification.
复制标题
DOI：
10.3389/fonc.2021.792516
复制
发表时间：
2021
影响因子：
4.7
通讯作者：
Chen B
中科院分区：
文献类型：
--
作者：
Wang P;Nie P;Dang Y;Wang L;Zhu K;Wang H;Wang J;Liu R;Ren J;Feng J;Fan H;Yu J;Chen B
开发一种深度学习模型，用于合成动态（FP-Dyn）序列的第一阶段，以补充非增强乳房MRI检查中信息的不足。共收集97例乳腺MRI图像，分别作为训练集（n = 45）、验证集（n = 31）和测试集（n = 21）。在训练集中建立了增强边界逼真合成（enhanced border lifelike synthesis， EDLS）模型，用于从验证集中的T1WI图像合成FP-Dyn图像。测量合成图像的峰值信噪比（PSNR）、结构相似度（SSIM）、均方误差（MSE）和平均绝对误差（MAE）。此外，三位放射科医生分别对图像质量进行了主观评估。在试验集中进一步评价合成FP-Dyn序列的诊断价值。从PSNR、SSIM、MSE和MAE的结果来看，EDLS模型的图像合成性能优于传统模型。主观结果显示合成图像与原始FP-Dyn图像具有显著的视觉一致性。合成FP-Dyn序列与未增强方案联合使用，MRI的敏感性、特异性、阳性预测值（PPV）、阴性预测值（NPV）分别为100%、72.73%、76.92%和100%，与全MRI方案诊断价值相近。EDLS模型可以合成真实的FP-Dyn序列，弥补增强图像的不足。与全MRI检查相比，它为减少检查时间和成本提供了新的途径，并且在不影响诊断准确性的情况下避免了造影剂的使用。
To develop a deep learning model for synthesizing the first phases of dynamic (FP-Dyn) sequences to supplement the lack of information in unenhanced breast MRI examinations. In total, 97 patients with breast MRI images were collected as the training set (n = 45), the validation set (n = 31), and the test set (n = 21), respectively. An enhance border lifelike synthesize (EDLS) model was developed in the training set and used to synthesize the FP-Dyn images from the T1WI images in the validation set. The peak signal-to-noise ratio (PSNR), structural similarity (SSIM), mean square error (MSE) and mean absolute error (MAE) of the synthesized images were measured. Moreover, three radiologists subjectively assessed image quality, respectively. The diagnostic value of the synthesized FP-Dyn sequences was further evaluated in the test set. The image synthesis performance in the EDLS model was superior to that in conventional models from the results of PSNR, SSIM, MSE, and MAE. Subjective results displayed a remarkable visual consistency between the synthesized and original FP-Dyn images. Moreover, by using a combination of synthesized FP-Dyn sequence and an unenhanced protocol, the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of MRI were 100%, 72.73%, 76.92%, and 100%, respectively, which had a similar diagnostic value to full MRI protocols. The EDLS model could synthesize the realistic FP-Dyn sequence to supplement the lack of enhanced images. Compared with full MRI examinations, it thus provides a new approach for reducing examination time and cost, and avoids the use of contrast agents without influencing diagnostic accuracy.
登录
查看更多内容
影响因子：
5.9
作者：
Baltzer, Pascal A. T.;Benndorf, Matthias;Kaiser, Werner A.
通讯作者：
Kaiser, Werner A.
影响因子：
5.6
作者：
Adhikari, Shyam Prasad;Yang, Heechan;Kim, Hyongsuk
通讯作者：
Kim, Hyongsuk
影响因子：
4.5
作者：
Monticciolo, Debra L.;Newell, Mary S.;Sickles, Edward A.
通讯作者：
Sickles, Edward A.
影响因子：
19.7
作者：
Kuhl, Christiane K.;Strobel, Kevin;Schrading, Simone
通讯作者：
Schrading, Simone
DOI：
10.1007/s00259-021-05413-0
发表时间：
2021-05-22
影响因子：
9.1
作者：
Schaefferkoetter, Joshua;Yan, Jianhua;Veit-Haibach, Patrick
通讯作者：
Veit-Haibach, Patrick