Moummad Ilyass, Jaudet Cyril, Lechervy Alexis, Valable Samuel, Raboutet Charlotte, Soilihi Zamila, Thariat Juliette, Falzone Nadia, Lacroix Joëlle, Batalla Alain, Corroyer-Dulmont Aurélien
Medical Physics Department, CLCC François Baclesse, 14000 Caen, France.
UMR GREYC, Normandie University, UNICAEN, ENSICAEN, CNRS, 14000 Caen, France.
Cancers (Basel). 2021 Dec 22;14(1):36. doi: 10.3390/cancers14010036.
Magnetic resonance imaging (MRI) is predominant in the therapeutic management of cancer patients, unfortunately, patients have to wait a long time to get an appointment for examination. Therefore, new MRI devices include deep-learning (DL) solutions to save acquisition time. However, the impact of these algorithms on intensity and texture parameters has been poorly studied. The aim of this study was to evaluate the impact of resampling and denoising DL models on radiomics.
Resampling and denoising DL model was developed on 14,243 T1 brain images from 1.5T-MRI. Radiomics were extracted from 40 brain metastases from 11 patients (2049 images). A total of 104 texture features of DL images were compared to original images with paired -test, Pearson correlation and concordance-correlation-coefficient (CCC).
When two times shorter image acquisition shows strong disparities with the originals concerning the radiomics, with significant differences and loss of correlation of 79.81% and 48.08%, respectively. Interestingly, DL models restore textures with 46.15% of unstable parameters and 25.96% of low CCC and without difference for the first-order intensity parameters.
Resampling and denoising DL models reconstruct low resolution and noised MRI images acquired quickly into high quality images. While fast MRI acquisition loses most of the radiomic features, DL models restore these parameters.
磁共振成像（MRI）在癌症患者的治疗管理中占主导地位，不幸的是，患者必须等待很长时间才能预约检查。因此，新型MRI设备采用深度学习（DL）解决方案以节省采集时间。然而，这些算法对强度和纹理参数的影响研究较少。本研究的目的是评估重采样和去噪DL模型对放射组学的影响。
在来自1.5T-MRI的14243张T1脑图像上开发重采样和去噪DL模型。从11例患者的40个脑转移瘤（2049张图像）中提取放射组学特征。通过配对检验、Pearson相关性和一致性相关系数（CCC）将DL图像的总共104个纹理特征与原始图像进行比较。
当图像采集时间缩短两倍时，放射组学方面与原始图像存在显著差异，分别有79.81%和48.08%的显著差异和相关性丧失。有趣的是，DL模型恢复了46.95%不稳定参数和25.96%低CCC的纹理，并且一阶强度参数无差异。
重采样和去噪DL模型将快速采集的低分辨率和有噪声的MRI图像重建为高质量图像。虽然快速MRI采集会丢失大部分放射组学特征，但DL模型可恢复这些参数。
