Kasuya Shusuke, Inaoka Tsutomu, Wada Akihiko, Nakatsuka Tomoya, Nakagawa Koichi, Terada Hitoshi
Department of Radiology, Toho University Sakura Medical Center, Sakura, Japan.
Department of Radiology, Juntendo University, Tokyo, Japan.
Pol J Radiol. 2023 Dec 8;88:e562-e573. doi: 10.5114/pjr.2023.133660. eCollection 2023.
To evaluate the feasibility of using a deep learning (DL) model to generate fat-suppression images and detect abnormalities on knee magnetic resonance imaging (MRI) through the fat-suppression image-subtraction method.
A total of 45 knee MRI studies in patients with knee disorders and 12 knee MRI studies in healthy volunteers were enrolled. The DL model was developed using 2-dimensional convolutional neural networks for generating fat-suppression images and subtracting generated fat-suppression images without any abnormal findings from those with normal/abnormal findings and detecting/classifying abnormalities on knee MRI. The image qualities of the generated fat-suppression images and subtraction-images were assessed. The accuracy, average precision, average recall, F-measure, sensitivity, and area under the receiver operator characteristic curve (AUROC) of DL for each abnormality were calculated.
A total of 2472 image datasets, each consisting of one slice of original T1WI, original intermediate-weighted images, generated fat-suppression (FS)-intermediate-weighted images without any abnormal findings, generated FS-intermediate-weighted images with normal/abnormal findings, and subtraction images between the generated FS-intermediate-weighted images at the same cross-section, were created. The generated fat-suppression images were of adequate image quality. Of the 2472 subtraction-images, 2203 (89.1%) were judged to be of adequate image quality. The accuracies for overall abnormalities, anterior cruciate ligament, bone marrow, cartilage, meniscus, and others were 89.5-95.1%. The average precision, average recall, and F-measure were 73.4-90.6%, 77.5-89.4%, and 78.4-89.4%, respectively. The sensitivity was 57.4-90.5%. The AUROCs were 0.910-0.979.
The DL model was able to generate fat-suppression images of sufficient quality to detect abnormalities on knee MRI through the fat-suppression image-subtraction method.
评估使用深度学习（DL）模型通过脂肪抑制图像减法生成脂肪抑制图像并检测膝关节磁共振成像（MRI）异常的可行性。
纳入45例膝关节疾病患者的膝关节MRI研究以及12例健康志愿者的膝关节MRI研究。使用二维卷积神经网络开发DL模型，用于生成脂肪抑制图像，从有正常/异常表现的图像中减去无任何异常表现的生成脂肪抑制图像，并检测/分类膝关节MRI上的异常。评估生成的脂肪抑制图像和减法图像的图像质量。计算DL对每种异常的准确率、平均精度、平均召回率、F值、灵敏度和受试者操作特征曲线下面积（AUROC）。
共创建了2472个图像数据集，每个数据集由一片原始T1加权成像、原始中等加权图像、无任何异常表现的生成脂肪抑制（FS）中等加权图像、有正常/异常表现的生成FS中等加权图像以及同一横截面生成的FS中等加权图像之间的减法图像组成。生成的脂肪抑制图像具有足够的图像质量。在2472个减法图像中，2203个（89.1%）被判定为具有足够的图像质量。总体异常、前交叉韧带、骨髓、软骨、半月板及其他方面的准确率为89.5% - 95.1%。平均精度、平均召回率和F值分别为73.4% - 90.6%、77.5% - 89.4%和78.4% - 89.4%。灵敏度为57.4% - 90.5%。AUROC为0.910 - 0.979。
DL模型能够生成质量足够高的脂肪抑制图像，通过脂肪抑制图像减法检测膝关节MRI上的异常。
