![]() Magnetic Resonance Imaging (MRI) is commonly used for the noninvasive assessment of meniscal morphology since MRI provides a three-dimensional view of the knee joint with high contrast between soft tissues. Meniscal tears are usually caused by trauma and degeneration ( Beaufils and Pujol, 2017) and might lead to a loss of function, early osteoarthritis, tibiofemoral osteophytes, and cartilage loss ( Ding et al., 2007 Snoeker et al., 2021). In patients with symptomatic osteoarthritis, meniscal damage is also found very frequently with a prevalence of up to 91% ( Bhattacharyya et al., 2003). Menisci are hydrated fibrocartilaginous soft tissues within the knee joint that absorb shocks, provide lubrication, and allow for joint stability during movement ( Markes et al., 2020). Furthermore, our method can be easily trained and applied to other MRI sequences. In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM. For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci. For optimal performance of our method, we investigate how to preprocess the MRI data and how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually. Our method is based on a Convolutional Neural Network (CNN) that operates on complete 3D MRI scans. We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. Archives
March 2023
Categories |