Fully Automatic Knee Bone Detection and Segmentation on Three-Dimensional MRI

Almajalid, Rania; Zhang, Ming; Shan, Juan

doi:10.3390/diagnostics12010123

Cited by 24 publications

(21 citation statements)

References 50 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By filtering the label map with a morphological opening operator during pre-processing, we eliminated the labelled one-pixel regions that interfered with the training process. With the filter, the training Dice coefficient converged to an excellent value of 98%, which compared favourably with two of the best algorithms reported in [ 23 , 24 ]. However, on more complicated volumes, the coefficient could fall to 90%.…”

Section: Resultssupporting

confidence: 59%

“…Additionally, ASD =

mm and RSD =

; these values for the tibia, femur, and patella were better than those obtained with most algorithms. In fact, our approach is superior to the well-known SegNet algorithm [ 21 ] (DSC = 64% with ASD = 0.56 mm) and compares well with two of the best segmentation algorithms [ 23 , 24 ] (DSC = 98.5%, ASD = 0.4 mm) found in the literature. As stated in [ 23 ], the 2.5D U-Net is more cost-effective in terms of memory needs and calculation time.…”

Section: Discussionmentioning

confidence: 49%

“…For the tibia bone, the results were DSC = 98.5%, ASD =

, and RSD =

. Almajalid et al [ 23 ] used an approach similar to the one proposed in this paper. The DSC values for the tibia were 96.83%, and those for the femur were 97.92%.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Bone Segmentation from MRI for Real-Time Knee Tracking in Fluoroscopic Imaging

Robert

Boulanger

2022

Diagnostics

View full text Add to dashboard Cite

Recent progress in real-time tracking of knee bone structures from fluoroscopic imaging using CT templates has opened the door to studying knee kinematics to improve our understanding of patellofemoral syndrome. The problem with CT imaging is that it exposes patients to extra ionising radiation, which adds to fluoroscopic imaging. This can be solved by segmenting bone templates from MRI instead of CT by using a deep neural network architecture called 2.5D U-Net. To train the network, we used the SKI10 database from the MICCAI challenge; it contains 100 knee MRIs with their corresponding annotated femur and tibia bones as the ground truth. Since patella tracking is essential in our application, the SKI10 database was augmented with a new label named UofA Patella . Using 70 MRIs from the database, a 2.5D U-Net was trained successfully after 75 epochs with an excellent final Dice score of 98%, which compared favourably with the best state-of-the-art algorithms. A test set of 30 MRIs were segmented using the trained 2.5D U-Net and then converted into 3D mesh templates by using a marching cube algorithm. The resulting 3D mesh templates were compared to the 3D mesh model extracted from the corresponding labelled data from the augmented SKI10. Even though the final Dice score (98%) compared well with the state-of-the-art algorithms, we initially found that the Euclidean distance between the segmented MRI and SKI10 meshes was over 6 mm in many regions, which is unacceptable for our application. By optimising many of the hyper-parameters of the 2.5D U-Net, we were able to find that, by changing the threshold used in the last layer of the network, one can significantly improve the average accuracy to mm with a variance of mm for most of the MRI mesh templates. These results illustrate that the Dice score is not always a good predictor of the geometric accuracy of segmentation and that fine-tuning hyper-parameters is critical for improving geometric accuracy.

show abstract

Section: Resultssupporting

confidence: 59%

“…Additionally, ASD =

mm and RSD =

Section: Discussionmentioning

confidence: 49%

See 1 more Smart Citation

Automatic Bone Segmentation from MRI for Real-Time Knee Tracking in Fluoroscopic Imaging

Robert

Boulanger

2022

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Almajalid et al's [60] used a customized U-Net model to identify the knee bone segmentation of tibia, femur, and patella bones. The Imorphics dataset OAI of 99 knee MRI cases with 160 2D slices was used.…”

Section: Research Backgroundmentioning

confidence: 99%

Automated Knee MR Images Segmentation of Anterior Cruciate Ligament Tears

Awan

Rahim

Salim

et al. 2022

Sensors

View full text Add to dashboard Cite

The anterior cruciate ligament (ACL) is one of the main stabilizer parts of the knee. ACL injury leads to causes of osteoarthritis risk. ACL rupture is common in the young athletic population. Accurate segmentation at an early stage can improve the analysis and classification of anterior cruciate ligaments tears. This study automatically segmented the anterior cruciate ligament (ACL) tears from magnetic resonance imaging through deep learning. The knee mask was generated on the original Magnetic Resonance (MR) images to apply a semantic segmentation technique with convolutional neural network architecture U-Net. The proposed segmentation method was measured by accuracy, intersection over union (IoU), dice similarity coefficient (DSC), precision, recall and F1-score of 98.4%, 99.0%, 99.4%, 99.6%, 99.6% and 99.6% on 11451 training images, whereas on the validation images of 3817 was, respectively, 97.7%, 93.8%,96.8%, 96.5%, 97.3% and 96.9%. We also provide dice loss of training and test datasets that have remained 0.005 and 0.031, respectively. The experimental results show that the ACL segmentation on JPEG MRI images with U-Nets achieves accuracy that outperforms the human segmentation. The strategy has promising potential applications in medical image analytics for the segmentation of knee ACL tears for MR images.

show abstract

“…A review paper on automated segmentation of pelvic cancer discussed the critically important issues to bridge the gap between computer vision and patient care and pointed to the need for better input data quality, more common dataset for development, and testing of segmentation algorithms [ 1 ]. The paper on the three-dimensional MRI of the knee discusses a non-invasive method of segmenting relevant structures, such as cartilage, bone marrow lesions, and meniscus [ 2 ]. Additionally, the paper on applying deep learning in CT images for pulmonary nodule detection reviews multiple CNN architectures focusing on the segmentation and classification aspects for computer-aided lung cancer diagnosis [ 3 ].…”

mentioning

confidence: 99%