MGACA-Net: a novel deep learning based multi-scale guided attention and context aggregation for localization of knee anterior cruciate ligament tears region in MRI images

被引:7
作者
Awan, Mazhar Javed [1 ,2 ]
Rahim, Mohd Shafry Mohd [1 ]
Salim, Naomie [1 ]
Nobanee, Haitham [3 ,4 ,5 ]
Asif, Ahsen Ali [2 ]
Attiq, Muhammad Ozair [2 ]
机构
[1] Univ Teknol Malaysia, Fac Comp, Johar Bahru, Johor, Malaysia
[2] Univ Management & Technol, Dept Software Engn, Lahore, Punjab, Pakistan
[3] Abu Dhabi Univ, Coll Business, Abu Dhabi, U Arab Emirates
[4] Univ Oxford, Oxford Ctr Islamic Studies, Oxford, Oxfordshire, England
[5] Univ Liverpool, Sch Hist Languages & Cultures, Liverpool, Lancashire, England
关键词
Knee bone; Anterior cruciate ligament; Magnetic resonance imaging Deep learning; Segmentation; Attention; Localization; Tears;
D O I
10.7717/peerj-cs.1483
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Anterior cruciate ligament (ACL) tears are a common knee injury that can have serious consequences and require medical intervention. Magnetic resonance imaging (MRI) is the preferred method for ACL tear diagnosis. However, manual segmentation of the ACL in MRI images is prone to human error and can be time-consuming. This study presents a new approach that uses deep learning technique for localizing the ACL tear region in MRI images. The proposed multi-scale guided attention-based context aggregation (MGACA) method applies attention mechanisms at different scales within the DeepLabv3+ architecture to aggregate context information and achieve enhanced localization results. The model was trained and evaluated on a dataset of 917 knee MRI images, resulting in 15265 slices, obtaining state-of-the-art results with accuracy scores of 98.63%, intersection over union (IOU) scores of 95.39%, Dice coefficient scores (DCS) of 97.64%, recall scores of 97.5%, precision scores of 98.21%, and F1 Scores of 97.86% on validation set data. Moreover, our method performed well in terms of loss values, with binary cross entropy combined with Dice loss (BCE_Dice_loss) and Dice_loss values of 0.0564 and 0.0236, respectively, on the validation set. The findings suggest that MGACA provides an accurate and efficient solution for automating the localization of ACL in knee MRI images, surpassing other state-of-the-art models in terms of accuracy and loss values. However, in order to improve robustness of the approach and assess its performance on larger data sets, further research is needed.
引用
收藏
页数:30
相关论文
共 33 条
[1]   Deep Learning Approaches for Automatic Localization in Medical Images [J].
Alaskar, H. ;
Hussain, A. ;
Almaslukh, B. ;
Vaiyapuri, T. ;
Sbai, Z. ;
Dubey, Arun Kumar .
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
[2]   RETRACTED: Machine Learning-Based Performance Comparison to Diagnose Anterior Cruciate Ligament Tears (Retracted Article) [J].
Awan, Mazhar Javed ;
Rahim, Mohd Shafry Mohd ;
Salim, Naomie ;
Rehman, Amjad ;
Nobanee, Haitham .
JOURNAL OF HEALTHCARE ENGINEERING, 2022, 2022
[3]   Automated Knee MR Images Segmentation of Anterior Cruciate Ligament Tears [J].
Awan, Mazhar Javed ;
Rahim, Mohd Shafry Mohd ;
Salim, Naomie ;
Rehman, Amjad ;
Garcia-Zapirain, Begonya .
SENSORS, 2022, 22 (04)
[4]   Improved Deep Convolutional Neural Network to Classify Osteoarthritis from Anterior Cruciate Ligament Tear Using Magnetic Resonance Imaging [J].
Awan, Mazhar Javed ;
Rahim, Mohd Shafry Mohd ;
Salim, Naomie ;
Rehman, Amjad ;
Nobanee, Haitham ;
Shabir, Hassan .
JOURNAL OF PERSONALIZED MEDICINE, 2021, 11 (11)
[5]   Optimising Knee Injury Detection with Spatial Attention and Validating Localisation Ability [J].
Belton, Niamh ;
Welaratne, Ivan ;
Dahlan, Adil ;
Hearne, Ronan T. ;
Hagos, Misgina Tsighe ;
Lawlor, Aonghus ;
Curran, Kathleen M. .
MEDICAL IMAGE UNDERSTANDING AND ANALYSIS (MIUA 2021), 2021, 12722 :71-86
[6]   Mechanisms of anterior cruciate ligament injury [J].
Boden, BP ;
Dean, GS ;
Feagin, JA ;
Garrett, WE .
ORTHOPEDICS, 2000, 23 (06) :573-578
[7]   Deep Learning for Detection of Complete Anterior Cruciate Ligament Tear [J].
Chang, Peter D. ;
Wong, Tony T. ;
Rasiej, Michael J. .
JOURNAL OF DIGITAL IMAGING, 2019, 32 (06) :980-986
[8]   Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [J].
Chen, Liang-Chieh ;
Zhu, Yukun ;
Papandreou, George ;
Schroff, Florian ;
Adam, Hartwig .
COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 :833-851
[9]   DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [J].
Chen, Liang-Chieh ;
Papandreou, George ;
Kokkinos, Iasonas ;
Murphy, Kevin ;
Yuille, Alan L. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) :834-848
[10]   ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data [J].
Diakogiannis, Foivos, I ;
Waldner, Francois ;
Caccetta, Peter ;
Wu, Chen .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2020, 162 (162) :94-114