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.

More from our Archive

• DOI: 10.3390/computation11070143 2023

  Mathematical Modelling of Tuberculosis Outbreak in an East African Country Incorporating Vaccination and Treatment

  Kayode Oshinubi, Olumuyiwa James Peter, Emmanuel Addai, Enock Mwizerwa, Oluwatosin Babasola, Ifeoma Veronica Nwabufo, Ibrahima Sane, Umar Muhammad Adam, Adejimi Adeniji, Janet O. Agbaje

• DOI: 10.7717/peerj-cs.1405 2023

  Addressing Internet of Things security by enhanced sine cosine metaheuristics tuned hybrid machine learning model and results interpretation based on SHAP approach

  Milos Dobrojevic, Miodrag Zivkovic, Amit Chhabra, Nor Samsiah Sani, Nebojsa Bacanin, Maifuza Mohd Amin

• DOI: 10.1145/3605889 2023

  Arabic ChatGPT Tweets Classification Using RoBERTa and BERT Ensemble Model

  Muhammad Mujahid, Khadija Kanwal, Furqan Rustam, Wajdi Aljedaani, Imran Ashraf

• DOI: 10.3390/computation11070126 2023

  Response Spectrum Analysis of Multi-Story Shear Buildings Using Machine Learning Techniques

  Manolis Georgioudakis, Vagelis Plevris

• DOI: 10.7717/peerj-cs.1483 2023

  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

  Mazhar Javed Awan, Mohd Shafry Mohd Rahim, Naomie Salim, Haitham Nobanee, Ahsen Ali Asif, Muhammad Ozair Attiq

• DOI: 10.3390/computation11070130 2023

  Applications of Modified Bessel Polynomials to Solve a Nonlinear Chaotic Fractional-Order System in the Financial Market: Domain-Splitting Collocation Techniques

  Mohammad Izadi, Hari Mohan Srivastava

• DOI: 10.4218/etrij.2023-0050 2023

  Miniaturized meander‐line dual‐band implantable antenna for biotelemetry applications

  Rajagopal Kangeyan, Madurakavi Karthikeyan

• DOI: 10.3390/computation11070129 2023

  Computation of the Exact Forms of Waves for a Set of Differential Equations Associated with the SEIR Model of Epidemics

  Nikolay K. Vitanov, Zlatinka I. Dimitrova

• DOI: 10.3390/computation11070127 2023

  Analytical and Numerical Results for the Diffusion-Reaction Equation When the Reaction Coefficient Depends on Simultaneously the Space and Time Coordinates

  Ali Habeeb Askar, Ádám Nagy, Imre Ferenc Barna, Endre Kovács

• DOI: 10.3390/computation11070124 2023

  Fast Operation of Determining the Sign of a Number in RNS Using the Akushsky Core Function

  Egor Shiriaev, Nikolay Kucherov, Mikhail Babenko, Anton Nazarov