A Comprehensive Survey on Bone Segmentation Techniques in Knee Osteoarthritis Research: From Conventional Methods to Deep Learning

Ahmed, Sozan Mohammed; Mstafa, Ramadhan J.

doi:10.3390/diagnostics12030611

Cited by 26 publications

(34 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the recognition of diseases, feature extraction is very helpful to machine learning (ML) algorithms. Many researchers used handcrafted features for KOA classification [ 49 ]. A new computer-based approach is proposed for segmenting knee menisci in MR images with the help of handcrafted features named HOG and LBP in which they used the variant of histogram HOG-UoCTTI.…”

Section: Related Workmentioning

confidence: 99%

Recognition of Knee Osteoarthritis (KOA) Using YOLOv2 and Classification Based on Convolutional Neural Network

Yunus

Amin

Sharif

et al. 2022

Life

View full text Add to dashboard Cite

Knee osteoarthritis (KOA) is one of the deadliest forms of arthritis. If not treated at an early stage, it may lead to knee replacement. That is why early diagnosis of KOA is necessary for better treatment. Manually KOA detection is a time-consuming and error-prone task. Computerized methods play a vital role in accurate and speedy detection. Therefore, the classification and localization of the KOA method are proposed in this work using radiographic images. The two-dimensional radiograph images are converted into three-dimensional and LBP features are extracted having the dimension of N × 59 out of which the best features of N × 55 are selected using PCA. The deep features are also extracted using Alex-Net and Dark-net-53 with the dimensions of N × 1024 and N × 4096, respectively, where N represents the number of images. Then, N × 1000 features are selected individually from both models using PCA. Finally, the extracted features are fused serially with the dimension of N × 2055 and passed to the classifiers on a 10-fold cross-validation that provides an accuracy of 90.6% for the classification of KOA grades. The localization model is proposed with the combination of an open exchange neural network (ONNX) and YOLOv2 that is trained on the selected hyper-parameters. The proposed model provides 0.98 mAP for the localization of classified images. The experimental analysis proves that the presented framework provides better results as compared to existing works.

show abstract

Section: Related Workmentioning

confidence: 99%

Recognition of Knee Osteoarthritis (KOA) Using YOLOv2 and Classification Based on Convolutional Neural Network

Yunus

Amin

Sharif

et al. 2022

Life

View full text Add to dashboard Cite

show abstract

“…Therefore, segmentation targets of previous studies are cartilage, meniscus, and bones (femur, tibia, and patella). Various studies have been published on segmenting knee structures, from existing analyticbased methods to recent machine learning-based methods [11][12].…”

Section: Introductionmentioning

confidence: 99%

“…Selecting the sequence is important in structure segmentation studies using MRI images [11,[13][14][15][16][17]. Existing knee structure segmentation studies have been conducted using diverse types of sequences [11,13].…”

Section: Introductionmentioning

confidence: 99%

A Method for Selecting Optimal MRI Sequence for Automatic Segmentation Based on Edge Analysis

Jung

Simonsen

Andersen

2023

Preprint

View full text Add to dashboard Cite

In segmentation research using magnetic resonance imaging (MRI) images, the sequence is an important factor affecting segmentation performance. Therefore, a selection method is required to find the best-suited sequence according to a segmentation target. This study presents a method for finding the most suitable MRI sequence for automatic segmentation. Based on profile information of virtual rays, we devised metrics to compute the edge sharpness and contrast. The analysis was proceeded using three sequences (T1: T1-weighted, PD: proton density-weighted, and SPGR: fat-suppressed 3D spoiled gradient-echo) from five defined edges (EBB: between cancellous bone and cortical bone, EBC: between cortical bone and cartilage, ECF: between cartilage and fat, ECM: between cartilage and meniscus, EBT: between cortical bone and tissue). The edge characteristics were compared in the three sequences using the proposed metrics, and the inter-subject variability was evaluated as well. In the case of sharpness, T1 showed the highest at the EBB, ECF, and EBT (p < .05). SPGR was the highest at the EBC, and PD was the highest at the ECM (p < .005). For contrast, T1 was the highest at the EBB and EBT (p < .05). SPGR was the highest at the ECF (p < .005), and PD was the highest at the ECM (p < .005). PD and SPGR had similar contrast values at the EBC (PD ≈ SPGR > T1). It was confirmed that the edge properties of the structure depend on the type of adjacent materials. The presented method showed consistent results according to the edge, and it was confirmed that new metrics were suitable for finding the most suitable sequence for segmentation. The method and metrics we present quantitatively evaluate the edge characteristics, which will be a useful way for finding the most suitable MRI sequence for segmentation study.

show abstract

“…As shown, machine learning methods have gained interest throughout the medical field, and the use of numerical methods may prove to also be a valuable tool to extend the methods used to assess damage to joint structures. In particular, machine learning and deep learning methods may prove useful especially in cases that require solving classification, detection, and related problems without the involvement of a radiologist [ 34 , 35 , 36 ].…”

Section: Introductionmentioning

confidence: 99%

Diagnostics of Articular Cartilage Damage Based on Generated Acoustic Signals Using ANN—Part II: Patellofemoral Joint

Karpiński

Krakowski

Jonak

et al. 2022

Sensors

View full text Add to dashboard Cite

Cartilage loss due to osteoarthritis (OA) in the patellofemoral joint provokes pain, stiffness, and restriction of joint motion, which strongly reduces quality of life. Early diagnosis is essential for prolonging painless joint function. Vibroarthrography (VAG) has been proposed in the literature as a safe, noninvasive, and reproducible tool for cartilage evaluation. Until now, however, there have been no strict protocols for VAG acquisition especially in regard to differences between the patellofemoral and tibiofemoral joints. The purpose of this study was to evaluate the proposed examination and acquisition protocol for the patellofemoral joint, as well as to determine the optimal examination protocol to obtain the best diagnostic results. Thirty-four patients scheduled for knee surgery due to cartilage lesions were enrolled in the study and compared with 33 healthy individuals in the control group. VAG acquisition was performed prior to surgery, and cartilage status was evaluated during the surgery as a reference point. Both closed (CKC) and open (OKC) kinetic chains were assessed during VAG. The selection of the optimal signal measures was performed using a neighborhood component analysis (NCA) algorithm. The classification was performed using multilayer perceptron (MLP) and radial basis function (RBF) neural networks. The classification using artificial neural networks was performed for three variants: I. open kinetic chain, II. closed kinetic chain, and III. open and closed kinetic chain. The highest diagnostic accuracy was obtained for variants I and II for the RBF 9-35-2 and MLP 10-16-2 networks, respectively, achieving a classification accuracy of 98.53, a sensitivity of 0.958, and a specificity of 1. For variant III, a diagnostic accuracy of 97.79 was obtained with a sensitivity and specificity of 0.978 for MLP 8-3-2. This indicates a possible simplification of the examination protocol to single kinetic chain analyses.

show abstract

A Comprehensive Survey on Bone Segmentation Techniques in Knee Osteoarthritis Research: From Conventional Methods to Deep Learning

Cited by 26 publications

References 87 publications

Recognition of Knee Osteoarthritis (KOA) Using YOLOv2 and Classification Based on Convolutional Neural Network

Recognition of Knee Osteoarthritis (KOA) Using YOLOv2 and Classification Based on Convolutional Neural Network

A Method for Selecting Optimal MRI Sequence for Automatic Segmentation Based on Edge Analysis

Diagnostics of Articular Cartilage Damage Based on Generated Acoustic Signals Using ANN—Part II: Patellofemoral Joint

Contact Info

Product

Resources

About