Quantitative Analysis of Patellar Tendon Abnormality in Asymptomatic Professional “Pallapugno” Players: A Texture-Based Ultrasound Approach

Meiburger, Kristen M.; Salvi, Massimo; Giacchino, Maurizio; Acharya, U. Rajendra; Minetto, Marco Alessandro; Caresio, Cristina; Molinari, Filippo

doi:10.3390/app8050660

Cited by 13 publications

(4 citation statements)

References 45 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several ways including ultrasound and magnetic resonance imaging (MRI) to measure the tendon related with the patellar. Some previous studies have shown that ultrasound is an effective way to evaluate patellar tendonitis [11][12][13]. Measurement using ultrasound is inexpensive and can avoid radiation.…”

Section: Introductionmentioning

confidence: 99%

Gender Differences in Patellar Positions among the Korean Population

et al. 2020

View full text Add to dashboard Cite

The various factors related to the morphometric characteristics of patella make it difficult to produce a standard interpretation of their respective values. A total of 1423 patients participated in this work. The distribution of Insall–Salvati ratios was investigated, and the upper and lower limits of two standard deviations were used to define the patellar alta and baja. An additional method was used, where 2.5% at each end of the distribution was defined as patellar alta and baja. Ratios in the females and males were 0.92 ± 0.14 and 0.87 ± 0.14, respectively. The ratios were considerably higher in females than in males (p < 0.05). Ratios defined for patellar alta and baja were 1.19 and 0.68 for females and 1.13 and 0.58 for males, respectively, when two standard deviations were used. Ratios defined for patellar alta and baja were 1.22 and 0.66 for females and 1.15 and 0.59 for males, respectively, when the extreme 2.5% method was used. No considerable differences in the patellar alta and baja were observed between the two methods. Patellar alta and baja were determined in ratios of more than 1.20 and less than 0.64, respectively. No significant differences in the patellar alta and baja were observed between the genders in the Korean population. Additionally, two standard deviations of the Insall–Salvati index are recommended for defining patellar alta and baja for the Korean population. However, we recommended analyzing the histogram distribution for the population, followed by an analysis of the patellar alta and baja.

show abstract

Section: Introductionmentioning

confidence: 99%

Gender Differences in Patellar Positions among the Korean Population

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Ultrasound imaging is considered one of the most preferred methods for analyzing the morphological aspects of atherosclerotic plaque [3], [4], and can be chosen over CT and MRI as it is real-time, does not use ionizing radiation, and is inexpensive, while still allowing a morphological analysis of changes including ulceration, heterogeneity, and echogenicity in plaques [5]. However, processing ultrasound images is challenging due to poor resolution [6], the presence of manual markers and artifacts.…”

Section: Introductionmentioning

confidence: 99%

“…This results in a search space of 50x4. The choice between the exploration and exploitation phases is controlled by a mathematical normalization function (NF) calculated from the search space, as shown in Eq (6)(7)…”

mentioning

confidence: 99%

CAROTIDNet: A Novel Carotid Symptomatic/Asymptomatic Plaque Detection System Using CNN-Based Tangent Optimization Algorithm in B-Mode Ultrasound Images

Ali,

Pathan,

Salvi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Deep learning methods have shown promise for automated medical image analysis tasks. However, class imbalance is a common challenge that can negatively impact model performance, especially for tasks with minority classes that are clinically significant. This study aims to address this challenge through a novel hyperparameter optimization technique for training convolutional neural networks on imbalanced data. We developed a custom Convolutional Neural Network (CNN) architecture and introduced a Tangent Optimization Algorithm (TOA) based on the trigonometric properties of the tangent function. The TOA optimizes hyperparameters during training without requiring data preprocessing or augmentation steps. We applied our approach to classifying B-mode ultrasound carotid artery plaque images as symptomatic or asymptomatic using a dataset with significant class imbalance. On k-fold cross-validation, our method achieved an average accuracy of 98.82%, a sensitivity of 99.41%, and a specificity of 95.74%. The proposed optimization technique provides a computationally efficient and interpretable solution for training deep learning models on unbalanced medical image datasets.

show abstract

“…Other methods in the literature have done research on other tendons rather than SST. In a similar research to [13], Meiburger et al [14] assessed the performance of 90 features, extracted from manually segmented regions, in a multivariate linear regression model for the patellar tendon abnormality detection. Their study showed that hand-crafted features can perform reasonably for tendon abnormality detection from US images.…”

Section: Introductionmentioning

confidence: 99%

Automatic Recognition of the Supraspinatus Tendinopathy from Ultrasound Images using Convolutional Neural Networks

Jahanifar¹,

Tajeddin²,

Hasani³

et al. 2020

Preprint

View full text Add to dashboard Cite

Tendon injuries like tendinopathies, full and partial thickness tears are prevalent, and the supraspinatus tendon (SST) is the most vulnerable ones in the rotator cuff. Early diagnosis of SST tendinopathies is of high importance and hard to achieve using ultrasound imaging. In this paper, an automatic tendinopathy recognition framework based on convolutional neural networks has been proposed to assist the diagnosis. This framework has two essential parts of tendon segmentation and classification. Tendon segmentation is done through a novel network, NASUNet, which follows an encoder-decoder architecture paradigm and utilizes a multi-scale Enlarging cell. Moreover, a general classification pipeline has been proposed for tendinopathy recognition, which supports different base models as the feature extractor engine. Two feature maps comprising positional information of the tendon region have been introduced as the network input to make the classification network spatial-aware. To evaluate the tendinopathy recognition system, a data set consisting of 100 SST ultrasound images have been acquired, in which tendinopathy cases are double-verified by magnetic resonance imaging. In both segmentation and classification tasks, lack of training data has been compensated by incorporating knowledge transferring, transfer learning, and data augmentation techniques. In cross-validation experiments, the proposed tendinopathy recognition model achieves 91% accuracy, 86.67% sensitivity, and 92.86% specificity, showing state-of-the-art performance against other models.

show abstract

Quantitative Analysis of Patellar Tendon Abnormality in Asymptomatic Professional “Pallapugno” Players: A Texture-Based Ultrasound Approach

Cited by 13 publications

References 45 publications

Gender Differences in Patellar Positions among the Korean Population

Gender Differences in Patellar Positions among the Korean Population

CAROTIDNet: A Novel Carotid Symptomatic/Asymptomatic Plaque Detection System Using CNN-Based Tangent Optimization Algorithm in B-Mode Ultrasound Images

Automatic Recognition of the Supraspinatus Tendinopathy from Ultrasound Images using Convolutional Neural Networks

Contact Info

Product

Resources

About