Muscle Type Classification on Ultrasound Imaging Using Deep Convolutional Neural Networks

Katakis, Sofoklis; Barotsis, Nikolaos; Kastaniotis, Dimitrios; Theoharatos, Christos; Tsourounis, Dimitrios; Fotopoulos, S.; Panagiotopoulos, Elias

doi:10.1109/ivmspw.2018.8448648

Cited by 7 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A previous report [29] introduced machine learning and statistical methods to measure the precision of the scores calculated using the mean square error, providing an accuracy of 0.74. Studies exist that describe biomarkers within the muscle using machine learning techniques, and those in which the muscle volume of adults with sarcopenia was estimated and/or classified, obtaining and accuracy of 0.80 [30,31,32,33,34]. The latter studies focused on images, while ours focused on another guideline based on patients’ clinical history, whereby it is suggested that a series of significant variables be taken into consideration if the patient has moderate or severe sarcopenia.…”

Section: Discussionmentioning

confidence: 99%

Automatic Classification of Sarcopenia Level in Older Adults: A Case Study at Tijuana General Hospital

Cristian

Soto

Lozano

et al. 2019

IJERPH

View full text Add to dashboard Cite

This paper presents a study based on data analysis of the sarcopenia level in older adults. Sarcopenia is a prevalent pathology in adults of around 50 years of age, whereby the muscle mass decreases by 1 to 2% a year, and muscle strength experiences an annual decrease of 1.5% between 50 and 60 years of age, subsequently increasing by 3% each year. The World Health Organisation estimates that 5–13% of individuals of between 60 and 70 years of age and 11–50% of persons of 80 years of age or over have sarcopenia. This study was conducted with 166 patients and 99 variables. Demographic data was compiled including age, gender, place of residence, schooling, marital status, level of education, income, profession, and financial support from the State of Baja California, and biochemical parameters such as glycemia, cholesterolemia, and triglyceridemia were determined. A total of 166 patients took part in the study, with an average age of 77.24 years. The purpose of the study was to provide an automatic classifier of sarcopenia level in older adults using artificial intelligence in addition to identifying the weight of each variable used in the study. We used machine learning techniques in this work, in which 10 classifiers were employed to assess the variables and determine which would provide the best results, namely, Nearest Neighbors (3), Linear SVM (Support Vector Machines) (C = 0.025), RBF (Radial Basis Function) SVM (gamma = 2, C = 1), Gaussian Process (RBF (1.0)), Decision Tree (max_depth = 3), Random Forest (max_depth=3, n_estimators = 10), MPL (Multilayer Perceptron) (alpha = 1), AdaBoost, Gaussian Naive Bayes, and QDA (Quadratic Discriminant Analysis). Feature selection determined by the mean for the variable ranking suggests that Age, Systolic Arterial Hypertension (HAS), Mini Nutritional Assessment (MNA), Number of chronic diseases (ECNumber), and Sodium are the five most important variables in determining the sarcopenia level, and are thus of great importance prior to establishing any treatment or preventive measure. Analysis of the relationships existing between the presence of the variables and classifiers used in moderate and severe sarcopenia revealed that the sarcopenia level using the RBF SVM classifier with Age, HAS, MNA, ECNumber, and Sodium variables has 82′5 accuracy, a 90′2 F1, and 82′8 precision.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Classification of Sarcopenia Level in Older Adults: A Case Study at Tijuana General Hospital

Cristian

Soto

Lozano

et al. 2019

IJERPH

View full text Add to dashboard Cite

show abstract

“…Meanwhile, the RAN was the latest development of the region-based convolutional neural network (RCNN) [36]. The classification entirely uses a CNN based on AlexNet, Deep-CNN, and VGG [30][31][32] (Figure 4).…”

Section: Network Architecturementioning

confidence: 99%

“…In 2018 (Figure 1), deep learning was increasingly used to support skeletal muscle and smooth muscle ultrasound imaging in order to improve reliability testing for the classification of muscle types [30], classifying muscles by gender [31], and the classification of muscle vibration [32]. Additionally, it supported the identification of landmarks such as segmentation in the orientation of muscle fibers [33] and tracking the cross-sectional area of the rectus femoris [34].…”

Section: Introductionmentioning

confidence: 99%

“…We found seven studies on skeletal muscles and three studies on smooth muscles from 2018 to 2020 which had case conditions and deep learning performance parameters. For skeletal muscle ultrasound imaging, image noise and muscle movement require special treatment for deep learning architecture and segmentation [30,41]. Smooth muscle research has focused on measuring muscle thickness [38]; however, the treatment of image problems in skeletal muscles and smooth muscles has not been compared in order to understand the current state of knowledge.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Review of the Challenges in Deep Learning for Skeletal and Smooth Muscle Ultrasound Images

et al. 2021

View full text Add to dashboard Cite

Deep learning has aided in the improvement of diagnosis identification, evaluation, and the interpretation of muscle ultrasound images, which may benefit clinical personnel. Muscle ultrasound images presents challenges such as low image quality due to noise, insufficient data, and different characteristics between skeletal and smooth muscles that can affect the effectiveness of deep learning results. From 2018 to 2020, deep learning has the improved solutions used to overcome these challenges; however, deep learning solutions for ultrasound images have not been compared to the conditions and strategies used to comprehend the current state of knowledge for handling skeletal and smooth muscle ultrasound images. This study aims to look at the challenges and trends of deep learning performance, especially in regard to overcoming muscle ultrasound image problems such as low image quality, muscle movement in skeletal muscles, and muscle thickness in smooth muscles. Skeletal muscle segmentation presents difficulties due to the regular movement of muscles and resulting noise, recording data through skipped connections, and modified layers required for upsampling. In skeletal muscle classification, the problems faced are area-specific, thus making a cropping strategy useful. Furthermore, there is no need to add additional layer modifications for smooth muscle segmentation as muscle thickness is the main problem in such cases.

show abstract

“…Deep learning method that mainly used for image problem is convolutional neural network (CNN). Several researchers have used CNN to classify medical imaging results such as [13] for classifying stroke, [14] for classifying type of muscle, and [15] for classifying abdominal ultrasound images. The used of CNN for classifying CXR has also been performed in [16] and [17] for classifying two classes, normal condition and pneumonia.…”

mentioning

confidence: 99%

Classification of pneumonia from X-ray images using siamese convolutional network

2020

View full text Add to dashboard Cite

Pneumonia is one of the highest global causes of deaths especially for children under 5 years old. This happened mainly because of the difficulties in identifying the cause of pneumonia. As a result, the treatment given may not be suitable for each pneumonia case. Recent studies have used deep learning approaches to obtain better classification within the cause of pneumonia. In this research, we used siamese convolutional network (SCN) to classify chest x-ray pneumonia image into 3 classes, namely normal conditions, bacterial pneumonia, and viral pneumonia. Siamese convolutional network is a neural network architecture that learns similarity knowledge between pairs of image inputs based on the differences between its features. One of the important benefits of classifying data with SCN is the availability of comparable images that can be used as a reference when determining class. Using SCN, our best model achieved 80.03% accuracy, 79.59% f1 score, and an improved result reasoning by providing the comparable images.

show abstract

Muscle Type Classification on Ultrasound Imaging Using Deep Convolutional Neural Networks

Cited by 7 publications

References 19 publications

Automatic Classification of Sarcopenia Level in Older Adults: A Case Study at Tijuana General Hospital

Automatic Classification of Sarcopenia Level in Older Adults: A Case Study at Tijuana General Hospital

A Review of the Challenges in Deep Learning for Skeletal and Smooth Muscle Ultrasound Images

Classification of pneumonia from X-ray images using siamese convolutional network

Contact Info

Product

Resources

About