Deep Neural Networks for Diagnosis of Osteoporosis: A Review

Wani, Insha Majeed; Arora, Sakshi

doi:10.1007/978-3-030-29407-6_6

Cited by 7 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the age calculated by a NN is logically considered their BA. The application of NN for BA assessment has shown high efficiency by all criteria, including the absence of syste matic errors commonly associated with MLRbased methods [22]. Recently, this strategy of data analysis has been widely used to explore the studying its possibilities in osteoporo sis screening and predicting osteoporotic fractures [23][24][25][26].…”

Section: Assessment Of the Bone Biological Age Using Multiple Regress...mentioning

confidence: 99%

See 1 more Smart Citation

Assessment of the bone biological age using multiple regression and neural network analysis

Grygorieva,

Pisaruk,

Gurianov

et al. 2024

PJS

View full text Add to dashboard Cite

Background. Nowadays, many studies confirm the increased risk of osteoporosis in the elderly. Strategies for optimizing diagnosis include a combined use of various methods, so calculating bone biological age (BA) can also be important for disease prediction. Recently, some new methodological approaches to BA calculation with the mathematical methods implementation were proposed. However, studies utilizing advanced approaches, particularly neural network (NN) in Ukraine, are limited. The purpose of this study was to develop a bone BA model and compare its accuracy using stepwise multiple regression (MLR) and NN analysis methods. Materials and methods. In a single-center cohort study, we retrospectively analyzed the data of 3,071 healthy women aged 40–90 years. The analysis of the study indices included the anthropometric parameters, dual-energy X-ray absorptiometry indices (DXA), and the parameters of the 10-year probability of major osteoporotic fractures (FRAX). For the development of bone BA models, MLR methods were used and the construction of the NN model was performed using a multilayer perceptron model. Results. As a result of the calculation, we received the MLR formula for bone BA determining bone mineral density (BMD) of lumbar spine and radius, minimal femoral and hip BMD as well as Trabecular Bone Score, and FRAX. The MLR equation allowed to calculation of the bone BA with an error of less than 4.9 years for study and control groups and demonstrated the high connection between calculated and chronological (ChrA) ages (R = 0.77; p < 0.00001). The use of NN analysis showed the best results using 6 input variables and 1 internal layer of 7 neurons. The assessment of the connection between BA and ChrA demonstrated a high coefficient of correlation (R = 0.88; p < 0.000001) with an average error of age calculation of less than 3.7 years for the study and control groups. Conclusions. A comparison of the accuracy of both models in bone BA estimation revealed a significant advantage of the deep learning NN, however, the use trained NN model requires specialized software, whereas the MLR formula can be used without additional costs.

show abstract

Section: Assessment Of the Bone Biological Age Using Multiple Regress...mentioning

confidence: 99%

“…Therefore, it is logical to consider the person age, calculated by a NN, as BA. The use of NN for the BA estimation has shown their high efficiency according to all criteria, in particular, the absence of systematic error characteristic of methods based on MLR [22,23].…”

Section: Notes: Y -Dependent Variable "Age"; Intercept -Free Member O...mentioning

confidence: 99%

Assessment of the bone biological age using multiple regression and neural network analysis

Grygorieva,

Pisaruk,

Gurianov

et al. 2024

PJS

View full text Add to dashboard Cite

show abstract

“…Currently, it is diagnosed by dual-energy X-ray absorptiometry as standard which gives an information about the bone mineral density. However, it is desirable to find a radiation-free and cheaper method to make it available in all countries [1,2].…”

Section: Introductionmentioning

confidence: 99%

“…While introduced first in 1943 [5], especially during the last decade, miscellaneaous research has been made for example in designing neural networks, that are helpful for diagnosis. More specifically, for the diagnosis of osteoporosis, there are two main inputs from which the neural networks are supposed to find a solution: questionnaires giving information about the patients and images of the bone recorded by different imaging methods [1]. In Ref.…”

Section: Introductionmentioning

confidence: 99%

Inverse modeling of cancellous bone using artificial neural networks

2022

View full text Add to dashboard Cite

Artificial neural networks are used to solve different tasks of daily life, engineering and medicine. In this work, we investigate its suitability for the examination of simulation results of cancellous bone with the aim to evaluate whether the bone is affected by osteoporosis. This bone disease is characterized by a reduction of the cortical bone phase, one of the two main components of the bone. The neural network predicts the simulated volume fraction in different parts of a cylinder, which models the bone. As a basis for its calculations, the neural network gets the information about the magnetic field inside the cylinder from finite element simulations. Examinations show that it is possible to train neural networks on solving that task with very high accuracies.

show abstract

Deep ensemble learning for osteoporosis diagnosis from knee X-rays: a preliminary cohort study in Kashmir valley

Wani,

Arora

2024

Neural Comput & Applic

View full text Add to dashboard Cite

Deep Neural Networks for Diagnosis of Osteoporosis: A Review

Cited by 7 publications

References 46 publications

Assessment of the bone biological age using multiple regression and neural network analysis

Assessment of the bone biological age using multiple regression and neural network analysis

Inverse modeling of cancellous bone using artificial neural networks

Deep ensemble learning for osteoporosis diagnosis from knee X-rays: a preliminary cohort study in Kashmir valley

Contact Info

Product

Resources

About