The Influence of the Normalisation of Spinal CT Images on the Significance of Textural Features in the Identification of Defects in the Spongy Tissue Structure

Dzierżak, Róża; Omiotek, Zbigniew; Tkacz, Ewaryst; Kȩpa, Andrzej

doi:10.1007/978-3-030-15472-1_7

Cited by 9 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The camera operates at a frame rate of up to 30 frames per second (FPS) and has a depth range of approximately 0.2 to 10 meters. Additionally, the D435i camera includes an integrated inertial measurement unit (IMU) that enables tracking and motion sensing capabilities 17 . On the other hand, the Intel RealSense L515 camera (Fig.…”

Section: Methodsmentioning

confidence: 99%

3D scanning technologies by optical RealSense cameras for SIREN-based 3D hand representation

Tymkovych,

Selivanova,

Avrunin

et al. 2023

Optical Fibers and Their Applications 2023

View full text Add to dashboard Cite

Modern 3D scanning technologies have revolutionized various industries, including healthcare and biomedical engineering. This research explores the application of 3D scanning in the field of medicine, focusing on the representation of 3D hand data using the SIREN (Sinusoidal Representation Network) approach. 3D scanning plays a vital role in hand prosthetics, enabling the development of personalized models that accurately replicate the shape and size of real hands. This allows for the production of prostheses tailored to the specific needs of patients, facilitating their reintegration into active life. RealSense 3D cameras, developed by Intel, are among the leading technologies for 3D scanning. However, the effective utilization of implicit representation of 3D data, such as SIREN, presents challenges in ensuring compatibility with the features and limitations of existing 3D scanning technologies. This study analyses the potential of SIREN for 3D hand data representation, addressing the existing constraints and limitations. By leveraging the capabilities of RealSense cameras and the flexibility of SIREN, we aim to enhance the analysis and processing of 3D data, opening new avenues for prosthesis design.

show abstract

Section: Methodsmentioning

confidence: 99%

3D scanning technologies by optical RealSense cameras for SIREN-based 3D hand representation

Tymkovych,

Selivanova,

Avrunin

et al. 2023

Optical Fibers and Their Applications 2023

View full text Add to dashboard Cite

show abstract

“…The image histogram normalisation process is one of the image preprocessing techniques frequently used for classification. As part of the studies previously carried out by the authors, it was shown that this operation reduces the classification accuracy from 4% for the TPR coefficient to 14% for ACC [ 34 ].…”

Section: Methodsmentioning

confidence: 99%

Application of Deep Convolutional Neural Networks in the Diagnosis of Osteoporosis

Dzierżak

Omiotek

2022

Sensors

View full text Add to dashboard Cite

The aim of this study was to assess the possibility of using deep convolutional neural networks (DCNNs) to develop an effective method for diagnosing osteoporosis based on CT images of the spine. The research material included the CT images of L1 spongy tissue belonging to 100 patients (50 healthy and 50 diagnosed with osteoporosis). Six pre-trained DCNN architectures with different topological depths (VGG16, VGG19, MobileNetV2, Xception, ResNet50, and InceptionResNetV2) were used in the study. The best results were obtained for the VGG16 model characterised by the lowest topological depth (ACC = 95%, TPR = 96%, and TNR = 94%). A specific challenge during the study was the relatively small (for deep learning) number of observations (400 images). This problem was solved using DCNN models pre-trained on a large dataset and a data augmentation technique. The obtained results allow us to conclude that the transfer learning technique yields satisfactory results during the construction of deep models for the diagnosis of osteoporosis based on small datasets of CT images of the spine.

show abstract

“…During the preprocessing, the image histogram normalization process was omitted because the available results indicate that this operation deteriorates the classification accuracy in the range from 4% for the TPR coefficient (classification sensitivity) to 14% for ACC (overall classification accuracy) [ 35 ].…”

Section: Methodsmentioning

confidence: 99%

Comparison of the Classification Results Accuracy for CT Soft Tissue and Bone Reconstructions in Detecting the Porosity of a Spongy Tissue

Dzierżak

Omiotek

Tkacz

et al. 2022

JCM

Self Cite

View full text Add to dashboard Cite

The aim of the study was to compare the accuracy of the classification pertaining to the results of two types of soft tissue and bone reconstructions of the spinal CT in detecting the porosity of L1 vertebral body spongy tissue. The dataset for each type of reconstruction (high-resolution bone reconstruction and soft tissue reconstruction) included 400 sponge tissue images from 50 healthy patients and 50 patients with osteoporosis. Texture feature descriptors were calculated based on the statistical analysis of the grey image histogram, autoregression model, and wavelet transform. The data dimensional reduction was applied by feature selection using nine methods representing various approaches (filter, wrapper, and embedded methods). Eleven methods were used to build the classifier models. In the learning process, hyperparametric optimization based on the grid search method was applied. On this basis, the most effective model and the optimal subset of features for each selection method used were determined. In the case of bone reconstruction images, four models achieved a maximum accuracy of 92%, one of which had the highest sensitivity of 95%, with a specificity of 89%. For soft tissue reconstruction images, five models achieved the highest testing accuracy of 95%, whereas the other quality indices (TPR and TNR) were also equal to 95%. The research showed that the images derived from soft tissue reconstruction allow for obtaining more accurate values of texture parameters, which increases the accuracy of the classification and offers better possibilities for diagnosing osteoporosis.

show abstract

The Influence of the Normalisation of Spinal CT Images on the Significance of Textural Features in the Identification of Defects in the Spongy Tissue Structure

Cited by 9 publications

References 18 publications

3D scanning technologies by optical RealSense cameras for SIREN-based 3D hand representation

3D scanning technologies by optical RealSense cameras for SIREN-based 3D hand representation

Application of Deep Convolutional Neural Networks in the Diagnosis of Osteoporosis

Comparison of the Classification Results Accuracy for CT Soft Tissue and Bone Reconstructions in Detecting the Porosity of a Spongy Tissue

Contact Info

Product

Resources

About