Artificial Intelligence-Powered System for Identifying Bone Deterioration in Radiological Imaging

Kaspars Sudars; Ivars Namatevs; Arturs Nikulins; Edgars Edelmers; Laura Neimane; Anda Slaidiņa; Oskars Radziņš

Artificial Intelligence-Powered System for Identifying Bone Deterioration in Radiological Imaging

Kaspars Sudars (Coresponding Author), Ivars Namatevs, Arturs Nikulins, Edgars Edelmers, Laura Neimane, Anda Slaidiņa, Oskars Radziņš

Rīga Stradiņš University

Research output: Contribution to conference › Paper › peer-review

Abstract

The aim of this research was to investigate the potential of deep convolutional neural networks (DCNN) for developing a reliable osteoporosis diagnostic tool using cone-beam computed tomography (CBCT) scans of the mandible. The study utilized CBCT scans of patients' mandibular bone tissue and incorporated two pre-existing DCNN architectures derived from the ResNet-101 model. Findings from the study suggest that employing transfer learning methodologies can produce satisfactory outcomes in the creation of deep learning models for osteoporosis detection, even when the availability of mandibular CBCT image datasets is restricted.

Original language	English
Number of pages	2
Publication status	Published - Jun 2023
Event	International Workshop on Embedded Digital Intelligence (iWoEDI'2023) - Riga, Latvia Duration: 20 Jun 2023 → 22 Jun 2023

Workshop

Workshop	International Workshop on Embedded Digital Intelligence (iWoEDI'2023)
Abbreviated title	iWoEDI
Country/Territory	Latvia
City	Riga
Period	20/06/23 → 22/06/23

Keywords*

osteoporosis
radiology
medicine
artificial intelligence

Field of Science*

3.2 Clinical medicine
1.2 Computer and information sciences

Publication Type*

3.4. Other publications in conference proceedings (including local)

Access to Document

https://events.edi.lv/iwoedi2023/wp-content/uploads/sites/2/2023/06/IWoEDI-2023-Artificial-Inteligence-Powered-System-for-Identifying-Bone-Deterioration-in-Radiological-Imaging.pdf

Cite this

Sudars, K., Namatevs, I., Nikulins, A., Edelmers, E., Neimane, L., Slaidiņa, A., & Radziņš, O. (2023). Artificial Intelligence-Powered System for Identifying Bone Deterioration in Radiological Imaging. Paper presented at International Workshop on Embedded Digital Intelligence (iWoEDI'2023), Riga, Latvia. https://events.edi.lv/iwoedi2023/wp-content/uploads/sites/2/2023/06/IWoEDI-2023-Artificial-Inteligence-Powered-System-for-Identifying-Bone-Deterioration-in-Radiological-Imaging.pdf

@conference{dd2eab66af054565a0f03cb52da01ef2,

title = "Artificial Intelligence-Powered System for Identifying Bone Deterioration in Radiological Imaging",

abstract = "The aim of this research was to investigate the potential of deep convolutional neural networks (DCNN) for developing a reliable osteoporosis diagnostic tool using cone-beam computed tomography (CBCT) scans of the mandible. The study utilized CBCT scans of patients' mandibular bone tissue and incorporated two pre-existing DCNN architectures derived from the ResNet-101 model. Findings from the study suggest that employing transfer learning methodologies can produce satisfactory outcomes in the creation of deep learning models for osteoporosis detection, even when the availability of mandibular CBCT image datasets is restricted.",

keywords = "osteoporosis, radiology, medicine, artificial intelligence",

author = "Kaspars Sudars and Ivars Namatevs and Arturs Nikulins and Edgars Edelmers and Laura Neimane and Anda Slaidiņa and Oskars Radziņ{\v s}",

year = "2023",

month = jun,

language = "English",

note = "International Workshop on Embedded Digital Intelligence (iWoEDI'2023), iWoEDI ; Conference date: 20-06-2023 Through 22-06-2023",

}

Sudars, K, Namatevs, I, Nikulins, A, Edelmers, E , Neimane, L , Slaidiņa, A & Radziņš, O 2023, 'Artificial Intelligence-Powered System for Identifying Bone Deterioration in Radiological Imaging', Paper presented at International Workshop on Embedded Digital Intelligence (iWoEDI'2023), Riga, Latvia, 20/06/23 - 22/06/23. <https://events.edi.lv/iwoedi2023/wp-content/uploads/sites/2/2023/06/IWoEDI-2023-Artificial-Inteligence-Powered-System-for-Identifying-Bone-Deterioration-in-Radiological-Imaging.pdf>

TY - CONF

T1 - Artificial Intelligence-Powered System for Identifying Bone Deterioration in Radiological Imaging

AU - Sudars, Kaspars

AU - Namatevs, Ivars

AU - Nikulins, Arturs

AU - Edelmers, Edgars

AU - Neimane, Laura

AU - Slaidiņa, Anda

AU - Radziņš, Oskars

PY - 2023/6

Y1 - 2023/6

N2 - The aim of this research was to investigate the potential of deep convolutional neural networks (DCNN) for developing a reliable osteoporosis diagnostic tool using cone-beam computed tomography (CBCT) scans of the mandible. The study utilized CBCT scans of patients' mandibular bone tissue and incorporated two pre-existing DCNN architectures derived from the ResNet-101 model. Findings from the study suggest that employing transfer learning methodologies can produce satisfactory outcomes in the creation of deep learning models for osteoporosis detection, even when the availability of mandibular CBCT image datasets is restricted.

AB - The aim of this research was to investigate the potential of deep convolutional neural networks (DCNN) for developing a reliable osteoporosis diagnostic tool using cone-beam computed tomography (CBCT) scans of the mandible. The study utilized CBCT scans of patients' mandibular bone tissue and incorporated two pre-existing DCNN architectures derived from the ResNet-101 model. Findings from the study suggest that employing transfer learning methodologies can produce satisfactory outcomes in the creation of deep learning models for osteoporosis detection, even when the availability of mandibular CBCT image datasets is restricted.

KW - osteoporosis

KW - radiology

KW - medicine

KW - artificial intelligence

M3 - Paper

T2 - International Workshop on Embedded Digital Intelligence (iWoEDI'2023)

Y2 - 20 June 2023 through 22 June 2023

ER -

Artificial Intelligence-Powered System for Identifying Bone Deterioration in Radiological Imaging

Abstract

Workshop

Keywords*

Field of Science*

Publication Type*

Access to Document

Fingerprint

Cite this