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

Research output: Contribution to conferencePaperpeer-review


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 languageEnglish
Number of pages2
Publication statusPublished - Jun 2023
EventInternational Workshop on Embedded Digital Intelligence (iWoEDI'2023) - Riga, Latvia
Duration: 20 Jun 202322 Jun 2023


WorkshopInternational Workshop on Embedded Digital Intelligence (iWoEDI'2023)
Abbreviated titleiWoEDI


  • 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)


Dive into the research topics of 'Artificial Intelligence-Powered System for Identifying Bone Deterioration in Radiological Imaging'. Together they form a unique fingerprint.

Cite this