20.500.12556/DiRROS-24515 Reference areas selection affects registration of AI-segmented mandibles acquired with CBCT Izbor referenčnih območij vpliva na registracijo z umetno inteligenco segmentiranih mandibul, pridobljenig s CBCT Precise registration of sequential 3D datasets is crucial for accurate dimensional analysis. Utilizing the Local Best-Fit (LBF) algorithm and stable Registration Reference Areas (RRAs) facilitates the accurate alignment of 3D surface models. Currently, Cone-beam Computed Tomography (CBCT) and Deep Learn-ing (DL) algorithms are at the forefront for segmenting CBCT scans to monitor morphological changes in the residual alveolar ridge. This study compares the effectiveness of different RRAs in registration sequen-tial 3D surface models of partially edentulous mandibles. DL-assisted software segmented two sequential CBCTs (T0 and T1) from 10 patients, producing sequential 3D mandibular models. These models were aligned using three distinct RRAs: (i) WHOLE, encompassing the entire surface model; (ii) MND_BODY, covering the mandibular body while excluding the unstable alveolar ridge; and (iii) SPIN_FOR, incorpo-rating stable RRAs (mental foramina and mental spine). An innovative method assessed registration accu-racy by generating centroids from cross-sectional outlines of the mandibular nerve canals at the anterior third (A), medial third (B), and posterior third (C) of the posterior edentulous areas. The distance between centroids at T0 and T1 quantified registration accuracy. The MND_BODY group exhibited superior accu-racy, whereas the SPIN_FOR group showed the least, with accuracy decreasing from A to C, suggesting rotational misalignments. When selecting RRAs, both stability and spatial distribution must be taken into account. For optimal alignment, sequential 3D surface models should use RRAs that are both stable and widely distributed. računalniško podprta obdelava slik računalniška tomografija s stožčastim stopom globoko učenje zobni modeli delne proteze trodimenzionalno slikanje true false true Angleški jezik Slovenski jezik Neznano 2025-12-03 14:00:37 2025-12-03 14:00:38 2025-12-04 03:46:31 0000-00-00 00:00:00 2024 0 0 str. 211-219 no. 3 Vol. 43 Nov. 2024 0000-00-00 Zaloznikova Objavljeno apc 0000-00-00 0000-00-00 0000-00-00 616-073.7:004.8 1580-3139 10.5566/ias.3289 245250307 RAZ_Leopold_Klemen_2024.pdf RAZ_Leopold_Klemen_2024.pdf 1 9F1997899782F9119BBF653D4F963C93 e042cf1cc0a9371784497742e4131412ab0a484c2fc7b4d7d5e6866e281606da 42c27f83-d048-11f0-94a7-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=36543 https://ias-iss.org/ojs/IAS/article/view/3289 0 512fbc62-d048-11f0-94a7-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=36544 Univerzitetni klinični center Ljubljana 0 0 0