{"id":{"repo_id":"uic","oai_identifier":"oai:figshare.com:article/32993771"},"canonical_url":"https://search.dev.ndltd.org/etd/uic/oai:figshare.com:article/32993771","repository":{"repo_id":"uic","name":"University of Illinois - Chicago","base_url":"https://api.figshare.com/v2/oai"},"display":{"title":"Assessment of Frontal Cephalogram Tracing Accuracy Generated by CNNs and Machine Learning","abstract":"Accurate diagnosis, precise treatment planning, and reliable prognosis are essential for successful orthodontic outcomes. Frontal (postero-anterior) cephalograms enhance diagnostic accuracy when properly traced and measured, however their can be variability between providers. Frontal cephalograms can now be efficiently generated from CBCT x-rays without additional radiation exposure. Artificial intelligence (AI) technologies have shown promise in automating radiographic landmark identification, which can eliminate provider error and reduce chair time. This study evaluated the accuracy of landmark detection and diagnostic measurements on CBCT-derived frontal cephalograms using a novel AI program, DR ANNIE™ (Data Research Artificial Neural Network Intelligence Expert; Research Foundation of Modern Bioprogressive Orthodontics), compared with manual tracings performed by experienced orthodontists. A total of 101 CBCT-derived frontal cephalograms were analyzed. Images were digitized automatically using DR ANNIE™ with auto-calibration and then manually traced by an experienced provider using Dolphin Imaging software. Clinically acceptable thresholds were predefined as 1.5 mm for linear measurements and 2° for angular measurements. Although statistically significant mean differences (p < 0.05) were observed between AI and human measurements for a substantial number of variables, the majority of these differences remained within clinically acceptable limits. Specifically, 90% of X-coordinate differences, 87% of Y-coordinate differences, and 77% of measurement differences were within established clinical thresholds. These findings support the clinical reliability of AI-assisted tracing for CBCT-derived frontal cephalograms.","abstract_html":"Accurate diagnosis, precise treatment planning, and reliable prognosis are essential for successful orthodontic outcomes. Frontal (postero-anterior) cephalograms enhance diagnostic accuracy when properly traced and measured, however their can be variability between providers. Frontal cephalograms can now be efficiently generated from CBCT x-rays without additional radiation exposure. Artificial intelligence (AI) technologies have shown promise in automating radiographic landmark identification, which can eliminate provider error and reduce chair time. This study evaluated the accuracy of landmark detection and diagnostic measurements on CBCT-derived frontal cephalograms using a novel AI program, DR ANNIE™ (Data Research Artificial Neural Network Intelligence Expert; Research Foundation of Modern Bioprogressive Orthodontics), compared with manual tracings performed by experienced orthodontists. A total of 101 CBCT-derived frontal cephalograms were analyzed. Images were digitized automatically using DR ANNIE™ with auto-calibration and then manually traced by an experienced provider using Dolphin Imaging software. Clinically acceptable thresholds were predefined as 1.5 mm for linear measurements and 2° for angular measurements. Although statistically significant mean differences (p &lt; 0.05) were observed between AI and human measurements for a substantial number of variables, the majority of these differences remained within clinically acceptable limits. Specifically, 90% of X-coordinate differences, 87% of Y-coordinate differences, and 77% of measurement differences were within established clinical thresholds. These findings support the clinical reliability of AI-assisted tracing for CBCT-derived frontal cephalograms.","abstract_has_math":false,"creators":["Mallory Kocher (24399377)"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-05-01T00:00:00Z","date_published":"2026-05-01T00:00:00Z","updated_at":"2026-07-27T21:33:36Z","subjects":["Orthodontics"],"languages":[],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.25417/uic.32993771.v1","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Mallory Kocher (24399377)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026-05-01T00:00:00Z"]},{"key":"dc:relation","label":"Dc Relation","values":["https://figshare.com/articles/thesis/Assessment_of_Frontal_Cephalogram_Tracing_Accuracy_Generated_by_CNNs_and_Machine_Learning/32993771"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Orthodontics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.25417/uic.32993771.v1"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Accurate diagnosis, precise treatment planning, and reliable prognosis are essential for successful orthodontic outcomes. Frontal (postero-anterior) cephalograms enhance diagnostic accuracy when properly traced and measured, however their can be variability between providers. Frontal cephalograms can now be efficiently generated from CBCT x-rays without additional radiation exposure. Artificial intelligence (AI) technologies have shown promise in automating radiographic landmark identification, which can eliminate provider error and reduce chair time. This study evaluated the accuracy of landmark detection and diagnostic measurements on CBCT-derived frontal cephalograms using a novel AI program, DR ANNIE™ (Data Research Artificial Neural Network Intelligence Expert; Research Foundation of Modern Bioprogressive Orthodontics), compared with manual tracings performed by experienced orthodontists. A total of 101 CBCT-derived frontal cephalograms were analyzed. Images were digitized automatically using DR ANNIE™ with auto-calibration and then manually traced by an experienced provider using Dolphin Imaging software. Clinically acceptable thresholds were predefined as 1.5 mm for linear measurements and 2° for angular measurements. Although statistically significant mean differences (p < 0.05) were observed between AI and human measurements for a substantial number of variables, the majority of these differences remained within clinically acceptable limits. Specifically, 90% of X-coordinate differences, 87% of Y-coordinate differences, and 77% of measurement differences were within established clinical thresholds. These findings support the clinical reliability of AI-assisted tracing for CBCT-derived frontal cephalograms."]},{"key":"dc:title","label":"Title","values":["Assessment of Frontal Cephalogram Tracing Accuracy Generated by CNNs and Machine Learning"]}]}],"canonical_facts":{"dc:creator":["Mallory Kocher (24399377)"],"dc:date":["2026-05-01T00:00:00Z"],"dc:description":["Accurate diagnosis, precise treatment planning, and reliable prognosis are essential for successful orthodontic outcomes. Frontal (postero-anterior) cephalograms enhance diagnostic accuracy when properly traced and measured, however their can be variability between providers. Frontal cephalograms can now be efficiently generated from CBCT x-rays without additional radiation exposure. Artificial intelligence (AI) technologies have shown promise in automating radiographic landmark identification, which can eliminate provider error and reduce chair time. This study evaluated the accuracy of landmark detection and diagnostic measurements on CBCT-derived frontal cephalograms using a novel AI program, DR ANNIE™ (Data Research Artificial Neural Network Intelligence Expert; Research Foundation of Modern Bioprogressive Orthodontics), compared with manual tracings performed by experienced orthodontists. A total of 101 CBCT-derived frontal cephalograms were analyzed. Images were digitized automatically using DR ANNIE™ with auto-calibration and then manually traced by an experienced provider using Dolphin Imaging software. Clinically acceptable thresholds were predefined as 1.5 mm for linear measurements and 2° for angular measurements. Although statistically significant mean differences (p < 0.05) were observed between AI and human measurements for a substantial number of variables, the majority of these differences remained within clinically acceptable limits. Specifically, 90% of X-coordinate differences, 87% of Y-coordinate differences, and 77% of measurement differences were within established clinical thresholds. These findings support the clinical reliability of AI-assisted tracing for CBCT-derived frontal cephalograms."],"dc:identifier":["10.25417/uic.32993771.v1"],"dc:relation":["https://figshare.com/articles/thesis/Assessment_of_Frontal_Cephalogram_Tracing_Accuracy_Generated_by_CNNs_and_Machine_Learning/32993771"],"dc:rights":["In Copyright"],"dc:subject":["Orthodontics"],"dc:title":["Assessment of Frontal Cephalogram Tracing Accuracy Generated by CNNs and Machine Learning"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T21:33:36Z"}