{"doi":"10.1109/tmi.2022.3174513","title":"Localization of Craniomaxillofacial Landmarks on CBCT Images Using 3D Mask R-CNN and Local Dependency Learning","abstract":"Cephalometric analysis relies on accurate detection of craniomaxillofacial (CMF) landmarks from cone-beam computed tomography (CBCT) images. However, due to the complexity of CMF bony structures, it is difficult to localize landmarks efficiently and accurately. In this paper, we propose a deep learning framework to tackle this challenge by jointly digitalizing 105 CMF landmarks on CBCT images. By explicitly learning the local geometrical relationships between the landmarks, our approach extends Mask R-CNN for end-to-end prediction of landmark locations. Specifically, we first apply a detection network on a down-sampled 3D image to leverage global contextual information to predict the approximate locations of the landmarks. We subsequently leverage local information provided by higher-resolution image patches to refine the landmark locations. On patients with varying non-syndromic jaw deformities, our method achieves an average detection accuracy of 1.38± 0.95mm, outperforming a related state-of-the-art method.","journal":"IEEE Transactions on Medical Imaging","year":2022,"id":240698,"datarank":0.5709993734655481,"base_score":3.8066624897703196,"endowment":3.8066624897703196,"self_citation_contribution":0.5709993734655481,"citation_network_contribution":0.0,"self_endowment_contribution":0.5709993734655481,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":44,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9599,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":270446,"name":"Chunfeng Lian","orcid":"0000-0002-9319-6633","position":1,"is_corresponding":false},{"id":656891,"name":"Deqiang Xiao","orcid":"0000-0002-7478-1394","position":2,"is_corresponding":false},{"id":443774,"name":"Han Deng","orcid":"0000-0001-9363-1722","position":3,"is_corresponding":false},{"id":368634,"name":"Kim-Han Thung","orcid":"0000-0003-1379-2185","position":4,"is_corresponding":false},{"id":443775,"name":"Peng Yuan","orcid":"0000-0003-4405-1830","position":5,"is_corresponding":false},{"id":391024,"name":"Jaime Gateño","orcid":"0000-0002-7597-6433","position":6,"is_corresponding":false},{"id":656889,"name":"Tianshu Kuang","orcid":"0000-0002-9439-464X","position":7,"is_corresponding":false},{"id":869355,"name":"David M. Alfi","orcid":null,"position":8,"is_corresponding":false},{"id":250559,"name":"Li Wang","orcid":"0000-0003-2165-0080","position":9,"is_corresponding":false},{"id":270449,"name":"Dinggang Shen","orcid":"0000-0002-7934-5698","position":10,"is_corresponding":false},{"id":391026,"name":"James J. Xia","orcid":"0000-0003-1386-0221","position":11,"is_corresponding":false},{"id":289667,"name":"Pew‐Thian Yap","orcid":"0000-0003-1489-2102","position":12,"is_corresponding":false},{"id":665277,"name":"Yankun Lang","orcid":"0000-0001-9823-3264","position":0,"is_corresponding":true}],"reference_count":53,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T00:22:51.435773Z","pmid":"35544487","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}