Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images
This study was designed to develop and verify a fully automated cephalometry landmark identification system, based on multi-stage convolutional neural networks (CNNs) architecture, using a combination dataset. In this research, we trained and tested multi-stage CNNs with 430 lateral and 430 MIP late...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/2/505 |
| _version_ | 1797412408869781504 |
|---|---|
| author | Min-Jung Kim Yi Liu Song Hee Oh Hyo-Won Ahn Seong-Hun Kim Gerald Nelson |
| author_facet | Min-Jung Kim Yi Liu Song Hee Oh Hyo-Won Ahn Seong-Hun Kim Gerald Nelson |
| author_sort | Min-Jung Kim |
| collection | DOAJ |
| description | This study was designed to develop and verify a fully automated cephalometry landmark identification system, based on multi-stage convolutional neural networks (CNNs) architecture, using a combination dataset. In this research, we trained and tested multi-stage CNNs with 430 lateral and 430 MIP lateral cephalograms synthesized by cone-beam computed tomography (CBCT) to make a combination dataset. Fifteen landmarks were manually and respectively identified by experienced examiner, at the preprocessing phase. The intra-examiner reliability was high (ICC = 0.99) in manual identification. The results of prediction of the system for average mean radial error (MRE) and standard deviation (SD) were 1.03 mm and 1.29 mm, respectively. In conclusion, different types of image data might be the one of factors that affect the prediction accuracy of a fully-automated landmark identification system, based on multi-stage CNNs. |
| first_indexed | 2024-03-09T05:02:38Z |
| format | Article |
| id | doaj.art-fb12e5d205464f77a6b56fedd5379c8e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:02:38Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-fb12e5d205464f77a6b56fedd5379c8e2023-12-03T12:59:18ZengMDPI AGSensors1424-82202021-01-0121250510.3390/s21020505Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination ImagesMin-Jung Kim0Yi Liu1Song Hee Oh2Hyo-Won Ahn3Seong-Hun Kim4Gerald Nelson5Department of Orthodontics, Graduate School, Kyung Hee University, Seoul 02447, KoreaDepartment of Orthodontics, Peking University School of Stomatology, Beijing 100081, ChinaDepartment of Oral and Maxillofacial Radiology, Graduate School, Kyung Hee University, Seoul 02447, KoreaDepartment of Orthodontics, Graduate School, Kyung Hee University, Seoul 02447, KoreaDepartment of Orthodontics, Graduate School, Kyung Hee University, Seoul 02447, KoreaDivision of Orthodontics, Department of Orofacial Science, University of California San Francisco, San Francisco, CA 94143, USAThis study was designed to develop and verify a fully automated cephalometry landmark identification system, based on multi-stage convolutional neural networks (CNNs) architecture, using a combination dataset. In this research, we trained and tested multi-stage CNNs with 430 lateral and 430 MIP lateral cephalograms synthesized by cone-beam computed tomography (CBCT) to make a combination dataset. Fifteen landmarks were manually and respectively identified by experienced examiner, at the preprocessing phase. The intra-examiner reliability was high (ICC = 0.99) in manual identification. The results of prediction of the system for average mean radial error (MRE) and standard deviation (SD) were 1.03 mm and 1.29 mm, respectively. In conclusion, different types of image data might be the one of factors that affect the prediction accuracy of a fully-automated landmark identification system, based on multi-stage CNNs.https://www.mdpi.com/1424-8220/21/2/505artificial intelligenceconvolutional neural networksautomatic identificationlateral cephalogramscone-beam computed tomographymaximum intensity projection (MIP) |
| spellingShingle | Min-Jung Kim Yi Liu Song Hee Oh Hyo-Won Ahn Seong-Hun Kim Gerald Nelson Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images Sensors artificial intelligence convolutional neural networks automatic identification lateral cephalograms cone-beam computed tomography maximum intensity projection (MIP) |
| title | Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images |
| title_full | Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images |
| title_fullStr | Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images |
| title_full_unstemmed | Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images |
| title_short | Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images |
| title_sort | automatic cephalometric landmark identification system based on the multi stage convolutional neural networks with cbct combination images |
| topic | artificial intelligence convolutional neural networks automatic identification lateral cephalograms cone-beam computed tomography maximum intensity projection (MIP) |
| url | https://www.mdpi.com/1424-8220/21/2/505 |
| work_keys_str_mv | AT minjungkim automaticcephalometriclandmarkidentificationsystembasedonthemultistageconvolutionalneuralnetworkswithcbctcombinationimages AT yiliu automaticcephalometriclandmarkidentificationsystembasedonthemultistageconvolutionalneuralnetworkswithcbctcombinationimages AT songheeoh automaticcephalometriclandmarkidentificationsystembasedonthemultistageconvolutionalneuralnetworkswithcbctcombinationimages AT hyowonahn automaticcephalometriclandmarkidentificationsystembasedonthemultistageconvolutionalneuralnetworkswithcbctcombinationimages AT seonghunkim automaticcephalometriclandmarkidentificationsystembasedonthemultistageconvolutionalneuralnetworkswithcbctcombinationimages AT geraldnelson automaticcephalometriclandmarkidentificationsystembasedonthemultistageconvolutionalneuralnetworkswithcbctcombinationimages |