File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/s00784-021-04365-x
- Scopus: eid_2-s2.0-85123171443
- PMID: 35032193
- WOS: WOS:000742794600001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Automatic detection and segmentation of morphological changes of the maxillary sinus mucosa on cone-beam computed tomography images using a three-dimensional convolutional neural network
Title | Automatic detection and segmentation of morphological changes of the maxillary sinus mucosa on cone-beam computed tomography images using a three-dimensional convolutional neural network |
---|---|
Authors | |
Keywords | Artificial intelligence Cone-beam computed tomography Convolutional neural network Maxillary sinus Mucosal retention cyst Mucosal thickening |
Issue Date | 2022 |
Citation | Clinical Oral Investigations, 2022, v. 26, n. 5, p. 3987-3998 How to Cite? |
Abstract | Objectives: To propose and evaluate a convolutional neural network (CNN) algorithm for automatic detection and segmentation of mucosal thickening (MT) and mucosal retention cysts (MRCs) in the maxillary sinus on low-dose and full-dose cone-beam computed tomography (CBCT). Materials and methods: A total of 890 maxillary sinuses on 445 CBCT scans were analyzed. The air space, MT, and MRCs in each sinus were manually segmented. Low-dose CBCTs were divided into training, training-monitoring, and testing datasets at a 7:1:2 ratio. Full-dose CBCTs were used as a testing dataset. A three-step CNN algorithm built based on V-Net and support vector regression was trained on low-dose CBCTs and tested on the low-dose and full-dose datasets. Performance for detection of MT and MRCs using area under the curves (AUCs) and for segmentation using Dice similarity coefficient (DSC) was evaluated. Results: For the detection of MT and MRCs, the algorithm achieved AUCs of 0.91 and 0.84 on low-dose scans and of 0.89 and 0.93 on full-dose scans, respectively. The median DSCs for segmenting the air space, MT, and MRCs were 0.972, 0.729, and 0.678 on low-dose scans and 0.968, 0.663, and 0.787 on full-dose scans, respectively. There were no significant differences in the algorithm performance between low-dose and full-dose CBCTs. Conclusions: The proposed CNN algorithm has the potential to accurately detect and segment MT and MRCs in maxillary sinus on CBCT scans with low-dose and full-dose protocols. Clinical relevance: An implementation of this artificial intelligence application in daily practice as an automated diagnostic and reporting system seems possible. |
Persistent Identifier | http://hdl.handle.net/10722/329768 |
ISSN | 2023 Impact Factor: 3.1 2023 SCImago Journal Rankings: 0.942 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hung, Kuo Feng | - |
dc.contributor.author | Ai, Qi Yong H. | - |
dc.contributor.author | King, Ann D. | - |
dc.contributor.author | Bornstein, Michael M. | - |
dc.contributor.author | Wong, Lun M. | - |
dc.contributor.author | Leung, Yiu Yan | - |
dc.date.accessioned | 2023-08-09T03:35:11Z | - |
dc.date.available | 2023-08-09T03:35:11Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Clinical Oral Investigations, 2022, v. 26, n. 5, p. 3987-3998 | - |
dc.identifier.issn | 1432-6981 | - |
dc.identifier.uri | http://hdl.handle.net/10722/329768 | - |
dc.description.abstract | Objectives: To propose and evaluate a convolutional neural network (CNN) algorithm for automatic detection and segmentation of mucosal thickening (MT) and mucosal retention cysts (MRCs) in the maxillary sinus on low-dose and full-dose cone-beam computed tomography (CBCT). Materials and methods: A total of 890 maxillary sinuses on 445 CBCT scans were analyzed. The air space, MT, and MRCs in each sinus were manually segmented. Low-dose CBCTs were divided into training, training-monitoring, and testing datasets at a 7:1:2 ratio. Full-dose CBCTs were used as a testing dataset. A three-step CNN algorithm built based on V-Net and support vector regression was trained on low-dose CBCTs and tested on the low-dose and full-dose datasets. Performance for detection of MT and MRCs using area under the curves (AUCs) and for segmentation using Dice similarity coefficient (DSC) was evaluated. Results: For the detection of MT and MRCs, the algorithm achieved AUCs of 0.91 and 0.84 on low-dose scans and of 0.89 and 0.93 on full-dose scans, respectively. The median DSCs for segmenting the air space, MT, and MRCs were 0.972, 0.729, and 0.678 on low-dose scans and 0.968, 0.663, and 0.787 on full-dose scans, respectively. There were no significant differences in the algorithm performance between low-dose and full-dose CBCTs. Conclusions: The proposed CNN algorithm has the potential to accurately detect and segment MT and MRCs in maxillary sinus on CBCT scans with low-dose and full-dose protocols. Clinical relevance: An implementation of this artificial intelligence application in daily practice as an automated diagnostic and reporting system seems possible. | - |
dc.language | eng | - |
dc.relation.ispartof | Clinical Oral Investigations | - |
dc.subject | Artificial intelligence | - |
dc.subject | Cone-beam computed tomography | - |
dc.subject | Convolutional neural network | - |
dc.subject | Maxillary sinus | - |
dc.subject | Mucosal retention cyst | - |
dc.subject | Mucosal thickening | - |
dc.title | Automatic detection and segmentation of morphological changes of the maxillary sinus mucosa on cone-beam computed tomography images using a three-dimensional convolutional neural network | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/s00784-021-04365-x | - |
dc.identifier.pmid | 35032193 | - |
dc.identifier.scopus | eid_2-s2.0-85123171443 | - |
dc.identifier.volume | 26 | - |
dc.identifier.issue | 5 | - |
dc.identifier.spage | 3987 | - |
dc.identifier.epage | 3998 | - |
dc.identifier.eissn | 1436-3771 | - |
dc.identifier.isi | WOS:000742794600001 | - |