Preliminary Study on the Diagnostic Performance of a Deep Learning System for Submandibular Gland Inflammation Using Ultrasonography Images
This study was performed to evaluate the diagnostic performance of deep learning systems using ultrasonography (USG) images of the submandibular glands (SMGs) in three different conditions: obstructive sialoadenitis, Sjögren’s syndrome (SjS), and normal glands. Fifty USG images with a confirmed diag...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/10/19/4508 |
| _version_ | 1797516222929043456 |
|---|---|
| author | Yoshitaka Kise Chiaki Kuwada Yoshiko Ariji Munetaka Naitoh Eiichiro Ariji |
| author_facet | Yoshitaka Kise Chiaki Kuwada Yoshiko Ariji Munetaka Naitoh Eiichiro Ariji |
| author_sort | Yoshitaka Kise |
| collection | DOAJ |
| description | This study was performed to evaluate the diagnostic performance of deep learning systems using ultrasonography (USG) images of the submandibular glands (SMGs) in three different conditions: obstructive sialoadenitis, Sjögren’s syndrome (SjS), and normal glands. Fifty USG images with a confirmed diagnosis of obstructive sialoadenitis, 50 USG images with a confirmed diagnosis of SjS, and 50 USG images with no SMG abnormalities were included in the study. The training group comprised 40 obstructive sialoadenitis images, 40 SjS images, and 40 control images, and the test group comprised 10 obstructive sialoadenitis images, 10 SjS images, and 10 control images for deep learning analysis. The performance of the deep learning system was calculated and compared between two experienced radiologists. The sensitivity of the deep learning system in the obstructive sialoadenitis group, SjS group, and control group was 55.0%, 83.0%, and 73.0%, respectively, and the total accuracy was 70.3%. The sensitivity of the two radiologists was 64.0%, 72.0%, and 86.0%, respectively, and the total accuracy was 74.0%. This study revealed that the deep learning system was more sensitive than experienced radiologists in diagnosing SjS in USG images of two case groups and a group of healthy subjects in inflammation of SMGs. |
| first_indexed | 2024-03-10T06:58:14Z |
| format | Article |
| id | doaj.art-b69cdf0703c5471582421c7a8def135e |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-10T06:58:14Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-b69cdf0703c5471582421c7a8def135e2023-11-22T16:20:27ZengMDPI AGJournal of Clinical Medicine2077-03832021-09-011019450810.3390/jcm10194508Preliminary Study on the Diagnostic Performance of a Deep Learning System for Submandibular Gland Inflammation Using Ultrasonography ImagesYoshitaka Kise0Chiaki Kuwada1Yoshiko Ariji2Munetaka Naitoh3Eiichiro Ariji4Department of Oral and Maxillofacial Radiology, School of Dentistry, Aichi Gakuin University, Nagoya 464-8651, JapanDepartment of Oral and Maxillofacial Radiology, School of Dentistry, Aichi Gakuin University, Nagoya 464-8651, JapanDepartment of Oral and Maxillofacial Radiology, School of Dentistry, Aichi Gakuin University, Nagoya 464-8651, JapanDepartment of Oral and Maxillofacial Radiology, School of Dentistry, Aichi Gakuin University, Nagoya 464-8651, JapanDepartment of Oral and Maxillofacial Radiology, School of Dentistry, Aichi Gakuin University, Nagoya 464-8651, JapanThis study was performed to evaluate the diagnostic performance of deep learning systems using ultrasonography (USG) images of the submandibular glands (SMGs) in three different conditions: obstructive sialoadenitis, Sjögren’s syndrome (SjS), and normal glands. Fifty USG images with a confirmed diagnosis of obstructive sialoadenitis, 50 USG images with a confirmed diagnosis of SjS, and 50 USG images with no SMG abnormalities were included in the study. The training group comprised 40 obstructive sialoadenitis images, 40 SjS images, and 40 control images, and the test group comprised 10 obstructive sialoadenitis images, 10 SjS images, and 10 control images for deep learning analysis. The performance of the deep learning system was calculated and compared between two experienced radiologists. The sensitivity of the deep learning system in the obstructive sialoadenitis group, SjS group, and control group was 55.0%, 83.0%, and 73.0%, respectively, and the total accuracy was 70.3%. The sensitivity of the two radiologists was 64.0%, 72.0%, and 86.0%, respectively, and the total accuracy was 74.0%. This study revealed that the deep learning system was more sensitive than experienced radiologists in diagnosing SjS in USG images of two case groups and a group of healthy subjects in inflammation of SMGs.https://www.mdpi.com/2077-0383/10/19/4508deep learningultrasonographysubmandibular glandobstructive sialoadenitisSjögren’s syndrome |
| spellingShingle | Yoshitaka Kise Chiaki Kuwada Yoshiko Ariji Munetaka Naitoh Eiichiro Ariji Preliminary Study on the Diagnostic Performance of a Deep Learning System for Submandibular Gland Inflammation Using Ultrasonography Images Journal of Clinical Medicine deep learning ultrasonography submandibular gland obstructive sialoadenitis Sjögren’s syndrome |
| title | Preliminary Study on the Diagnostic Performance of a Deep Learning System for Submandibular Gland Inflammation Using Ultrasonography Images |
| title_full | Preliminary Study on the Diagnostic Performance of a Deep Learning System for Submandibular Gland Inflammation Using Ultrasonography Images |
| title_fullStr | Preliminary Study on the Diagnostic Performance of a Deep Learning System for Submandibular Gland Inflammation Using Ultrasonography Images |
| title_full_unstemmed | Preliminary Study on the Diagnostic Performance of a Deep Learning System for Submandibular Gland Inflammation Using Ultrasonography Images |
| title_short | Preliminary Study on the Diagnostic Performance of a Deep Learning System for Submandibular Gland Inflammation Using Ultrasonography Images |
| title_sort | preliminary study on the diagnostic performance of a deep learning system for submandibular gland inflammation using ultrasonography images |
| topic | deep learning ultrasonography submandibular gland obstructive sialoadenitis Sjögren’s syndrome |
| url | https://www.mdpi.com/2077-0383/10/19/4508 |
| work_keys_str_mv | AT yoshitakakise preliminarystudyonthediagnosticperformanceofadeeplearningsystemforsubmandibularglandinflammationusingultrasonographyimages AT chiakikuwada preliminarystudyonthediagnosticperformanceofadeeplearningsystemforsubmandibularglandinflammationusingultrasonographyimages AT yoshikoariji preliminarystudyonthediagnosticperformanceofadeeplearningsystemforsubmandibularglandinflammationusingultrasonographyimages AT munetakanaitoh preliminarystudyonthediagnosticperformanceofadeeplearningsystemforsubmandibularglandinflammationusingultrasonographyimages AT eiichiroariji preliminarystudyonthediagnosticperformanceofadeeplearningsystemforsubmandibularglandinflammationusingultrasonographyimages |