Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs
Patients with odontogenic cysts and tumors may have to undergo serious surgery unless the lesion is properly detected at the early stage. The purpose of this study is to evaluate the diagnostic performance of the real-time object detecting deep convolutional neural network You Only Look Once (YOLO)...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/9/6/1839 |
| _version_ | 1797565495881236480 |
|---|---|
| author | Hyunwoo Yang Eun Jo Hyung Jun Kim In-ho Cha Young-Soo Jung Woong Nam Jun-Young Kim Jin-Kyu Kim Yoon Hyeon Kim Tae Gyeong Oh Sang-Sun Han Hwiyoung Kim Dongwook Kim |
| author_facet | Hyunwoo Yang Eun Jo Hyung Jun Kim In-ho Cha Young-Soo Jung Woong Nam Jun-Young Kim Jin-Kyu Kim Yoon Hyeon Kim Tae Gyeong Oh Sang-Sun Han Hwiyoung Kim Dongwook Kim |
| author_sort | Hyunwoo Yang |
| collection | DOAJ |
| description | Patients with odontogenic cysts and tumors may have to undergo serious surgery unless the lesion is properly detected at the early stage. The purpose of this study is to evaluate the diagnostic performance of the real-time object detecting deep convolutional neural network You Only Look Once (YOLO) v2—a deep learning algorithm that can both detect and classify an object at the same time—on panoramic radiographs. In this study, 1602 lesions on panoramic radiographs taken from 2010 to 2019 at Yonsei University Dental Hospital were selected as a database. Images were classified and labeled into four categories: dentigerous cysts, odontogenic keratocyst, ameloblastoma, and no lesion. Comparative analysis among three groups (YOLO, oral and maxillofacial surgeons, and general practitioners) was done in terms of precision, recall, accuracy, and F1 score. While YOLO ranked highest among the three groups (precision = 0.707, recall = 0.680), the performance differences between the machine and clinicians were statistically insignificant. The results of this study indicate the usefulness of auto-detecting convolutional networks in certain pathology detection and thus morbidity prevention in the field of oral and maxillofacial surgery. |
| first_indexed | 2024-03-10T19:12:59Z |
| format | Article |
| id | doaj.art-5e2e3363b19043f4a9d77523231727b3 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-10T19:12:59Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-5e2e3363b19043f4a9d77523231727b32023-11-20T03:38:50ZengMDPI AGJournal of Clinical Medicine2077-03832020-06-0196183910.3390/jcm9061839Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic RadiographsHyunwoo Yang0Eun Jo1Hyung Jun Kim2In-ho Cha3Young-Soo Jung4Woong Nam5Jun-Young Kim6Jin-Kyu Kim7Yoon Hyeon Kim8Tae Gyeong Oh9Sang-Sun Han10Hwiyoung Kim11Dongwook Kim12Department of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Radiology, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Radiology, Research Institute of Radiological Science, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaDepartment of Oral & Maxillofacial Surgery, Yonsei University College of Dentistry, 50-1 Yonsei-ro, Seodaemun-gu, Seoul 03722, KoreaPatients with odontogenic cysts and tumors may have to undergo serious surgery unless the lesion is properly detected at the early stage. The purpose of this study is to evaluate the diagnostic performance of the real-time object detecting deep convolutional neural network You Only Look Once (YOLO) v2—a deep learning algorithm that can both detect and classify an object at the same time—on panoramic radiographs. In this study, 1602 lesions on panoramic radiographs taken from 2010 to 2019 at Yonsei University Dental Hospital were selected as a database. Images were classified and labeled into four categories: dentigerous cysts, odontogenic keratocyst, ameloblastoma, and no lesion. Comparative analysis among three groups (YOLO, oral and maxillofacial surgeons, and general practitioners) was done in terms of precision, recall, accuracy, and F1 score. While YOLO ranked highest among the three groups (precision = 0.707, recall = 0.680), the performance differences between the machine and clinicians were statistically insignificant. The results of this study indicate the usefulness of auto-detecting convolutional networks in certain pathology detection and thus morbidity prevention in the field of oral and maxillofacial surgery.https://www.mdpi.com/2077-0383/9/6/1839YOLOdeep learningpanoramic radiographyodontogenic cystsodontogenic tumorcomputer-assisted diagnosis |
| spellingShingle | Hyunwoo Yang Eun Jo Hyung Jun Kim In-ho Cha Young-Soo Jung Woong Nam Jun-Young Kim Jin-Kyu Kim Yoon Hyeon Kim Tae Gyeong Oh Sang-Sun Han Hwiyoung Kim Dongwook Kim Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs Journal of Clinical Medicine YOLO deep learning panoramic radiography odontogenic cysts odontogenic tumor computer-assisted diagnosis |
| title | Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs |
| title_full | Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs |
| title_fullStr | Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs |
| title_full_unstemmed | Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs |
| title_short | Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs |
| title_sort | deep learning for automated detection of cyst and tumors of the jaw in panoramic radiographs |
| topic | YOLO deep learning panoramic radiography odontogenic cysts odontogenic tumor computer-assisted diagnosis |
| url | https://www.mdpi.com/2077-0383/9/6/1839 |
| work_keys_str_mv | AT hyunwooyang deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT eunjo deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT hyungjunkim deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT inhocha deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT youngsoojung deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT woongnam deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT junyoungkim deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT jinkyukim deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT yoonhyeonkim deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT taegyeongoh deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT sangsunhan deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT hwiyoungkim deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs AT dongwookkim deeplearningforautomateddetectionofcystandtumorsofthejawinpanoramicradiographs |