Application of Convolutional Neural Network in the Diagnosis of Jaw Tumors
1
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
Objectives: Ameloblastomas and keratocystic odontogenic tumors (KCOTs) are important odontogenic tumors of the jaw. While their radiological findings are similar, the behaviors of these two types of tumors are different. Precise preoperative diagnosis of these tumors can help oral and maxillofacial surgeons plan appropriate treatment. In this study, we created a convolutional neural network (CNN) for the detection of ameloblastomas and KCOTs. Methods: Five hundred digital panoramic images of ameloblastomas and KCOTs were retrospectively collected from a hospital information system, whose patient information could not be identified, and preprocessed by inverse logarithm and histogram equalization. To overcome the imbalance of data entry, we focused our study on 2 tumors with equal distributions of input data. We implemented a transfer learning strategy to overcome the problem of limited patient data. Transfer learning used a 16-layer CNN (VGG-16) of the large sample dataset and was refined with our secondary training dataset comprising 400 images. A separate test dataset comprising 100 images was evaluated to compare the performance of CNN with diagnosis results produced by oral and maxillofacial specialists. Results: The sensitivity, specificity, accuracy, and diagnostic time were 81.8%, 83.3%, 83.0%, and 38 seconds, respectively, for the CNN. These values for the oral and maxillofacial specialist were 81.1%, 83.2%, 82.9%, and 23.1 minutes, respectively. Conclusions: Ameloblastomas and KCOTs could be detected based on digital panoramic radiographic images using CNN with accuracy comparable to that of manual diagnosis by oral maxillofacial specialists. These results demonstrate that CNN may aid in screening for ameloblastomas and KCOTs in a substantially shorter time.
Abstract
Objectives: Ameloblastomas and keratocystic odontogenic tumors (KCOTs) are important odontogenic tumors of the jaw. While their radiological findings are similar, the behaviors of these two types of tumors are different. Precise preoperative diagnosis of these tumors can help oral and maxillofacial surgeons plan appropriate treatment. In this study, we created a convolutional neural network (CNN) for the detection of ameloblastomas and KCOTs. Methods: Five hundred digital panoramic images of ameloblastomas and KCOTs were retrospectively collected from a hospital information system, whose patient information could not be identified, and preprocessed by inverse logarithm and histogram equalization. To overcome the imbalance of data entry, we focused our study on 2 tumors with equal distributions of input data. We implemented a transfer learning strategy to overcome the problem of limited patient data. Transfer learning used a 16-layer CNN (VGG-16) of the large sample dataset and was refined with our secondary training dataset comprising 400 images. A separate test dataset comprising 100 images was evaluated to compare the performance of CNN with diagnosis results produced by oral and maxillofacial specialists. Results: The sensitivity, specificity, accuracy, and diagnostic time were 81.8%, 83.3%, 83.0%, and 38 seconds, respectively, for the CNN. These values for the oral and maxillofacial specialist were 81.1%, 83.2%, 82.9%, and 23.1 minutes, respectively. Conclusions: Ameloblastomas and KCOTs could be detected based on digital panoramic radiographic images using CNN with accuracy comparable to that of manual diagnosis by oral maxillofacial specialists. These results demonstrate that CNN may aid in screening for ameloblastomas and KCOTs in a substantially shorter time.
참고문헌 (18)
- Apajalahti S, "Imaging characteristics of ameloblastomas and diagnostic value of computed tomography and magnetic resonance imaging in a series of 26 patients", Oral Surg Oral Med Oral Pathol Oral Radiol, 120(2), pp.e118~e130 (2015)[DOI]
- Jaeger F, "Prevalence profile of odontogenic cysts and tumors on Brazilian sample after the reclassification of odontogenic keratocyst", J Craniomaxillofac Surg, 45(2), pp.267~270 (2017)[DOI]
- Ariji Y, "Imaging features contributing to the diagnosis of ameloblastomas and keratocystic odontogenic tumours: logistic regression analysis", Dentomaxillofac Radiol, 40(3), pp.133~140 (2011)[DOI]
- Hayashi K, "Dynamic multislice helical CT of ameloblastoma and odontogenic keratocyst: correlation between contrast enhancement and angiogenesis", J Comput Assist Tomogr, 26(6), pp.922~926 (2002)[DOI]
- Minami M, "Cystic lesions of the maxillomandibular region: MR imaging distinction of odontogenic keratocysts and ameloblastomas from other cysts", AJR Am J Roentgenol, 166(4), pp.943~949 (1996)[DOI]
- Min S, "Deep learning in bioinformatics", Brief Bioinform, 18(5), pp.851~869 (2017)
- Shichijo S, "Application of convolutional neural networks in the diagnosis of helicobacter pylori infection based on endoscopic images", EBioMedicine, 25, pp.106~111 (2017)[DOI]
- Shin HC, "Deep convolutional neural networks for computeraided detection: CNN architectures, dataset characteristics and transfer learning", IEEE Trans Med Imaging, 35(5), pp.1285~1298 (2016)[DOI]
- [URL]
- Russakovsky O, "ImageNet large scale visual recognition challenge", Int J Comput Vis, 115(3), pp.211~252 (2015)[DOI]
- Sturm I, "Interpretable deep neural networks for single-trial EEG classification", J Neurosci Methods, 274, pp.141~145 (2016)[DOI]
- Oh S, "Ensemble learning with active example selection for imbalanced biomedical data classification", IEEE, 2011, pp.8(2), 316~325
- Malin BA, "Biomedical data privacy: problems, perspectives, and recent advances", J Am Med Inform Assoc, 20(1), pp.2~6 (2013)[DOI]
- Erhan D, "Why does unsupervised pre-training help deep learning?", J Mach Learn Res, 11, pp.625~660 (2010)
- Greenspan H, "Guest editorial deep learning in medical imaging: overview and future promise of an exciting new technique", IEEE Trans Med Imaging, 35(5), pp.1153~1159 (2016)[DOI]
- Bar Y, "Deep learning with non-medical training used for chest pathology identification", Medical imaging 2015: computeraided diagnosis (Proceedings of SPIE 9414) (2015), International Society for Optics and Photonics
- Raoof S, "Interpretation of plain chest roentgenogram", Chest, 141(2), pp.545~558 (2012)[DOI]
- Berbaum K, "The effect of comparison films upon resident interpretation of pediatric chest radiographs", Invest Radiol, 20(2), pp.124~128 (1985)[DOI]