Àá½Ã¸¸ ±â´Ù·Á ÁÖ¼¼¿ä. ·ÎµùÁßÀÔ´Ï´Ù.
KMID : 1024020230530010027
Imaging Science in Dentistry
2023 Volume.53 No. 1 p.27 ~ p.34
Effect of deep transfer learning with a different kind of lesion on classification performance of pre-trained model: Verification with radiolucent lesions on panoramic radiographs
Yoshitaka Kise

Yoshiko Ariji
Chiaki Kuwada
Motoki Fukuda
Eiichiro Ariji
Abstract
Purpose: The aim of this study was to clarify the influence of training with a different kind of lesion on the perfor- mance of a target model.

Materials and Methods: A total of 310 patients (211 men, 99 women; average age, 47.9¡¾16.1 years) were selected and their panoramic images were used in this study. We created a source model using panoramic radiographs including mandibular radiolucent cyst-like lesions (radicular cyst, dentigerous cyst, odontogenic keratocyst, and ameloblastoma). The model was simulatively transferred and trained on images of Stafne¡¯s bone cavity. A learning model was created using a customized DetectNet built in the Digits version 5.0 (NVIDIA, Santa Clara, CA). Two machines (Machines A and B) with identical specifications were used to simulate transfer learning. A source model was created from the data consisting of ameloblastoma, odontogenic keratocyst, dentigerous cyst, and radicular cyst in Machine A. Thereafter, it was transferred to Machine B and trained on additional data of Stafne¡¯s bone cavity to create target models. To investigate the effect of the number of cases, we created several target models with different numbers of Stafne¡¯s bone cavity cases.

Results: When the Stafne¡¯s bone cavity data were added to the training, both the detection and classification performances for this pathology improved. Even for lesions other than Stafne¡¯s bone cavity, the detection sensitivities tended to increase with the increase in the number of Stafne¡¯s bone cavities.

Conclusion: This study showed that using different lesions for transfer learning improves the performance of the model.
KEYWORD
Deep Learning, Machine Learning, Jaw Diseases, Radiography, Panoramic
FullTexts / Linksout information
 
Listed journal information
ÇмúÁøÈïÀç´Ü(KCI) KoreaMed