التفاصيل البيبلوغرافية
| العنوان: |
Transferable Architecture for Segmenting Maxillary Sinuses on Texture-Enhanced Occipitomental View Radiographs |
| المؤلفون: |
Peter Chondro, Qazi Mazhar ul Haq, Shanq-Jang Ruan, Lieber Po-Hung Li |
| المصدر: |
Mathematics, Vol 8, Iss 5, p 768 (2020) |
| بيانات النشر: |
MDPI AG, 2020. |
| سنة النشر: |
2020 |
| المجموعة: |
LCC:Mathematics |
| مصطلحات موضوعية: |
maxillary sinus, radiography, enhancement, semantic segmentation, transfer knowledge, Mathematics, QA1-939 |
| الوصف: |
Maxillary sinuses are the most prevalent locations for paranasal infections on both children and adults. Common diagnostic material for this particular disease is through the screening of occipitomental-view skull radiography (SXR). With the growing cases on paranasal infections, expediting the diagnosis has become an important innovation aspect that could be addressed through the development of a computer-aided diagnosis system. As the preliminary stage of the development, an automatic segmentation over the maxillary sinuses is required to be developed. This study presents a computer-aided detection (CAD) module that segments maxillary sinuses from a plain SXR that has been preprocessed through the novel texture-based morphological analysis (ToMA). Later, the network model from the Transferable Fully Convolutional Network (T-FCN) performs pixel-wise segmentation of the maxillary sinuses. T-FCN is designed to be trained with multiple learning stages, which enables re-utilization of network weights to be adjusted based on newer dataset. According to the experiments, the proposed system achieved segmentation accuracy at 85.70%, with 50% faster learning time. |
| نوع الوثيقة: |
article |
| وصف الملف: |
electronic resource |
| اللغة: |
English |
| تدمد: |
2227-7390 |
| Relation: |
https://www.mdpi.com/2227-7390/8/5/768; https://doaj.org/toc/2227-7390 |
| DOI: |
10.3390/math8050768 |
| URL الوصول: |
https://doaj.org/article/fa1702a58ac54765a454b5709e29f1ce |
| رقم الانضمام: |
edsdoj.fa1702a58ac54765a454b5709e29f1ce |
| قاعدة البيانات: |
Directory of Open Access Journals |
Full Text Finder