Deep learning for detection and 3D segmentation of maxillofacial bone lesions in cone beam CT.
Talia YeshuaShmuel LadyzhenskyAmal Abu-NasserRagda Abdalla-AslanTami BoharonAvital Itzhak-PurAsher AlexanderAkhilanand ChaurasiaAdir CohenJacob SosnaIsaac LeichterChen NadlerPublished in: European radiology (2023)
• A deep learning algorithm was developed for automatic detection and 3D segmentation of various maxillofacial bone lesions in CBCT scans, irrespective of the CBCT device or the scanning protocol. • The developed algorithm can detect incidental jaw lesions with high accuracy, generates a 3D segmentation of the lesion, and calculates the lesion volume.
Keyphrases
- deep learning
- convolutional neural network
- image quality
- artificial intelligence
- computed tomography
- machine learning
- cone beam
- bone mineral density
- real time pcr
- loop mediated isothermal amplification
- dual energy
- label free
- contrast enhanced
- randomized controlled trial
- high resolution
- soft tissue
- postmenopausal women
- positron emission tomography
- body composition