Human Breast Numerical Model Generation Based on Deep Learning for Photoacoustic Imaging
Autor: | Yiyun Wang, Juze Zhang, Yaxin Ma, Changchun Yang, Fei Gao, Feng Gao |
---|---|
Rok vydání: | 2020 |
Předmět: |
medicine.diagnostic_test
Computer science business.industry Deep learning Spectrum Analysis Photoacoustic imaging in biomedicine Pattern recognition medicine.disease Photoacoustic Techniques Optical imaging Breast cancer Deep Learning medicine Ultrasound imaging Mammography Humans Artificial intelligence Breast business Human breast Ultrasonography |
Zdroj: | EMBC |
ISSN: | 2694-0604 |
Popis: | Photoacoustic imaging which combines high contrast of optical imaging and high resolution of ultrasound imaging, can provide functional information, potentially playing a crucial role in the study of breast cancer diagnostics. However, open source dataset for PA imaging research is insufficient on account of lacking clinical data. To tackle this problem, we propose a method to automatically generate breast numerical model for photoacoustic imaging. The different type of tissues is automatically extracted first by employing deep learning and other methods from mammography. And then the tissues are combined by mathematical set operation to generate a new breast image after being assigned optical and acoustic parameters. Finally, breast numerical model with proper optical and acoustic properties are generated, which are specifically suitable for PA imaging studies, and the experiment results indicate that our method is feasible with high efficiency. |
Databáze: | OpenAIRE |
Externí odkaz: |