Application of RESNET50 Convolution Neural Network for the Extraction of Optical Parameters in Scattering Media
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909742104838144 |
|---|---|
| author | Deng, Bowen Zhang, Yihan Parkes, Andrew Bentley, Alex Wright, Amanda Pound, Michael Somekh, Michael |
| author_facet | Deng, Bowen Zhang, Yihan Parkes, Andrew Bentley, Alex Wright, Amanda Pound, Michael Somekh, Michael |
| contents | Estimation of the optical properties of scattering media such as tissue is important in diagnostics as well as in the development of techniques to image deeper. As light penetrates the sample scattering events occur that alter the propagation direction of the photons in a random manner leading degradation of image quality. The distribution of the scattered light does, however, give a measure of the optical properties such as the reduced scattering coefficient and the absorption coefficient. Unfortunately, inverting scattering patterns to recover the optical properties is not simple especially in the regime where the light is partially randomized. Machine learning has been proposed by several authors as a means of recovering these properties from either the back scattered or the transmitted light. In the present paper we train a general purpose convolutional neural network RESNET 50 with simulated data based on Monte Carlo simulations. We show that compared with previous work our approach gives comparable or better reconstruction accuracy with training on a much smaller dataset. Moreover, by training on multiple parameters such as the intensity distribution at multiple planes or the exit angle and spatial distribution one achieves improved performance compared to training on a single input such as the intensity distribution captured at the sample surface. While our approach gives good parameter reconstruction, we identify factors that limit accuracy of the recovered properties, particularly the absorption coefficient. In the light of these limitations, we suggest how the present approach may be enhanced for even better performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16647 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Application of RESNET50 Convolution Neural Network for the Extraction of Optical Parameters in Scattering Media Deng, Bowen Zhang, Yihan Parkes, Andrew Bentley, Alex Wright, Amanda Pound, Michael Somekh, Michael Optics Machine Learning Estimation of the optical properties of scattering media such as tissue is important in diagnostics as well as in the development of techniques to image deeper. As light penetrates the sample scattering events occur that alter the propagation direction of the photons in a random manner leading degradation of image quality. The distribution of the scattered light does, however, give a measure of the optical properties such as the reduced scattering coefficient and the absorption coefficient. Unfortunately, inverting scattering patterns to recover the optical properties is not simple especially in the regime where the light is partially randomized. Machine learning has been proposed by several authors as a means of recovering these properties from either the back scattered or the transmitted light. In the present paper we train a general purpose convolutional neural network RESNET 50 with simulated data based on Monte Carlo simulations. We show that compared with previous work our approach gives comparable or better reconstruction accuracy with training on a much smaller dataset. Moreover, by training on multiple parameters such as the intensity distribution at multiple planes or the exit angle and spatial distribution one achieves improved performance compared to training on a single input such as the intensity distribution captured at the sample surface. While our approach gives good parameter reconstruction, we identify factors that limit accuracy of the recovered properties, particularly the absorption coefficient. In the light of these limitations, we suggest how the present approach may be enhanced for even better performance. |
| title | Application of RESNET50 Convolution Neural Network for the Extraction of Optical Parameters in Scattering Media |
| topic | Optics Machine Learning |
| url | https://arxiv.org/abs/2404.16647 |