Bianchetti, G. (2023) Machine learning-based metabolic imaging: A bridge between in vitro models and clinical applications. Il nuovo cimento C, 46 (3). pp. 1-9. ISSN 1826-9885
|
Text
ncc12640.pdf - Published Version Download (109kB) | Preview |
Abstract
A multiparametric approach is necessary to understand the intricate processes driving cellular physiological and pathological states. Current developments in the field of optical microscopy offer a deeper understanding in the evaluation of minute molecular changes, together with an even greater volume of biological data. Among these developments is functional metabolic imaging, a field that integrates molecular biology and in vivo imaging and sheds light on a number of metabolic processes that are crucial to cell survival. A few inherent limitations of the frequently used methods can also be solved by using probes that modify the picture in response to chemical changes occurring in the region of interest. To decode the extensive useful biological material that is concealed in pictures, more potent image analysis techniques are needed in addition to advancements in the image cap- ture process. Many machine learning (ML)-based techniques have recently been developed to achieve this goal. After providing a brief overview of metabolic and multiparametric imaging and the ML-based approaches that we are interested in, I will present different applications that I have developed to enable a more in-depth investigation of lipid turnover and membrane phase states, which are necessary to understand the functional and structural changes occurring in the disease.
| Item Type: | Article |
|---|---|
| Subjects: | 500 Scienze naturali e Matematica > 530 Fisica |
| Depositing User: | Marina Spanti |
| Date Deposited: | 29 Jan 2024 12:21 |
| Last Modified: | 29 Jan 2024 12:21 |
| URI: | http://eprints.bice.rm.cnr.it/id/eprint/22612 |
Actions (login required)
 |
View Item |
