DEEP-squared: deep learning powered De-scattering with Excitation Patterning
Limited throughput is a key challenge in in vivo deep tissue imaging using nonlinear optical microscopy. Point scanning multiphoton microscopy, the current gold standard, is slow especially compared to the widefield imaging modalities used for optically cleared or thin specimens. We recently introdu...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2024
|
| Online Access: | https://hdl.handle.net/1721.1/154315 |
| _version_ | 1824457978666811392 |
|---|---|
| author | Wijethilake, Navodini Anandakumar, Mithunjha Zheng, Cheng So, Peter T. C. Yildirim, Murat Wadduwage, Dushan N. |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Wijethilake, Navodini Anandakumar, Mithunjha Zheng, Cheng So, Peter T. C. Yildirim, Murat Wadduwage, Dushan N. |
| author_sort | Wijethilake, Navodini |
| collection | MIT |
| description | Limited throughput is a key challenge in in vivo deep tissue imaging using nonlinear optical microscopy. Point scanning multiphoton microscopy, the current gold standard, is slow especially compared to the widefield imaging modalities used for optically cleared or thin specimens. We recently introduced “De-scattering with Excitation Patterning” or “DEEP” as a widefield alternative to point-scanning geometries. Using patterned multiphoton excitation, DEEP encodes spatial information inside tissue before scattering. However, to de-scatter at typical depths, hundreds of such patterned excitations were needed. In this work, we present DEEP<jats:sup>2</jats:sup>, a deep learning-based model that can de-scatter images from just tens of patterned excitations instead of hundreds. Consequently, we improve DEEP’s throughput by almost an order of magnitude. We demonstrate our method in multiple numerical and experimental imaging studies, including in vivo cortical vasculature imaging up to 4 scattering lengths deep in live mice. |
| first_indexed | 2024-09-23T09:55:39Z |
| format | Article |
| id | mit-1721.1/154315 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:18:35Z |
| publishDate | 2024 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1543152024-12-23T05:20:35Z DEEP-squared: deep learning powered De-scattering with Excitation Patterning Wijethilake, Navodini Anandakumar, Mithunjha Zheng, Cheng So, Peter T. C. Yildirim, Murat Wadduwage, Dushan N. Massachusetts Institute of Technology. Department of Mechanical Engineering Massachusetts Institute of Technology. Laser Biomedical Research Center Massachusetts Institute of Technology. Department of Biological Engineering Picower Institute for Learning and Memory Limited throughput is a key challenge in in vivo deep tissue imaging using nonlinear optical microscopy. Point scanning multiphoton microscopy, the current gold standard, is slow especially compared to the widefield imaging modalities used for optically cleared or thin specimens. We recently introduced “De-scattering with Excitation Patterning” or “DEEP” as a widefield alternative to point-scanning geometries. Using patterned multiphoton excitation, DEEP encodes spatial information inside tissue before scattering. However, to de-scatter at typical depths, hundreds of such patterned excitations were needed. In this work, we present DEEP<jats:sup>2</jats:sup>, a deep learning-based model that can de-scatter images from just tens of patterned excitations instead of hundreds. Consequently, we improve DEEP’s throughput by almost an order of magnitude. We demonstrate our method in multiple numerical and experimental imaging studies, including in vivo cortical vasculature imaging up to 4 scattering lengths deep in live mice. 2024-04-30T18:15:43Z 2024-04-30T18:15:43Z 2023-09-13 2024-04-30T18:12:26Z Article http://purl.org/eprint/type/JournalArticle 2047-7538 https://hdl.handle.net/1721.1/154315 Wijethilake, N., Anandakumar, M., Zheng, C. et al. DEEP-squared: deep learning powered De-scattering with Excitation Patterning. Light Sci Appl 12, 228 (2023). en 10.1038/s41377-023-01248-6 Light: Science & Applications Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Springer Science and Business Media LLC Springer Science and Business Media LLC |
| spellingShingle | Wijethilake, Navodini Anandakumar, Mithunjha Zheng, Cheng So, Peter T. C. Yildirim, Murat Wadduwage, Dushan N. DEEP-squared: deep learning powered De-scattering with Excitation Patterning |
| title | DEEP-squared: deep learning powered De-scattering with Excitation Patterning |
| title_full | DEEP-squared: deep learning powered De-scattering with Excitation Patterning |
| title_fullStr | DEEP-squared: deep learning powered De-scattering with Excitation Patterning |
| title_full_unstemmed | DEEP-squared: deep learning powered De-scattering with Excitation Patterning |
| title_short | DEEP-squared: deep learning powered De-scattering with Excitation Patterning |
| title_sort | deep squared deep learning powered de scattering with excitation patterning |
| url | https://hdl.handle.net/1721.1/154315 |
| work_keys_str_mv | AT wijethilakenavodini deepsquareddeeplearningpowereddescatteringwithexcitationpatterning AT anandakumarmithunjha deepsquareddeeplearningpowereddescatteringwithexcitationpatterning AT zhengcheng deepsquareddeeplearningpowereddescatteringwithexcitationpatterning AT sopetertc deepsquareddeeplearningpowereddescatteringwithexcitationpatterning AT yildirimmurat deepsquareddeeplearningpowereddescatteringwithexcitationpatterning AT wadduwagedushann deepsquareddeeplearningpowereddescatteringwithexcitationpatterning |