1
|
Aghigh A, Jargot G, Zaouter C, Preston SEJ, Mohammadi MS, Ibrahim H, Del Rincón SV, Patten K, Légaré F. A comparative study of CARE 2D and N2V 2D for tissue-specific denoising in second harmonic generation imaging. J Biophotonics 2024:e202300565. [PMID: 38566461 DOI: 10.1002/jbio.202300565] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/27/2023] [Revised: 03/11/2024] [Accepted: 03/17/2024] [Indexed: 04/04/2024]
Abstract
This study explored the application of deep learning in second harmonic generation (SHG) microscopy, a rapidly growing area. This study focuses on the impact of glycerol concentration on image noise in SHG microscopy and compares two image restoration techniques: Noise-to-Void 2D (N2V 2D, no reference image restoration) and content-aware image restoration (CARE 2D, full reference image restoration). We demonstrated that N2V 2D effectively restored the images affected by high glycerol concentrations. To reduce sample exposure and damage, this study further addresses low-power SHG imaging by reducing the laser power by 70% using deep learning techniques. CARE 2D excels in preserving detailed structures, whereas N2V 2D maintains natural muscle structure. This study highlights the strengths and limitations of these models in specific SHG microscopy applications, offering valuable insights and potential advancements in the field .
Collapse
Affiliation(s)
- Arash Aghigh
- Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada
| | - Gaëtan Jargot
- Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada
| | - Charlotte Zaouter
- Armand-Frappier Santé Biotechnologie Research Centre, Laval, Québec, Canada
| | - Samuel E J Preston
- Department of Experimental Medicine, Faculty of Medicine, McGill University, Montréal, Québec, Canada
- Gerald Bronfman Department of Oncology, Segal Cancer Centre, Lady Davis Institute and Jewish General Hospital, McGill University, Montréal, Québec, Canada
| | - Melika Saadat Mohammadi
- Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada
| | - Heide Ibrahim
- Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada
| | - Sonia V Del Rincón
- Department of Experimental Medicine, Faculty of Medicine, McGill University, Montréal, Québec, Canada
- Gerald Bronfman Department of Oncology, Segal Cancer Centre, Lady Davis Institute and Jewish General Hospital, McGill University, Montréal, Québec, Canada
| | - Kessen Patten
- Armand-Frappier Santé Biotechnologie Research Centre, Laval, Québec, Canada
| | - François Légaré
- Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada
| |
Collapse
|
2
|
Aghigh A, Preston SEJ, Jargot G, Ibrahim H, Del Rincón SV, Légaré F. Nonlinear microscopy and deep learning classification for mammary gland microenvironment studies. Biomed Opt Express 2023; 14:2181-2195. [PMID: 37206132 PMCID: PMC10191635 DOI: 10.1364/boe.487087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 03/26/2023] [Accepted: 03/29/2023] [Indexed: 05/21/2023]
Abstract
Tumors, their microenvironment, and the mechanisms by which collagen morphology changes throughout cancer progression have recently been a topic of interest. Second harmonic generation (SHG) and polarization second harmonic (P-SHG) microscopy are label-free, hallmark methods that can highlight this alteration in the extracellular matrix (ECM). This article uses automated sample scanning SHG and P-SHG microscopy to investigate ECM deposition associated with tumors residing in the mammary gland. We show two different analysis approaches using the acquired images to distinguish collagen fibrillar orientation changes in the ECM. Lastly, we apply a supervised deep-learning model to classify naïve and tumor-bearing mammary gland SHG images. We benchmark the trained model using transfer learning with the well-known MobileNetV2 architecture. By fine-tuning the different parameters of these models, we show a trained deep-learning model that suits such a small dataset with 73% accuracy.
Collapse
Affiliation(s)
- Arash Aghigh
- Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada
| | - Samuel E. J. Preston
- Department of Experimental Medicine, Faculty of Medicine, McGill University, Montréal, Québec, Canada
- Gerald Bronfman Department of Oncology, Segal Cancer Centre, Lady Davis Institute and Jewish General Hospital, McGill University, Montreal, Quebec, Canada
| | - Gaëtan Jargot
- Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada
| | - Heide Ibrahim
- Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada
| | - Sonia V Del Rincón
- Department of Experimental Medicine, Faculty of Medicine, McGill University, Montréal, Québec, Canada
- Gerald Bronfman Department of Oncology, Segal Cancer Centre, Lady Davis Institute and Jewish General Hospital, McGill University, Montreal, Quebec, Canada
| | - François Légaré
- Centre Énergie Matériaux Télécommunications, Institut National de la Recherche Scientifique, Varennes, Québec, Canada
| |
Collapse
|
3
|
Aghigh A, Bancelin S, Rivard M, Pinsard M, Ibrahim H, Légaré F. Second harmonic generation microscopy: a powerful tool for bio-imaging. Biophys Rev 2023; 15:43-70. [PMID: 36909955 PMCID: PMC9995455 DOI: 10.1007/s12551-022-01041-6] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2022] [Accepted: 12/21/2022] [Indexed: 01/20/2023] Open
Abstract
Second harmonic generation (SHG) microscopy is an important optical imaging technique in a variety of applications. This article describes the history and physical principles of SHG microscopy and its more advanced variants, as well as their strengths and weaknesses in biomedical applications. It also provides an overview of SHG and advanced SHG imaging in neuroscience and microtubule imaging and how these methods can aid in understanding microtubule formation, structuration, and involvement in neuronal function. Finally, we offer a perspective on the future of these methods and how technological advancements can help make SHG microscopy a more widely adopted imaging technique.
Collapse
Affiliation(s)
- Arash Aghigh
- Centre Énergie Matériaux Télécommunications, Institut National de La Recherche Scientifique, Varennes, QC Canada
| | | | - Maxime Rivard
- National Research Council Canada, Boucherville, QC Canada
| | - Maxime Pinsard
- Institut National de Recherche en Sciences Et Technologies Pour L’environnement Et L’agriculture, Paris, France
| | - Heide Ibrahim
- Centre Énergie Matériaux Télécommunications, Institut National de La Recherche Scientifique, Varennes, QC Canada
| | - François Légaré
- Centre Énergie Matériaux Télécommunications, Institut National de La Recherche Scientifique, Varennes, QC Canada
| |
Collapse
|