1
|
Wang T, Dremel J, Richter S, Polanski W, Uckermann O, Eyüpoglu I, Czarske JW, Kuschmierz R. Resolution-enhanced multi-core fiber imaging learned on a digital twin for cancer diagnosis. NEUROPHOTONICS 2024; 11:S11505. [PMID: 38298866 PMCID: PMC10828892 DOI: 10.1117/1.nph.11.s1.s11505] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/20/2023] [Revised: 01/04/2024] [Accepted: 01/08/2024] [Indexed: 02/02/2024]
Abstract
Significance Deep learning enables label-free all-optical biopsies and automated tissue classification. Endoscopic systems provide intraoperative diagnostics to deep tissue and speed up treatment without harmful tissue removal. However, conventional multi-core fiber (MCF) endoscopes suffer from low resolution and artifacts, which hinder tumor diagnostics. Aim We introduce a method to enable unpixelated, high-resolution tumor imaging through a given MCF with a diameter of around 0.65 mm and arbitrary core arrangement and inhomogeneous transmissivity. Approach Image reconstruction is based on deep learning and the digital twin concept of the single-reference-based simulation with inhomogeneous optical properties of MCF and transfer learning on a small experimental dataset of biological tissue. The reference provided physical information about the MCF during the training processes. Results For the simulated data, hallucination caused by the MCF inhomogeneity was eliminated, and the averaged peak signal-to-noise ratio and structural similarity were increased from 11.2 dB and 0.20 to 23.4 dB and 0.74, respectively. By transfer learning, the metrics of independent test images experimentally acquired on glioblastoma tissue ex vivo can reach up to 31.6 dB and 0.97 with 14 fps computing speed. Conclusions With the proposed approach, a single reference image was required in the pre-training stage and laborious acquisition of training data was bypassed. Validation on glioblastoma cryosections with transfer learning on only 50 image pairs showed the capability for high-resolution deep tissue retrieval and high clinical feasibility.
Collapse
Affiliation(s)
- Tijue Wang
- TU Dresden, Laboratory of Measurement and Sensor System Technique, Dresden, Germany
- TU Dresden, Competence Center BIOLAS, Dresden, Germany
- TU Dresden, Else Kröner Fresenius Center for Digital Health, Germany
| | - Jakob Dremel
- TU Dresden, Laboratory of Measurement and Sensor System Technique, Dresden, Germany
- TU Dresden, Competence Center BIOLAS, Dresden, Germany
- TU Dresden, Else Kröner Fresenius Center for Digital Health, Germany
| | - Sven Richter
- TU Dresden, Else Kröner Fresenius Center for Digital Health, Germany
- University Hospital Carl Gustav Carus, TU Dresden, Department of Neurosurgery, Dresden, Germany
| | - Witold Polanski
- TU Dresden, Else Kröner Fresenius Center for Digital Health, Germany
- University Hospital Carl Gustav Carus, TU Dresden, Department of Neurosurgery, Dresden, Germany
| | - Ortrud Uckermann
- TU Dresden, Else Kröner Fresenius Center for Digital Health, Germany
- University Hospital Carl Gustav Carus, TU Dresden, Department of Neurosurgery, Dresden, Germany
- University Hospital Carl Gustav Carus, TU Dresden, Division of Medical Biology, Department of Psychiatry, Faculty of Medicine, Dresden, Germany
| | - Ilker Eyüpoglu
- TU Dresden, Else Kröner Fresenius Center for Digital Health, Germany
- University Hospital Carl Gustav Carus, TU Dresden, Department of Neurosurgery, Dresden, Germany
| | - Jürgen W. Czarske
- TU Dresden, Laboratory of Measurement and Sensor System Technique, Dresden, Germany
- TU Dresden, Competence Center BIOLAS, Dresden, Germany
- TU Dresden, Else Kröner Fresenius Center for Digital Health, Germany
- TU Dresden, Excellence Cluster Physics of Life, Dresden, Germany
- TU Dresden, School of Science, Faculty of Physics, Dresden, Germany
| | - Robert Kuschmierz
- TU Dresden, Laboratory of Measurement and Sensor System Technique, Dresden, Germany
- TU Dresden, Competence Center BIOLAS, Dresden, Germany
- TU Dresden, Else Kröner Fresenius Center for Digital Health, Germany
| |
Collapse
|
2
|
Choi YK, Feng L, Jeong WK, Kim J. Connecto-informatics at the mesoscale: current advances in image processing and analysis for mapping the brain connectivity. Brain Inform 2024; 11:15. [PMID: 38833195 DOI: 10.1186/s40708-024-00228-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2024] [Accepted: 05/08/2024] [Indexed: 06/06/2024] Open
Abstract
Mapping neural connections within the brain has been a fundamental goal in neuroscience to understand better its functions and changes that follow aging and diseases. Developments in imaging technology, such as microscopy and labeling tools, have allowed researchers to visualize this connectivity through high-resolution brain-wide imaging. With this, image processing and analysis have become more crucial. However, despite the wealth of neural images generated, access to an integrated image processing and analysis pipeline to process these data is challenging due to scattered information on available tools and methods. To map the neural connections, registration to atlases and feature extraction through segmentation and signal detection are necessary. In this review, our goal is to provide an updated overview of recent advances in these image-processing methods, with a particular focus on fluorescent images of the mouse brain. Our goal is to outline a pathway toward an integrated image-processing pipeline tailored for connecto-informatics. An integrated workflow of these image processing will facilitate researchers' approach to mapping brain connectivity to better understand complex brain networks and their underlying brain functions. By highlighting the image-processing tools available for fluroscent imaging of the mouse brain, this review will contribute to a deeper grasp of connecto-informatics, paving the way for better comprehension of brain connectivity and its implications.
Collapse
Affiliation(s)
- Yoon Kyoung Choi
- Brain Science Institute, Korea Institute of Science and Technology (KIST), Seoul, South Korea
- Department of Computer Science and Engineering, Korea University, Seoul, South Korea
| | | | - Won-Ki Jeong
- Department of Computer Science and Engineering, Korea University, Seoul, South Korea
| | - Jinhyun Kim
- Brain Science Institute, Korea Institute of Science and Technology (KIST), Seoul, South Korea.
- Department of Computer Science and Engineering, Korea University, Seoul, South Korea.
- KIST-SKKU Brain Research Center, SKKU Institute for Convergence, Sungkyunkwan University, Suwon, South Korea.
| |
Collapse
|
3
|
Tian L, Intes X, Yang W. Special Section Guest Editorial: Computational Approaches for Neuroimaging. NEUROPHOTONICS 2022; 9:041401. [PMID: 36062025 PMCID: PMC9438161 DOI: 10.1117/1.nph.9.4.041401] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
This guest editorial provides an introduction to the Special Section on Computational Approaches for Neuroimaging.
Collapse
Affiliation(s)
- Lei Tian
- Boston University, Department of Electrical and Computer Engineering, Boston, Massachusetts, United States
- Boston University, Department of Biomedical Engineering, Boston, Massachusetts, United States
| | - Xavier Intes
- Rensselaer Polytechnic Institute, Department of Biomedical Engineering, Troy, New York, United States
| | - Weijian Yang
- University of California, Davis (UC Davis), Department of Electrical and Computer Engineering, Davis, California, United States
| |
Collapse
|