Deep learning-based localization algorithms on fluorescence human brain 3D reconstruction: a comparative study using stereology as a reference

Year: 2024

Authors: Checcucci C., Wicinski B., Mazzamuto G., Scardigli M., Ramazzotti J., Brady N., Pavone FS., Hof PR., Costantini I., Frasconi P.

Autors Affiliation: Univ Florence, Dept Informat Engn, ,FI, I-50100 Florence, FI, Italy; Icahn Sch Med Mt Sinai, Friedman Brain Inst, Nash Family Dept Neurosci, New York, NY 10029 USA; European Lab Nonlinear Spect LENS, I-50019 Sesto Fiorentino, FI, Italy; CNR, Natl Inst Opt CNR INO, I-50019 Sesto Fiorentino, FI, Italy; Univ Florence, Dept Expt & Clin Med, I-50100 Florence, FI, Italy; Univ Florence, Dept Phys & Astron, I-50019 Sesto Fiorentino, FI, Italy; Univ Florence, Dept Biol, I-50019 Sesto Fiorentino, FI, Italy.

Abstract: 3D reconstruction of human brain volumes at high resolution is now possible thanks to advancements in tissue clearing methods and fluorescence microscopy techniques. Analyzing the massive data produced with these approaches requires automatic methods able to perform fast and accurate cell counting and localization. Recent advances in deep learning have enabled the development of various tools for cell segmentation. However, accurate quantification of neurons in the human brain presents specific challenges, such as high pixel intensity variability, autofluorescence, non-specific fluorescence and very large size of data. In this paper, we provide a thorough empirical evaluation of three techniques based on deep learning (StarDist, CellPose and BCFind-v2, an updated version of BCFind) using a recently introduced three-dimensional stereological design as a reference for large-scale insights. As a representative problem in human brain analysis, we focus on a 4 -cm(3) portion of the Broca’s area. We aim at helping users in selecting appropriate techniques depending on their research objectives. To this end, we compare methods along various dimensions of analysis, including correctness of the predicted density and localization, computational efficiency, and human annotation effort. Our results suggest that deep learning approaches are very effective, have a high throughput providing each cell 3D location, and obtain results comparable to the estimates of the adopted stereological design.

Journal/Review: SCIENTIFIC REPORTS

Volume: 14 (1)      Pages from: 14629-1  to: 14629-14

More Information: This project received funding fro m the European Union’s Horizon 2020 research and innovation Framework Programme under grant agreement No. 654148 (Laserlab-Europe), from the European Union’s Horizon 2020 Framework Programme for Research and Innovation under the Specific Grant Agreement No. 945539 (Human Brain Project SGA3), from the General Hospital Corporation Center of the National Institutes of Health under award number U01 MH117023, from the Italian Ministry for Education in the framework of Euro-Bioimaging Italian Node (ESFRI research infrastructure), and BRAIN CONNECTS (award number U01 NS132181). Finally, this research was carried out with the contribution from Fondazione CR Firenze. The content of this work is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
KeyWords: Cell detection; Deep-learning; Human brain; Broca´s area; 3D reconstruction; Fluorescence microscopy; Stereology
DOI: 10.1038/s41598-024-65092-3

Connecting to view paper tab on IsiWeb: Click here