The Role of Geometry in Convolutional Neural Networks for Medical Imaging
Mayo Clinic Proceedings: Digital Health · 2023-12 · 1 (4) · 519-526
DOI: 10.1016/j.mcpdig.2023.08.006 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Mayo Clinic Proceedings: Digital Health, 2023-12. Verfasst von Yashbir Singh und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Mayo Clinic, Rochester, MN. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Department of Radiology, Weill Cornell Medicine, Mayo Clinic.
Abstract (Originalsprache)
Convolutional neural networks (CNNs) have played an important role in medical imaging-from diagnostics to research to data integration. This has allowed clinicians to plan operations, diagnose patients earlier, and study rare diseases in more detail. However, data quality, quantity, and imbalance all pose challenges for CNN training and accuracy; in addition, training costs can be high when many types of CNNs are needed in a health care system. Topology and geometry provide tools to ameliorate these challenges for CNNs when they are integrated into the CNN architecture, particularly in the data preprocessing steps or convolution layers. This paper reviews the current integration of geometric tools within CNN architectures to reduce the burden of large training datasets and offset computational costs. This paper also identifies fertile areas for future research into the integration of geometric tools with CNNs.
Autor:innen und Institutionen
- Department of Radiology, Mayo Clinic, Rochester, MN.
- Staticlysm LLC, Miami, FL.
- Department of Medical Education, West Virginia University, Morgantown, WV.
- Center for Individualized Medicine, Mayo Clinic, Rochester, MN.
- Department of Mathematics, Stanford University, Stanford, CA.
Förderung
- Department of Radiology, Weill Cornell Medicine
- Mayo Clinic
Zitieren
APA
Singh, Y., Farrelly, C., Hathaway, Q. A., Choudhary, A., Carlsson, G., Erickson, B., & Leiner, T. (2023). The Role of Geometry in Convolutional Neural Networks for Medical Imaging. Mayo Clinic Proceedings: Digital Health, 1(4), 519-526. https://doi.org/10.1016/j.mcpdig.2023.08.006
Vancouver
Singh Y, Farrelly C, Hathaway QA, Choudhary A, Carlsson G, Erickson B, et al. The Role of Geometry in Convolutional Neural Networks for Medical Imaging. Mayo Clinic Proceedings: Digital Health. 2023;1(4):519-526. doi:10.1016/j.mcpdig.2023.08.006
BibTeX
@article{Singh2023,
author = {Singh, Yashbir and Farrelly, Colleen and Hathaway, Quincy A and Choudhary, Ashok and Carlsson, Gunnar and Erickson, Bradley and Leiner, Tim},
title = {The Role of Geometry in Convolutional Neural Networks for Medical Imaging},
journal = {Mayo Clinic Proceedings: Digital Health},
year = {2023},
volume = {1},
number = {4},
pages = {519--526},
doi = {10.1016/j.mcpdig.2023.08.006}
}
EUVIMED