A survey of feature detection methods for localisation of plain sections of axial brain magnetic ...

@article{76842,
   author = {Martinů, Jiří and Novotný, Jan and Adámek, Karel and Čermák, Petr and Kozel, Jiri and Skoloudik, David},
   article_number = {April 2023},
   doi = {http://dx.doi.org/10.1016/j.bspc.2023.104611},
   keywords = {Image processing;Medical imaging;Magnetic resonance imaging;Computer visions;Feature detection},
   language = {eng},
   issn = {1746-8094},
   journal = {Biomedical Signal Processing and Control},
   title = {A survey of feature detection methods for localisation of plain sections of axial brain magnetic resonance imaging},
   url = {https://www.sciencedirect.com/science/article/pii/S1746809423000447?via%3Dihub},
   volume = {82},
   year = {2023}
}

TY  - JOUR
ID  - 76842
AU  - Martinů, Jiří - Novotný, Jan - Adámek, Karel - Čermák, Petr - Kozel, Jiri - Skoloudik, David
PY  - 2023
TI  - A survey of feature detection methods for localisation of plain sections of axial brain magnetic resonance imaging
JF  - Biomedical Signal Processing and Control
VL  - 82
IS  - April 2023
SP  - "104611-1"-"104611-15"
EP  - "104611-1"-"104611-15"
PB  - Elsevier
SN  - 17468094
KW  - Image processing;Medical imaging;Magnetic resonance imaging;Computer visions;Feature detection
UR  - https://www.sciencedirect.com/science/article/pii/S1746809423000447?via%3Dihub
N2  - Matching MRI brain images between patients or mapping patients' MRI slices to the simulated atlas of a brain is key to the automatic registration of MRI of a brain. The ability to match MRI images would also enable such applications as indexing and searching MRI images among multiple patients or selecting images from the region of interest. In this work, we have introduced robustness, accuracy and cumulative distance metrics and methodology that allows us to compare different techniques and approaches in matching brain MRI of different patients or matching MRI brain slice to a position in the brain atlas. To that end, we have used feature detection methods AGAST, AKAZE, BRISK, GFTT, HardNet, and ORB, which are established methods in image processing, and compared them on their resistance to image degradation and their ability to match the same brain MRI slice of different patients. We have demonstrated that some of these techniques can correctly match most of the brain MRI slices of different patients. When matching is performed with the atlas of the human brain, their performance is significantly lower. The best performing feature detection method was a combination of SIFT detector and HardNet descriptor that achieved 93% accuracy in matching images with other patients and only 52% accurately matched images when compared to atlas.
ER  - 

MARTINŮ, Jiří, Jan NOVOTNÝ, Karel ADÁMEK, Petr ČERMÁK, Jiri KOZEL a David SKOLOUDIK. A survey of feature detection methods for localisation of plain sections of axial brain magnetic resonance imaging. \textit{Biomedical Signal Processing and Control}. Elsevier, 2023, roč.~82, April 2023, s.~''104611-1''-''104611-15'', 15 s. ISSN~1746-8094. Dostupné z: https://dx.doi.org/10.1016/j.bspc.2023.104611.