• Je něco špatně v tomto záznamu ?

A novel deep learning-based method for automatic stereology of microglia cells from low magnification images

H. Morera, P. Dave, Y. Kolinko, S. Alahmari, A. Anderson, G. Denham, C. Davis, J. Riano, D. Goldgof, LO. Hall, GJ. Harry, PR. Mouton

. 2024 ; 102 (-) : 107336. [pub] 20240223

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc24014560

Microglial cells mediate diverse homeostatic, inflammatory, and immune processes during normal development and in response to cytotoxic challenges. During these functional activities, microglial cells undergo distinct numerical and morphological changes in different tissue volumes in both rodent and human brains. However, it remains unclear how these cytostructural changes in microglia correlate with region-specific neurochemical functions. To better understand these relationships, neuroscientists need accurate, reproducible, and efficient methods for quantifying microglial cell number and morphologies in histological sections. To address this deficit, we developed a novel deep learning (DL)-based classification, stereology approach that links the appearance of Iba1 immunostained microglial cells at low magnification (20×) with the total number of cells in the same brain region based on unbiased stereology counts as ground truth. Once DL models are trained, total microglial cell numbers in specific regions of interest can be estimated and treatment groups predicted in a high-throughput manner (<1 min) using only low-power images from test cases, without the need for time and labor-intensive stereology counts or morphology ratings in test cases. Results for this DL-based automatic stereology approach on two datasets (total 39 mouse brains) showed >90% accuracy, 100% percent repeatability (Test-Retest) and 60× greater efficiency than manual stereology (<1 min vs. ∼ 60 min) using the same tissue sections. Ongoing and future work includes use of this DL-based approach to establish clear neurodegeneration profiles in age-related human neurological diseases and related animal models.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc24014560
003      
CZ-PrNML
005      
20240905133817.0
007      
ta
008      
240725e20240223xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1016/j.ntt.2024.107336 $2 doi
035    __
$a (PubMed)38402997
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Morera, Hunter $u Department of Computer Science and Engineering, University of South Florida, Tampa, FL 33620, USA. Electronic address: hmorera@usf.edu
245    12
$a A novel deep learning-based method for automatic stereology of microglia cells from low magnification images / $c H. Morera, P. Dave, Y. Kolinko, S. Alahmari, A. Anderson, G. Denham, C. Davis, J. Riano, D. Goldgof, LO. Hall, GJ. Harry, PR. Mouton
520    9_
$a Microglial cells mediate diverse homeostatic, inflammatory, and immune processes during normal development and in response to cytotoxic challenges. During these functional activities, microglial cells undergo distinct numerical and morphological changes in different tissue volumes in both rodent and human brains. However, it remains unclear how these cytostructural changes in microglia correlate with region-specific neurochemical functions. To better understand these relationships, neuroscientists need accurate, reproducible, and efficient methods for quantifying microglial cell number and morphologies in histological sections. To address this deficit, we developed a novel deep learning (DL)-based classification, stereology approach that links the appearance of Iba1 immunostained microglial cells at low magnification (20×) with the total number of cells in the same brain region based on unbiased stereology counts as ground truth. Once DL models are trained, total microglial cell numbers in specific regions of interest can be estimated and treatment groups predicted in a high-throughput manner (<1 min) using only low-power images from test cases, without the need for time and labor-intensive stereology counts or morphology ratings in test cases. Results for this DL-based automatic stereology approach on two datasets (total 39 mouse brains) showed >90% accuracy, 100% percent repeatability (Test-Retest) and 60× greater efficiency than manual stereology (<1 min vs. ∼ 60 min) using the same tissue sections. Ongoing and future work includes use of this DL-based approach to establish clear neurodegeneration profiles in age-related human neurological diseases and related animal models.
650    _2
$a zvířata $7 D000818
650    _2
$a myši $7 D051379
650    _2
$a lidé $7 D006801
650    12
$a mikroglie $7 D017628
650    12
$a deep learning $7 D000077321
650    _2
$a mozek $x patologie $7 D001921
650    _2
$a počet buněk $x metody $7 D002452
655    _2
$a časopisecké články $7 D016428
700    1_
$a Dave, Palak $u Department of Computer Science and Engineering, University of South Florida, Tampa, FL 33620, USA
700    1_
$a Kolinko, Yaroslav $u Department of Histology and Embryology & Biomedical Center, Faculty of Medicine in Pilsen, Charles University, Pilsen, Czech Republic
700    1_
$a Alahmari, Saeed $u Department of Computer Science, Najran University, Najran 66462, Saudi Arabia
700    1_
$a Anderson, Aidan $u SRC Biosciences, Tampa, FL 33606, USA
700    1_
$a Denham, Grant $u SRC Biosciences, Tampa, FL 33606, USA
700    1_
$a Davis, Chloe $u SRC Biosciences, Tampa, FL 33606, USA
700    1_
$a Riano, Juan $u SRC Biosciences, Tampa, FL 33606, USA
700    1_
$a Goldgof, Dmitry $u Department of Computer Science and Engineering, University of South Florida, Tampa, FL 33620, USA
700    1_
$a Hall, Lawrence O $u Department of Computer Science and Engineering, University of South Florida, Tampa, FL 33620, USA
700    1_
$a Harry, G Jean $u Mechanistic Toxicology Branch, Division of Translational Toxicology, NIEHS/NIH, Research Triangle Park, NC 27709, USA
700    1_
$a Mouton, Peter R $u Department of Computer Science and Engineering, University of South Florida, Tampa, FL 33620, USA; SRC Biosciences, Tampa, FL 33606, USA. Electronic address: peter@disector.com
773    0_
$w MED00005596 $t Neurotoxicology and teratology $x 1872-9738 $g Roč. 102 (20240223), s. 107336
856    41
$u https://pubmed.ncbi.nlm.nih.gov/38402997 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20240725 $b ABA008
991    __
$a 20240905133811 $b ABA008
999    __
$a ok $b bmc $g 2143993 $s 1226426
BAS    __
$a 3
BAS    __
$a PreBMC-MEDLINE
BMC    __
$a 2024 $b 102 $c - $d 107336 $e 20240223 $i 1872-9738 $m Neurotoxicology and teratology $n Neurotoxicol Teratol $x MED00005596
LZP    __
$a Pubmed-20240725

Najít záznam

Citační ukazatele

Nahrávání dat ...

Možnosti archivace

Nahrávání dat ...