PMID- 33996226
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20210518
IS  - 2156-7085 (Print)
IS  - 2156-7085 (Electronic)
IS  - 2156-7085 (Linking)
VI  - 12
IP  - 4
DP  - 2021 Apr 1
TI  - Auto-detection of cervical collagen and elastin in Mueller matrix polarimetry 
      microscopic images using K-NN and semantic segmentation classification.
PG  - 2236-2249
LID - 10.1364/BOE.420079 [doi]
AB  - We propose an approach for discriminating fibrillar collagen fibers from elastic 
      fibers in the mouse cervix in Mueller matrix microscopy using convolutional 
      neural networks (CNN) and K-nearest neighbor (K-NN) for classification. Second 
      harmonic generation (SHG), two-photon excitation fluorescence (TPEF), and Mueller 
      matrix polarimetry images of the mice cervix were collected with a 
      self-validating Mueller matrix micro-mesoscope (SAMMM) system. The components and 
      decompositions of each Mueller matrix were arranged as individual channels of 
      information, forming one 3-D voxel per cervical slice. The classification 
      algorithms analyzed each voxel and determined the amount of collagen and elastin, 
      pixel by pixel, on each slice. SHG and TPEF were used as ground truths. To assess 
      the accuracy of the results, mean-square error (MSE), peak signal-to-noise ratio 
      (PSNR), and structural similarity (SSIM) were used. Although the training and 
      testing is limited to 11 and 5 cervical slices, respectively, MSE accuracy was 
      above 85%, SNR was greater than 40 dB, and SSIM was larger than 90%.
CI  - (c) 2021 Optical Society of America under the terms of the OSA Open Access 
      Publishing Agreement.
FAU - Roa, Camilo
AU  - Roa C
AD  - Department of Biological Sciences, College of Arts, Sciences and Education, 
      Florida International University, 11200 SW 8th Street, Miami, FL 33199, USA.
AD  - These authors contributed equally.
FAU - Du Le, V N
AU  - Du Le VN
AUID- ORCID: 0000-0002-4054-4200
AD  - Department of Biomedical Engineering, College of Engineering and Computing, 
      Florida International University, 10555 West Flagler Street, Miami, FL 33174, 
      USA.
AD  - These authors contributed equally.
AD  - vidule@fiu.edu.
FAU - Mahendroo, Mala
AU  - Mahendroo M
AD  - Department of Obstetrics and Gynecology, University of Texas Southwestern Medical 
      Center, Dallas, Texas 75390, USA.
FAU - Saytashev, Ilyas
AU  - Saytashev I
AUID- ORCID: 0000-0003-4213-1175
AD  - Department of Ophthalmology, Herbert Wertheim College of Medicine, Florida 
      International University, 11200 SW 8 Street, Miami, FL 33199, USA.
FAU - Ramella-Roman, Jessica C
AU  - Ramella-Roman JC
AD  - Department of Biomedical Engineering, College of Engineering and Computing, 
      Florida International University, 10555 West Flagler Street, Miami, FL 33174, 
      USA.
AD  - Department of Ophthalmology, Herbert Wertheim College of Medicine, Florida 
      International University, 11200 SW 8 Street, Miami, FL 33199, USA.
AD  - jramella@fiu.edu.
LA  - eng
PT  - Journal Article
DEP - 20210323
PL  - United States
TA  - Biomed Opt Express
JT  - Biomedical optics express
JID - 101540630
PMC - PMC8086465
COIS- The authors declare no conflicts of interest.
EDAT- 2021/05/18 06:00
MHDA- 2021/05/18 06:01
PMCR- 2021/04/01
CRDT- 2021/05/17 06:12
PHST- 2021/01/19 00:00 [received]
PHST- 2021/03/10 00:00 [revised]
PHST- 2021/03/17 00:00 [accepted]
PHST- 2021/05/17 06:12 [entrez]
PHST- 2021/05/18 06:00 [pubmed]
PHST- 2021/05/18 06:01 [medline]
PHST- 2021/04/01 00:00 [pmc-release]
AID - 420079 [pii]
AID - 10.1364/BOE.420079 [doi]
PST - epublish
SO  - Biomed Opt Express. 2021 Mar 23;12(4):2236-2249. doi: 10.1364/BOE.420079. 
      eCollection 2021 Apr 1.