PMID- 30001401
OWN - NLM
STAT- MEDLINE
DCOM- 20190108
LR  - 20190108
IS  - 1932-6203 (Electronic)
IS  - 1932-6203 (Linking)
VI  - 13
IP  - 7
DP  - 2018
TI  - Brain haemorrhage detection using a SVM classifier with electrical impedance
      tomography measurement frames.
PG  - e0200469
LID - 10.1371/journal.pone.0200469 [doi]
AB  - Brain haemorrhages often require urgent treatment with a consequent need for
      quick and accurate diagnosis. Therefore, in this study, we investigate Support
      Vector Machine (SVM) classifiers for detecting brain haemorrhages using
      Electrical Impedance Tomography (EIT) measurement frames. A 2-layer model of the 
      head, along with a series of haemorrhages, is designed as both numerical models
      and physical phantoms. EIT measurement frames, taken from an electrode array
      placed on the head surface, are used to train and test linear SVM classifiers.
      Various scenarios are implemented on both platforms to examine the impact of
      variables such as noise level, lesion location, lesion size, variation in
      electrode positioning, and variation in anatomy, on the classifier performance.
      The classifier performed well in numerical models (sensitivity and specificity of
      90%+) with signal-to-noise ratios of 60 dB+, was independent of lesion location, 
      and could detect lesions reliably down to the tested minimum volume of 5 ml.
      Slight variations in electrode layout did not affect performance. Performance was
      affected by variations in anatomy however, emphasising the need for large
      training sets covering different anatomies. The phantom models proved more
      challenging, with maximal sensitivity and specificity of 75% when used with the
      linear SVM. Finally, the performance of two more complex classifiers is briefly
      examined and compared to the linear SVM classifier. These results demonstrate
      that a radial basis function (RBF) SVM classifier and a neural network classifier
      can improve detection accuracy. Classifiers applied to EIT measurement frames is 
      a novel approach for lesion detection and may offer an effective diagnostic tool 
      clinically. A challenge is to translate the strong results from numerical models 
      into real world phantoms and ultimately human patients, as well as the selection 
      and development of optimal classifiers for this application.
FAU - McDermott, Barry
AU  - McDermott B
AUID- ORCID: 0000-0002-4593-5331
AD  - Translational Medical Device Lab, National University of Ireland Galway, Galway, 
      Ireland.
FAU - O'Halloran, Martin
AU  - O'Halloran M
AD  - Translational Medical Device Lab, National University of Ireland Galway, Galway, 
      Ireland.
FAU - Porter, Emily
AU  - Porter E
AUID- ORCID: 0000-0002-7787-3139
AD  - Translational Medical Device Lab, National University of Ireland Galway, Galway, 
      Ireland.
FAU - Santorelli, Adam
AU  - Santorelli A
AD  - Translational Medical Device Lab, National University of Ireland Galway, Galway, 
      Ireland.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20180712
PL  - United States
TA  - PLoS One
JT  - PloS one
JID - 101285081
SB  - IM
MH  - *Electric Impedance
MH  - Humans
MH  - *Intracranial Hemorrhages/diagnostic imaging/physiopathology
MH  - *Models, Cardiovascular
MH  - *Phantoms, Imaging
MH  - *Tomography
PMC - PMC6042738
COIS- The authors have declared that no competing interests exist.
EDAT- 2018/07/13 06:00
MHDA- 2019/01/09 06:00
CRDT- 2018/07/13 06:00
PHST- 2018/02/12 00:00 [received]
PHST- 2018/06/27 00:00 [accepted]
PHST- 2018/07/13 06:00 [entrez]
PHST- 2018/07/13 06:00 [pubmed]
PHST- 2019/01/09 06:00 [medline]
AID - 10.1371/journal.pone.0200469 [doi]
AID - PONE-D-18-04744 [pii]
PST - epublish
SO  - PLoS One. 2018 Jul 12;13(7):e0200469. doi: 10.1371/journal.pone.0200469.
      eCollection 2018.