Detail
Article
Online article
FT
Medvik - BMC
  • Something wrong with this record ?

Evaluating nnU-Net for early ischemic change segmentation on non-contrast computed tomography in patients with Acute Ischemic Stroke

H. El-Hariri, LA. Souto Maior Neto, P. Cimflova, F. Bala, R. Golan, A. Sojoudi, C. Duszynski, I. Elebute, SH. Mousavi, W. Qiu, BK. Menon

. 2022 ; 141 (-) : 105033. [pub] 20211113

Language English Country United States

Document type Journal Article, Research Support, Non-U.S. Gov't

Persistent link   https://www.medvik.cz/link/bmc22011117

Grant support
CIHR - Canada

Identifying the presence and extent of early ischemic changes (EIC) on Non-Contrast Computed Tomography (NCCT) is key to diagnosing and making time-sensitive treatment decisions in patients that present with Acute Ischemic Stroke (AIS). Segmenting EIC on NCCT is however a challenging task. In this study, we investigated a 3D CNN based on nnU-Net, a self-adapting CNN technique that has become the state-of-the-art in medical image segmentation, for segmenting EIC in NCCT of AIS patients. We trained and tested this model on a sizeable and heterogenous dataset of 534 patients, split into 438 for training and validation and 96 for testing. On this test set, we additionally assessed the inter-rater performance by comparing the proposed approach against two reference segmentation annotations by expert neuroradiologist readers, using this as the benchmark against which to compare our model. In terms of spatial agreement, we report median Dice Similarity Coefficients (DSCs) of 39.8% for the model vs. Reader-1, 39.4% for the model vs. Reader-2, and 55.6% for Reader-2 vs. Reader-1. In terms of lesion volume agreement, we report Intraclass Correlation Coefficients (ICCs) of 83.4% for model vs. Reader-1, 80.4% for model vs. Reader-2, and 94.8% for Reader-2 vs. Reader-1. Based on these results, we conclude that our model performs well relative to expert human performance and therefore may be useful as a decision-aid for clinicians.

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22011117
003      
CZ-PrNML
005      
20220506125842.0
007      
ta
008      
220425s2022 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1016/j.compbiomed.2021.105033 $2 doi
035    __
$a (PubMed)34802712
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a El-Hariri, Houssam $u Circle Neurovascular Imaging Inc, Calgary, AB, Canada. Electronic address: houssam.elhariri@circlenvi.com
245    10
$a Evaluating nnU-Net for early ischemic change segmentation on non-contrast computed tomography in patients with Acute Ischemic Stroke / $c H. El-Hariri, LA. Souto Maior Neto, P. Cimflova, F. Bala, R. Golan, A. Sojoudi, C. Duszynski, I. Elebute, SH. Mousavi, W. Qiu, BK. Menon
520    9_
$a Identifying the presence and extent of early ischemic changes (EIC) on Non-Contrast Computed Tomography (NCCT) is key to diagnosing and making time-sensitive treatment decisions in patients that present with Acute Ischemic Stroke (AIS). Segmenting EIC on NCCT is however a challenging task. In this study, we investigated a 3D CNN based on nnU-Net, a self-adapting CNN technique that has become the state-of-the-art in medical image segmentation, for segmenting EIC in NCCT of AIS patients. We trained and tested this model on a sizeable and heterogenous dataset of 534 patients, split into 438 for training and validation and 96 for testing. On this test set, we additionally assessed the inter-rater performance by comparing the proposed approach against two reference segmentation annotations by expert neuroradiologist readers, using this as the benchmark against which to compare our model. In terms of spatial agreement, we report median Dice Similarity Coefficients (DSCs) of 39.8% for the model vs. Reader-1, 39.4% for the model vs. Reader-2, and 55.6% for Reader-2 vs. Reader-1. In terms of lesion volume agreement, we report Intraclass Correlation Coefficients (ICCs) of 83.4% for model vs. Reader-1, 80.4% for model vs. Reader-2, and 94.8% for Reader-2 vs. Reader-1. Based on these results, we conclude that our model performs well relative to expert human performance and therefore may be useful as a decision-aid for clinicians.
650    _2
$a lidé $7 D006801
650    _2
$a počítačové zpracování obrazu $x metody $7 D007091
650    12
$a ischemická cévní mozková příhoda $x diagnostické zobrazování $7 D000083242
650    12
$a cévní mozková příhoda $x diagnostické zobrazování $7 D020521
650    _2
$a počítačová rentgenová tomografie $7 D014057
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Souto Maior Neto, Luis A $u Circle Neurovascular Imaging Inc, Calgary, AB, Canada. Electronic address: luis.maior@circlenvi.com
700    1_
$a Cimflova, Petra $u Department of Clinical Neurosciences, Foothills Medical Center, University of Calgary, Calgary, AB, Canada; Department of Medical Imaging, St. Anne's University Hospital Brno and Faculty of Medicine, Masaryk University, Brno, Czech Republic; Faculty of Medicine and University Hospital, Hradec Kralove, Czech Republic; Department of Radiology, Cumming School of Medicine, University of Calgary, Canada
700    1_
$a Bala, Fouzi $u Department of Clinical Neurosciences, Foothills Medical Center, University of Calgary, Calgary, AB, Canada
700    1_
$a Golan, Rotem $u Circle Neurovascular Imaging Inc, Calgary, AB, Canada
700    1_
$a Sojoudi, Alireza $u Circle Neurovascular Imaging Inc, Calgary, AB, Canada
700    1_
$a Duszynski, Chris $u Circle Neurovascular Imaging Inc, Calgary, AB, Canada
700    1_
$a Elebute, Ibukun $u Circle Neurovascular Imaging Inc, Calgary, AB, Canada
700    1_
$a Mousavi, Seyed Hossein $u Circle Neurovascular Imaging Inc, Calgary, AB, Canada
700    1_
$a Qiu, Wu $u Department of Clinical Neurosciences, Foothills Medical Center, University of Calgary, Calgary, AB, Canada
700    1_
$a Menon, Bijoy K $u Department of Clinical Neurosciences, Foothills Medical Center, University of Calgary, Calgary, AB, Canada; Department of Radiology, Cumming School of Medicine, University of Calgary, Canada; Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Canada; Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Canada
773    0_
$w MED00001218 $t Computers in biology and medicine $x 1879-0534 $g Roč. 141, č. - (2022), s. 105033
856    41
$u https://pubmed.ncbi.nlm.nih.gov/34802712 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20220425 $b ABA008
991    __
$a 20220506125834 $b ABA008
999    __
$a ok $b bmc $g 1788952 $s 1162315
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2022 $b 141 $c - $d 105033 $e 20211113 $i 1879-0534 $m Computers in biology and medicine $n Comput Biol Med $x MED00001218
GRA    __
$p CIHR $2 Canada
LZP    __
$a Pubmed-20220425

Find record

Citation metrics

Archiving options