CT-Based Prediction of Liver Function and Post-PVE Hypertrophy Using an Artificial Neural Network.
artificial neural network
computed tomography
liver function
liver volume
portal vein embolization
Journal
Journal of clinical medicine
ISSN: 2077-0383
Titre abrégé: J Clin Med
Pays: Switzerland
ID NLM: 101606588
Informations de publication
Date de publication:
12 Jul 2021
12 Jul 2021
Historique:
received:
01
06
2021
revised:
05
07
2021
accepted:
09
07
2021
entrez:
24
7
2021
pubmed:
25
7
2021
medline:
25
7
2021
Statut:
epublish
Résumé
This study aimed to evaluate whether hypertrophy after portal vein embolization (PVE) and maximum liver function capacity (LiMAx) are predictable by an artificial neural network (ANN) model based on computed tomography (CT) texture features. We report a retrospective analysis on 118 patients undergoing preoperative assessment by CT before and after PVE for subsequent extended liver resection due to a malignant tumor at RWTH Aachen University Hospital. The LiMAx test was carried out in a subgroup of 55 patients prior to PVE. Associations between CT texture features and hypertrophy as well as liver function were assessed by a multilayer perceptron ANN model. Liver volumetry showed a median hypertrophy degree of 33.9% (16.5-60.4%) after PVE. Non-response, defined as a hypertrophy grade lower than 25%, was found in 36.5% (43/118) of the cases. The ANN prediction of the hypertrophy response showed a sensitivity of 95.8%, specificity of 44.4% and overall prediction accuracy of 74.6% ( Our study shows that an ANN model based on CT texture features is able to predict the maximum liver function capacity and may be useful to assess potential hypertrophy after performing PVE.
Sections du résumé
BACKGROUND
BACKGROUND
This study aimed to evaluate whether hypertrophy after portal vein embolization (PVE) and maximum liver function capacity (LiMAx) are predictable by an artificial neural network (ANN) model based on computed tomography (CT) texture features.
METHODS
METHODS
We report a retrospective analysis on 118 patients undergoing preoperative assessment by CT before and after PVE for subsequent extended liver resection due to a malignant tumor at RWTH Aachen University Hospital. The LiMAx test was carried out in a subgroup of 55 patients prior to PVE. Associations between CT texture features and hypertrophy as well as liver function were assessed by a multilayer perceptron ANN model.
RESULTS
RESULTS
Liver volumetry showed a median hypertrophy degree of 33.9% (16.5-60.4%) after PVE. Non-response, defined as a hypertrophy grade lower than 25%, was found in 36.5% (43/118) of the cases. The ANN prediction of the hypertrophy response showed a sensitivity of 95.8%, specificity of 44.4% and overall prediction accuracy of 74.6% (
CONCLUSION
CONCLUSIONS
Our study shows that an ANN model based on CT texture features is able to predict the maximum liver function capacity and may be useful to assess potential hypertrophy after performing PVE.
Identifiants
pubmed: 34300246
pii: jcm10143079
doi: 10.3390/jcm10143079
pmc: PMC8306993
pii:
doi:
Types de publication
Journal Article
Langues
eng
Références
Eur Radiol. 2014 May;24(5):1013-9
pubmed: 24531844
J Am Coll Surg. 2013 Jul;217(1):126-33; discussion 133-4
pubmed: 23632095
Radiology. 2018 Aug;288(2):407-415
pubmed: 29688159
J Thorac Imaging. 2020 May;35 Suppl 1:S58-S65
pubmed: 32195886
Sci Rep. 2020 Jul 23;10(1):12268
pubmed: 32703988
Ann Surg. 2000 Dec;232(6):777-85
pubmed: 11088072
Int J Surg. 2018 Apr;52:74-81
pubmed: 29425829
Dig Dis Sci. 2014 Dec;59(12):2983-91
pubmed: 24993690
World J Surg Oncol. 2020 Jun 24;18(1):140
pubmed: 32580729
Cancer Res. 2017 Nov 1;77(21):e104-e107
pubmed: 29092951
Cardiovasc Intervent Radiol. 2020 Jun;43(6):875-881
pubmed: 31974746
Radiology. 2011 Sep;260(3):727-33
pubmed: 21712472
Obes Surg. 2015 Nov;25(11):2047-53
pubmed: 25869925
Neuroimage. 2006 Jul 1;31(3):1116-28
pubmed: 16545965
Eur J Surg Oncol. 2013 Nov;39(11):1230-5
pubmed: 23994139
World J Hepatol. 2015 Aug 18;7(17):2069-79
pubmed: 26301049
J Gastrointest Surg. 2014 Jan;18(1):45-51
pubmed: 24129824
Eur Radiol Exp. 2020 Apr 6;4(1):20
pubmed: 32249336
Sci Rep. 2014 Jul 08;4:5621
pubmed: 25001391
J Gastrointest Surg. 2021 Feb;25(2):405-410
pubmed: 31997073
Invest Radiol. 2015 Apr;50(4):290-6
pubmed: 25493416
Eur Radiol. 2019 Nov;29(11):5861-5872
pubmed: 30899977
Ann Med Surg (Lond). 2017 Dec 07;25:6-11
pubmed: 29326811
Langenbecks Arch Surg. 2012 Dec;397(8):1297-304
pubmed: 22729717
J Magn Reson Imaging. 2015 Feb;41(2):322-8
pubmed: 24347292
Transpl Int. 2010 Oct;23(10):1023-32
pubmed: 20444241
Ann Surg. 2009 Jul;250(1):119-25
pubmed: 19561474