Rapid automated diagnosis of primary hepatic tumour by mass spectrometry and artificial intelligence.
artificial intelligence
liver cancer
liver surgery
liver tumours
mass spectrometry
resection margins
Journal
Liver international : official journal of the International Association for the Study of the Liver
ISSN: 1478-3231
Titre abrégé: Liver Int
Pays: United States
ID NLM: 101160857
Informations de publication
Date de publication:
12 2020
12 2020
Historique:
received:
14
02
2020
revised:
17
06
2020
accepted:
09
07
2020
pubmed:
15
7
2020
medline:
22
6
2021
entrez:
15
7
2020
Statut:
ppublish
Résumé
Complete surgical resection with negative margin is one of the pillars in treatment of liver tumours. However, current techniques for intra-operative assessment of tumour resection margins are time-consuming and empirical. Mass spectrometry (MS) combined with artificial intelligence (AI) is useful for classifying tissues and provides valuable prognostic information. The aim of this study was to develop a MS-based system for rapid and objective liver cancer identification and classification. A large dataset derived from 222 patients with hepatocellular carcinoma (HCC, 117 tumours and 105 non-tumours) and 96 patients with mass-forming cholangiocarcinoma (MFCCC, 50 tumours and 46 non-tumours) were analysed by Probe Electrospray Ionization (PESI) MS. AI by means of support vector machine (SVM) and random forest (RF) algorithms was employed. For each classifier, sensitivity, specificity and accuracy were calculated. The overall diagnostic accuracy exceeded 94% in both the AI algorithms. For identification of HCC vs non-tumour tissue, RF was the best, with 98.2% accuracy, 97.4% sensitivity and 99% specificity. For MFCCC vs non-tumour tissue, both algorithms gave 99.0% accuracy, 98% sensitivity and 100% specificity. The herein reported MS-based system, combined with AI, permits liver cancer identification with high accuracy. Its bench-top size, minimal sample preparation and short working time are the main advantages. From diagnostics to therapeutics, it has the potential to influence the decision-making process in real-time with the ultimate aim of improving cancer patient cure.
Sections du résumé
BACKGROUND AND AIMS
Complete surgical resection with negative margin is one of the pillars in treatment of liver tumours. However, current techniques for intra-operative assessment of tumour resection margins are time-consuming and empirical. Mass spectrometry (MS) combined with artificial intelligence (AI) is useful for classifying tissues and provides valuable prognostic information. The aim of this study was to develop a MS-based system for rapid and objective liver cancer identification and classification.
METHODS
A large dataset derived from 222 patients with hepatocellular carcinoma (HCC, 117 tumours and 105 non-tumours) and 96 patients with mass-forming cholangiocarcinoma (MFCCC, 50 tumours and 46 non-tumours) were analysed by Probe Electrospray Ionization (PESI) MS. AI by means of support vector machine (SVM) and random forest (RF) algorithms was employed. For each classifier, sensitivity, specificity and accuracy were calculated.
RESULTS
The overall diagnostic accuracy exceeded 94% in both the AI algorithms. For identification of HCC vs non-tumour tissue, RF was the best, with 98.2% accuracy, 97.4% sensitivity and 99% specificity. For MFCCC vs non-tumour tissue, both algorithms gave 99.0% accuracy, 98% sensitivity and 100% specificity.
CONCLUSIONS
The herein reported MS-based system, combined with AI, permits liver cancer identification with high accuracy. Its bench-top size, minimal sample preparation and short working time are the main advantages. From diagnostics to therapeutics, it has the potential to influence the decision-making process in real-time with the ultimate aim of improving cancer patient cure.
Identifiants
pubmed: 32662575
doi: 10.1111/liv.14604
pmc: PMC7754124
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
3117-3124Informations de copyright
© 2020 The Authors. Liver International published by John Wiley & Sons Ltd.
Références
Am J Med. 2019 Jul;132(7):795-801
pubmed: 30710543
Liver Int. 2020 Dec;40(12):3117-3124
pubmed: 32662575
Angew Chem Int Ed Engl. 2009;48(44):8240-2
pubmed: 19746375
Appl Spectrosc. 2010 Nov;64(11):1251-8
pubmed: 21073794
Lancet. 2018 Mar 31;391(10127):1301-1314
pubmed: 29307467
J Am Soc Mass Spectrom. 2012 Oct;23(10):1741-9
pubmed: 22847392
Proc Natl Acad Sci U S A. 2017 Jun 27;114(26):6700-6705
pubmed: 28607048
Sci Rep. 2016 Dec 21;6:39284
pubmed: 28000726
World J Gastroenterol. 2014 Nov 21;20(43):15955-64
pubmed: 25473149
Sci Transl Med. 2013 Jul 17;5(194):194ra93
pubmed: 23863833
Mass Spectrom Rev. 2016 May-Jun;35(3):361-438
pubmed: 25252132
Best Pract Res Clin Gastroenterol. 2014 Oct;28(5):753-70
pubmed: 25260306
Breast Cancer Res. 2017 May 23;19(1):59
pubmed: 28535818
Chem Rev. 2013 Apr 10;113(4):2269-308
pubmed: 23301684
PLoS Med. 2016 Aug 30;13(8):e1002108
pubmed: 27575375
Surg Endosc. 2017 Mar;31(3):1361-1370
pubmed: 27501728
Methods Mol Biol. 2009;492:453-60
pubmed: 19241051
Anal Biochem. 2013 Oct 1;441(1):32-7
pubmed: 23851340
Anal Bioanal Chem. 2020 Apr;412(10):2191-2209
pubmed: 31820027
Biochem J. 1966 Dec;101(3):792-810
pubmed: 16742460
J Mass Spectrom. 2013 Nov;48(11):1178-87
pubmed: 24259206
J Hepatol. 2017 Aug;67(2):302-309
pubmed: 28336466
J Chromatogr A. 2010 Jun 18;1217(25):3946-54
pubmed: 20223463
Clin Chem. 2019 May;65(5):674-683
pubmed: 30770374
Int J Cancer. 2019 Apr 15;144(8):1941-1953
pubmed: 30350310
Trends Biotechnol. 2011 Mar;29(3):136-43
pubmed: 21292337
Science. 2004 Oct 15;306(5695):471-3
pubmed: 15486296
Nat Rev Gastroenterol Hepatol. 2011 Apr;8(4):189-200
pubmed: 21460876
Updates Surg. 2019 Mar;71(1):57-66
pubmed: 30852806
Proc Natl Acad Sci U S A. 2014 Jul 29;111(30):11121-6
pubmed: 24982150
Lancet Oncol. 2009 Jan;10(1):35-43
pubmed: 19058754
Br Med J. 1957 May 25;1(5029):1205-11
pubmed: 13426585
PLoS One. 2016 Sep 22;11(9):e0163180
pubmed: 27658243
Sci Transl Med. 2017 Sep 6;9(406):
pubmed: 28878011