Restricted accessResearch articleFirst published online 2020-01
Automated Machine Learning Diagnostic Support System as a Computational Biomarker for Detecting Drug-Induced Liver Injury Patterns in Whole Slide Liver Pathology Images
Drug-induced liver injury (DILI) is a challenging disease to diagnose, a leading cause of acute liver failure, and responsible for drug withdrawal from the market. There is no symptom, no biomarker or test for detection, no therapy, but discontinuation of the drug. Pharmaceutical companies spend huge money, time, and scientific research efforts to test DILI effects and drug efficacy. A preclinical diagnostic support system is designed and proposed for DILI detection and classification on liver biopsy histopathology images. Heterogeneity features and automated machine learning (AutoML) models were tested to classify DILI injury patterns on whole slide image. Fractal and lacunarity values were used to detect hepatocellular necrotic injury patterns caused on a rat liver (in vivo) by 10 drugs at four dose levels. Correlations between fractal and lacunarity values were statistically analyzed for the 10 drugs; the Pearson correlation (r = 0.9809), p-value (1.6612E-06), and R2 (0.9582) were found to be high in the case of carbon tetrachloride. The AutoML model was tested to understand the injury patterns on a subset of 1,277 histology images. The AutoML algorithm was able to classify necrotic injury patterns accurately with an average precision of 98.6% on a score threshold of 0.5.
Get full access to this article
View all access options for this article.
References
1.
NavarroVJ, SeniorJR: Drug-related hepatotoxicity. N Engl J Med, 2006; 354:731–739.
2.
HaqueT, SasatomiE, HayashiPH: Drug-induced liver injury: pattern recognition and future directions. Gut Liver, 2016; 10:27–36.
3.
LarsonAM, PolsonJ, FontanaRJ, et al.: Acetaminophen-induced acute liver failure: results of a United States multicenter, prospective study. Hepatology, 2005; 42:1364–1372.
4.
Food and Drug AdministrationU.S. Department of Health and Human Services: Guidance for industry drug-induced liver injury: premarketing clinical evaluation. Drug Saf, 2009:1–25.
5.
ChalasaniNP, HayashiPH, BonkovskyHL, NavarroVJ, LeeWM, FontanaRJ: ACG clinical guideline: the diagnosis and management of idiosyncratic drug-induced liver injury. Am J Gastroenterol, 2014; 109:950–966.
6.
KleinerDE: The pathology of drug-induced liver injury. Semin Liver Dis, 2009; 29:364–372.
7.
WatkinsPB, SeligmanPJ, PearsJS, AviganMI, SeniorJR: Using controlled clinical trials to learn more about acute drug-induced liver injury. Hepatology, 2008; 48:1680–1689.
8.
ApicaBS, LeeWM: Drug-induced liver injury. McManusLM, MitchellRN (eds.), pp. 1825–1837. In: Pathobiology of Human Disease: A Dynamic Encyclopedia of Disease Mechanisms. Elsevier Inc., San Diego, CA, 2014.
DananG, BenichouC: Causality assessment of adverse reactions to drugs-I. A novel method based on the conclusions of international consensus meetings: application to drug-induced liver injuries. J Clin Epidemiol, 1993; 46:1323–1330.
11.
MariaVAJ, VictorinoRMM: Development and validation of a clinical scale for the diagnosis of drug-induced hepatitis. Hepatology, 1997; 26:664–669.
LightDW, LexchinJR: Pharmaceutical research and development: what do we get for all that money?. BMJ, 2012; 345:e4348.
14.
KaitinKI: Deconstructing the drug development process: the new face of innovation. Clin Pharmacol Ther, 2010; 87:356–361.
15.
United States National Library of Medicine: LiverTox—Clinical and Research Information on Drug-Induced Liver Injury. United States National Library of Medicine, Bethesda, MD, 2016.
16.
KimJW, PhongsamranPV: Drug-induced liver disease and drug use considerations in liver disease. J Pharm Pract, 2009; 22:278–289.
17.
FontanaR: Acute Liver Failure Due to Drugs. Semin Liver Dis, 2008; 28:175–187.
18.
BuckleyD, FrisbyJP, FreemanJ: Lightness perception can be affected by surface curvature from stereopsis. Perception, 1994; 23:869–881.
19.
ZanoniM, Arcelli FontanaF, StellaF: On applying machine learning techniques for design pattern detection. J Syst Softw, 2015; 103:102–117.
20.
UrbanG, BacheKM, PhanD, et al.: Deep learning for drug discovery and cancer research: automated analysis of vascularization images. IEEE/ACM Trans Comput Biol Bioinforma, 2018 [Epub ahead of print]; DOI:10.1109/TCBB.2018.2841396.
21.
CruzJA, WishartDS: Applications of machine learning in cancer prediction and prognosis. Cancer Inform, 2006; 2:59–77.
22.
KourouK, ExarchosTP, ExarchosKP, KaramouzisMV, FotiadisDI: Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J, 2015; 13:8–17.
23.
EstevaA, KuprelB, NovoaRA, et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017; 542:115–118.
24.
LewisJH, KleinerDE: Hepatic injury due to drugs, herbal compounds, chemicals and toxins. In: MacSween's Pathology of the Liver, Burt AD, Portmann BC, Ferrell LD (eds.), pp. 645–760. Churchill Livingstone, San Diego, CA, 2012.
25.
IgarashiY, NakatsuN, YamashitaT, et al.: Open TG-GATEs: a large-scale toxicogenomics database. Nucleic Acids Res, 2015; 43(D1):D921–D927.
26.
MandelbrotB: How long is the coast of Britain? Statistical self-similarity and fractional dimension. Science (80-), 1967; 156:636–638.
27.
PlotnickRE, GardnerRH, O'NeillRV: Lacunarity indices as measures of landscape texture. Landsc Ecol, 1993; 8:201–211.
28.
GuoQ, ShaoJ, RuizVF: Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms. Int J Comput Assist Radiol Surg, 2009; 4:11–25.
TăluS, VlăduţiuC, LupaşcuCA: Characterization of human retinal vessel arborisation in normal and amblyopic eyes using multifractal analysis. Int J Ophthalmol, 2015; 8:996–1002.
31.
GeraetsWGM, Van der SteltPF: Fractal properties of bone. Dentomaxillofacial Radiol, 2000; 29:144–153.
32.
LennonFE, CianciGC, KantetiR, et al.: Unique fractal evaluation and therapeutic implications of mitochondrial morphology in malignant mesothelioma. Sci Rep, 2016; 6:24578.
33.
KarperienAL: FracLac for Image J. National Institute of Health, Bethesda, MD, 2013.
LoC-M, (Jack) LiY-C: Machine learning based cancer detection using various image modalities. Comput Methods Programs Biomed, 2018; 156:A1.
36.
SharmaH, ZerbeN, KlempertI, HellwichO, HufnaglP: Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology. Comput Med Imaging Graph, 2017; 61:2–13.
37.
CoudrayN, OcampoPS, SakellaropoulosT, et al.: Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med, 2018; 24:1559–1567.
38.
AinscoughBJ, BarnellEK, RonningP, et al.: A deep learning approach to automate refinement of somatic variant calling from cancer sequencing data. Nat Genet, 2018; 50:1735–1743.
39.
BychkovD, LinderN, TurkkiR, et al.: Deep learning based tissue analysis predicts outcome in colorectal cancer. Sci Rep, 2018; 8:3395.
40.
FlemingN: How artificial intelligence is changing drug discovery. Nature, 2018; 557:S55–S57.
41.
ChenH, EngkvistO, WangY, OlivecronaM, BlaschkeT: The rise of deep learning in drug discovery. Drug Discov Today, 2018; 23:1241–1250.
42.
LeeJG, JunS, ChoYW, et al.: Deep learning in medical imaging: general overview. Korean J Radiol, 2017; 18:570–584.
43.
XuY, DaiZ, ChenF, GaoS, PeiJ, LaiL: Deep learning for drug-induced liver injury. J Chem Inf Model, 2015; 55:2085–2093.
