Outlier detection and removal improves accuracy of machine learning approach to multispectral burn diagnostic imaging

Journal of Biomedical Optics

Volumn 20, Issue 12, 2015, Pages

  Li, Weizhi ^a   Mo, Weirong ^a   Zhang, Xu ^a   Squiers, John J ^a,b   Lu, Yang ^a   Sellke, Eric W ^a   Fan, Wensheng ^a   Dimaio, J Michael ^a,b   Thatcher, Jeffrey E ^a  

^a Spectral MD Inc ^*  (United States)

^b BAYLOR RESEARCH INSTITUTE   (United States)

Author keywords

burn; machine learning; medical imaging; model accuracy; multispectral imaging; outlier detection

Indexed keywords

ALGORITHMS; ARTIFICIAL INTELLIGENCE; CLASSIFICATION (OF INFORMATION); DATA HANDLING; DIAGNOSIS; LEARNING SYSTEMS; MEDICAL IMAGING; STATISTICAL TESTS; STATISTICS; TISSUE;

10-FOLD CROSS-VALIDATION; BURN; CLASSIFICATION ACCURACY; CLASSIFICATION MODELS; MACHINE LEARNING APPROACHES; MODEL ACCURACY; MULTISPECTRAL IMAGING; OUTLIER DETECTION;

DATA MINING;

ALGORITHM; ANIMAL; ARTIFACT; AUTOMATED PATTERN RECOGNITION; BURN; COMPUTER ASSISTED DIAGNOSIS; EPILUMINESCENCE MICROSCOPY; FLUORESCENCE IMAGING; IMAGE ENHANCEMENT; IMAGE SUBTRACTION; INJURIES; MACHINE LEARNING; PATHOLOGY; PIG; PROCEDURES; REPRODUCIBILITY; SENSITIVITY AND SPECIFICITY; SKIN; SPECTROSCOPY;

ALGORITHMS; ANIMALS; ARTIFACTS; BURNS; DERMOSCOPY; IMAGE ENHANCEMENT; IMAGE INTERPRETATION, COMPUTER-ASSISTED; MACHINE LEARNING; OPTICAL IMAGING; PATTERN RECOGNITION, AUTOMATED; REPRODUCIBILITY OF RESULTS; SENSITIVITY AND SPECIFICITY; SKIN; SPECTRUM ANALYSIS; SUBTRACTION TECHNIQUE; SWINE;

EID: 84940421624     PISSN: 10833668     EISSN: 15602281     Source Type: Journal    
DOI: 10.1117/1.JBO.20.12.121305     Document Type: Article

References (22)

1. C. Fischer and L. Kakoulli, "Multispectral and hyperspectral imaging technologies in conservation: current research and potential applications," Stud. Conserv. 7, 3-16 (2006).
2. G. Lu and B. Fei, "Medical hyperspectral imaging: a review," J. Biomed. Opt. 19(1), 010901 (2014).
3. R. Lu and Y. Chen, "Hyperspectral imaging for safety inspection of food and agricultural products," Proc. SPIE 3544, 121-133 (1999).
4. F. Meer et al., "Multi- and hyperspectral geologic remote sensing: a review," Int. J. Appl. Earth Obs. Geoinf. 14(1), 112-128 (2012).
5. V. T. Valery, "Light-tissue interactions," in Biomedical Photonics Handbook, pp. 1-27, CRC Press, Boca Raton, Florida (2003).
6. R. Moza, J. M. Dimaio, and J. Melendez, "Deep-tissue dynamic monitoring of decubitus ulcers: wound care assessment," IEEE Eng. Med. Biol. Mag. 29, 71-77 (2010).
7. D. R. King et al., "Surgical wound debridement sequentially characterized in a porcine burn model with multispectral imaging," Burns (2015), Epub ahead of print.
8. A. Jaskille et al., "Critical review of burn depth assessment techniques: part II. Review of laser Doppler technology," J. Burn. Care Res. 31(1), 151-157 (2010).
9. S. L. Jacques, "Optical properties of biological tissues: a review," Phys. Med. Biol. 58(12), R37-R61 (2013).
10. W.-F. Cheong, S. A. Prahl, and A. J. Welch, "A review of the optical properties of biological tissues," IEEE J. Quant. Electron. 26(12) (2002).
11. C. Cortes and V. Vapnik, "Support-vectors networks," Mach. Learn. 20, 273-297 (1995).
12. H. Akbari et al., "Cancer detection using infrared hyperspectral imaging," Cancer Sci. 102(4), 852-857 (2011).
13. D. Yodovsky et al., "Assessing diabetic food ulcer development risk with hyperspectral tissue oximetry," J. Biomed. Opt. 16(2), 026009 (2011).
14. F. E. Grubbs, "Procedures for detection outlying observations in samples," Technometrics 11(1), 1-21 (1969).
15. D. Coursineau, "Outliers detection and treatment: a review," Int. J. Psychol. Res. 3(1), 58-67 (2010).
16. J. Aldrich, "R. A. Fisher and the making of maximum likelihood 1912- 1922," Stat. Sci. 12(3), 162-176 (1997).
17. J. Gauvain and C. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Process. 2(2), 291 (1994).
18. W. Mo et al., "The importance of illumination in a non-contact photoplethysmography imaging system for burn wound assessment," Proc. SPIE 9303, 93030M (2015).
19. R. Gurfinkel et al., "Histological assessment of tangentially excised burn eschars," Can. J. Plastic Surg. 18, e33-e36 (2010).
20. I. Guyon and A. Elisseeff, "An introduction to variable and feature selection," J. Mach. Learn. Res. 3, 1157-1182 (2003).
21. H. Peng, F. Long, and C. Ding, "Feature selection based on mutual information: criteria of max-dependency, max-relevance, and minredundancy," IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1226-1238 (2005).
22. J. J. Squiers et al., "Quantifying regional left ventricular contractile function: leave it to the machines?" J. Thorac. Cardiovasc. Surg. 150, 247-249 (2015).