NEURON CELL CLASSIFICATION USING MACHINE LEARNING ALGORITHMS: METHODOLOGICAL CONSIDERATIONS

Slade Matthews, Ian Spence

References

  1. [1] Jelinek HF, Maddalena DJ, Spence I. Application ofartificial neural networks to cat retinal ganglion cellcategorization. Proc 5th Australian Conference on NeuralNetworks. Brisbane 1994:177-80.
  2. [2] Jelinek HF, Cesar J, R.M., Leandro JJG, Spence I.Automated morphometric analysis of the cat retinalalpha/Y, beta/X and delta ganglion cells using waveletstatistical moment and clustering algorithms. Journal ofIntegrative Neuroscience, 3(4),2004, 415-32.
  3. [3] Karperien A, Jelinek HF, Milosevic NT, Cracow, Poland.Reviewing lacunarity analysis and classification ofmicroglia in neuroscience. European Congress ofMathematics and Theoretical Biology. Cracow, Poland2011.
  4. [4] Karperien A, Jelinek HF, Milosevic NT. Multifractals: aReview with an Application in Neuroscience.Proceedings of the 18th International Conference onControl Systems and Computer Science: InterdisciplinaryApproaches to Fractal Analysis, (IAFA 2011). Bucharest,Romania 2011.
  5. [5] Cornforth D, Jelinek HF, Peichl L. Fractop: a tool forautomated biological image classification. 6th AIAustralasia-Japan Joint Workshop, Australian NationalUniversity, Canberra.; 2002, 141-8.
  6. [6] Cesar-Jr. RM, da F. Costa L. Shape characterization innatural scales by using the multiscale bending energy.Proc 13th ICPR - International Conference on PatternRecognition Technical University of Vienna, Austria:IEEE Press 1996:735-9.
  7. [7] Costa LdF, Cesar, Jr. R.M., Coelho, R.C. and Tanaka, J.S.Analysis and synthesis of morphologically realistic neuralnetworks. In: R.R. Poznanski, ed. Modeling in theneurosciences: Harwood academic:505-28.
  8. [8] Yang G, Masland RH. Receptive fields and dendriticstructure of directionally selective retinal ganglion cells. JNeurosci, 14(9),1994, 5267-80.
  9. [9] Kolb H, Nelson R, Mariani A. Amarcrine cells, Bipolarcells and ganglion cells of the cat retina: a Golgi study.Vision Res, 21,1981, 1081-114.
  10. [10] Boycott BB, Wassle H. The morphological types ofganglion cells of the domestic cat's retina. Journal ofPhysiology, 240(2),1974, 397-419.
  11. [11] Sun W, Li N, He S. Large-scale morphological survey ofmouse retinal ganglion cells. Journal of ComparativeNeurology, 451,2002, 115-26.4.2 AUC versus accuracy4603
  12. [12] Peichl L. Alpha and delta ganglion cells in the rat retina. Jof Comp Neurol, 286,1989, 120-39.
  13. [13] Tauchi M, Morigiwa K, Fukuda Y. Morphologicalcomparisons between outer and inner ramifying alpha cellsof the albino rat retina. Experimental Brain Research,88,1992, 67-77.
  14. [14] Huxlin KR, Goodchild AK. Retinal ganglion cells in thealbino rat: revised morphological classification. Journal ofComparative Neurology, 385(2),1997, 309-23.
  15. [15] Perry VH. The ganglion cell layer of the retina of the rat: aGolgi study. Proceedings of the Royal Society of London -Series B: Biological Sciences, 204(1156),1979, 363-75.
  16. [16] Fernández E, Eldred WD, Ammermuller J, Block A, VonBloh W, Kolb H. Complexity and scaling properties ofamacrine, ganglion, horizontal, and bipoloar cells in theturtle retina. J of Comp Neurol, 347,1994, 397-408.
  17. [17] Baxt WG. Analysis of the clinical variables drivingdecision in an artificial neural network trained to identifythe presence of myocardial infarction [see comments]. AnnEmerg Med, 21(12),1992, 1439-44.
  18. [18] Dreiseitl S, Ohno-Machado L, Vinterbo S. Evaluatingvariable selection methods for diagnosis of myocardialinfarction. Proc AMIA Symp,1999, 246-50.
  19. [19] Tu JV. Advantages and disadvantages of using artificialneural networks versus logistic regression for predictingmedical outcomes [see comments]. J Clin Epidemiol,49(11),1996, 1225-31.
  20. [20] Baxt W. Application of artificial neural networks toclinical medicine. Lancet, 346,1995, 1135-38.
  21. [21] Burke HB. Artificial neural networks for cancer research:outcome prediction. Semin Surg Oncol, 10(1),1994, 73-9.
  22. [22] Zernikow B, Holtmannspotter K, Michel E, Hornschuh F,Groote K, Hennecke KH. Predicting length-of-stay inpreterm neonates. Eur J Pediatr, 158(1),1999, 59-62.
  23. [23] Duh MS, Walker AM, Pagano M, Kronlund K. Predictionand cross-validation of neural networks versus logisticregression: using hepatic disorders as an example. Am JEpidemiol, 147(4),1998, 407-13.
  24. [24] Matthews S, Jelinek HF, Spence I. Classification of RatRetinal Ganglion cells using logistic regression and neuralnetworks. College of Health Sciences ResearchConference (From Cell to Society 3). Leura, NSW 2002.
  25. [25] Smith TG, Lange GD, Marks WB. Fractal methods andresults in cellular morphology - dimensions, lacunarity andmultifractals. Journal of Neuroscience Methods, 69,1996,123-36.
  26. [26] Milošević NT, Ristanović D, Jelinek HF, Rajković K.Quantitative analysis of dendritic morphology of the alphaand delta retinal ganglion cells in the rat: a cellclassification study. J Theor Biol, 259,2009, 142-50.
  27. [27] Carter RM, Yan Y. Measurement of particle shape usingdigital imaging techniques. Journal of Physics:Conference Series, 15,2005, 177-82.
  28. [28] Pohlman S, Powell KA, Obuchowski NA, Chilcote WA,Grundfest-Broniatowski S. Quantitative classification ofbreast tumors in digitized mammograms. Medical Physics,23(8),1996, 1337-45.
  29. [29] Witten H, Frank E, Data Mining: Practical MachineLearning Tools and Techniques with JavaImplementations. (Sydney: Morgan Kaufmann 1989).
  30. [30] Jelinek HF, Depardieu C, Lucas C, Cornforth D, HuangW, Cree MJ. Towards vessel characterisation in thevicinity of the optic disk in digital retinal images. Imageand Vision Computing New Zealand 2005, Otago; 2005,351-7.
  31. [31] Cardiovascular bedside arrhythmia monitoring quickguide. 2002 [cited; Available from:http://www.clinicalwindow.net
  32. [32] Brown JE. Dendritic fields of retinal ganglion cells of therat. Journal of Neurophysiology, 28,1965, 1091-100.
  33. [33] Peichl L, Wassle H. Morphological identification of on-and off-center brisk transient (Y) cells in the cat retina.Procedings of the Royal Society London Series B,212,1981, 139-56.
  34. [34] Fukuda Y. A Three-Group Classification of Rat RetinalGanglion Cells: Histological and Physiological Studies.Brain Research, 119,1977, 327-44.
  35. [35] Bruno OM, Cesar RM, Jr., Consularo LA, Da FontouraCosta L. Automatic feature selection for biological shapeclassification in Σynergos. In: L. da Fontoura Costa,Ciimara G., editors. SIBGRAPI’98 InternationalSymposium on Computer Graphics, Image Processing,and Vision, IMPA, Rio de Janeiro, Brazil: The Institute ofElectrical 9nd Electronics Engineers, Inc.; 1998, 363-70.
  36. [36] Tourassi GD, Floyd CE. The effect of data sampling onthe performance evaluation of artificial neural networks.Medical Decision Making, 17,1997, 186-92.
  37. [37] Provost F. Machine Learning from Imbalanced Data Sets.In: N. Japkowicz, editor. Learning from Imbalanced DataSets: Papers from the AAAI Workshop, Austin, Texas:American Association for Artificial Intelligence, MelanoPark, California; 2000, 94-100.
  38. [38] Weiss SM, Kulikowski CA, Computer systems that learn :classification and prediction methods from statistics,neural nets, machine learning, and expert systems. (SanMateo, Calif.: M. Kaufmann Publishers 1991).

Important Links:

Go Back