Method-Induced Errors in Fractal Analysis of Lung Microscopic Images Segmented with the Use of HistAENN (Histogram-Based Autoencoder Neural Network)
Source abstract
Abstract
The designing of Computer-Aided Diagnosis (CADx) is necessary to improve patient condition analysis and reduce human error. HistAENN (Histogram-based Autoencoder Neural Network, the first hierarchy level) and the fractal-based estimator (the second hierarchy level) are assumed for segmentation and image analysis, respectively. The aim of the study is to investigate how to select or preselect algorithms at the second hierarchy level algorithm using small data sets and the semisupervised training principle. Method-induced errors are evaluated using the Monte Carlo test and an overlapping table is proposed for the rejection or tentative acceptance of particular segmentation and fractal analysis algorithms. This study uses lung histological slides and the results show that 2D box-counting substantially outweighs lacunarity for considered configurations. These findings also suggest that the proposed method is applicable for further designing of classification algorithms, which is essential for researchers, software developers, and forensic pathologist communities.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: AI in cancer detection · Digital Imaging for Blood Diseases · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Epidemiology and Management, Pomeranian Medical University, Zolnierska 48 St., 71210 Szczecin, Poland
Department of Signal Processing and Multimedia Engineering, West Pomeranian University of Technology Szczecin, 26. Kwietnia 10 St., 71126 Szczecin, Poland
Department of Forensic Medicine, Pomeranian Medical University, Powstancow Wielkopolskich 72 St., 70111 Szczecin, Poland
Funding
Narodowe Centrum Nauki
References (77)
Show source-provided references
1. Computer-Aided Diagnosis in Medical Imaging: Historical Review, Current Status and Future Potential10.1016/j.compmedimag.2007.02.002 ↗
2. Li, Q., and Nishikawa, R.M. (2015). Computer-Aided Detection and Diagnosis in Medical Imaging, CRC Press.10.1201/b18191 ↗
3. Automated Cervical Screening and Triage, Based on HPV Testing and Computer-Interpreted Cytology10.1093/jnci/djy044 ↗
4. Examination of peripheral blood films using automated microscopy; evaluation of Diffmaster Octavia and Cellavision DM9610.1136/jcp.2005.035402 ↗
5. Examination of peripheral blood smears: Performance evaluation of a digital microscope system using a large-scale leukocyte database10.1111/ijlh.12391 ↗
6. LeCun, Y., Kavukcuoglu, K., and Farabet, C. (June, January 30). Convolutional networks and applications in vision. Proceedings of the 2010 IEEE International Symposium on Circuits and Systems, Paris, France.10.1109/ISCAS.2010.5537907 ↗
7. Deep learning10.1038/nature14539 ↗
8. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning (Adaptive Computation and Machine Learning), MIT Press.
9. Fractal analysis of remotely sensed images: A review of methods and applications10.1080/01431160600676695 ↗
10. Metropolis, N. (1989). Monte Carlo Method. From Cardinals to Chaos: Reflection on the Life and Legacy of Stanislaw Ulam, CUP Archive.
11. Why the Monte Carlo method is so important today10.1002/wics.1314 ↗
12. Lee, D.H. (2013, January 16–21). Pseudo-Label: The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks. Proceedings of the ICML 2013 Workshop: Challenges in Representation Learning (WREPL), Atlanta, GA, USA.
13. Using clustering analysis to improve semi-supervised classification10.1016/j.neucom.2012.08.020 ↗
14. Pattern classification and clustering: A review of partially supervised learning approaches10.1016/j.patrec.2013.10.017 ↗
15. Feng, Z., Nie, D., Wang, L., and Shen, D. (2018, January 4–7). Semi-supervised learning for pelvic MR image segmentation based on multi-task residual fully convolutional networks. Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA.10.1109/ISBI.2018.8363713 ↗
16. Fractal and multifractal analysis: A review10.1016/j.media.2009.05.003 ↗
17. Xiao, X., Zhao, J., Qiang, Y., Wang, H., Xiao, Y., Zhang, X., and Zhang, Y. (2018). An Automated Segmentation Method for Lung Parenchyma Image Sequences Based on Fractal Geometry and Convex Hull Algorithm. Appl. Sci., 8.10.3390/app8050832 ↗
18. Uncertainty in Fractal Dimension Estimated from Power Spectra and Variogram10.1007/BF02768900 ↗
19. Kendall, A., Badrinarayanan, V., and Cipolla, R. (arXiv, 2015). Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding, arXiv.
20. Gal, Y. (2016). Uncertainty in Deep Learning. [Ph.D. Thesis, University of Cambridge].
21. Comparison of fractal dimension estimation algorithms for epileptic seizure onset detection10.1088/1741-2560/7/4/046007 ↗
22. Shi, C.T. (2018). Signal Pattern Recognition Based on Fractal Features and Machine Learning. Appl. Sci., 8.10.3390/app8081327 ↗
23. Li, J., Sun, C., and Du, Q. (2006, January 8–11). A New Box-Counting Method for Estimation of Image Fractal Dimension. Proceedings of the 2006 International Conference on Image Processing, Atlanta, GA, USA.10.1109/ICIP.2006.313005 ↗
24. Reproducibility of 2D and 3D Fractal Analysis Techniques for the Assessment of Spatial Heterogeneity of Regional Blood Flow in Rectal Cancer10.1148/radiol.12111316 ↗
25. Zio, E. (2013). Practical Applications of Monte Carlo Simulation for System Reliability Analysis. The Monte Carlo Simulation Method for System Reliability and Risk Analysis, Springer. Chapter: The Monte Carlo Simulation Method for System Reliability and Risk Analysis.10.1007/978-1-4471-4588-2 ↗
26. Article: Software Reliability Testing using Monte Carlo Methods
27. A Framework for the Development of Computerized Adaptive Tests
28. Kim, T.H., and Adeli, H. (2010). Markov Chain Monte Carlo Random Testing. Advances in Computer Science and Information Technology, Springer.10.1007/978-3-642-13577-4 ↗
29. Measures of Niche Overlap, I10.1093/imammb/3.2.99 ↗
30. Cornell, H. (2011). Encyclopedia of Theoretical Ecology, University of California Press. Chapter: Niche Overlap.
31. Fasel, B., and Gatica-Perez, D. (2006, January 20–24). Rotation-Invariant Neoperceptron. Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China.10.1109/ICPR.2006.1020 ↗
32. Rotation-invariant convolutional neural networks for galaxy morphology prediction10.1093/mnras/stv632 ↗
33. Cheng, G., Zhou, P., and Han, J. (2016, January 27–30). RIFD-CNN: Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.315 ↗
34. Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images10.1109/TGRS.2016.2601622 ↗
35. Marcos, D., Volpi, M., and Tuia, D. (2016, January 4–8). Learning rotation invariant convolutional filters for texture classification. Proceedings of the 23rd International Conference on Pattern Recognition, Cancun, Mexico.10.1109/ICPR.2016.7899932 ↗
36. TurboPixels: Fast Superpixels Using Geometric Flows10.1109/TPAMI.2009.96 ↗
37. Superpixels: An evaluation of the state-of-the-art10.1016/j.cviu.2017.03.007 ↗
38. Watershed Cuts: Thinnings, Shortest Path Forests, and Topological Watersheds10.1109/TPAMI.2009.71 ↗
39. River channel segmentation in polarimetric SAR images: Watershed transform combined with average contrast maximisation10.1016/j.eswa.2017.04.018 ↗
40. Ciecholewski, M. (2017). Malignant and Benign Mass Segmentation in Mammograms Using Active Contour Methods. Symmetry, 9.10.3390/sym9110277 ↗
41. Active contours driven by region-scalable fitting and optimized Laplacian of Gaussian energy for image segmentation10.1016/j.sigpro.2016.12.021 ↗
42. Histopathological Evaluation of Lung Autopsy: 100 Cases Study
43. Spectrum of histopathological lesions in lung autopsy10.5455/jrmds.2015323 ↗
44. Lung cancer—A fractal viewpoint10.1038/nrclinonc.2015.108 ↗
45. Spectrum of Histomorphological Changes in Lungs at Autopsy: A 5 Year Study10.21276/APALM.2017.961 ↗
46. Prevalence of Lung Lesions at Autopsy: A Histopathological Study
47. Correlations Between the Autolytic Changes and Postmortem Interval in Refrigerated Cadavers10.1515/rjim-2016-0012 ↗
48. OpenSlide: A Vendor-Neutral Software Foundation for Digital Pathology10.4103/2153-3539.119005 ↗
49. Martinez, K., and Cupitt, J. (2005, January 14). VIPS—A highly tuned image processing software architecture. Proceedings of the IEEE International Conference on Image Processing, Genova, Italy.10.1109/ICIP.2005.1530120 ↗
50. Baddeley, A., and Jensen, E.B.V. (2005). Stereology for Statisticians, Chapman & Hall/CRC.10.1201/9780203496817 ↗
51. Mei, S., Wang, Y., and Wen, G. (2018). Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Network Model. Sensors, 18.10.3390/s18041064 ↗
52. Liang, P., Shi, W., and Zhang, X. (2018). Remote Sensing Image Classification Based on Stacked Denoising Autoencoder. Remote Sens., 10.10.3390/rs10010016 ↗
53. MathWorks (2018). Image Processing Toolbox. User’s Guide, MathWorks.
54. Dlib-ml: A Machine Learning Toolkit
55. NVIDIA (2018). cuDNN Developer Guide, NVDIA.
56. Stroustrup, B. (2014). Programming: Principles and Practical Using C++, Addison-Wesley. [2nd ed.].
57. Mandelbrot, B. (1983). The Fractal Geometry of the Nature, W. H. Freeman and Company.10.1119/1.13295 ↗
58. Peitgen, H., Jürgens, H., and Saupe, D. (1991). Fractals for the Classrooms: Part One: Introduction to Fractals and Chaos, Springer-Verlag.10.1007/978-1-4757-4740-9_1 ↗
59. Peitgen, H., Jürgens, H., and Saupe, D. (1992). Fractals for the Classrooms: Part Two: Complex Systems and Mandelbrot, Springer-Verlag.10.1007/978-1-4612-4406-6 ↗
60. Lacunarity analysis: A general technique for the analysis of spatial patterns10.1103/PhysRevE.53.5461 ↗
61. Principles of geostatistics10.2113/gsecongeo.58.8.1246 ↗
62. Wackernagel, H. (2003). Multivariate Geostatistics. A Introduction with Applications, Springer.10.1007/978-3-662-05294-5 ↗
63. Computation of the Fractal Dimension of Topographic Surfaces using the Triangular Prism Surface Area Method10.1016/0098-3004(86)90047-6 ↗
64. Three New Implementations of the Triangular Prism Method for Computing the Fractal Dimension of Remote Sensing Images10.14358/PERS.72.4.373 ↗
65. Fractal character of fracture surfaces of metals10.1038/308721a0 ↗
66. From Slit–Island Method to Ising Model—Analysis of Grayscale Images10.2478/amcs-2014-0004 ↗
67. Harte, D. (2001). Multifractals. Theory and Applications, Chapman & Hall/CRC.10.1201/9781420036008 ↗
68. Seuront, L. (2010). Fractals and Multifractals in Ecology and Aquatic Science, CRC Press.10.1201/9781420004243 ↗
69. Kaye, B. (1994). A Random Walk Through Fractal Dimensions, Wiley-VCH.10.1002/9783527615995 ↗
70. A Stochastic Approximation Method10.1214/aoms/1177729586 ↗
71. Mei, S., Montanari, A., and Nguyen, P.M. (2018). A mean field view of the landscape of two-layer neural networks. Proc. Natl. Acad. Sci. USA, 1–7.10.1073/pnas.1806579115 ↗
72. El-Baz, A., Jilang, X., and Suri, J.S. (2016). Biomedical Image Segmentation: Advances and Trends, CRC Press.10.1201/9781315372273 ↗
73. Do we Need Hundreds of Classifiers to Solve Real World Classification Problems?
74. Chapella, O., Schölkopf, B., and Zien, A. (2006). Semi–Supervised Learning, MIT Press.10.7551/mitpress/9780262033589.001.0001 ↗
75. Albalate, A., and Minker, W. (2011). Semi–Supervised and Unsupervised Machine Learning, Wiley.
76. Gan, G., Ma, C., and Wu, J. (2007). Data Clustering. Theory, Algorithms, and Applications, SIAM.10.1137/1.9780898718348 ↗
77. Aggarwal, C.C., and Reddy, C.K. (2014). Data Clustering. Algorithms and Applications, Chapman & Hall/CRC.