Urinary Bladder Tumor Grade Diagnosis Using On-line Trained Neural Networks

This paper extends the line of research that considers the application of Artificial Neural Networks (ANNs) as an automated system, for the assignment of tumors grade. One hundred twenty nine cases were classified according to the WHO grading system by experienced pathologists in three classes: Grade I, Grade II and Grade III. 36 morphological and textural, cell nuclei features represented each case. These features were used as an input to the ANN classifier, which was trained using a novel stochastic training algorithm, namely, the Adaptive Stochastic On-Line method. The resulting automated classification system achieved classification accuracy of 90%, 94.9% and 97.3% for tumors of Grade I, II and III respectively.

[1]  Anil K. Jain,et al.  Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  W. Murphy,et al.  Transitional cell neoplasms of the urinary bladder. Can biologic potential be predicted from histologic grading? , 1987, Cancer.

[3]  George D. Magoulas,et al.  Tumor detection in colonoscopic images using hybrid methods for on-line neural network training , 2001 .

[4]  Richard S. Sutton,et al.  Adapting Bias by Gradient Descent: An Incremental Version of Delta-Bar-Delta , 1992, AAAI.

[5]  P. Wingo,et al.  Cancer statistics, 1997 , 1997, CA: a cancer journal for clinicians.

[6]  M. Boon,et al.  Analysis of the performance of pathologists in the grading of bladder tumors. , 1983, Human pathology.

[7]  Halbert White,et al.  Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings , 1990, Neural Networks.

[8]  M. N. Vrahatis,et al.  Adaptive stepsize algorithms for on-line training of neural networks , 2001 .

[9]  George D. Magoulas,et al.  Hybrid methods using evolutionary algorithms for on-line training , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[10]  Panagiota Spyridonos,et al.  Neural network-based segmentation and classification system for automated grading of histologic sections of bladder carcinoma. , 2002, Analytical and quantitative cytology and histology.

[11]  Nabil Belacel,et al.  Multicriteria fuzzy assignment method: a useful tool to assist medical diagnosis , 2001, Artif. Intell. Medicine.

[12]  M Petein,et al.  Computerized morphonuclear cell image analyses of malignant disease in bladder tissues. , 1990, The Journal of urology.

[13]  T Jarkrans,et al.  Grading of transitional cell bladder carcinoma by texture analysis of histological sections. , 1994, Analytical cellular pathology : the journal of the European Society for Analytical Cellular Pathology.

[14]  Richard S. Sutton,et al.  Online Learning with Random Representations , 1993, ICML.

[15]  Thibault Langlois,et al.  Parameter adaptation in stochastic optimization , 1999 .

[16]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[17]  Vassilis P. Plagianakos,et al.  Improved Neural Network-based Interpretation of Colonoscopy Images Through On-line Learning and Evolution , 2001 .

[18]  E Bengtsson,et al.  Grading of transitional cell bladder carcinoma by image analysis of histological sections. , 1995, Analytical cellular pathology : the journal of the European Society for Analytical Cellular Pathology.