Neural network diagnosis of malignant melanoma from color images

Malignant melanoma is the deadliest form of all skin cancers. Approximately 32,000 new cases of malignant melanoma were diagnosed in 1991 in the United States, with approximately 80% of patients expected to survive 5 years. Fortunately, if detected early, even malignant melanoma may be treated successfully, Thus, in recent years, there has been rising interest in the automated detection and diagnosis of skin cancer, particularly malignant melanoma. Here, the authors present a novel neural network approach for the automated separation of melanoma from 3 benign categories of tumors which exhibit melanoma-like characteristics. The approach uses discriminant features, based on tumor shape and relative tumor color, that are supplied to an artificial neural network for classification of tumor images as malignant or benign. With this approach, for reasonably balanced training/testing sets, the authors are able to obtain above 80% correct classification of the malignant and benign tumors on real skin tumor images.<<ETX>>

[1]  A. Kopf,et al.  Early detection of malignant melanoma: The role of physician examination and self‐examination of the skin , 1985, CA: a cancer journal for clinicians.

[2]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[3]  Richard Lippmann,et al.  Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[4]  James A. Pittman,et al.  Recognizing Hand-Printed Letters and Digits , 1989, NIPS.

[5]  R. Lippmann.  Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[6]  A. Chiabrera,et al.  A neural network approach for bone fracture healing assessment , 1990, IEEE Engineering in Medicine and Biology Magazine.

[7]  W.V. Stoecker,et al.  Boundary detection in skin tumor images: An overall approach and a radial search algorithm , 1990, Pattern Recognit..

[8]  Scott E. Umbaugh.  Computer vision in medicine: color metrics and image segmentation methods for skin cancer diagnosis , 1990 .

[9]  Mehmet Celenk,et al.  A color clustering technique for image segmentation , 1990, Comput. Vis. Graph. Image Process..

[10]  A. Kopf,et al.  Malignant melanoma in the 1990s: The continued importance of earlydetection and the role of physician examination and self‐examination of theskin , 1991, CA: a cancer journal for clinicians.

[11]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[12]  Riccardo Poli,et al.  A neural network expert system for diagnosing and treating hypertension , 1991, Computer.

[13]  W V Stoecker,et al.  Texture in skin images: comparison of three methods to determine smoothness. , 1992, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[14]  R. H. Moss,et al.  Digital imaging in dermatology. , 1992, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[15]  W V Stoecker,et al.  Automatic detection of asymmetry in skin tumors. , 1992, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[16]  P. Wilding,et al.  Application of neural networks to the interpretation of laboratory data in cancer diagnosis. , 1992, Clinical chemistry.

[17]  Fikret Ercal,et al.  Boundary detection and color segmentation in skin tumor images , 1993, Electronic Imaging.