Ercal F, Chawla A, Stoecker W V, Lee H C, Moss R H
Department of Computer Science, University of Missouri-Rolla 65401.
IEEE Trans Biomed Eng. 1994 Sep;41(9):837-45. doi: 10.1109/10.312091.
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 five years [1]. 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 [2]. In this paper, we present a novel neural network approach for the automated separation of melanoma from three benign categories of tumors which exhibit melanoma-like characteristics. Our 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, we are able to obtain above 80% correct classification of the malignant and benign tumors on real skin tumor images.
恶性黑色素瘤是所有皮肤癌中最致命的一种。1991年，美国约有32000例新的恶性黑色素瘤病例被诊断出来，预计约80%的患者能存活五年[1]。幸运的是，如果能早期发现，即使是恶性黑色素瘤也可能得到成功治疗。因此，近年来，人们对皮肤癌，尤其是恶性黑色素瘤的自动检测和诊断的兴趣日益浓厚[2]。在本文中，我们提出了一种新颖的神经网络方法，用于从表现出类似黑色素瘤特征的三类良性肿瘤中自动分离出黑色素瘤。我们的方法使用基于肿瘤形状和相对肿瘤颜色的判别特征，将这些特征提供给人工神经网络，以将肿瘤图像分类为恶性或良性。通过这种方法，对于合理平衡的训练/测试集，我们能够在真实皮肤肿瘤图像上获得80%以上的恶性和良性肿瘤正确分类率。
