A NON INVASIVE DERMATOLOGICAL LESION CLASSIFIER

非侵入性皮肤病病变分类器

• 批准号: 6143548
• 负责人: Eric R. Craine
• 金额: $ 36.31万
• 依托单位: WESTERN RESEARCH COMPANY, INC.
• 依托单位国家: 美国
• 财政年份: 1998
• 资助国家: 美国
• 起止时间: 1998-11-01 至 2002-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/6143548
• 关键词: artificial intelligence; biomedical automation; biomedical equipment development; clinical research; computer assisted diagnosis; diagnosis design /evaluation; fluorescence spectrometry; histology; human subject; neoplasm /cancer classification /staging; neoplasm /cancer diagnosis; noninvasive diagnosis; reflection spectrometry; skin neoplasms; spectrometry

Skin cancer is the fastest growing cancer. Approximately 34,100 Americans developed cutaneous melanoma in 1995; of the survivors, many must contend with the ongoing trauma of disfigurement and fear. Skin biopsies are now the most frequently performed medical procedure. It is axiomatic among dermatologists that early detection and diagnosis are critical. Great strides have been made in early detection of suspect skin lesions; however failure to biopsy the right lesion has severe consequences. The dilemma is exacerbated since 50- 80 percent of biopsies prove unnecessary, contributing to an enormous waste of health care dollars, patient trauma and negative patient behavior feedback. The Phase I work in dermatological spectroscopy and artificial neural net technology suggest that an automated clinical diagnostic aid which produces a quantitative rather than qualitative diagnostic assessment of skin lesions is possible. This project proposes development and testing of such a product. During Phase II a large number of spectroscopic samples of melanoma and nevi will be used to complete development of an artificial neural net classifier. Such a classifier system will lead to a commercial product to discriminate "normal," pre-cancerous and cancerous skin lesions. PROPOSED COMMERCIAL APPLICATION: The proposed project will lead to a non-invasive, in-office, real-time test to provide an automated, repeatable diagnostic probability of the nature of skin lesions prior to biopsy. Skin biopsies are now the most frequently performed reimbursed Medicare procedure, and as many as 50-80% are found not to be necessary after the fact. The low cost of this test, and rapid amortization of the system, coupled with the enormous health care cost savings possible in conjunction with a significant and widely recognized health problem, suggest that this product could have great commercial potential.

皮肤癌是增长最快的癌症。约 34,100 美国人于 1995 年患上皮肤黑色素瘤；在幸存者中，许多人必须 应对持续的毁容和恐惧创伤。皮肤活检是 现在是最常进行的医疗程序。这是不言自明的 皮肤科医生认为早期发现和诊断至关重要。大踏步前进 已早期发现可疑皮肤病变；然而未能 活检对病变部位有严重后果。困境进一步加剧 因为 50-80% 的活检被证明是不必要的，从而导致了巨大的 医疗费用的浪费、患者的创伤和患者的消极行为 反馈。第一阶段的工作是皮肤科光谱学和人工神经网络 网络技术表明，一种自动化的临床诊断辅助工具可以产生 对皮肤病变进行定量而非定性的诊断评估 可能的。该项目建议开发和测试此类产品。 在第二阶段，大量黑色素瘤和痣的光谱样本 将用于完成人工神经网络分类器的开发。 这样的分类器系统会导致商业产品出现歧视 “正常”、癌前和癌性皮肤病变。 拟议的商业应用： 拟议的项目将进行非侵入性、办公室内实时测试，以提供 在活检前自动、可重复地诊断皮肤病变性质的概率。 皮肤活检现在是最常进行的医疗保险报销程序， 多达50-80%事后发现没有必要。 成本低 这个测试，系统的快速摊销，加上巨大的医疗保健 与显着且广泛认可的健康相结合，可以节省成本 问题表明该产品可能具有巨大的商业潜力。