STTR Phase II: Dermatologist-level detection of suspicious pigmented skin lesions from high-resolution full-body images

这一小型企业技术转让(STTR)第二阶段项目包括皮肤癌的早期检测，从而产生更好的结果，并降低死亡率和医疗保健支出。在美国，每年有近500万人因皮肤癌接受治疗，每年的费用估计为81亿美元。据估计，每年的生产率损失将额外损失45亿美元。在美国，皮肤癌的诊断存在着相当大的健康差距；目前看皮肤科医生的平均等待时间为32.3天，但不同地区的等待时间差别很大。早期发现通过减少手术切除的大小和程度以及减少晚期患者从系统治疗中经历的副作用来减少毁容。此外，该项目还提高了美国的经济竞争力。这个小型企业技术转让(STTR)第二阶段项目旨在生产一种适用于大视场图像的新型有色病变分析系统。该产品将建立在先前开发的全身摄影系统和概念验证病变分类软件的基础上，作为一种在第一阶段开发的医疗设备。皮肤镜般的分辨率为系统提供了坚实的基础，该系统可以自动(无需皮肤科医生的参与)在临床环境和/或放射学中心(类似于如何进行乳房X光检查)检测和分类各种皮肤状况。皮肤癌，包括黑色素瘤和非黑色素瘤，是美国最常见的癌症类型。在初级保健环境中早期识别可疑的色素病变可以改善黑色素瘤的预后，并可能将治疗成本降低20倍。这项技术为医疗保健系统提供了一种高度敏感、特定和经济的手段，为所有高危个体提供年度皮肤癌筛查。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This Small Business Technology Transfer (STTR) Phase II project includes early detection of skin cancers, resulting in better outcomes and a reduction in mortality and healthcare expenditures. Each year in the United States, nearly 5 million people are treated for skin cancer, with an annual cost estimated at $8.1 billion. Annual productivity losses are estimated to cost an additional $4.5 billion. There is a considerable health disparity in the diagnosis of skin cancer within the U.S.; The average wait time to see a dermatologist is currently 32.3 days but it varies greatly by location. Early detection reduces disfigurement by reducing the size and extent of surgical removal and reducing the side effects that late-stage patients experience from systemic therapies. Furthermore, the project increases the economic competitiveness of the U.S. This Small Business Technology Transfer (STTR) Phase II project is to productize a novel, pigmented, lesion analysis system for wide field-of-view images. The product will be built on a previously developed total body photography system and proof of concept lesion classification software as a medical device that was developed in Phase I. The dermatoscope-like resolution provides a solid foundation for a system that can automatically (without the involvement of a dermatologist) detect and classify various skin conditions in a clinical setting and/or a radiology center (similar to how mammograms are done). Skin cancers, including both melanomas and non-melanomas, are the most common types of cancer in the United States. Early-stage identification of suspicious pigmented lesions in primary care settings can lead to improved melanoma prognosis and a possible 20-fold reductions in treatment cost. This technology provides the healthcare system with a highly sensitive, specific, and economical means of providing annual skin cancer screening to all at risk individuals.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.