STTR Phase I: Intelligent Scoring of Inflammatory Skin Disease Progression

这个小企业技术转让(STTR)第一阶段项目的更广泛的影响和商业潜力是使提供者能够以更低的成本有效地治疗患有慢性炎症性皮肤病的患者。今天，初级保健医生经常将患有这些疾病的患者转介给皮肤科医生进行初步诊断和多次后续预约，特别是当给患者开出高成本、高接触性的治疗方法(如生物制品)或程序(如光疗)时。通过引入这种自动严重程度评分系统，这些供应商将拥有皮肤科医生的专业知识，使他们能够评估疾病严重程度，并提供以前只能通过专家提供的系统治疗。它还将建立更客观的评估，评估患者的进展，以根据需要调整剂量和治疗。对于制药公司来说，在临床试验期间让非专家进行这些严重性评估的能力减少了昂贵和限制性的人员要求。成本较低的试验可以帮助加快新药上市的速度。这项创新将通过以一种新颖的方式应用已知的机器学习技术来解决困难的视觉问题，从而增强科学和技术的理解。这个小企业技术转移(STTR)第一阶段项目将构建一个临床工具的原型，可以评估慢性皮肤炎的图像，确定其严重程度，并建议治疗。该系统将能够指导用户在图像收集过程中只需最少的培训，确定信息是否足够，并通过新的机器学习技术请求额外的信息。目前，临床医生试图评估慢性炎症性皮肤病的严重性依赖于一系列估计和人工加权平均值，这是一个耗时且有偏见的过程。这项第一阶段的研究将探索算法需要哪些信息来确定牛皮癣的严重程度。它将决定机器是否有可能引导成像器以更高的细节通过感兴趣的成像区域，而不是整个身体。它还将探索以多快的速度和实际情况进行这样的计算。该项目的最终目标是一个工作原型，它可以持续地对几个牛皮癣病例进行评分，并作为未来工作中原型扩展的概念证明。该奖项反映了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。

The broader impact and commercial potential of this Small Business Technology Transfer(STTR) Phase I project is to empower providers with the unprecedented ability to treat patientswith chronic inflammatory skin disease effectively and at a lower cost. Today, primary carephysicians often refer patients with these conditions to dermatologists for the initial diagnosisand multiple follow-up appointments, especially when patients are prescribed high cost, hightouch therapies like biologics or procedures, such as phototherapy. By introducing thisautomated severity scoring system, these providers will have the expertise of dermatologists attheir fingertips, giving them the ability to assess disease severity and provide systemictreatments previously available only through specialists. It will also establish more objectiveassessments, evaluating patient progress to adjust dosage and treatments as necessary. Forpharmaceutical companies, the ability to have non-specialists make these severity assessmentsduring clinical trials reduces expensive and restrictive staffing requirements. Less expensive trials canhelp expedite new drugs to market. This innovation will enhance scientific and technologicalunderstanding by applying known machine learning techniques in a novel manner to solve adifficult visual problem.This Small Business Technology Transfer (STTR) Phase I project will prototype a clinical toolthat can assess images of a chronic skin inflammation, determine its severity, and suggesttreatment. This system will be able to guide users with minimal training through the imagecollection process, determine if the information is sufficient, and request additional information ifrequired via novel machine learning techniques. Currently, clinicians trying to assess theseverity of chronic inflammatory skin diseases rely on a series of estimations and manualweighted averages, a time consuming and biased process. This Phase I research will explorewhat information is necessary for an algorithm to determine the severity of a psoriasis case. Itwill determine if it is possible for a machine to guide an imager through imaging regions ofinterest at higher detail, rather than the entire body at large. It will also explore how quickly andpractically such a calculation can be performed. The end goal of the project is a workingprototype that can consistently score a few psoriasis cases and serve as a proof of concept forexpansion of the prototype in future work.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.