A Second Look at DREAM: Towards a New Paradigm in Meibomian Gland Evaluation Using Artificial Intelligence

重新审视 DREAM：利用人工智能迈向睑板腺评估的新范式

• 批准号: 10432877
• 负责人: Meng Ching Lin
• 金额: $ 21.96万
• 依托单位: UNIVERSITY OF CALIFORNIA BERKELEY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-30 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10432877
• 关键词: Affect; Algorithms; Area; Artificial Intelligence; Atrophic; Characteristics; Classification; Clinical; Clinical Data; Clinical Management; Clinical Trials; Consumption; Correlation Studies; Data; Data Set; Databases; Diagnosis; Evaluation; Eyelid structure; Fatty Acids; Film; Gland; Goals; Hand; Health; Human; Image; Image Analysis; Individual; Laboratories; Lead; Learning; Length; Link; Lipids; Machine Learning; Measurement; Measures; Medical History; Medical Imaging; Methodology; Methods; Morphology; Osmolar Concentration; Outcome; Pathologic; Pathology; Patients; Personal Satisfaction; Phenotype; Process; Production; Property; Publishing; Quality of life; Questionnaires; Randomized Controlled Clinical Trials; Risk; Scanning; Scheme; Second Look Surgery; Series; Serum; Signs and Symptoms; Societies; Standardization; Symptoms; Technology; Thinness; Time; Training; Update; Visual; Width; Work; algorithm training; aqueous; clinical database; cost; data management; demographics; evaporation; eye dryness; improved; machine learning algorithm; meibomian gland; meibomian gland dysfunction; novel; ocular surface; research clinical testing; response; supervised learning; symptomatology; unsupervised learning

Project Summary Dry eye (DE) is a highly prevalent condition with significant impacts on individuals and society that continues to evade easy diagnosis and treatment. The most common cause of DE is thought to be Meibomian gland dysfunction (MGD). The Meibomian glands in the upper and lower eyelids secrete lipids that form a thin film covering the aqueous tears and inhibit their evaporation. In MGD, it is thought that inadequate and/or poor quality tear lipids are secreted, leading to tear film instability, evaporation, and symptoms of DE. The glandular changes that occur in MGD are not well understood, nor are we able to identify which aspects of MGD pose the greatest risk for tear film instability and DE. The Dry Eye Assessment and Management (DREAM) Study was a clinical trial of ω3 fatty acid supplements for the treatment of DE. Over the course of the trial a large database of meibography images – infrared images of the everted eyelids that reveal the Meibomian glands – was compiled and analyzed using a novel scheme to characterize 13 different aspects of the glands by visual inspection and analyze their relationships to the clinically assessed quality of the secreted lipids. The process was arduous and time consuming, inherently subject to human bias, and provided little new information on the links between Meibomian gland characteristics and DE signs and symptoms. Recent advances in artificial intelligence (AI) have allowed us to train supervised machine learning algorithms on meibography images to automatically detect and quantify detailed morphological features of the individual glands. These detailed morphological features potentially contain a wealth of information about the health and functioning of the Meibomian glands, and could provide valuable information on the mechanisms behind MGD and its clinical implications. A further emerging AI technology for use in medical imaging – unsupervised discriminative feature learning – mitigates the human bias, and could potentially discover previously unidentified properties in meibography images, and possible links to crucial clinical endpoints like tear film instability and DE symptoms. In this project, we propose to utilize this new AI technology to re-analyze the DREAM Study clinical database of meibography images to dramatically extend their initial findings. Specifically, we will employ unsupervised discriminative feature learning to mitigate the human bias in meibography analysis, discover previously unrecognized features of the Meibomian glands, and to analyze the links between these features and MGD, tear film instability, and the clinical signs and symptoms indicative of DE.

项目摘要 干眼症(DE)是一种高度流行的疾病，对个人和社会都有重大影响 继续逃避简单的诊断和治疗。最常见的DE原因被认为是眉毛 腺体功能障碍(MGD)。上眼睑和下眼睑中的眉肌腺分泌脂类，形成一种薄的 覆盖在含水泪液上的薄膜，并抑制其蒸发。在MGD中，人们认为不充分和/或很差 高质量的泪脂被分泌，导致泪膜不稳定，蒸发，以及DE的症状。腺体 我们不能很好地理解MGD中发生的变化，也不能确定MGD的哪些方面 最大的风险是泪膜不稳定和DE。 干眼评估和管理(DREAM)研究是ω3脂肪酸的临床试验 治疗DE的补充剂。在试验过程中，一个大型的蜂窝图像数据库- 外翻眼皮的红外图像揭示了眉肌腺-使用 一种新的方案，通过肉眼检查表征腺体的13个不同方面并分析它们 与临床评估的脂类分泌质量的关系。这一过程是艰巨的，也是时间的 消费，天生受制于人类的偏见，并且几乎没有提供关于 眉毛腺特征及DE征象和症状。 人工智能(AI)的最新进展使我们能够训练有监督的机器学习 用于自动检测和量化子宫肌细胞形态特征的计算机图像处理算法 单独的腺体。这些详细的形态特征可能包含关于 眉板腺的健康和功能，并可提供有关机制的宝贵信息 MGD背后的原因及其临床意义。用于医学成像的另一种新兴的人工智能技术- 无监督的鉴别性特征学习-减轻人类的偏见，并可能发现 以前在核磁共振图像中未识别的属性，以及可能与关键临床终点的链接，如 泪膜不稳定和DE症状。 在这个项目中，我们建议利用这一新的人工智能技术来重新分析梦想研究临床 数据库，以极大地扩展他们的初步发现。具体地说，我们将聘用 发现无监督的鉴别特征学习可以减少人类在胚胎描记分析中的偏见 以前未被识别的眉毛腺的特征，并分析这些特征之间的联系 以及MGD、泪膜不稳定，以及提示DE的临床症状和体征。