Objective and noninvasive diagnosis of middle-ear and conductive pathologies using simulation-based inference and transfer learning applied to clinical data

使用基于模拟的推理和应用于临床数据的迁移学习来客观、无创地诊断中耳和传导性病变

• 批准号: 10599340
• 负责人: Hamid Motallebzadeh
• 金额: $ 17.75万
• 依托单位: CALIFORNIA STATE UNIVERSITY SACRAMENTO
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-05-01 至 2025-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10599340
• 关键词: Affect; Age; Air; Anatomy; Audiology; Behavior; Characteristics; Classification; Clinical; Clinical Data; Clinical Research; Complex; Computer Models; Conductive hearing loss; Data; Data Set; Diagnosis; Diagnostic; Differential Diagnosis; Dimensions; Ear; Elements; Exhibits; External auditory canal; Eye; Feasibility Studies; Frequencies; Geometry; Goals; Hearing Tests; Human; Image; Individual; Knowledge; Label; Ligaments; Literature; Machine Learning; Manuals; Maps; Measurement; Measures; Methodology; Methods; Mining; Modeling; Monitor; Noise; Normal Range; Operative Surgical Procedures; Otosclerosis; Outcome; Outcome Study; Output; Pathologic; Pathology; Patients; Pattern Recognition; Performance; Physicians; Physiological; Population; Postoperative Period; Preparation; Probability; Process; Property; Randomized; Reporting; Risk; Roentgen Rays; Sampling; Series; Specificity; Specimen; Stapes; Statistical Data Interpretation; Structure; Surgical Disarticulation; Symptoms; Techniques; Testing; Training; Trauma; Tympanometry; Uncertainty; Variant; X-Ray Computed Tomography; age related; bone; computerized data processing; cost; cost effective; diagnostic criteria; electric impedance; experience; feature extraction; feature selection; feeding; hands-on learning; hearing impairment; image registration; improved; insight; large datasets; machine learning algorithm; microCT; middle ear; neural network; neural network architecture; noninvasive diagnosis; pressure; response; sample fixation; simulation; stem; tool; transfer learning

Conductive hearing loss affects all ages and represents over 50% of hearing impairments, but unlike sensorineural loss, the potential for treatment is high. Conductive loss stems from a diverse set of possible pathologies, such as ossicular fixation, ossicular disarticulation, or superior-canal dehiscence, each of which requires a different treatment. Moreover, these distinct pathologies can result from similar physical traumas and exhibit similar symptoms, which means that in most cases x-ray-based imaging and exploratory surgeries are used to confirm a suspected pathology. Because of the high cost, risk to the patient, and subjectivity of existing diagnostic options, an inexpensive, noninvasive measure would be valuable to assess the middle-ear (ME) status, to reduce uncertainties about the diagnosis prior to surgery, and to monitor outcomes postoperatively. Wideband tympanometry (WBT), which uses an ear-canal probe to quickly measure the frequency-varying admittance/impedance of the ME across a range of negative and positive static pressures, could become a cost- effective tool for noninvasively diagnosing ME pathologies. However, the task of mining complex WBT datasets for reliable indicators of ME pathologies has proven challenging. Machine learning (ML), with its powerful pattern- recognition and classification capabilities, may provide a reliable methodology for doing this. However, only very limited attempts have been made thus far to incorporate ML into ME assessments, mainly due to the lack of large-enough WBT datasets of confirmed pathologies that are usually required to train ML algorithms. We propose to train an inference neural network (NN) to perform fast and accurate objective interpretations of WBT data. To account for the lack of sufficient pathology-identified training data, we propose using synthetic WBT responses from anatomically realistic finite-element (FE) models of the human ear with verified mechanistic behavior. Randomly varying the material properties and geometric parameters of the models within normal and beyond-normal ranges will mimic normal and pathological conditions while accounting for inter-subject variability, age-related changes to the ME structures, and measurement noise. The inference NN will be trained on this population of model parameters and responses to produce a probability distribution for each parameter value whenever it is presented with a new WBT response. Since each model parameter maps to a specific physiological characteristic of the ME, the predicted parameter values can indicate whether a response exhibits normal or pathological characteristics. Next, the NN knowledge will be expanded by applying transfer learning to the limited available clinical WBT data of confirmed pathological cases, along with additional noninvasive clinical data such as audiograms and air–bone gap measurements. The outcome of the project will be a trained inference NN for noninvasive objective assessments of the likelihood that a given ear has one (or more) of various conductive pathologies. Its use could reduce the need for or avoid unnecessary exploratory surgery, improve the specificity of preoperative preparations, and provide a low-cost means of postoperative monitoring.

导电性听力损失影响了所有年龄段，占听力障碍的50％以上，但与 感官损失，治疗的可能性很高。来自各种可能的导电损失植物 病理学，例如固定，耳鼻喉科或上等裂开，每种病理 需要不同的治疗方法。此外，这些独特的病理可能是由类似的身体创伤引起的 暴露了类似症状，这意味着在大多数情况下，基于X射线的成像和探索性手术是 用于确认可疑的病理。由于成本很高，患者的风险以及现有的主观性 诊断选择，廉价的无创测量对于评估中耳（ME）将是有价值的 状态，以减少对手术前诊断的不确定性，并也监测结果。 宽带鼓膜法（WBT），它使用早期探针快速测量频率变化 ME在一系列负面和积极的静态压力中对ME的接纳/阻抗可能会成为成本 - 无创诊断性ME病理学的有效工具。但是，挖掘复杂WBT数据集的任务 对于我的可靠指标，病理学已被证明是挑战。机器学习（ML），具有强大的模式 - 识别和分类功能可以为此提供可靠的方法。但是，只有非常 到目前为止，已经有限尝试将ML纳入我的评估，这主要是由于缺乏 训练ML算法所需的已确认病理的大型WBT数据集。我们 提议培训推理神经网络（NN）以对WBT进行快速准确的客观解释 数据。为了说明缺乏足够的病理识别培训数据，我们建议使用合成WBT 具有经过验证的机械的人耳的解剖学有限元（Fe）模型的响应 行为。在正常和 超出正常范围将模仿正常和病理状况，同时考虑受试者间的可变性， 与年龄相关的ME结构变化和测量噪声。推理NN将接受此培训 模型参数的群体和响应，以产生每个参数值的概率分布 每当提出新的WBT响应时。由于每个模型参数映射到特定 ME的物理特征，预测的参数值可以指示响应是否表现出来 正常或病理特征。接下来，通过应用转移学习来扩展NN知识 对于已确认的病理病例的有限的可用临床WBT数据以及其他无创的 临床数据，例如听力图和空气骨间隙测量。该项目的结果将是训练有素的 对特定耳朵具有一个（或更多）的可能性无创客观评估的推理NN 各种导电病理。它的使用可以减少或避免不必要的探索性手术， 提高术前制剂的特异性，并提供术后监测的低成本手段。