AIDen: An AI-empowered detection and diagnosis system for jaw lesions using CBCT

AIDen：使用 CBCT 的人工智能驱动下颌病变检测和诊断系统

• 批准号: 10383494
• 负责人: Jing Li
• 金额: $ 30万
• 依托单位: MS TECHNOLOGIES CORPORATION
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10383494
• 关键词: 3-Dimensional; Active Learning; Address; Adopted; Affect; Agreement; Algorithms; Anatomy; Appearance; Area; Artificial Intelligence; Clinical; Clinical Decision Support Systems; Clinics and Hospitals; Complex; Data; Data Set; Dental; Dental Schools; Dentists; Detection; Diagnosis; Differential Diagnosis; Disease; Endodontics; Environment; Expert Systems; Goals; Image; Image Analysis; Jaw; Knowledge; Lesion; Location; Machine Learning; Mathematics; Medical; Oral; Oral Medicine; Oral Surgical Procedures; Patients; Performance; Periapical Periodontitis; Phase; Population; Private Practice; Process; Publications; Radiation exposure; Reproducibility; Research; Research Institute; Savings; Shapes; Site; Small Business Technology Transfer Research; Structure; System; Techniques; Technology; Three-Dimensional Image; Three-Dimensional Imaging; Time; Training; Uncertainty; Validation; Visual; Work; age group; automated segmentation; base; clinical decision support; deep learning; deep learning algorithm; design; empowered; feasibility testing; human error; imaging Segmentation; imaging modality; improved; individual patient; innovation; learning strategy; machine learning pipeline; novel; optimal treatments; periapical; prevent; public health relevance; radiological imaging; radiomics; software systems; treatment planning

Dental CBCT is a 3D imaging modality widely adopted to help dentists detect and diagnose jaw lesions. Due to minimum information loss (compared to conventional 2D radiography) and low radiation exposure (compared to conventional CT), it has become the “go-to” radiographic technique in various dental fields. Gaps: Accompanying the clear benefits of dental CBCT is an overwhelming amount of 3D data presented to clinicians. Clinician-based CBCT interpretation suffers from low inter-/intra-observer agreement and low accuracy. AI/Deep Learning (DL) holds great promise to automate CBCT image analysis and provide objective, accurate detection and diagnosis capabilities to support clinical decision. However, limited research has been done due to unique and significant challenges: (1) Dental CBCT provides 3D images composed of a complicated mix of different oral structures/contents, preventing the direct use of existing general-purse DL algorithms for image segmentation and calling for new DL designs. (2) AI/DL is known to be data-hungry. It is very difficult to obtain a large number of accurately-annotated CBCT images to train DL due to complex oral anatomy and inevitable human errors, which calls for efficient strategies to reduce annotation effort for DL training. (3) Due to these challenges, the current software systems used to assist clinicians in dental CBCT interpretation do not provide advanced AI- based lesion detection and diagnosis capabilities, which makes this STTR project timely and important. We recently developed a DL algorithm that integrates unique oral anatomy into the DL design, namely “Anatomically-Constrained dense UNet (AC-UNet)”. In addition to improving accuracy, AC-UNet is also annotation-efficient as it is not only trained using CBCT images but also constrained by anatomical domain knowledge through novel mathematical encoding and posterior regularization-based optimization. Applied to a preliminary dataset of CBCTs with periapical lesions indicative of Apical Periodontitis (AP), AC-UNet achieved high accuracy in segmentation and lesion detection on CBCT images and outperformed state-of-the-art DL algorithms. Our long-term goal is to develop the first-ever AI-based software system called “AIDen” to perform automatic segmentation, lesion detection, and differential diagnosis based on dental CBCT for a variety of jaw lesions/diseases with high accuracy, reliability, and reproducibility. AIDen will assist clinicians in providing optimal treatment decision for each patient. Our Phase-I goal is to develop and test the feasibility of AIDen for lesion detection and differential diagnosis focusing on AP, a highly-prevalent jaw lesion/disease. Three aims are: (1) Optimize design: to develop an extension of AC-UNet to integrate a broader range of different types of oral-anatomical knowledge into the DL design; (2) Optimize training: to develop an Active Learning strategy to further improve annotation efficiency of AC-UNet training; (3) Clinical validation and preliminary assessment of diagnosis capability for clinical decision support. All aims will lay groundwork for Phase-II when an end-to-end AIDen system will be built and validated using multi-site datasets and address a variety of jaw lesions/diseases.

牙科CBCT是一种被广泛采用的3D成像模式，可帮助牙科医生检测和诊断颌骨病变。由于 最小的信息损失（与传统的2D射线照相相比）和低辐射暴露（与 传统CT），它已成为各种牙科领域的“首选”放射摄影技术。标签：陪伴 牙科CBCT的明显好处是向临床医生提供了大量的3D数据。基于临床医生 CBCT解释存在观察者间/观察者内一致性低和准确性低的问题。AI/深度学习（DL） CBCT图像分析自动化，提供客观、准确的检测和诊断， 支持临床决策。然而，有限的研究已经完成，由于独特和重要的 挑战：（1）牙科CBCT提供由不同口腔组织的复杂混合组成的3D图像， 结构/内容，防止直接使用现有的通用钱包DL算法进行图像分割 并呼吁新的DL设计。(2)AI/DL是众所周知的数据饥渴。很难获得大量的 由于复杂的口腔解剖结构和不可避免的人为错误， 这需要有效的策略来减少DL训练的注释工作。(3)由于这些挑战， 用于辅助临床医生进行牙科CBCT解释的当前软件系统不提供先进的AI， 基于病变检测和诊断能力，这使得这个STTR项目及时和重要。我们 最近开发了一种DL算法，该算法将独特的口腔解剖学整合到DL设计中，即 解剖学约束的密集UNet（AC-UNet）。除了提高准确性，AC-UNet还 注释效率高，因为它不仅使用CBCT图像进行训练，而且还受解剖区域的约束 通过新颖的数学编码和基于后验正则化的优化来获取知识。应用于 具有提示根尖牙周炎（AP）的根尖周病变的CBCT的初步数据集，AC-UNet达到 CBCT图像分割和病变检测的准确性高，性能优于最先进的DL 算法我们的长期目标是开发有史以来第一个基于AI的软件系统“AIDen”， 基于牙科CBCT的各种颌骨的自动分割、病变检测和鉴别诊断 病变/疾病，具有高准确性、可靠性和可重复性。AIDen将协助临床医生提供 为每位患者提供最佳治疗方案。我们的第一阶段目标是开发和测试AIDen的可行性， 病变检测和鉴别诊断，重点是AP，一种高度流行的颌骨病变/疾病。三个目标 （1）优化设计：开发AC-UNet的扩展，以整合更广泛的不同类型的 口腔解剖学知识融入DL设计;（2）优化培训：制定主动学习策略， 进一步提高AC-UNet训练的标注效率;（3）临床验证和初步评估 临床决策支持的诊断能力。所有目标都将为第二阶段奠定基础， AIDen系统将使用多中心数据集构建和验证，并解决各种颌骨病变/疾病。