人工智能模型是否像心脏病学家一样倾听? 弥合人工智能和临床推理之间的差距在心脏声音分类中使用可解释的人工智能
1Faculty of Computing and Information Technology (FCIT), King Abdulaziz University, Jeddah 21589, Saudi Arabia.
Bioengineering (Basel, Switzerland)
|June 26, 2025
概括
可解释的人工智能 (XAI) 和注意力机制增强了对心声分类的深度学习. 将多头注意力与ResNet50集成,提高了准确度至97.3%,以及可解释性,专注于临床相关的心声特征.
科学领域:
- 心脏病学 心脏病学
- 人工智能的人工智能
- 生物医学信号处理
背景情况:
- 深度学习自动化了心声分类,但与罕见疾病作斗争,并依赖临床医生的专业知识.
- 当前的自动细分方法引入了变化,影响了分类准确性和信任度.
- 预训练模型显示不一致的准确性,需要可解释的方法来验证结果并了解临床相关性.
研究的目的:
- 评估深度学习模型是否使用可解释AI (XAI) 专注于临床相关的心声特征.
- 调查注意力机制是否可以提高分类性能,并专注于有意义的信号段.
- 在使用XAI和注意力机制的手动细分数据集上评估深度学习模型.
主要方法:
- 应用可解释AI (XAI) 技术,特别是Grad-CAM,以可视化模型的注意力.
- 集成的多头注意力机制与预训练模型,如ResNet50.
- 利用手动细分的数据集对模型行为和性能进行客观评估.
主要成果:
- 整合多头注意力显著提高了分类准确性和可解释性.
- 具有多头注意力的ResNet50实现了97.3%的准确性,超过了基线和SE增强模型.
- 可解释性的平均交叉度 (mIoU) 从75.7%增加到82.0%,表明对诊断相关区域的重点更好.
结论:
- 可解释性AI (XAI) 对于通过确保对临床特征的关注来验证深度学习心声分类至关重要.
- 多头注意力机制提高了心声分类模型的准确性和可解释性.
- 这项研究证明了将XAI和注意力机制结合在手动细分数据上的有效性,以实现可靠的心脏诊断.
相关概念视频
01:15Heart Sounds
2.3K
Heart sounds are generated by the turbulence in blood flow due to the closing of heart valves. These sounds are best perceived slightly away from the valves, where the blood flow disseminates the sound.
Auscultation is the process of listening to these internal body sounds using a stethoscope. The heart produces four types of sounds, but only two—S1 and S2—can usually be heard with a stethoscope.
S1, also known as the "lub" sound, is caused by the closure of atrioventricular (A-V)...
Auscultation is the process of listening to these internal body sounds using a stethoscope. The heart produces four types of sounds, but only two—S1 and S2—can usually be heard with a stethoscope.
S1, also known as the "lub" sound, is caused by the closure of atrioventricular (A-V)...
2.3K
01:30Heart Failure IV: Classification and Diagnostic Evaluation
43
Heart failure can be classified in various ways, with the most common classifications based on physical activity limitations, disease progression, severity, and treatment strategies.The Functional Classification of Heart Failure divides patients into four categories based on physical activity limitation due to symptom burden.Class I: Patients in this class have cardiac disease but no physical activity limitations. Ordinary activities like walking, climbing stairs, or routine tasks do not cause...
43
01:17Classification of Illness
8.0K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
8.0K
01:26Classification of Systems-I
319
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
319