混合深度学习辅助多重分类:恶性甲状腺结节的分类
Mayuresh Bhagavat Gulame1, Vaibhav V Dixit2
1Department of Electronics & Telecommunication, G H Raisoni College of Engineering and Management, Pune, Maharashtra, India.
概括
这项研究引入了一种新的混合深度学习模型,用于准确检测和分类甲状腺结节. 与传统方法相比,人工智能驱动的方法显著提高了诊断准确性.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 在瘤学瘤学.
背景情况:
- 超声波是甲状腺结节诊断的标准,但区分良性和恶性结节是具有挑战性的.
- 深度学习 (DL) 在医学图像分析方面提供了进步,但在甲状腺结节检测方面面临准确性障碍.
- 准确区分甲状腺结节对于有效的患者管理和治疗至关重要.
研究的目的:
- 开发和评估一种创新的混合深度学习模型,用于甲状腺结节的多重分类.
- 用先进的AI技术提高甲状腺结节检测和分级的准确性和有效性.
- 将传统的成像功能与深度学习相结合,以提高诊断性能.
主要方法:
- 开发了一个混合深度学习模型,将深度Maxout和卷积神经网络 (CNN) 结合起来.
- 图像预处理包括用于降噪的中间模糊和用于细分的MPIU-Net.
- 特征提取涉及LGBP,多文本和基于LTP的方法,其次是数据增强.
- 使用DBNAAF模型进行转移学习,用于恶性结节分级和TIRADS分数分类.
主要成果:
- 拟议的混合模型实现了0.9445的马修斯相关系数 (MCC),超过了DCNN (0.6858) 和CNN (0.7780) 等其他模型.
- 该模型在分类甲状腺结核和分类恶性结核方面表现出卓越的性能.
- 整合各种特征提取技术和深度学习架构,有助于高诊断准确度.
结论:
- 开发的混合深度学习模型显示了准确和高效的甲状腺结节检测和分类的巨大潜力.
- 这种人工智能辅助的方法可以帮助临床医生区分恶性和良性甲状腺结节,提高诊断信心.
- 这项研究强调了将先进的图像处理,特征提取和深度学习用于医疗图像分析的有效性.
相关概念视频
01:27Hyperthyroidism II: Pathophysiology
Hyperthyroidism is a hypermetabolic state caused by elevated levels of thyroid hormones, triiodothyronine (T3) and thyroxine (T4). It results from dysregulation at the thyroid, pituitary, or immune system level and affects multiple organ systems.PathophysiologyThe most common cause of hyperthyroidism is Graves’ disease, an autoimmune disorder in which antibodies, specifically thyroid-stimulating antibodies (TSAb), a subtype of TSH receptor antibodies (TRAb), bind to and activate TSH receptors...
01:24Graves Disease II: Pathophysiology
Graves’ disease is an autoimmune disorder characterized by the production of thyroid-stimulating immunoglobulins (TSI) that activate TSH receptors, leading to excessive synthesis and release of thyroid hormones (T3 and T4) and resulting in hyperthyroidism.Among all causes of hyperthyroidism, Graves’ disease is the most common and can happen at any age, though it is more frequent in women. It produces a hypermetabolic state with features such as weight loss, tachycardia, tremor, and heat...