相关概念视频
lncRNA - Long Non-coding RNAs
In humans, more than 80% of the genome gets transcribed. However, only around 2% of the genome codes for proteins. The remaining part produces non-coding RNAs which includes ribosomal RNAs, transfer RNAs, telomerase RNAs, and regulatory RNAs, among other types. A large number of regulatory non-coding RNAs have been classified into two groups depending upon their length – small non-coding RNAs, such as microRNA, which are less than 200 nucleotides in length, and long non-coding RNA (lncRNA)...
Brain Imaging
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).
您也可能阅读
相关文章
通过共同作者、期刊和引用图与本文相关的文章。
排序
Same author
Correction: AI-driven saliency-guided retinal vessel segmentation framework for sustainable digital pathology.
Frontiers in medicine·2026
Same author
Exploring Spectral Graph Theory in Combinatorial Chemistry.
Combinatorial chemistry & high throughput screening·2026
可以解释的CNN用于通过基于XAI的关键特征识别识别来检测和分类脑瘤.
Shagufta Iftikhar1, Nadeem Anjum1, Abdul Basit Siddiqui1
1Department of Computer Science, Capital University of Science and Technology, Islamabad, Pakistan.
Brain informatics
|April 30, 2025
概括
这项研究引入了使用可解释AI (XAI) 和卷积神经网络 (CNN) 的更简单,可解释的大脑瘤分类模型. 这种新的方法实现了高精度,专注于可靠的瘤检测和分类的相关特征.
更多相关视频
14:27Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
15.6K
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.1K
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 计算神经科学是一种神经科学.
背景情况:
- 现有的脑瘤分类模型经常表现出复杂的结构,阻碍了解释性,并可能导致依赖无关的特征.
- 模型的复杂性增加了层和参数的数量,使分类过程复杂化并降低了透明度.
研究的目的:
- 开发一种新的方法,将可解释AI (XAI) 技术与简化的卷积神经网络 (CNN) 架构结合起来,用于脑瘤分类.
- 通过确保专注于相关特征和减少复杂性来提高模型的透明度和稳定性.
主要方法:
- 整合XAI技术,包括梯度加权类激活映射 (Grad-Cam),Shapley增量解释 (Shap) 和局部可解释模型不可知解释 (LIME),与CNN架构.
- 网络层的最小化,以减少模型的复杂性,并改善对瘤检测的关键特征的关注.
主要成果:
- 拟议的模型在可见数据上达到99%的准确性,在未见数据上达到95%的准确性,显示出强大的概括性和可靠性.
- XAI技术为模型的决策过程提供了明确的见解,证实了对相关瘤特征的关注.
结论:
- 开发的方法在脑瘤分类中提供了简单性,可解释性和高准确性的平衡.
- 这种方法代表了显著的进步,提高了大脑瘤检测医疗图像分析的透明度和可靠性.
