arXiv 2207.130212024-11-21eess.IVcs.CV

CTVR-EHO TDA-IPH：用于脑肿瘤分割与分类的拓扑优化卷积视觉循环网络

CTVR-EHO TDA-IPH Topological Optimized Convolutional Visual Recurrent Network for Brain Tumor Segmentation and Classification

Amity University Rajasthan（拉贾斯坦邦阿米蒂大学）；Guru Ghasidas Vishwavidyalaya（古鲁·加西达斯大学）；SVKM’s NMIMS (Deemed to be University)（SVKM NMIMS（被视为大学））

Dhananjay Joshi, Bhupesh Kumar Singh, Kapil Kumar Nagwanshi, Nitin S. Choubey

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出TDA-IPH分割与CTVR-EHO分类框架，结合拓扑数据分析、AlexNet、Bi-VLSTM和象群优化，实现脑肿瘤高精度分割分类，准确率达99.8%。

摘要：

在当今医疗保健领域，脑肿瘤检测已变得普遍。然而，人工脑肿瘤分类方法耗时较长。因此，许多医学领域的研究人员使用深度卷积神经网络（DCNN）来进行准确诊断并辅助患者治疗。传统技术存在过拟合以及无法提取必要特征等问题。为克服这些问题，我们开发了基于拓扑数据分析的改进持续同调（TDA-IPH）模型，以及带有象群优化超参数调优的卷积迁移学习与视觉循环学习（CTVR-EHO）模型，用于脑肿瘤分割与分类。首先，设计基于拓扑数据分析的改进持续同调方法对脑肿瘤图像进行分割。然后，从分割后的图像中，通过AlexNet模型和双向视觉长短期记忆网络（Bi-VLSTM）利用迁移学习提取特征。接着，使用象群优化（EHO）对两个网络的超参数进行调优，以获得最优结果。最后，将提取的特征进行拼接，并使用softmax激活层进行分类。对所提出的CTVR-EHO和TDA-IPH方法的仿真结果基于精确率、准确率、召回率、损失和F分数等指标进行分析。与其他现有的脑肿瘤分割和分类模型相比，所提出的CTVR-EHO和TDA-IPH方法表现出高准确率（99.8%）、高召回率（99.23%）、高精确率（99.67%）和高F分数（99.59%）。

英文摘要：

In today's world of health care, brain tumor detection has become common. However, the manual brain tumor classification approach is time-consuming. So Deep Convolutional Neural Network (DCNN) is used by many researchers in the medical field for making accurate diagnoses and aiding in the patient's treatment. The traditional techniques have problems such as overfitting and the inability to extract necessary features. To overcome these problems, we developed the Topological Data Analysis based Improved Persistent Homology (TDA-IPH) and Convolutional Transfer learning and Visual Recurrent learning with Elephant Herding Optimization hyper-parameter tuning (CTVR-EHO) models for brain tumor segmentation and classification. Initially, the Topological Data Analysis based Improved Persistent Homology is designed to segment the brain tumor image. Then, from the segmented image, features are extracted using TL via the AlexNet model and Bidirectional Visual Long Short-Term Memory (Bi-VLSTM). Next, elephant Herding Optimization (EHO) is used to tune the hyperparameters of both networks to get an optimal result. Finally, extracted features are concatenated and classified using the softmax activation layer. The simulation result of this proposed CTVR-EHO and TDA-IPH method is analyzed based on precision, accuracy, recall, loss, and F score metrics. When compared to other existing brain tumor segmentation and classification models, the proposed CTVR-EHO and TDA-IPH approaches show high accuracy (99.8%), high recall (99.23%), high precision (99.67%), and high F score (99.59%).

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。