Medical Image Segmentation Algorithm Based on Optimized Convolutional Neural Network-Adaptive Dropout Depth Calculation
Feng-Ping An,Jun-e Liu +1 more
Reads0
Chats0
TLDR
The experimental results show that not only are the segmentation effects of the proposed method improved compared with those of the traditional machine learning and other deep learning methods but also the method has a high adaptive segmentation ability for various medical images.Abstract:
Medical image segmentation is a key technology for image guidance. Therefore, the advantages and disadvantages of image segmentation play an important role in image-guided surgery. Traditional machine learning methods have achieved certain beneficial effects in medical image segmentation, but they have problems such as low classification accuracy and poor robustness. Deep learning theory has good generalizability and feature extraction ability, which provides a new idea for solving medical image segmentation problems. However, deep learning has problems in terms of its application to medical image segmentation: one is that the deep learning network structure cannot be constructed according to medical image characteristics; the other is that the generalizability y of the deep learning model is weak. To address these issues, this paper first adapts a neural network to medical image features by adding cross-layer connections to a traditional convolutional neural network. In addition, an optimized convolutional neural network model is established. The optimized convolutional neural network model can segment medical images using the features of two scales simultaneously. At the same time, to solve the generalizability problem of the deep learning model, an adaptive distribution function is designed according to the position of the hidden layer, and then the activation probability of each layer of neurons is set. This enhances the generalizability of the dropout model, and an adaptive dropout model is proposed. This model better addresses the problem of the weak generalizability of deep learning models. Based on the above ideas, this paper proposes a medical image segmentation algorithm based on an optimized convolutional neural network with adaptive dropout depth calculation. An ultrasonic tomographic image and lumbar CT medical image were separately segmented by the method of this paper. The experimental results show that not only are the segmentation effects of the proposed method improved compared with those of the traditional machine learning and other deep learning methods but also the method has a high adaptive segmentation ability for various medical images. The research work in this paper provides a new perspective for research on medical image segmentation.read more
Citations
More filters
Journal ArticleDOI
Assisted Diagnosis of Alzheimer’s Disease Based on Deep Learning and Multimodal Feature Fusion
Yu Wang,Xi Liu,Chongchong Yu +2 more
TL;DR: Wang et al. as mentioned in this paper proposed a multimodal diagnosis method for Alzheimer's disease based on three-dimensional shufflenet (3DShuffleNet) and principal component analysis network (PCANet).
Journal ArticleDOI
Real-time application based CNN architecture for automatic USCT bone image segmentation
TL;DR: A new segmentation application based on various Convolutional Neural Network models for Ultrasonic Computed Tomographic (USCT) images, which proves to be a good candidate for medical real-time applications thanks to its implementation on the GPU.
Book ChapterDOI
Detection and Classification of Encephalon Tumor Using Extreme Learning Machine Learning Algorithm Based on Deep Learning Method
TL;DR: In this article , the encephalon tumor was detected from three schemes, that is, initially, they have collected some raw data and put into the machine learning model; secondly, the classification process is done by extreme learning machine (ELM); and finally, the tumors are extracted from most commonly method gray level co-occurrence method (GLCM).
Proceedings ArticleDOI
Performance Analysis of Ultrasound Ovarian Tumour Segmentation Using GrabCut and FL-SNNM
K. Srilatha,V. Ulagamuthalvi +1 more
TL;DR: The most important aim of the proposed work is ultrasound ovarian tumour segmentation and subsequently apply ultrasound image is in step by step approach, namely pre-processing and segmentation.
Book ChapterDOI
A review of deep learning models for medical diagnosis
TL;DR: In this paper, the authors reviewed the latest AI research in the immense field of medical science, covering various architectures and approaches, with special attention given to brain tumor analysis, and compared results with existing architectures.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Posted Content
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Proceedings Article
Greedy Layer-Wise Training of Deep Networks
TL;DR: These experiments confirm the hypothesis that the greedy layer-wise unsupervised training strategy mostly helps the optimization, by initializing weights in a region near a good local minimum, giving rise to internal distributed representations that are high-level abstractions of the input, bringing better generalization.
Related Papers (5)
Medical image segmentation algorithm based on feedback mechanism convolutional neural network
An Feng-Ping,Liu Zhi-wen +1 more
Medical image segmentation algorithm based on multilayer boundary perception-self attention deep learning model
Feng-Ping An,Jun-e Liu +1 more