Stacked Multiscale Feature Learning for Domain Independent Medical Image Segmentation
نویسندگان
چکیده
In this work we propose a feature-based segmentation approach that is domain independent. While most existing approaches are based on application-specific hand-crafted features, we propose a framework for learning features from data itself at multiple scales and depth. Our features can be easily integrated into classifiers or energy-based segmentation algorithms. We test the performance of our proposed method on two MICCAI grand challenges, obtaining the top score on VESSEL12 and competitive performance on BRATS2012.
منابع مشابه
Automatic Lung Vessel Segmentation via Stacked Multiscale Feature Learning
We introduce a representation learning approach to segmenting vessels in the lungs. Our algorithm takes as input a CT volume and outputs a learned feature vector for each voxel. These feature vectors are then passed into a logistic regression classifier for making a probabilistic prediction on the occurrence of a vessel. Our features are learned using both multiple layers and scales which captu...
متن کاملCluster-Based Image Segmentation Using Fuzzy Markov Random Field
Image segmentation is an important task in image processing and computer vision which attract many researchers attention. There are a couple of information sets pixels in an image: statistical and structural information which refer to the feature value of pixel data and local correlation of pixel data, respectively. Markov random field (MRF) is a tool for modeling statistical and structural inf...
متن کاملDiagnosis of brain tumor using PNN neural networks
Cells grow and then need a very neat method to create new cells that work properly to maintain the health of the body. When the ability to control the growth of the cells is lost, they are unconsidered and often divided without order. Exemplified cells form a tissue mass called the tumor. In fact, brain tumors are abnormal and uncontrolled cell proliferations. Segmentation methods are used in b...
متن کاملImage alignment via kernelized feature learning
Machine learning is an application of artificial intelligence that is able to automatically learn and improve from experience without being explicitly programmed. The primary assumption for most of the machine learning algorithms is that the training set (source domain) and the test set (target domain) follow from the same probability distribution. However, in most of the real-world application...
متن کاملImage Classification via Sparse Representation and Subspace Alignment
Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to d...
متن کامل