Retrieval of Brain Tumors by Adaptive Spatial Pooling and Fisher Vector Representation

By Jun Cheng, Wei Yang, Meiyan Huang, Wei Huang, Jun Jiang, Yujia Zhou, Ru Yang, Jie Zhao, Yanqiu Feng, Qianjin Feng and 1 more. 2016

275 citations recorded by the source corpus.

Content-based image retrieval (CBIR) techniques have currently gained increasing popularity in the medical field because they can use numerous and valuable archived images to support clinical decisions. In this paper, we concentrate on developing a CBIR system for retrieving brain tumors in T1-weighted contrast-enhanced MRI images. Specifically, when the user roughly outlines the tumor region of a query image, brain tumor images in the database of the same pathological type are expected to be returned. We propose a novel feature extraction framework to improve the retrieval performance. The proposed framework consists of three steps. First, we augment the tumor region and use the augmented tumor region as the region of interest to incorporate informative contextual information. Second, the augmented tumor region is split into subregions by an adaptive spatial division method based on intensity orders; within each subregion, we extract raw image patches as local features. Third, we apply the Fisher kernel framework to aggregate the local features of each subregion into a respective single vector representation and concatenate these per-subregion vector representations to obtain an image-level signature. After feature extraction, a closed-form metric learning algorithm is applied to measure the similarity between the query image and database images. Extensive experiments are conducted on a large dataset of 3604 images with three types of brain tumors, namely, meningiomas, gliomas, and pituitary tumors. The mean average precision can reach 94.68%. Experimental results demonstrate the power of the proposed algorithm against some related state-of-the-art methods on the same dataset.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Continual Learning through Retrieval and Imagination (2022, methodology): “Embedding networks map data into a low-dimensional output, where similar data are clustered together and dissimilar data are far apart (Chopra et al. 2005; Wang et al. 2019b, 2021a,b).”
GAN Memory with No Forgetting (2020, neutral): “…the superiority of our GAN memory over existing replay-based methods, we design a challenging lifelong generation problem consisting of 6 perceptually-distant tasks/datasets (see Figure 5): Flowers [56], Cathedrals [96], Cats [94], Brain-tumor images [15], Chest X-rays [35], and Anime faces.”
A Deep Learning Approach for Brain Tumor Classification and Segmentation Using a Multiscale Convolutional Neural Network (2021, methodology): “[32] Fisher kernel 0.947 Abiwinanda et al. [24] CNN 0.841 Pashaei et al. [25] CNN 0.810 Pashaei et al. [25] CNN and KELM 0.936 Sultan et al. [26] CNN 0.961 Anaraki et al. [27] CNN and GA 0.942 Our approach Multiscale CNN 0.973 The two studies conducted by Cheng et al. [5,32] are examples of…”
Brain Tumor Type Classification via Capsule Networks (2018, methodology): “To test our proposed approach, we have used the data set presented in References [8,21].”
Capsule Networks for Brain Tumor Classification Based on MRI Images and Coarse Tumor Boundaries (2018, methodology): “2), we have used a brain MRI dataset [26], consisting of 3064 images from 233 patients, diagnosed with one of the three brain tumor types.”
Deep Learning for Multigrade Brain Tumor Classification in Smart Healthcare Systems: A Prospective Survey (2020, methodology): “For instance, [43] and [44] investigated CapsNets for BTC but using only a single data set introduced in [106].”
Towards a guideline for evaluation metrics in medical image segmentation (2022, unknown): “[30,31] and cell nuclei detection in pathology microscopy from Caicedo et al.”
MRI-Based Brain Tumor Classification Using Ensemble of Deep Features and Machine Learning Classifiers (2021, methodology): “Cheng et al. [14] employed FV to retrieve the brain tumor.”