A survey on deep learning in medical image analysis

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource

/pdf/the-multimodal-brain-tumor-image-segmentation-benchmark-2gfraj98dk.pdf

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical images. At the core of these advances is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Deep learning is rapidly becoming the state of the art, leading to enhanced performance in various medical applications. We introduce the fundamentals of deep learning methods and review their successes in image registration, detection of anatomical and cellular structures, tissue segmentation, computer-aided disease diagnosis and prognosis, and so on. We conclude by discussing research issues and suggesting future directions for further improvement.

/pdf/deep-learning-in-medical-image-analysis-4jwausnkq2.pdf

Deep Learning in Medical Image Analysis

http://www.eecs.qmul.ac.uk/~sgg/papers/ShanGongMcOwan_IVC09.pdf

Facial expression recognition based on Local Binary Patterns: A comprehensive study

This paper proposes a novel approach to extract image features for texture classification. The proposed features are robust to image rotation, less sensitive to histogram equalization and noise. It comprises of two sets of features: dominant local binary patterns (DLBP) in a texture image and the supplementary features extracted by using the circularly symmetric Gabor filter responses. The dominant local binary pattern method makes use of the most frequently occurred patterns to capture descriptive textural information, while the Gabor-based features aim at supplying additional global textural information to the DLBP features. Through experiments, the proposed approach has been intensively evaluated by applying a large number of classification tests to histogram-equalized, randomly rotated and noise corrupted images in Outex, Brodatz, Meastex, and CUReT texture image databases. Our method has also been compared with six published texture features in the experiments. It is experimentally demonstrated that the proposed method achieves the highest classification accuracy in various texture databases and image conditions.

/pdf/dominant-local-binary-patterns-for-texture-classification-44ftm1mhx0.pdf

Dominant Local Binary Patterns for Texture Classification

In general image recognition problems, discriminative information often lies in local image patches. For example, most human identity information exists in the image patches containing human faces. The same situation stays in medical images as well. “Bodypart identity” of a transversal slice—which bodypart the slice comes from—is often indicated by local image information, e.g., a cardiac slice and an aorta arch slice are only differentiated by the mediastinum region. In this work, we design a multi-stage deep learning framework for image classification and apply it on bodypart recognition. Specifically, the proposed framework aims at: 1) discover the local regions that are discriminative and non-informative to the image classification problem, and 2) learn a image-level classifier based on these local regions. We achieve these two tasks by the two stages of learning scheme, respectively. In the pre-train stage, a convolutional neural network (CNN) is learned in a multi-instance learning fashion to extract the most discriminative and and non-informative local patches from the training slices. In the boosting stage, the pre-learned CNN is further boosted by these local patches for image classification. The CNN learned by exploiting the discriminative local appearances becomes more accurate than those learned from global image context. The key hallmark of our method is that it automatically discovers the discriminative and non-informative local patches through multi-instance deep learning. Thus, no manual annotation is required. Our method is validated on a synthetic dataset and a large scale CT dataset. It achieves better performances than state-of-the-art approaches, including the standard deep CNN.

Multi-Instance Deep Learning: Discover Discriminative Local Anatomies for Bodypart Recognition

Image representation plays an important role in medical image analysis. The key to the success of different medical image analysis algorithms is heavily dependent on how we represent the input data, namely features used to characterize the input image. In the literature, feature engineering remains as an active research topic, and many novel hand-crafted features are designed such as Haar wavelet, histogram of oriented gradient, and local binary patterns. However, such features are not designed with the guidance of the underlying dataset at hand. To this end, we argue that the most effective features should be designed in a learning based manner, namely representation learning, which can be adapted to different patient datasets at hand. In this paper, we introduce a deep learning framework to achieve this goal. Specifically, a stacked independent subspace analysis (ISA) network is adopted to learn the most effective features in a hierarchical and unsupervised manner. The learnt features are adapted to the dataset at hand and encode high level semantic anatomical information. The proposed method is evaluated on the application of automatic prostate MR segmentation. Experimental results show that significant segmentation accuracy improvement can be achieved by the proposed deep learning method compared to other state-of-the-art segmentation approaches.

/pdf/representation-learning-a-unified-deep-learning-framework-17n0a9x8q2.pdf

Representation learning: a unified deep learning framework for automatic prostate MR segmentation.

This paper proposes a novel facial expression recognition approach based on two sets of features extracted from the face images: texture features and global appearance features. The first set is obtained by using the extended local binary patterns in both intensity and gradient maps and computing the Tsallis entropy of the Gabor filtered responses. The second set of features is obtained by performing null-space based linear discriminant analysis on the training face images. The proposed method is evaluated by extensive experiments on the JAFFE database, and compared with two widely used facial expression recognition approaches. Experimental results show that the proposed approach maintains high recognition rate in a wide range of resolution levels and outperforms the other alternative methods.

/pdf/facial-expression-recognition-using-advanced-local-binary-1wdqp880zc.pdf

Facial Expression Recognition using Advanced Local Binary Patterns, Tsallis Entropies and Global Appearance Features

In this paper, we propose a new face recognition approach based on local binary patterns (LBP). The proposed approach has the following novel contributions. (i) As compared with the conventional LBP, anisotropic structures of the facial images can be captured effectively by the proposed approach using elongated neighborhood distribution, which is called the elongated LBP (ELBP). (ii) A new feature, called Average Maximum Distance Gradient Magnitude (AMDGM), is proposed. AMDGM embeds the gray level difference information between the reference pixel and neighboring pixels in each ELBP pattern. (iii) It is found that the ELBP and AMDGM features are well complement with each other. The proposed method is evaluated by performing facial expression recognition experiments on two databases: ORL and FERET. The proposed method is compared with two widely used face recognition approaches. Furthermore, to test the robustness of the proposed method under the condition that the resolution level of the input images is low, we also conduct additional face recognition experiments on the two databases by reducing the resolution of the input facial images. The experimental results show that the proposed method gives the highest recognition accuracy in both normal environment and low image resolution conditions.

Shu Liao

Papers

Dominant Local Binary Patterns for Texture Classification

Multi-Instance Deep Learning: Discover Discriminative Local Anatomies for Bodypart Recognition

Representation learning: a unified deep learning framework for automatic prostate MR segmentation.

Facial Expression Recognition using Advanced Local Binary Patterns, Tsallis Entropies and Global Appearance Features

Face recognition by using elongated local binary patterns with average maximum distance gradient magnitude