Medical Image Analysis With Deep Neural Networks
01 Jan 2019-pp 75-97
TL;DR: The essentials of deep learning methods with convolutional neural networks are presented and their achievements in medical image analysis, such as in deep feature representation, detection, segmentation, classification, and prediction are analyzed.
Abstract: Deep learning is an essential method of machine learning. Deep learning is rapidly suitable for the most sophisticated stage of a technology, prominent to enriched performance in numerous medical applications. The latest growth in machine learning, specifically with respect to deep learning, aids in recognition, classification, and computation of patterns in medical images. The main aim of these improvements is the ability to derive feature representation from learned data rather than designing those features by hand from domain-specific knowledge. In deep learning, the bottom-level network represents a low-level feature representation while the top-level network represents the output feature information. The computation of a deep learning network is faster with cheap hardware. In this chapter, we present the essentials of deep learning methods with convolutional neural networks and analyze their achievements in medical image analysis, such as in deep feature representation, detection, segmentation, classification, and prediction. Finally, we conclude by a discussion of research challenges and indicate future directions for further enhancements.
Citations
More filters
TL;DR: Wang et al. as mentioned in this paper presented several deep classifiers based on the convolutional neural networks for the classification of SPECT bone images for the automated diagnosis of metastasis on which the SPECT imaging solely focuses.
Abstract: SPECT nuclear medicine imaging is widely used for treating, diagnosing, evaluating and preventing various serious diseases. The automated classification of medical images is becoming increasingly important in developing computer-aided diagnosis systems. Deep learning, particularly for the convolutional neural networks, has been widely applied to the classification of medical images. In order to reliably classify SPECT bone images for the automated diagnosis of metastasis on which the SPECT imaging solely focuses, in this paper, we present several deep classifiers based on the deep networks. Specifically, original SPECT images are cropped to extract the thoracic region, followed by a geometric transformation that contributes to augment the original data. We then construct deep classifiers based on the widely used deep networks including VGG, ResNet and DenseNet by fine-tuning their parameters and structures or self-defining new network structures. Experiments on a set of real-world SPECT bone images show that the proposed classifiers perform well in identifying bone metastasis with SPECT imaging. It achieves 0.9807, 0.9900, 0.9830, 0.9890, 0.9802 and 0.9933 for accuracy, precision, recall, specificity, F-1 score and AUC, respectively, on the test samples from the augmented dataset without normalization.
19 citations
TL;DR: A novel hybrid Convolutional Neural Network (CNN) model is proposed using three classification approaches and suggests that the proposed ensemble classifier using Support Vector Machine with Radial Basis Function and Logistic Regression classifiers has the best performance with 98.55% accuracy.
Abstract: Pneumonia is an acute respiratory infection that has led to significant deaths of people worldwide. This lung disease is more common in people older than 65 and children under five years old. Although the treatment of pneumonia can be challenging, it can be prevented by early diagnosis using Computer-Aided Diagnosis (CAD) systems. Chest X-Rays (CXRs) are currently the primary imaging tool for detection of pneumonia, which are widely used by radiologists. While the standard approach of detecting pneumonia is based on clinicians’ decisions, various Deep Learning (DL) methods have been developed for detection of pneumonia considering CAD system. In this regard, a novel hybrid Convolutional Neural Network (CNN) model is proposed using three classification approaches. In the first classification approach, Fully-Connected (FC) layers are utilized for the classification of CXR images. This model is trained for several epochs and the weights that result in the highest classification accuracy are saved. In the second classification approach, the trained optimized weights are utilized to extract the most representative CXR image features and Machine Learning (ML) classifiers are employed to classify the images. In the third classification approach, an ensemble of the proposed classifiers is created to classify CXR images. The results suggest that the proposed ensemble classifier using Support Vector Machine (SVM) with Radial Basis Function (RBF) and Logistic Regression (LR) classifiers has the best performance with 98.55% accuracy. Ultimately, this model is deployed to create a web-based CAD system to assist radiologists in pneumonia detection with a significant accuracy.
16 citations
TL;DR: A one-dimensional (1-D) deep convolutional generative adversarial network (DCGAN) is developed to generate artificial HRRPs and the experimental results show that the generated data are similar to the true HRRs and demonstrate that the proposed framework outperforms the state-of-the-art oversampling methods when handling the imbalanced problem.
Abstract: In radar high-resolution range profile (HRRP) recognition, the recognition accuracy will decline when the training samples in some classes (majority classes) greatly outnumbers other classes (minority classes). To alleviate the above imbalanced problem, an HRRP data augmentation framework is proposed. A one-dimensional (1-D) deep convolutional generative adversarial network (DCGAN) is developed to generate artificial HRRPs. The fidelity of the generated HRRPs is evaluated subjectively in the raw data domain and quantitatively by the similarity in the feature domain. The experimental results show that the generated data are similar to the true HRRPs and demonstrate that the proposed framework outperforms the state-of-the-art oversampling methods when handling the imbalanced problem.
9 citations
Cites background from "Medical Image Analysis With Deep Ne..."
...A CNN is a multiple-layer classifier that introduces the convolutional operator, and it can capture detailed features from the initial convolution layers and global features from the final layer [46]....
[...]
TL;DR: A defect detection system that automates the very labor-intensive and therefore time-heavy and expensive process of manually cataloging and evaluating fabrics for defects.
Abstract: Defect detection is a crucial step in textile and apparel quality control. An efficient defect detection system can ensure the overall quality of the processes and products that are acceptable to c...
7 citations
TL;DR: In this article , the authors introduce a next-generation annotation tool called NOVA for emotional behavior analysis, which implements a workflow that interactively incorporates the human in the loop, and it can easily be used by non-experts and lead to a high computer selfefficacy.
Abstract: In this article, we introduce a next-generation annotation tool called NOVA for emotional behaviour analysis, which implements a workflow that interactively incorporates the ‘human in the loop’. A main aspect of NOVA is the possibility of applying semi-supervised active learning where Machine Learning techniques are used already during the annotation process by giving the possibility to pre-label data automatically. Furthermore, NOVA implements recent eXplainable AI (XAI) techniques to provide users with both, a confidence value of the automatically predicted annotations, as well as visual explanations. We investigate how such techniques can assist non-experts in terms of trust, perceived self-efficacy, cognitive workload as well as creating correct mental models about the system by conducting a user study with 53 participants. The results show that NOVA can easily be used by non-experts and lead to a high computer self-efficacy. Furthermore, the results indicate that XAI visualisations help users to create more correct mental models about the machine learning system compared to the baseline condition. Nevertheless, we suggest that explanations in the field of AI have to be more focused on user-needs as well as on the classification task and the model they want to explain.
5 citations
References
More filters
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
Proceedings Article•
03 Dec 2012TL;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.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, 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. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
73,978 citations
Proceedings Article•
01 Jan 2015TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.
42,067 citations
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
40,257 citations