Amin Khatami

Medical image analysis using wavelet transform and deep belief networks

Abstract This paper introduces a three-step framework for classifying multiclass radiography images. The first step utilizes a de-noising technique based on wavelet transform (WT) and the statistical Kolmogorov Smirnov (KS) test to remove noise and insignificant features of the images. An unsupervised deep belief network (DBN) is designed for learning the unlabelled features in the second step. Although small-scale DBNs have demonstrated significant potential, the computational cost of training the restricted Boltzmann machine is a major issue when scaling to large networks. Moreover, noise in radiography images can cause a significant corruption of information that hinders the performance of DBNs. The combination of WT and KS test in the first step helps improve performance of DBNs. Discriminative feature subsets obtained in the first two steps serve as inputs into classifiers in the third step for evaluations. Five frequently used classifiers including naive Bayes, radial basis function network, random forest, sequential minimal optimization, and support vector machine and four different case studies are implemented for experiments using the Image Retrieval in Medical Application data set. The experimental results show that the three-step framework has significantly reduced computational cost and yielded a great performance for multiclass radiography image classification. Along with effective applications in image processing in other fields published in the literature, deep learning network in this paper has again demonstrated its robustness in handling a complex set of medical images. This implies that the proposed approach can be implemented in real practice for analysing noisy radiography images, which have many useful medical applications such as diagnosis of diseases related to lung, breast, musculoskeletal or pediatric studies.

A new PSO-based approach to fire flame detection using K-Medoids clustering

Colour space with a linear multiplication of a conversion matrix and colour features.A contrast enhancement method is performed on RGB images before conversion.PSO and sample pixels obtain weights of the colour-differentiator conversion matrix.K-medoids provides a fitness metric for the PSO procedure. Automated computer vision-based fire detection has gained popularity in recent years, as every fire detection needs to be fast and accurate. In this paper, a new fire detection method using image processing techniques is proposed. We explore how to create a fire flame-based colour space via a linear multiplication of a conversion matrix and colour features of a sample image. We show how the matrix multiplication can result in a differentiating colour space, in which the fire part is highlighted and the non-fire part is dimmed. Particle Swarm Optimization (PSO) and sample pixels from an image are used to obtain the weights of the colour-differentiating conversion matrix, and K-medoids provides a fitness metric for the PSO procedure. The obtained conversion matrix can be used for fire detection on different fire images without performing the PSO procedure. This allows a fast and easy implementable fire detection system. The empirical results indicate that the proposed method provides both qualitatively and quantitatively better results when compared to some of the conventional and state-of-the-art algorithms.

A Wavelet Deep Belief Network-Based Classifier for Medical Images

Accurately and quickly classifying high dimensional data using machine learning and data mining techniques is problematic and challenging. This paper proposes an efficient and effective technique to properly extract high level features from medical images using a deep network and precisely classify them using support vector machine. A wavelet filter is applied at the first step of the proposed method to obtain the informative coefficient matrix of each image and to reduce dimensionality of feature space. A four-layer deep belief network is also utilized to extract high level features. These features are then fed to a support vector machine to perform accurate classification. Comparative empirical results demonstrate the strength, precision, and fast-response of the proposed technique.

A deep-structural medical image classification for a Radon-based image retrieval

Content-based image retrieval is an effective and efficient technique to retrieve images from a big dataset with similar images. To have a robust retrieval system, a proper and accurate classification scheme is required to categorise the information of shape, texture, and colours. In this paper, a deep convolutional neural network is proposed to classify the information of radiology images. Deep networks need millions of data, but the lack of availability of balanced large datasets in medical domain motivates us to trust on even the second prediction category rather than just the best one. Hence the best predicted categories are considered for a query test, followed by a similarity-based search technique. This results in a proper classification performance. Moreover, as Radon transformation is famous in medical domain, this conversion technique is utilized for a similarity-based search scheme, after measuring by a k-nearest neighbours algorithm. The experimental results and comparison show that this strategy not only improve the performance, but also save the computational costs.

A sequential search-space shrinking using CNN transfer learning and a Radon projection pool for medical image retrieval

Abstract Closing the semantic gap in medical image analysis is critical. Access to large-scale datasets might help to narrow the gap. However, large and balanced datasets may not always be available. On the other side, retrieving similar images from an archive is a valuable task to facilitate better diagnosis. In this work, we concentrate on forming a search space, consisting of the most similar images for a given query, to be used for a similarity-based search technique in a retrieval system. We propose a two-step hierarchical shrinking search space when local binary patterns are used. Transfer learning via convolutional neural networks is utilized for the first stage of search space shrinking, followed by creating a selection pool using Radon transform for further reduction. The difference between two orthogonal Radon projections is considered in the selection pool to extract more information. The IRMA dataset, from ImageCLEF initiative, containing 14,400 X-ray images, is used to validate the proposed scheme. We report a total IRMA error of 168.05 (or 90.30% accuracy) which is the best result compared with existing methods in the literature for this dataset when real-time processing is considered.

A Particle Swarm Optimization-based washout filter for improving simulator motion fidelity

The washout filter for a driving simulator is able to regenerate high fidelity vehicle translational and rotational motions within the simulators physical limitations and return the simulator platform back to its initial position. The classical washout filter provides a popular solution that has been broadly utilized in different commercial simulators due to its simplicity, short processing time, and reasonable performance. One limitation of the classical washout filter is its sub-optimal parameter tuning process, which is based on the trial-and-error method. This leads to an inefficient workspace usage and, consequently, generation of false motion cues that lead to simulator sickness. Ignorance of a human sensation model in its design is another drawback of classical washout filters. The purpose of this study is to use Particle Swarm Optimization (PSO) to design and tune the washout filter parameters, in order to increase motion fidelity, decrease the human sensation error, and improve efficiency of the workspace usage. The proposed PSO-based washout filter is designed and implemented using the MATLAB/Simulink software package. The results indicate the effectiveness of the PSO-based washout filter in reducing the human sensation error, increasing the capability of reference shape tracking, and improving efficiency of the workspace usage.

A New Color Space Based on K-Medoids Clustering for Fire Detection

Pixel color has proven to be a useful and robust cue for detection of most objects of interest like fire. In this paper, a hybrid intelligent algorithm is proposed to detect fire pixels in the background of an image. The proposed algorithm is introduced by the combination of a computational search method based on a swarm intelligence technique and the Kemdoids clustering method in order to form a Fire-based Color Space (FCS), in fact, the new technique converts RGB color system to FCS through a 3*3 matrix. This algorithm consists of five main stages:(1) extracting fire and non-fire pixels manually from the original image. (2) using K-medoids clustering to find a Cost function to minimize the error value. (3) applying Particle Swarm Optimization (PSO) to search and find the best W components in order to minimize the fitness function. (4) reporting the best matrix including feature weights, and utilizing this matrix to convert the all original images in the database to the new color space. (5) using Otsu threshold technique to binarize the final images. As compared with some state-of-the-art techniques, the experimental results show the ability and efficiency of the new method to detect fire pixels in color images.

An efficient hybrid algorithm for fire flame detection

Proposing efficient methods for fire protection is becoming more and more important, because a small flame of fire may cause huge problems in social safety. In this paper, an effective fire flame detection method is investigated. This fire detection method includes four main stages: in the first step, a linear transformation is applied to convert red, green, and blue (RGB) color space through a 3*3 matrix to a new color space. In the next step, fuzzy c-mean clustering method (FCM) is used to distinguish between fire flame and non-fire flame pixels. Particle Swarm Optimization algorithm (PSO) is also utilized in the last step to decrease the error value measured by FCM after conversion. Finally, we apply Otsu threshold method to the new converted images to make a binary picture. Empirical results show the strength, accuracy and fast-response of the proposed algorithm in detecting fire flames in color images.

A Haptics Feedback Based-LSTM Predictive Model for Pericardiocentesis Therapy Using Public Introperative Data

Proposing a robust and fast real-time medical procedure, operating remotely is always a challenging task, due mainly to the effect of delay and dropping of the speed of networks, on operations. If a further stage of prediction is properly designed on remotely operated systems, many difficulties could be tackled. Hence, in this paper, an accurate predictive model, calculating haptics feedback in percutaneous heart biopsy is investigated. A one-layer Long Short-Term Memory based (LSTM-based) Recurrent Neural Network, which is a natural fit for understanding haptics time series data, is utilised. An offline learning procedure is proposed to build the model, followed by an online procedure to operate on new experiments, remotely fed to the system. Statistical analyses prove that the error variation of the model is significantly narrow, showing the robustness of the model. Moreover, regarding computational costs, it takes 0.7 ms to predict a time step further online, which is quick enough for real-time haptic interaction.

Parallel Deep Solutions for Image Retrieval from Imbalanced Medical Imaging Archives

Abstract Learning and extracting representative features along with similarity measurements in high dimensional feature spaces is a critical task. Moreover, the problem of how to bridge the semantic gap, between the low-level information captured by a machine learning model and the high-level one interpreted by a human operator, is still a practical challenge, especially in medicine. In medical applications, retrieving similar images from archives of past cases can be immensely beneficial in diagnostic imaging. However, large and balanced datasets may not be available for many reasons. Exploring the ways of using deep networks, for classification to retrieval, to fill this semantic gap was a key question for this research. In this work, we propose a parallel deep solution approach based on convolutional neural networks followed by a local search using LBP, HOG and Radon features. The IRMA dataset, from ImageCLEF initiative, containing 14,400 X-ray images, is employed to validate the proposed scheme. With a total IRMA error of 165.55, the performance of our scheme surpasses the dictionary approach and many other learning methods applied on the same dataset.