Khan A. Wahid

Efficient hardware implementation of an image compressor for wireless capsule endoscopy applications

The paper presents an area- and power-efficient implementation of an image compressor for wireless capsule endoscopy application. The architecture uses a direct mapping to compute the two-dimensional discrete cosine transform which eliminates the need of transpose operation and results in reduced area and low processing time. The algorithm has been modified to comply with the JPEG standard and the corresponding quantization tables have been developed and the architecture is implemented using the CMOS 0.18um technology. The processor costs less than 3.5k cells, runs at a maximum frequency of 150 MHz, and consumes 10 mW of power. The test results of several endoscopic colour images show that higher compression ratio (over 85%) can be achieved with high quality image reconstruction (over 30 dB).

Automated Bleeding Detection in Capsule Endoscopy Videos Using Statistical Features and Region Growing

Wireless Capsule Endoscopy (WCE) is a technology in the field of endoscopic imaging which facilitates direct visualization of the entire small intestine. Many algorithms are being developed to automatically identify clinically important frames in WCE videos. This paper presents a supervised method for automated detection of bleeding regions present in WCE frames or images. The proposed method characterizes the image regions by using statistical features derived from the first order histogram probability of the three planes of RGB color space. Despite being inconsistent and tiresome, manual selection of regions has been a popular technique for creating training data in the studies of capsule endoscopic images. We propose a semi-automatic region-annotation algorithm for creating training data efficiently. All possible combinations of different features are exhaustively analyzed to find the optimum feature set with the best performance. During operation, regions from images are obtained by applying a segmentation method. Finally, a trained neural network recognizes the patterns of the data arising from bleeding and non-bleeding regions.

Low Power and Low Complexity Compressor for Video Capsule Endoscopy

The main challenge in video capsule endoscopic system is to reduce the area and power consumption while maintaining acceptable video reconstruction. In this paper, a subsample-based data compressor for video endoscopy application is presented. The algorithm is developed around the special features of endoscopic images that consists of a differential pulse-coded modulation (DPCM) followed by Golomb-Rice coding. Based on the nature of endoscopic images, several subsampling schemes on the chrominance components are applied. This video compressor is designed in a way to work with any commercial low-power image sensors that outputs image pixels in a raster scan fashion, eliminating the need of memory buffer and temporary storage (as needed in transform coding schemes). An image corner clipping algorithm is also introduced. The reconstructed images have been verified by five medical doctors for acceptability. The proposed low-complexity design is implemented in a 0.18 μm CMOS technology and consumes 592 standard cells, 0.16 × 0.16 mm silicon area, and 42 μW of power. Compared to other algorithms targeted to video capsule endoscopy, the proposed raster-scan-based scheme performs strongly with a compression ratio of 80% and a very high reconstruction peak signal-to-noise ratio (over 48 dB).

Hybrid DWT-DCT algorithm for biomedical image and video compression applications

Digital image and video in their raw form require an enormous amount of storage capacity. Considering the important role played by digital imaging and video in medical and health science, it is necessary to develop a system that produces high degree of compression while preserving critical image/video information. In this paper, we present a hybrid algorithm that performs the discrete cosine transform on the discrete wavelet transform coefficients. Simulation has been carried out on several medical and endoscopic images and videos. The results show that the proposed hybrid algorithm performs much better in term of peak-signal-to-noise-ratio with a higher compression ratio compared to standalone DCT and DWT algorithms. The scheme is intended to be used as the image/video compressor engine in medical imaging and video applications, such as, telemedicine and wireless capsule endoscopy.

Improved Compressed Sensing-Based Algorithm for Sparse-View CT Image Reconstruction

In computed tomography (CT), there are many situations where reconstruction has to be performed with sparse-view data. In sparse-view CT imaging, strong streak artifacts may appear in conventionally reconstructed images due to limited sampling rate that compromises image quality. Compressed sensing (CS) algorithm has shown potential to accurately recover images from highly undersampled data. In the past few years, total-variation-(TV-) based compressed sensing algorithms have been proposed to suppress the streak artifact in CT image reconstruction. In this paper, we propose an efficient compressed sensing-based algorithm for CT image reconstruction from few-view data where we simultaneously minimize three parameters: the ℓ 1 norm, total variation, and a least squares measure. The main feature of our algorithm is the use of two sparsity transforms—discrete wavelet transform and discrete gradient transform. Experiments have been conducted using simulated phantoms and clinical data to evaluate the performance of the proposed algorithm. The results using the proposed scheme show much smaller streaking artifacts and reconstruction errors than other conventional methods.

Bleeding detection in wireless capsule endoscopy based on color features from histogram probability

This paper presents a novel technique for detecting bleeding regions in capsule endoscopy images. The proposed algorithm extracts color features from image-regions by calculating mean, standard deviation, skew and energy from the first order histogram of the RGB planes separately. Through the use of RGB color space, three times more number of features can be obtained than while using a grayscale image. Such color features have been used in content based retrieval system in pathology images. However, in spite of simplicity and ease of calculation, these features have not yet been studied in the classification of bleeding and non-bleeding regions in capsule endoscopic images. This paper studies the feasibility of using these features by assessing all possible feature subsets through the use of classification accuracy. The proposed algorithm could obtain classification accuracy up to 89%.

Compressed sensing-based MRI reconstruction using complex double-density dual-tree DWT

Undersampling k-space data is an efficient way to speed up the magnetic resonance imaging (MRI) process. As a newly developed mathematical framework of signal sampling and recovery, compressed sensing (CS) allows signal acquisition using fewer samples than what is specified by Nyquist-Shannon sampling theorem whenever the signal is sparse. As a result, CS has great potential in reducing data acquisition time in MRI. In traditional compressed sensing MRI methods, an image is reconstructed by enforcing its sparse representation with respect to a basis, usually wavelet transform or total variation. In this paper, we propose an improved compressed sensing-based reconstruction method using the complex double-density dual-tree discrete wavelet transform. Our experiments demonstrate that this method can reduce aliasing artifacts and achieve higher peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) index.

A statistical feature based novel method to detect bleeding in wireless capsule endoscopy images

Wireless capsule endoscopy (WCE) is a recently developed technology to detect small intestine diseases, such as bleeding. In this paper, a scheme for automatic bleeding detection from WCE video is proposed based on different statistical measures computed from a new red to green (R/G) pixel ratio intensity plane of RGB color images. Different statistical parameters, namely mean, mode, maximum, minimum, skewness, median, variance, and kurtosis are used to extract variation in spatial characteristics in R/G intensity plane of bleeding and non-bleeding WCE RGB images. Depending on the ability to provide significantly distinguishable characteristics, in the proposed feature vector, median, variance, and kurtosis of R/G ratio values corresponding to a WCE image are considered. For the purpose of classification, K-nearest neighbor (KNN) classifier is employed. From extensive experimentation on several WCE videos collected from a publicly available database, it is observed that the proposed method can successfully detect bleeding and non-bleeding images with high level of accuracy, sensitivity and specificity in comparison to that of some of the existing methods.

Lossless and low-power image compressor for wireless capsule endoscopy

We present a lossless and low-complexity image compression algorithm for endoscopic images. The algorithm consists of a static prediction scheme and a combination of golomb-rice and unary encoding. It does not require any buffer memory and is suitable to work with any commercial low-power image sensors that output image pixels in raster-scan fashion. The proposed lossless algorithm has compression ratio of approximately 73% for endoscopic images. Compared to the existing lossless compression standard such as JPEG-LS, the proposed scheme has better compression ratio, lower computational complexity, and lesser memory requirement. The algorithm is implemented in a 0.18 µm CMOS technology and consumes 0.16mm × 0.16mm silicon area and 18 µW of power when working at 2 frames per second.

Automatic bleeding detection in wireless capsule endoscopy based on RGB pixel intensity ratio

Wireless capsule endoscopy (WCE) is one of the most effective technologies to diagnose gastrointestinal (GI) diseases, such as bleeding in GI tract. Because of long duration of WCE video containing large number images, it is a burden for clinician to detect diseases in real time. In this paper, an automatic bleeding image detection method is proposed utilizing the variation of pixel intensities in RGB color planes. Based on statistical behavior of bleeding and non-bleeding pixel intensities in terms of pixel intensity ratio in different planes, distinguishing color texture feature of an image is developed. Support vector machine (SVM) classifier is employed to detect bleeding and non-bleeding images from WCE videos. From extensive experimentation on real time WCE video recordings, it is found that the proposed method can accurately detect bleeding images with high sensitivity and specificity.