Robust Image Compression Algorithm for Video Capsule Endoscopy: A Review

As higher resolution sensors and fast readout sensors (FRS) emerge, the band width of pixel data to be transmitted from the sensor increases drastically in recent years. However, it becomes difficult to support the whole required band width, and compressing pixel data in the sensor can resolve this band width limitation. Currently there are few available Bayer compression algorithms for sensors. Even if we use the standard differential pulse coded modulation (DPCM), it is difficult to obtain the high quality image with meaningful compression ratio. We propose the new compression algorithm, Impulse Noise Immune Bayer Image Compression (INIBIC), which is a more efficient way to use it on sensor. Firstly, INIBIC is suitable for sensor owe to low complexity and low power. Secondly, INIBIC can accurately predict through direction estimation and minimize data loss at edges in images, and this accurate direction estimation induces high quality in image reconstruction even in higher compression ratio. Thirdly, INIBIC makes better compression through effective bit-allocation for bad pixels (BPs), which come from sensor defects and result in much loss in DPCM.

The problem of increasing the efficiency of coding of halftone images in the space of bit planes of differences in pixel values obtained using differential coding (DPCM – Differential pulse-code modulation) is considered. For a compact representation of DPCM pixel values, it is proposed to use a combined compression encoder that implements arithmetic coding and run-length coding. An arithmetic encoder provides high compression ratios, but has high computational complexity and significant encoding overhead. This makes it effective primarily for compressing the mean-value bit-planes of DPCM pixel values. Run-length coding is extremely simple and outperforms arithmetic coding in compressing long sequences of repetitive symbols that often occur in the upper bit planes of DPCM pixel values. For DPCM bit planes of pixel values of any image, a combination of simple run length coders and complex arithmetic coders can be selected that provides the maximum compression ratio for each bit plane and all planes in general with the least computational complexity. As a result, each image has its own effective combined encoder structure, which depends on the distribution of bits in the bit planes of the DPCM pixel values. To adapt the structure of the combined encoder to the distribution of bits in the bit planes of DPCM pixel values, the article proposes to use prediction of the volume of arithmetic code based on entropy and comparison of the obtained predicted value with the volume of run length code. The entropy is calculated based on the values of the number of repetitions of ones and zero symbols, which are obtained as intermediate results of the run length encoding. This does not require additional computational costs. It was found that in comparison with the adaptation of the combined encoder structure using direct determination of the arithmetic code volume of each bit plane of DPCM pixel values, the proposed encoder structure provides a significant reduction in computational complexity while maintaining high image compression ratios.

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).

Now it is a tedious work for clinicians to interpret the images acquired by wireless endoscopy system, and a viable solution is to construct a map, which is the two- dimensional representation of gastrointestinal (GI) tract, to reduce the redundancy of images and improve the understandability of them. But it is difficult for traditional wireless endoscopy system to realize image capture with wide field of view and so it is difficult to generate the map of GI tract. A wireless Micro-Ball endoscopy system makes the full view image capture possible. Then image registration is a key technology for constructing the map. This paper discusses and analyzes two key problems on image registration in detail for Micro-Ball endoscopy system. A two-threshold criterion is proposed for determining the possibility of valid registration between two images, and a MSE approach is also given out to appropriately decide the registration direction in the final step of registration process.

Wireless capsule endoscopy has become a common procedure for diagnostic inspection of gastrointestinal tract. This method offers a less-invasive alternative to traditional endoscopy and provides the opportunity for exploring inaccessible areas of the small intestine. Current capsule endoscopes, however, move by peristalsis and are not capable of detailed and on-demand inspection of desired locations. Here, we propose and develop two wireless endoscopes with maneuverable vision systems to enhance diagnosis of gastrointestinal disorders. The vision systems in these capsules are equipped with mechanical actuators to adjust the position of the camera. This may help to cover larger areas of the digestive tract and investigate desired locations.

In this paper, a two-dimensional to three-dimensional mapping of the wireless capsule endoscopy (WCE) images is proposed as well as the alignment of the consecutive images. The aim of this project is to reduce the diagnosis time of the doctor using the acquired data. This paper resolves a serious limitation of the inverse projection of the WCE images appeared previously. The novelty of this paper lies in three aspects. Firstly, as the main axis of the WCE is not always aligned with the center of the small bowel, the angle needs to be adjusted to obtain better visual effect. The inverse projected images considering the angle of the WCE are obtained from the innovative mathematical model proposed in this project. After compensating the angle, all the information in the interior wall of the small intestine will be clearly presented. Secondly, the redundancy of the images captured along a trajectory, where, they share a portion of overlapped information is exploited by motion estimation to enhance the final resolution. Therefore, doctors do not need to inspect the same region of the images without any benefit and the diagnosis time is significantly decreased. Finally, the cropped segments are merged into a single image which can fully represent the interior wall of the small intestine.

Video Capsule Endoscopy: What Is the Future?

Safety of capsule endoscopy in patients with pacemakers

This paper presents a methodology for detecting abnormal patterns in wireless capsule endoscopy (WCE) images. In particular, an average of 50,000 images are obtained during an WCE exam. Usually, these images are reviewed in a form of a video at speeds between 5 to 40 image-frames/sec. The time spent by a physician reading the results of WCE images varies between 45 to 180 minutes. This presents a major problem which is the reading process that consumes a significant amount of time and the results take several days before they become available since the physician has to find the time to study each video uninterrupted for up to 3 hours. The methodology presented here is based on the automatic detection of abnormal WCE patterns in an effort for reducing the reading time of the WCE images and the cost of the procedure as well. The methodology consists of a synergistic integration of image processing, analysis and recognition techniques for achieving the automatic detection of the WCE abnormal patterns.

Background and study aims When capsule endoscopy (CE) detects a small bowel (SB) target lesion that may be manageable with enteroscopy, the selection of the insertion route is critical. Time- and progression-based CE indices have been proposed for localization of SB lesions. This systematic review analysed the role of CE transit indicators in choosing the insertion route for double-balloon enteroscopy (DBE). Methods A comprehensive literature search identified papers assessing the role of CE on the choice of the route selection for DBE. Data on CE, criteria for route selection, and DBE success parameters were retrieved and analyzed according to the PRISMA statement. Risk of bias was assessed through the STROBE assessment. The primary outcome evaluated was DBE success rate in reaching a SB lesion, measured as the ratio of positive initial DBE to the number of total DBE. Results Seven studies including 262 CEs requiring subsequent DBE were selected. Six studies used time-based indices and one used the PillCam Progress indicator. SB lesions were identified and insertion route was selected according to a specific cut-off, using fixed landmarks for defining SB transit except for one study in which the mouth-cecum transit was considered. DBE success rate was high in all studies, ranging from 78.3 % to 100 %. Six of seven studies were high quality. Conclusions The precise localization of SB lesions remains an open issue, and larger studies are required to determine the most accurate index for selecting the DBE insertion route. In the future, 3 D localization technologies and tracking systems will be essential to accomplish this tricky task.

This paper presents a method for detecting bleeding and tumors within capsule endoscopy (CE) images. Because CE can be used for visual, non-invasive examinations of the small bowel, it has recently become widely used. However, as a capsule progresses along the gastrointestinal tract, it collects vast quantities of images that make diagnosis a very time-consuming task. To address this problem, many computational approaches for anomaly detection have been proposed. Common to most approaches is the belief that color, texture, and shape are the most promising features for detecting anomalies within CE images. However, given that the requirements for each type of feature vary according to the anomaly, generally, it is essential to apply a complicated combination of techniques for multiple-feature extraction. In this study, in order to realize a scheme that covers the features of color, texture, and shape and can be applied to lesion areas of various sizes, a geometric image feature called local-contrast-enhanced higher-order local auto-correlation (LCE-HLAC) is proposed. Moreover, although the HSV color space is generally regarded as being appropriate for the analysis of CE images, imbalances in the distributions of utilized hue components limit discriminatory performance for normal and anomalous images. Accordingly, an image pre-processing method that uses a non-linear conversion model for the HSV color space is also proposed. Anomaly detection is implemented using a support vector machine classifier. The results of experiments, conducted with normal, bleeding, and tumor images obtained from 28 patients, demonstrate both the feasibility and superiority of the proposed method for both bleeding and tumor detection tasks.

Wireless capsule endoscopy (WCE) is a new technology for small bowel imaging. To report our initial experience with sensitivity of high quality enteroclysis in patients with small bowel ulcers detected by WCE. Medical records of all patients referred for WCE from December, 2001 to April, 2002 at our institution were reviewed. All patients had negative upper and lower endoscopies and small bowel barium studies before WCE. There were 40 patients (19 female, mean age 57.3 yr) during this study period. Three patients had multiple small bowel ulcers detected by WCE. One with ileal ulcers and abdominal pain had an enteroclysis at another hospital before WCE. Review of the study at our institution showed that it was of excellent quality and was normal. Two patients with chronic iron deficiency anemia had multiple small bowel ulcers and were referred after WCE for a repeat small bowel barium study by biphasic enteroclysis performed by experienced GI radiologists. The radiologists were told in advance of the WCE findings. Both studies were considered technically to be of perfect quality. Despite this, both studies were negative. All 3 patients improved after therapy for Crohn's disease. Our data indicates that WCE may be more sensitive for small bowel ulcers than the best enteroclysis available.

With the development of wireless capsule endoscopy (WCE) and its extensive applications in clinic, doctors need to spend more time on reviewing the WCE images for lesions diagnosis. Therefore, automatic lesion detection for WCE has gradually become a research hotspot, which aims to reduce the pressure of doctors and improves the diagnosis efficiency. Many researchers adopted the traditional machine learning method to realize polyp detections, however, these methods need to extract the features manually, which were unable to find higher features of WCE images. So, in this study, we proposed a novel method that based on convolution neural network (CNN) to automatically recognize polyp in small bowel WCE image. We utilized the Alexnet architecture, one of the classical CNN, to extract the features of WCE images and classify polyp images from normal ones. We selected 14408 images from different patients, including 408 polyp images and 14000 normal images. Since the amount of initial polyp images is small, then, we did the data augmentation, including rotation, luminance change, blurring, and noise. At last the experimental results demonstrated that the method we proposed had a promising performance in polyp detection, whose accuracy, sensitivity and specificity can reach at 99.88%, 99.40% and 99.93%, respectively. Additionally, we evaluated ROC curve and its AUC value, which further confirmed that our model has a high accuracy and reliability in polyp detection. This proposed method has great potential to be used in the clinical examination to help doctors from the tedious image reviewing work.

Image compression is the technique of reducing the number of bits required to represent a digital image, which can be accomplished by reducing the redundant and visually irrelevant information present in the images. In this study, a Wavelet Difference Reduction (WDR) coding based image compression technique is proposed which uses Principal Component Analysis (PCA). These techniques are combined in order to achieve high compression ratio with an acceptable degradation in the compressed images. The input image is first compressed using PCA. Few of the Principal Components are used to reconstruct the image. The reconstructed image obtained by PCA is further used as an input data for WDR compression. Since WDR is a wavelet based coding technique so it exploits local characteristics of the image and leads to high Compression Ratio (CR). Here, PCA and WDR are combined because PCA gives high image quality but low CR on the other hand WDR works opposite of it as it gives high CR. The proposed technique is applied on several test images and results are compared with WDR and JPEG2000 techniques. Results clearly show that the proposed technique is better than the existing techniques in terms of both objective and subjective fidelity criteria.

Images include information about human body which is used for different purpose such as medical examination security and other plans Compression of images is used in some applications such as profiling information and transmission systems. Regard to importance of images information, lossless or loss compression is preferred. Lossless compressions are JPEG, JPEG-LS and JPEG2000 are few well-known methods for lossless compression. We will use differential pulse code modulation for image compression with Huffman encoder, which is one of the latest and provides good compression ratio, peak signal to noise ratio and minimum mean square error. In real time application which needs hardware implementation, low complex algorithm accelerate compression process. In this paper, we use differential pulse code modulation for image compression lossless and near-lossless compression method is introduced which is efficient due to its high compression ratio and simplicity. This method is consists of a new transformation method called Enhanced DPCM Transformation (EDT) which has a good energy compaction and a suitable Huffman encoding. After introducing this compression method it is applied on different images from Corel dataset for experimental results and analysis. Also we compare it with other existing methods with respect to parameter compression ratio, peak signal noise ratio and mean square error.