A modular and programmable development platform for capsule endoscopy system.

In this paper, a new low complexity and lossless image compression system for capsule endoscopy (CE) is presented. The compressor consists of a low-cost YEF color space converter and variable-length predictive with a combination of Golomb-Rice and unary encoding. All these components have been heavily optimized for low-power and low-cost and lossless in nature. As a result, the entire compression system does not incur any loss of image information. Unlike transform based algorithms, the compressor can be interfaced with commercial image sensors which send pixel data in raster-scan fashion that eliminates the need of having large buffer memory. The compression algorithm is capable to work with white light imaging (WLI) and narrow band imaging (NBI) with average compression ratio of 78% and 84% respectively. Finally, a complete capsule endoscopy system is developed on a single, low-power, 65-nm field programmable gate arrays (FPGA) chip. The prototype is developed using circular PCBs having a diameter of 16 mm. Several in-vivo and ex-vivo trials using pig's intestine have been conducted using the prototype to validate the performance of the proposed lossless compression algorithm. The results show that, compared with all other existing works, the proposed algorithm offers a solution to wireless capsule endoscopy with lossless and yet acceptable level of compression.

This study aimed to compare the diagnostic effectiveness of narrow band imaging and autofluorescence imaging for malignant laryngopharyngeal tumours. Between May 2010 and October 2010, 50 consecutive patients with suspected laryngopharyngeal tumour underwent endoscopic laryngopharynx examination. The morphological characteristics of laryngopharyngeal lesions were analysed using high performance endoscopic systems equipped with narrow band imaging and autofluorescence imaging modes. The diagnostic effectiveness of white light image, narrow band imaging and autofluorescence imaging endoscopy for benign and malignant laryngopharyngeal lesions was evaluated. Under narrow band imaging endoscopy, the superficial microvessels of squamous cell carcinomas appeared as dark brown spots or twisted cords. Under autofluorescence imaging endoscopy, malignant lesions appeared as bright purple. The sensitivity of malignant lesion diagnosis was not significantly different between narrow band imaging and autofluorescence imaging modes, but was better than for white light image endoscopy (χ2 = 12.676, p = 0.002). The diagnostic specificity was significantly better in narrow band imaging mode than in both autofluorescence imaging and white light imaging mode (χ2 = 8.333, p = 0.016). Narrow band imaging endoscopy is the best option for the diagnosis and differential diagnosis of laryngopharyngeal tumours.

1278 NARROW BAND IMAGING DIGITAL FLEXIBLE URETEROSCOPY IN DETECTION OF THE UPPER URINARY TRACT TRANSITIONAL CELL CARCINOMA: INITIAL EXPERIENCE

Narrow Band Imaging in Gynecology

What's known on the subject? and What does the study add? In recent years, more attention has focused on the role of narrow band imaging (NBI) in bladder cancer detection and NBI technology has spread rapidly. It is an important method for diagnosing new or recurrent bladder cancer. But its diagnostic accuracy is still uncertain. This paper summarizes the diagnostic accuracy of NBI in bladder cancer and compares NBI with white light imaging. The results show that NBI cystoscopy significantly improves the detection accuracy in bladder cancer, compared with white light imaging. However, some limitations still exist. Multicentre randomized studies are recommended to determine whether the visual advantages of NBI can translate into real therapeutic benefit for individual patients. • To assess the test performance and clinical effectiveness of narrow band imaging (NBI) cystoscopy compared with white light imaging (WLI) cystoscopy in people suspected of new or recurrent bladder cancer. • Literature on NBI cystoscopy in the diagnosis of bladder cancer was searched in PubMed, EMBASE, Cochrane Library, MEDLINE and CNKI, with hand searching of relevant congress abstracts and journals. • The literature was selected according to inclusion and exclusion criteria. The Meta-DiSc1.4 software was used to review management and analysis. • Eight studies including 1022 patients assessed test performance. • On a per-person analysis, the pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio and diagnostic odds ratio of NBI and WLI were respectively 0.943 (95% CI 0.914-0.964) and 0.848 (95% CI 0.803-0.885), 0.847 (95% CI 0.812-0.878) and 0.870 (95% CI 0.831-0.903), 7.038 (95% CI 3.357-14.754) and 6.938 (95% CI 2.052-23.465), 0.054 (95% CI 0.012-0.237) and 0.181 (95% CI 0.091-0.361), and 185.32 (95% CI 45.714-751.26) and 42.931 (95% CI 8.088-227.88). • The area under the curve and Q* of NBI and WLI were respectively 0.9781 and 0.8944, and 0.9337 and 0.8253. • For the characterization of carcinoma in situ, the pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio and diagnostic odds ratio of NBI were 0.927 (95% CI 0.878-0.960), 0.768 (95% CI 0.730-0.802), 4.545 (95% CI 2.820-7.325), 0.125 (95% CI 0.051-0.304) and 48.884 (95% CI 15.642-152.77) on a per-person analysis. • The area under the curve and Q* were 0.9391 and 0.8763. • NBI is an effective method for the identification of abnormal lesions including carcinoma in situ and can provide higher diagnostic precision of bladder cancer than WLI.

Previous studies have yielded conflicting results on the colonic polyp detection rate with narrow-band imaging (NBI) compared with white-light imaging (WLI). We compared the mean number of colonic polyps detected per patient for NBI versus WLI using a next-generation NBI system (EVIS LUCERA ELITE; Olympus Medical Systems) used with standard-definition (SD) colonoscopy and wide-angle (WA) colonoscopy. this study is a 2 × 2 factorial, prospective, multicenter randomized controlled trial. this study was conducted at five academic centers in Japan. patients were allocated to one of four groups: (1) WLI with SD colonoscopy (H260AZI), (2) NBI with SD colonoscopy (H260AZI), (3) WLI with WA colonoscopy (CF-HQ290), and (4) NBI with WA colonoscopy (CF-HQ290). the mean numbers of polyps detected per patient were compared between the four groups: WLI with/without WA colonoscopy and NBI with/without WA colonoscopy. Of the 454 patients recruited, 431 patients were enrolled. The total numbers of polyps detected by WLI with SD, NBI with SD, WLI with WA, and NBI with WA were 164, 176, 188, and 241, respectively. The mean number of polyps detected per patient was significantly higher in the NBI group than in the WLI group (2.01 vs 1.56; P = 0.032). The rate was not higher in the WA group than in the SD group (1.97 vs 1.61; P = 0.089). Although WA colonoscopy did not improve the polyp detection, next-generation NBI colonoscopy represents a significant improvement in the detection of colonic polyps.

A Prospective Study for Differential Diagnosis of Gastric Small Depressive Lesions By Narrow Band Imaging (NBI) Combined with Magnifying Endoscopy

To characterize the appearance of normal and malignant upper urinary tract lesion appearance under narrow-band imaging (NBI) using the new URF-V digital flexible ureteroscope (DFU), and to determine if NBI, when used in conjunction with white light (WL), could improve detection of malignancy. NBI and WL were performed in 27 patients at our university teaching hospital, 14 with known cases of upper urinary tract transitional-cell carcinoma (UUT-TCC) as follow-up (group A), and 13 patients with first-suspicion of cancer (group B). Full renal collecting system examination was performed first under WL and then under NBI by a single urologist. Biopsies were taken from all detected lesions using the biopsy forceps and sent for examination by a pathologist who was blinded to the gross description of the lesion. Pathology interpretations were then compared with the corresponding WL and NBI images. Holmium laser vaporization was performed for all apparent lesions. Subjectively, NBI significantly improved the endoscopic visualization of the tumors, providing a detailed description of their limits and vascular architecture. Objectively, five additional tumors (14.2%) in four patients, as well the extended limits of three tumors (8.5%) in three patients were detected by NBI when findings by WL imaging were considered normal. This is one of the first reports regarding NBI for UUT-TCC. From this study, we recommend this technology as a valuable diagnostic method, because it considerably improves tumor detection rate by 22.7% compared with WL.

BACKGROUNDOlympus Corporation has developed texture and color enhancement imaging (TXI) as a novel image-enhancing endoscopic technique.AIMTo investigate the effectiveness of TXI in identifying colorectal adenomas using magnifying observation.METHODSColorectal adenomas were observed by magnified endoscopy using white light imaging (WLI), TXI, narrow band imaging (NBI), and chromoendoscopy (CE). This study adopted mode 1 of TXI. Adenomas were confirmed by histological examination. TXI visibility was compared with the visibility of WLI, NBI, and CE for tumor margin, and vessel and surface patterns of the Japan NBI expert team (JNET) classification. Three expert endoscopists and three non-expert endoscopists evaluated the visibility scores, which were classified as 1, 2, 3, and 4.RESULTSSixty-one consecutive adenomas were evaluated. The visibility score for tumor margin of TXI (3.47 ± 0.79) was significantly higher than that of WLI (2.86 ± 1.02, P < 0.001), but lower than that of NBI (3.76 ± 0.52, P < 0.001), regardless of the endoscopist’s expertise. TXI (3.05 ± 0.79) had a higher visibility score for the vessel pattern of JNET classification than WLI (2.17 ± 0.90, P < 0.001) and CE (2.47 ± 0.87, P < 0.001), but lower visibility score than NBI (3.79 ± 0.47, P < 0.001), regardless of the experience of endoscopists. For the visibility score for the surface pattern of JNET classification, TXI (2.89 ± 0.85) was superior to WLI (1.95 ± 0.79, P < 0.01) and CE (2.75 ± 0.90, P = 0.002), but inferior to NBI (3.67 ± 0.55, P < 0.001).CONCLUSIONTXI provided higher visibility than WLI, lower than NBI, and comparable to or higher than CE in the magnified observation of colorectal adenomas.

Background/Objectives: Gastrointestinal diseases (GID), such as oesophagitis, polyps, and ulcerative colitis, contribute significantly to global morbidity and mortality. Conventional diagnostic methods employing white light imaging (WLI) in wireless capsule endoscopy (WCE) provide limited spectrum information, therefore influencing classification performance. Methods: A new technique called Spectrum Aided Vision Enhancer (SAVE), which converts traditional WLI images into hyperspectral imaging (HSI)-like representations, hence improving diagnostic accuracy. HSI involves the acquisition of image data across numerous wavelengths of light, extending beyond the visible spectrum, to deliver comprehensive information regarding the material composition and attributes of the imaged objects. This technique facilitates improved tissue characterisation, rendering it especially effective for identifying abnormalities in medical imaging. Using a carefully selected dataset consisting of 6000 annotated photos taken from the KVASIR and ETIS-Larib Polyp Database, this work classifies normal, ulcers, polyps, and oesophagitis. The performance of both the original WLI and SAVE transformed images was assessed using advanced deep learning architectures. The principal outcome was the overall classification accuracy for normal, ulcer, polyp, and oesophagitis categories, contrasting SAVE-enhanced images with standard WLI across five deep learning models. Results: The principal outcome of this study was the enhancement of diagnostic accuracy for gastrointestinal disease classification, assessed through classification accuracy, precision, recall, and F1 score. The findings illustrate the efficacy of the SAVE method in improving diagnostic performance without requiring specialised equipment. With the best accuracy of 98% attained using EfficientNetB7, compared to 97% with WLI, experimental data show that SAVE greatly increases classification metrics across all models. With relative improvement from 85% (WLI) to 92% (SAVE), VGG16 showed the highest accuracy. Conclusions: These results confirm that the SAVE algorithm significantly improves the early identification and classification of GID, therefore providing a potential development towards more accurate, non-invasive GID diagnostics with WCE.

Image enhancement technique plays a vital role in image analysis. White-band images (WBI) and narrow band images (NBI) are the two types of images that are widely used in capsule endoscopy. It is a general practice to compress the images and process them at the chip level embedded in the capsule in order to minimize the power consumption. In the due course, it is often required to enhance the features of the image so that, most favorable information from the images can be extracted. Loss of naturalness in the image while processing for image enhancement is observed. In this paper, a technique called brightness enhancement followed by color restoration is suggested for images with non-linear illumination. The technique employs a bright pass filter which acts on reflectance and luminance forms of image obtained after decomposing of the original image. The simulation experiment is carried on both white-band images and narrow-band images.

Objective The purpose of this work was to compare the efficacy of narrow band imaging-assisted transurethral resection of bladder tumour (TURB)with conventional white light imaging-assisted TURB in primary non-muscle-invasive bladder cancer. Methods Several databases were searched, including Cochrance Libarary, PubMed, Embase, Wanfang, VIP, CNKI and CBM. The endpoints were biochemical failure in 3 months , 1 year and 2 years . We performed a meta-analysis of the published data. The results are expressed as risk ratio (RR), with the corresponding 95% confidence interval (CI). Results The final analysis included seven trials comprising 1889 patients. Biochemical failure in 3months(RR0.73, 95%CI 0.55-0.96; P=0.02), 1 year(RR 0.69, 95%CI 0.58-0.80; P<0.01) and 2 years (RR 0.58, 95%CI 0.41-0.82; P=0.002)were fewer in patients who received narrow band imaging-assisted TURB . The recurrence rates of 3 months, 1 year and 2 years were 14.44%, 29.35% and 30% in white light imaging group.The recurrence rates of 3 months, 1 year and 2 years were 3.61%, 9.35% and 12.59% lower in narrow band imaging group compared with white light imaging group. Conclusions Narrow band imaging-assisted TURB was superior to conventional white light imaging-assisted TURB in primary non-muscle-invasive bladder cancer in 2 years. Key words: Bladder neoplasms; Meta-analysis; Narrow band imaging; White light imaging

To cope with the growing prevalence of colorectal cancer (CRC), screening\nprograms for polyp detection and removal have proven their usefulness.\nColonoscopy is considered the best-performing procedure for CRC screening. To\nease the examination, deep learning based methods for automatic polyp detection\nhave been developed for conventional white-light imaging (WLI). Compared with\nWLI, narrow-band imaging (NBI) can improve polyp classification during\ncolonoscopy but requires special equipment. We propose a CycleGAN-based\nframework to convert images captured with regular WLI to synthetic NBI (SNBI)\nas a pre-processing method for improving object detection on WLI when NBI is\nunavailable. This paper first shows that better results for polyp detection can\nbe achieved on NBI compared to a relatively similar dataset of WLI. Secondly,\nexperimental results demonstrate that our proposed modality translation can\nachieve improved polyp detection on SNBI images generated from WLI compared to\nthe original WLI. This is because our WLI-to-SNBI translation model can enhance\nthe observation of polyp surface patterns in the generated SNBI images.\n

A Novel External Lead Sensor Array Placement Approach for Capsule Endoscopy

Accurate visual classification of bladder tissue during Trans-Urethral Resection of Bladder Tumor (TURBT) procedures is essential to improve early cancer diagnosis and treatment. During TURBT interventions, White Light Imaging (WLI) and Narrow Band Imaging (NBI) techniques are used for lesion detection. Each imaging technique provides diverse visual information that allows clinicians to identify and classify cancerous lesions. Computer vision methods that use both imaging techniques could improve endoscopic diagnosis. We address the challenge of tissue classification when annotations are available only in one domain, in our case WLI, and the endoscopic images correspond to an unpaired dataset, i.e. there is no exact equivalent for every image in both NBI and WLI domains. We propose a semi-surprised Generative Adversarial Network (GAN)-based method composed of three main components: a teacher network trained on the labeled WLI data; a cycle-consistency GAN to perform unpaired image-to-image translation, and a multi-input student network. To ensure the quality of the synthetic images generated by the proposed GAN we perform a detailed quantitative, and qualitative analysis with the help of specialists. The overall average classification accuracy, precision, and recall obtained with the proposed method for tissue classification are 0.90, 0.88, and 0.89 respectively, while the same metrics obtained in the unlabeled domain (NBI) are 0.92, 0.64, and 0.94 respectively. The quality of the generated images is reliable enough to deceive specialists. This study shows the potential of using semi-supervised GAN-based bladder tissue classification when annotations are limited in multi-domain data.