A frame reduction system based on a color structural similarity (CSS) method and Bayer images analysis for capsule endoscopy

Optical color routing enabled by deep learning

Nano-color routing has emerged as an immensely popular and widely discussed subject in the realms of light field manipulation, image sensing, and the integration of deep learning. The conventional dye filters employed in commercial applications have long been hampered by several limitations, including subpar signal-to-noise ratio, restricted upper bounds on optical efficiency, and challenges associated with miniaturization. Nonetheless, the advent of bandpass-free color routing has opened up unprecedented avenues for achieving remarkable optical spectral efficiency and operation at sub-wavelength scales within the area of image sensing applications. This has brought about a paradigm shift, fundamentally transforming the field by offering a promising solution to surmount the constraints encountered with traditional dye filters. This review presents a comprehensive exploration of representative deep learning-driven nano-color routing structure designs, encompassing forward simulation algorithms, photonic neural networks, and various global and local topology optimization methods. A thorough comparison is drawn between the exceptional light-splitting capabilities exhibited by these methods and those of traditional design approaches. Additionally, the existing research on color routing is summarized, highlighting a promising direction for forthcoming development, delivering valuable insights to advance the field of color routing and serving as a powerful reference for future endeavors.

A systematic review on diagnosis and treatment of gastrointestinal diseases by magnetically controlled capsule endoscopy and artificial intelligence

Background

Magnetically controlled capsule endoscopy (MCCE) is a non-invasive, painless, comfortable, and safe equipment to diagnose gastrointestinal diseases (GID), partially overcoming the shortcomings of conventional endoscopy and wireless capsule endoscopy (WCE). With advancements in technology, the main technical parameters of MCCE have continuously been improved, and MCCE has become more intelligent.

Objectives

The aim of this systematic review was to summarize the research progress of MCCE and artificial intelligence (AI) in the diagnosis and treatment of GID.

Data Sources and Methods

We conducted a systematic search of PubMed and EMBASE for published studies on GID detection of MCCE, physical factors related to MCCE imaging quality, the application of AI in aiding MCCE, and its additional functions. We synergistically reviewed the included studies, extracted relevant data, and made comparisons.

Results

MCCE was confirmed to have the same performance as conventional gastroscopy and WCE in detecting common GID, while it lacks research in detecting early gastric cancer (EGC). The body position and cleanliness of the gastrointestinal tract are the main factors affecting imaging quality. The applications of AI in screening intestinal diseases have been comprehensive, while in the detection of common gastric diseases such as ulcers, it has been developed. MCCE can perform some additional functions, such as observations of drug behavior in the stomach and drug damage to the gastric mucosa. Furthermore, it can be improved to perform a biopsy.

Conclusion

This comprehensive review showed that the MCCE technology has made great progress, but studies on GID detection and treatment by MCCE are in the primary stage. Further studies are required to confirm the performance of MCCE.

Development and Verification of a Deep Learning Algorithm to Evaluate Small-Bowel Preparation Quality

Capsule endoscopy (CE) quality control requires an objective scoring system to evaluate the preparation of the small bowel (SB). We propose a deep learning algorithm to calculate SB cleansing scores and verify the algorithm’s performance. A 5-point scoring system based on clarity of mucosal visualization was used to develop the deep learning algorithm (400,000 frames; 280,000 for training and 120,000 for testing). External validation was performed using additional CE cases (n = 50), and average cleansing scores (1.0 to 5.0) calculated using the algorithm were compared to clinical grades (A to C) assigned by clinicians. Test results obtained using 120,000 frames exhibited 93% accuracy. The separate CE case exhibited substantial agreement between the deep learning algorithm scores and clinicians’ assessments (Cohen’s kappa: 0.672). In the external validation, the cleansing score decreased with worsening clinical grade (scores of 3.9, 3.2, and 2.5 for grades A, B, and C, respectively, p < 0.001). Receiver operating characteristic curve analysis revealed that a cleansing score cut-off of 2.95 indicated clinically adequate preparation. This algorithm provides an objective and automated cleansing score for evaluating SB preparation for CE. The results of this study will serve as clinical evidence supporting the practical use of deep learning algorithms for evaluating SB preparation quality.

Automatic detection and classification of protruding lesions in wireless capsule endoscopy images based on a deep convolutional neural network

BACKGROUND AND AIMS

Protruding lesions of the small bowel vary in wireless capsule endoscopy (WCE) images, and their automatic detection may be difficult. We aimed to develop and test a deep learning-based system to automatically detect protruding lesions of various types in WCE images.

METHODS

We trained a deep convolutional neural network (CNN), using 30,584 WCE images of protruding lesions from 292 patients. We evaluated CNN performance by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, using an independent set of 17,507 test images from 93 patients, including 7507 images of protruding lesions from 73 patients.

RESULTS

The developed CNN analyzed 17,507 images in 530.462 seconds. The AUC for detection of protruding lesions was 0.911 (95% confidence interval [Cl], 0.9069-0.9155). The sensitivity and specificity of the CNN were 90.7% (95% CI, 90.0%-91.4%) and 79.8% (95% CI, 79.0%-80.6%), respectively, at the optimal cut-off value of 0.317 for probability score. In a subgroup analysis of the category of protruding lesions, the sensitivities were 86.5%, 92.0%, 95.8%, 77.0%, and 94.4% for the detection of polyps, nodules, epithelial tumors, submucosal tumors, and venous structures, respectively. In individual patient analyses (n = 73), the detection rate of protruding lesions was 98.6%.

CONCLUSION

We developed and tested a new computer-aided system based on a CNN to automatically detect various protruding lesions in WCE images. Patient-level analyses with larger cohorts and efforts to achieve better diagnostic performance are necessary in further studies.