This paper reviews automated visual-based defect detection approaches applicable to various materials, such as metals, ceramics and textiles. In the first part of the paper, we present a general taxonomy of the different defects that fall in two classes: visible (e.g., scratches, shape error, etc.) and palpable (e.g., crack, bump, etc.) defects. Then, we describe artificial visual processing techniques that are aimed at understanding of the captured scenery in a mathematical/logical way. We continue with a survey of textural defect detection based on statistical, structural and other approaches. Finally, we report the state of the art for approaching the detection and classification of defects through supervised and non-supervised classifiers and deep learning.

Flexible colonoscopy remains the prime mean of screening for colorectal cancer (CRC) and the gold standard of all population-based screening pathways around the world. Almost 60% of CRC deaths could be prevented with screening. However, colonoscopy attendance rates are affected by discomfort, fear of pain and embarrassment or loss of control during the procedure. Moreover, the emergence and global thread of new communicable diseases might seriously affect the functioning of contemporary centres performing gastrointestinal endoscopy. Innovative solutions are needed: artificial intelligence (AI) and physical robotics will drastically contribute for the future of the healthcare services. The translation of robotic technologies from traditional surgery to minimally invasive endoscopic interventions is an emerging field, mainly challenged by the tough requirements for miniaturization. Pioneering approaches for robotic colonoscopy have been reported in the nineties, with the appearance of inchworm-like devices. Since then, robotic colonoscopes with assistive functionalities have become commercially available. Research prototypes promise enhanced accessibility and flexibility for future therapeutic interventions, even via autonomous or robotic-assisted agents, such as robotic capsules. Furthermore, the pairing of such endoscopic systems with AI-enabled image analysis and recognition methods promises enhanced diagnostic yield. By assembling a multidisciplinary team of engineers and endoscopists, the paper aims to provide a contemporary and highly-pictorial critical review for robotic colonoscopes, hence providing clinicians and researchers with a glimpse of the major changes and challenges that lie ahead.

Background and Aims: Colorectal cancer (CRC) is a major cause of morbidity and mortality worldwide. Despite offering a prime paradigm for screening, CRC screening is often hampered by invasiveness. Endoo is a potentially painless colonoscopy method with an active locomotion tethered capsule offering diagnostic and therapeutic capabilities. Materials and Methods: The Endoo system comprises a soft-tethered capsule, which embeds a permanent magnet controlled by an external robot equipped with a second permanent magnet. Capsule navigation is achieved via closed-loop interaction between the two magnets. Ex-vivo tests were conducted by endoscopy experts and trainees to evaluate the basic key features, usability, and compliance in comparison with conventional colonoscopy (CC) in feasibility and pilot studies. Results: Endoo showed a 100% success rate in operating channel and target approach tests. Progression of the capsule was feasible and repeatable. The magnetic link was lost an average of 1.28 times per complete procedure but was restored in 100% of cases. The peak value of interaction forces was higher in the CC group than the Endoo group (4.12N vs. 1.17N). The cumulative interaction forces over time were higher in the CC group than the Endoo group between the splenic flexure and mid-transverse colon (16.53Ns vs. 1.67Ns, p < 0.001), as well as between the hepatic flexure and cecum (28.77Ns vs. 2.47Ns, p = 0.005). The polyp detection rates were comparable between groups (9.1 ± 0.9% vs. 8.7 ± 0.9%, CC and Endoo respectively, per procedure). Robotic colonoscopies were completed in 67% of the procedures performed with Endoo (53% experts and 100% trainees). Conclusions: Endoo allows smoother navigation than CC and possesses comparable features. Although further research is needed, magnetic capsule colonoscopy demonstrated promising results compared to CC.

No abstract

VRViz: Native VR Visualization of ROS Topics .