Automated Adaptive Brightness in Wireless Capsule Endoscopy Using Image Segmentation and Sigmoid Function

Abstract

Wireless capsule endoscopy (WCE) plays an important role in the diagnosis of gastrointestinal (GI) diseases by capturing images of human small intestine. Accurate diagnosis of endoscopic images depends heavily on the quality of captured images. Along with image and frame rate, brightness of the image is an important parameter that influences the image quality which leads to the design of an efficient illumination system. Such design involves the choice and placement of proper light source and its ability to illuminate GI surface with proper brightness. Light emitting diodes (LEDs) are normally used as sources where modulated pulses are used to control LED's brightness. In practice, instances like under- and over-illumination are very common in WCE, where the former provides dark images and the later provides bright images with high power consumption. In this paper, we propose a low-power and efficient illumination system that is based on an automated brightness algorithm. The scheme is adaptive in nature, i.e., the brightness level is controlled automatically in real-time while the images are being captured. The captured images are segmented into four equal regions and the brightness level of each region is calculated. Then an adaptive sigmoid function is used to find the optimized brightness level and accordingly a new value of duty cycle of the modulated pulse is generated to capture future images. The algorithm is fully implemented in a capsule prototype and tested with endoscopic images. Commercial capsules like Pillcam and Mirocam were also used in the experiment. The results show that the proposed algorithm works well in controlling the brightness level accordingly to the environmental condition, and as a result, good quality images are captured with an average of 40% brightness level that saves power consumption of the capsule.

Rational Design of Photochromic Analogues of Tricyclic Drugs

“…Overall, the photopharmacological properties of cryptozepines set the stage for interesting assays in vivo . If they can be enterically administered in the inactive form ( trans ), these drugs could be remotely photoactivated at the desired location and time using the built-in light-emitting diode (LED) of an endoscopy capsule, potentially allowing to treat gastrointestinal tract diseases without producing (adverse) effects in other regions or organs. More invasive applications include the manipulation of cardiac function in vivo using optoelectronic devices coupled to cardiac patches. , In any case, to test the feasibility of future therapies based on photoswitchable drugs, both isomers must be pharmacologically characterized.…”

A Fluorescence-Based Wireless Capsule Endoscopy System for Detecting Colorectal Cancer

“…This would help the physicians examine the abnormality visually, thereby increasing the efficiency, as well as the reliability of the system. The battery life of the proposed capsule can be improved by using the adaptive illumination technique [76]. Moreover, we have previously tested the PillCam SB3 capsule on horses [77].…”

An improved advertising CTR prediction approach based on the fuzzy deep neural network

“…The LR model is described in S4 Fig . The activation function of the node in the output layer is a sigmoid function [ 25 ]. The output value of the node (value of the activation function) h θ ( x ′) is the probability that a user will click on the advertisement; it can also be described as P ( y = 1| x ′; θ ′).…”

“…This paper regards the cross-entropy as the objective function [ 25 ]. It can be described as formula ( 31 ).…”