Search

A computer-aided detection (CAD) tool for locating and detecting polyps can help reduce the chance of missing polyps during colonoscopy. Nevertheless, state-of-the-art algorithms were either computationally complex or suffered from low sensitivity and therefore unsuitable to be used in real clinical setting. In this paper, a novel regression-based Convolutional Neural Network (CNN) pipeline is presented for polyp detection during colonoscopy. The proposed pipeline was constructed in two parts: 1) to learn the spatial features of colorectal polyps, a fast object detection algorithm named ResYOLO was pre-trained with a large non-medical image database and further fine-tuned with colonoscopic images extracted from videos; and 2) temporal information was incorporated via a tracker named Efficient Convolution Operators (ECO) for refining the detection results given by ResYOLO. Evaluated on 17,574 frames extracted from 18 endoscopic videos of the AsuMayoDB, the proposed method was able to detect frames with polyps with a precision of 88.6%, recall of 71.6% and processing speed of 6.5 frames per second, i.e. the method can accurately locate polyps in more frames and at a faster speed compared to existing methods. In conclusion, the proposed method has great potential to be used to assist endoscopists in tracking polyps during colonoscopy.

Time–frequency (T–F) analysis is often used to study the non-stationary cardiovascular oscillations such as heart rate and blood pressure variabilities in dynamic situations. This study intends to use the T–F recursive autoregressive technique to investigate variability in pulse transit time (PTT), which is a cardiovascular parameter of emerging interest due to its potential to estimate blood pressure non-invasively, continuously and without a cuff. Recent studies suggest that PTT is not only related to systolic blood pressure (SBP) but also to heart rate. Therefore, in this study, variability of PTT is analyzed together with the variabilities of R–R interval (RRI) from electrocardiogram and beat-to-beat SBP on 9 normotensive subjects before and shortly after three successive bouts of treadmill exercise. The results showed that both low frequency (LF) and high frequency (HF) components were found in the spectra of RRI, SBP and PTT in the 5-min recordings collected before and after exercise. Compared to the baseline, a decrease in the power of the HF component of RRI followed by an increase in its LF component indicated firstly a vagal withdrawal and then sympathetic activity enhancement after successive bouts of exercise. On the other hand, although changes in the LF and HF components of PTT were more similar to those of SBP than of RRI, the LF/HF ratio of SBP was almost 4 times higher than that of PTT. Based on the results, it is therefore suggested that the relationship between SBP and PTT is frequency-dependent.