Chronic obstructive pulmonary disease

Summary

Chronic obstructive pulmonary disease (COPD) is a type of progressive lung disease characterized by long-term respiratory symptoms and airflow limitation. The main symptoms of COPD include shortness of breath and a cough, which may or may not produce mucus. COPD progressively worsens, with everyday activities such as walking or dressing becoming difficult. While COPD is incurable, it is preventable and treatable. The two most common types of COPD are emphysema and chronic bronchitis and have been the two classic COPD phenotypes. Emphysema is defined as enlarged airspaces (alveoli) whose walls have broken down resulting in permanent damage to the lung tissue. Chronic bronchitis is defined as a productive cough that is present for at least three months each year for two years. Both of these conditions can exist without airflow limitation when they are not classed as COPD. Emphysema is just one of the structural abnormalities that can limit airflow and can exist witho

Official source

https://en.wikipedia.org/wiki/Chronic_obstructive_pulmonary_disease

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related publications (24)

Related publications

Related people (1)

Related people

Related units (1)

Related units

Related concepts (117)

Related concepts

Related courses (10)

Related courses

Related lectures (10)

Related lectures

LSSANet: A Long Short Slice-Aware Network for Pulmonary Nodule Detection

Bo Du, Rui Xu, Jiancheng Yang

Convolutional neural networks (CNNs) have been demonstrated to be highly effective in the field of pulmonary nodule detection. However, existing CNN based pulmonary nodule detection methods lack the ability to capture long-range dependencies, which is vital for global information extraction. In computer vision tasks, non-local operations have been widely utilized, but the computational cost could be very high for 3D computed tomography (CT) images. To address this issue, we propose a long short slice-aware network (LSSANet) for the detection of pulmonary nodules. In particular, we develop a new non-local mechanism termed long short slice grouping (LSSG), which splits the compact non-local embeddings into a short-distance slice grouped one and a long-distance slice grouped counterpart. This not only reduces the computational burden, but also keeps long-range dependencies among any elements across slices and in the whole feature map. The proposed LSSG is easy-to-use and can be plugged into many pulmonary nodule detection networks. To verify the performance of LSSANet, we compare with several recently proposed and competitive detection approaches based on 2D/3D CNN. Promising evaluation results on the large-scale PN9 dataset demonstrate the effectiveness of our method. Code is at https:// github.com/Ruixxxx/LSSANet.

SPRINGER INTERNATIONAL PUBLISHING AG2022

Electrical spinal cord stimulation protocols to regulate neurological functions after spinal cord injury

Salif Axel Komi

Spinal cord injury (SCI) is a life-changing event. People who suffer from it lose their abilityto move normally and are subject to life-threatening symptoms. When the insult is not toosevere, partial recovery is possible. Otherwise, for severely affected people, the perspectives toever retrieve normal functions is almost non-existent. A critically important window to promoteplasticity is in the acute phase after the trauma (weeks to months). However, at this stage,people cannot take active part in rehabilitation programs due to their incapacity to activate theirlimbs and to the apparition of severe autonomic symptoms such as orthostatic hypotension.Hence, current activity-based treatments are of little help for this population. Consequently, SCIdramatically affects their autonomy and quality of life on the life-long term.Continuous Epidural Electrical Stimulation (EES) of the spinal cord has been proposed as amethod to reactivate dormant neural networks innervated below the site of injury. It enablesrobust control over locomotion and autonomic functions. In animal models of severe lesion,continuous EES promoted long lasting recovery of motor abilities when coupled with an intensivetraining. In human, its recent application indeed supported overground walking in chronicallyand severely injured people, but only showed limited plastic effects when compared to animals.Why? Recent advances support that continuous EES abolishes proprioceptive feedback thatis essential to promote recovery. Moreover, late treatment of severe injuries consistently fail apromoting recuperation of functions. Alternatively, over the last decade, our laboratory developeda spatio-temporally patterned approach to EES. In addition to restore fine control over motorfunctions, this technique avoids the caveats of continuous EES, and hypothetically opens a windowof opportunity for plasticity to happen. In this thesis, we propose a translation of this concept tohumans. We first demonstrate that spatio-temporal EES restores robust and versatile locomotorcontrol in people with chronic incomplete, though severe, SCI. Furthermore, the results supportan aptitude of this approach to promote long lasting recovery of functions without stimulationafter 5 months of intensive training. We then report on a patient-tailored technology, thatincludes personalized computational models enabling precise pre-operative planning strategies, anew electrode-lead and control softwares. This technology enables restoration of various motorfunctions in people with chronic and motor-complete injuries within few hours after beginningof therapy. Finally, we transfer this targeted approach to the control of blood pressure. Wedemonstrate that closed-loop stimulation protocols support a precise control over arterial bloodpressure in rodents, non-humane primates and humans with severe SCI submitted to challengingcardiovascular conditions. Combined, the results presented in this manuscript open a clinicallyrealistic perspective for the application of EES acutely after injury and to potentially promoterobust recovery in severe SCI.

EPFL2021

, ,

Objective. Bioelectronic medicine is an emerging field that aims at developing closed-loop neuromodulation protocols for the autonomic nervous system (ANS) to treat a wide range of disorders. When designing a closed-loop protocol for real time modulation of the ANS, the computational execution time and the memory and power demands of the decoding step are important factors to consider. In the context of cardiovascular and respiratory diseases, these requirements may partially explain why closed-loop clinical neuromodulation protocols that adapt stimulation parameters on patient's clinical characteristics are currently missing. Approach. Here, we developed a lightweight learning-based decoder for the classification of cardiovascular and respiratory functional challenges from neural signals acquired through intraneural electrodes implanted in the cervical vagus nerve (VN) of five anaesthetized pigs. Our algorithm is based on signal temporal windowing, nine handcrafted features, and random forest (RF) model for classification. Temporal windowing ranging from 50 ms to 1 s, compatible in duration with cardio-respiratory dynamics, was applied to the data in order to mimic a pseudo real-time scenario. Main results. We were able to achieve high balanced accuracy (BA) values over the whole range of temporal windowing duration. We identified 500 ms as the optimal temporal windowing duration for both BA values and computational execution time processing, achieving more than 86% for BA and a computational execution time of only similar to 6.8 ms. Our algorithm outperformed in terms of BA and computational execution time a state of the art decoding algorithm tested on the same dataset (Vallone et al 2021 J. Neural Eng. 18 0460a2). We found that RF outperformed other machine learning models such as support vector machines, K-nearest neighbors, and multi-layer perceptrons. Significance. Our approach could represent an important step towards the implementation of a closed-loop neuromodulation protocol relying on a single intraneural interface able to perform real-time decoding tasks and selective modulation of the VN.

IOP Publishing Ltd2022

, ,

IOP Publishing Ltd2022

Electrical spinal cord stimulation protocols to regulate neurological functions after spinal cord injury

Salif Axel Komi

EPFL2021