Inflammatory, Hypersensitivity and Immune Lung Diseases, including Parasitic Diseases.
Fred W Wright in Radiology of the Chest and Related Conditions, 2022
Lung manifestations are commonly nodules which may be single or multiple (Illus. WEGENER'S GRANULOMA, Vasculitis Pt. 13, 14a, 15a, c-d, 16a-b, 17a-d, 18a-c, 19a-b, 20a-c & 21a-c). When multiple they are commonly bilateral and widely distributed with no predilection for any lung area and vary in size from a few up to 10 cm in diameter. They may be well or poorly demarcated and frequently cavitate producing thick or thin walled cavities. Apical nodules, especially if cavitating, are not uncommonly mistaken for tuberculosis. Fluid may be seen within the cavities. The pattern of lung disease frequently changes. Patients may also present with pulmonary oedema, lung collapse, consolidation or frank clinical pneumonia. In some cases the picture is complicated by pulmonary haemorrhage (giving rise to low density infiltrates which clear). CT may be helpful in showing the nodular or broncho-pneumonic pattern of the disease (as shown in the illustrations quoted above); some long-term cases may show evidence of an interstitial fibrosis and evidence of tracheobronchial wall damage with narrowing and/or bronchiectasis, the fibrosis perhaps in some cases being related to cyclophosphamide treatment.
Artificial Intelligence Based COVID-19 Detection using Medical Imaging Methods: A Review
S. Prabha, P. Karthikeyan, K. Kamalanand, N. Selvaganesan in Computational Modelling and Imaging for SARS-CoV-2 and COVID-19, 2021
Image data acquisition is an essential step to design and develop AI-based methods for COVID-19 detection. Lung infection or pneumonia is the most common complication of COVID-19. Chest X-ray and CT are widely-accepted imaging modalities for the diagnosis of lung diseases. Large public CT or X-ray datasets are available for lung diseases. However, the number of CT or X-ray datasets available for the development of AI methods for COVID-19 applications is minimal. Most of the published works so far have used medical images from different websites, and some of the works have used their self-collected images. Table 1.2 reports available datasets from different websites (normal, COVID-19 and other pneumonia) in terms of modality used, number of subjects available. its sources and existing deep-learning models available on websites.
X-Ray Dark-Field Imaging of Lung Cancer in Mice
Ayman El-Baz, Jasjit S. Suri in Lung Imaging and CADx, 2019
Lung diseases are one of the leading causes of morbidity and mortality worldwide. Lung cancer, in particular, accounts for 1.6 million deaths per year in the world [1]. It is by far the most common cause of cancer-related deaths for both genders (Figure 4.1). There are no particular symptoms or signs for lung cancer detection at an early stage. Therefore, most patients are diagnosed at an advanced stage of the disease when treatment options are limited. The 5-year survival rate of patients with lung cancer at diagnosis is only around 15% [2]. However, when diagnosed at an early stage, lung cancer has a much better prognosis with 5-year survival rates up to 70% [3]. The most common risk factors are cigarette smoking or secondhand exposure, environmental exposures to carcinogens (e.g., asbestos, radon), and comorbidities such as human immunodeficiency virus infection, idiopathic pulmonary fibrosis, chronic obstructive pulmonary disease, and tuberculosis [4].
Interval aerobic exercise in individuals with advanced interstitial lung disease: a feasibility study
Published in Physiotherapy Theory and Practice, 2021
Lisa Wickerson, Dina Brooks, John Granton, W. Darlene Reid, Dmitry Rozenberg, Lianne G. Singer, Sunita Mathur
During aerobic exercise, acute responses in ILD include tachypnea, ventilation/perfusion mismatching, diffusion limitation, hypoxemia, increased pulmonary arterial pressure and reliance on anaerobic metabolism (Agusti et al, 1991; Hansen and Wasserman, 1996). These cardio-respiratory responses and accompanying symptoms (i.e. dyspnea and leg fatigue) may impact the feasibility of exercise in terms of a decreased ability to exercise at a prescribed workload, unintended breaks and early termination of exercise. Aerobic exercise is primarily prescribed using constant load endurance training in people with chronic lung disease. Interval exercise, defined as repeated bouts of higher intensity exercise interspersed with pre-defined recovery periods of rest or lighter intensity exercise, has been suggested as an alternative exercise strategy. Interval exercise can impose a high load to the peripheral muscles with a reduced reliance on anaerobic metabolism and lower blood lactate accumulation (Astrand and Rodahl, 1986; Billat, 2001).
Association between duration of coal dust exposure and respiratory impairment in coal miners of West Bengal, India
Published in International Journal of Occupational Safety and Ergonomics, 2021
Shilpi K. Prasad, Siddhartha Singh, Ananya Bose, Bimlesh Prasad, Oly Banerjee, Ankita Bhattacharjee, Bithin K. Maji, Amalendu Samanta, Sandip Mukherjee
Different lung function indices of pulmonary function tests can be used to diagnose ventilatory disorders and differentiate between obstructive and restrictive lung diseases. These lung function indices include FVC (the amount of air that can be forcibly exhaled from the lungs after taking the deepest breath possible), FEV1 s (the maximum volume of air that can be forcefully expired within 1 s after maximal inspiration), the FEV1 s/FVC ratio also called the Tiffeneau–Pinelli index (the ratio of FEV1 s to FVC expressed as a percentage), FEF25–75% (the amount of air of forced expiratory flow over the middle half of the FVC), PEF (the maximum airflow rate attained during forced expiration) and MVV (the maximum volume of air expired in a specified period during repetitive maximal effort).
Potential value and impact of data mining and machine learning in clinical diagnostics
Published in Critical Reviews in Clinical Laboratory Sciences, 2021
Maryam Saberi-Karimian, Zahra Khorasanchi, Hamideh Ghazizadeh, Maryam Tayefi, Sara Saffar, Gordon A. Ferns, Majid Ghayour-Mobarhan
Machine learning has already made an impact in the prediction of pulmonary disease (Table 6). Young et al. investigated the important risk factors related to respiratory disease by data mining [83]. The authors divided total data into a respiratory disease group and a healthy group and applied data mining methods such as logistic regression, Bayesian network, neural network, CART, and C5.0. The CART model was the most accurate model for the prediction. Additionally, smoking, stress, and depression were revealed as the major risk factors of respiratory disease. Previous studies have applied machine learning to help with pulmonary function test analysis, aiding to enhance the screening and management of pulmonary nodules [84], as well as with the detection and exacerbation prediction of chronic obstructive pulmonary disease (COPD) [85]. In regards to COPD, Shah et al. developed a robust algorithm to identify and forecast exacerbation of COPD using machine learning techniques [86]. This research suggests the application of SVM models show better accuracy in forecasting COPD exacerbations.
Related Knowledge Centers
- Breathing
- Bronchiole
- Bronchus
- Gas Exchange
- Respiratory Tract
- Trachea
- Pleural Cavity
- Pathology
- Pulmonary Alveolus
- Pulmonary Pleurae