Diffuse Cystic Lung Diseases

Obaidat, Baha; Yazdani, Dina; Wikenheiser-Brokamp, Kathryn A.; Gupta, Nishant

doi:10.4187/respcare.07117

Cited by 22 publications

(29 citation statements)

References 127 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Соты имеют толщину стенки менее 2 мм среди неизмененной ткани легких; толщина стенки у булл -менее 1 мм, а их диаметр больше 1 см, толщина стенок сот равняется 1-3 мм, диаметр колеблется от 3 до 10 мм [30]. Диффузные кистозные изменения легких возникают при ЛАМ, ЛЛКГ, синдроме Берта-Хогга-Дюбе, при лимфоцитарной интерстициальной пневмонии, обнаруживаемой при лейкозах и лимфомах, при первичных и метастатических злокачественных образованиях, при врожденной аденоматозной мальформации легких, реже при пневмоцистной и стафилококковой пневмонии, метастатическом эндометриозе [31][32][33][34][35]. Кистозные болезни легких чаще наблюдаются при орфанных заболеваниях, однако у многих из них кисты не являются облигатным симптомом [31].…”

Section: Discussionunclassified

“…При ЛАМ и ЛЛКГ образование кист в ткани легких -неотъемлемый рентгеноморфологический признак, играющий основную роль для правильной постановки диагноза [36]. ЛАМ и ЛЛКГ -наиболее час тые кистозные болезни легких, имеющие яркую рентгеноморфологическую картину, но во многих случаях требуется дифференциальная диагностика с другими заболеваниями [34,37].…”

Section: Discussionunclassified

“…ЛАМ, ЛЛКГ, опухоли легких, эндометриоз часто протекают бессимптомно, манифестируя спонтанными рецидивирующими пневмотораксами, имеют сходную клиническую картину, что затрудняет правильную диаг ностику этих заболеваний [5,30,31,34].…”

Section: Discussionunclassified

“…Гистологический маркер дифференциального диагноза при ЛАМ -наличие кистозных полостей с гладкомышечными узелками в их стенках с положительной ИГХ реакцией с HMB-45. Гладкомышечные пучки могут быть обнаружены при фиброзном гиперчувствительном пневмоните, обычной интерстициальной пневмонии, метастатической доброкачественной лейомиоме, эндометриальной стромальной саркоме при наличии веретенообразных клеток, однако при этих заболеваниях маркер HMB-45 отрицательный [34].…”

Section: Discussionunclassified

See 3 more Smart Citations

Anatomic pathology and computed tomography of diffuse cystic lung diseases

Chernyaev¹,

Самсонова²,

Averyanov³

et al. 2021

Clin. Exp. Morphology

View full text Add to dashboard Cite

Introduction. Cystic lung diseases are rare (orphan) diseases. Lung cysts are an important X-ray and morphological sign that contributes to the correct diagnosis. The aim of the researchwas to describe histologic features and computed tomography findings in patients with pulmonary Langerhans cell histiocytosis (PLCH), lymphangioleiomyomatosis (LAM), primary malignant lung tumors, and endometriosis of the lung. Materials and methods. We evaluated video-assisted surgical lung biopsies from 139 patients, with 86 patients having LAM, 47 having PLCH, and in threes having primary peripheral lung adenocarcinoma and endometriosis of the lung. The average age of patients with LAM was 41±10 years, LCG – 32±11 years, lung adenocarcinoma – 62±3.5 years, and endometriosis of the lung – 32±4.1 years. All patients had undergone high-resolution computed tomography of the lungs (HRCT) before the biopsy was obtained. We performed histological and immunohistochemical examinations of lung tissue specimens. Antibodies to CD1a, SMA, HMB-45, CD207 (langerin), CD10, receptors to progesterone, and estrogen were used in the study. Results. We described HRCT, histological, and immunohistochemical features of cystic lung diseases, including characteristics of the walls of cystic cavities in patients with PLCH, LAM, primary malignant lung tumors, and endometriosis of the lung. Conclusion. The variety of causes of lung cysts required a differential diagnosis, considering the patients’ ages, HRCT data indicating the localization of the pathological process, histology, and immunohistochemistry if necessary. Keywords: сystic lung diseases, computed tomography, pathological anatomy, Langerhans cell histiocytosis, lymphangioleiomyomatosis, malignant tumors, endometriosis

show abstract

Section: Discussionunclassified

See 2 more Smart Citations

Anatomic pathology and computed tomography of diffuse cystic lung diseases

Chernyaev¹,

Самсонова²,

Averyanov³

et al. 2021

Clin. Exp. Morphology

View full text Add to dashboard Cite

show abstract

“…The most common etiologies of DCLDs include lymphangioleiomyomatosis (LAM), pulmonary Langerhans cell histiocytosis (PLCH), lymphoid interstitial pneumonia, and Birt-Hogg-Dubé syndrome. [ 1 , 2 ] LAM is a rare and low-grade neoplasm that occurs mostly in women at their reproductive age. It occurs in a sporadic form or associated with tuberous sclerosis complex.…”

Section: Introductionmentioning

confidence: 99%

Association between pulmonary artery to aorta diameter ratio with pulmonary hypertension and outcomes in diffuse cystic lung diseases

et al. 2021

View full text Add to dashboard Cite

To investigate the importance of pulmonary vascular measurements on computed tomography (CT) in predicting pulmonary hypertension (PH) and worse outcomes in diffuse cystic lung diseases (DCLDs). We conducted a cross-sectional study of patients with DCLDs. Patients underwent pulmonary function tests, a six-minute walk test (6MWT), chest CT, transthoracic echocardiography, and right heart catheterization. Pulmonary artery (PA) diameter and PA-ascending aorta ratio (PA-Ao ratio) were obtained from CT. Mean pulmonary artery pressure (mPAP) from right heart catheterization was correlated with tomographic, functional, and echocardiographic variables. The association between the PA-Ao ratio with outcomes was determined by Kaplan–Meier curves. Thirty-four patients were included (18 with pulmonary Langerhans cell histiocytosis and 16 with lymphangioleiomyomatosis, mean age 46 ± 9 years). Forced expiratory volume in the first second and lung diffusing capacity for carbon monoxide were 47 ± 20% and 38 ± 21% predicted, respectively. PA diameter and PA-Ao ratio were 29 ± 6 mm and 0.95 ± 0.24, respectively. PA-Ao ratio > 1 occurred in 38.2% of patients. PA-Ao ratio was a good predictor of PH. mPAP correlated best with PA-Ao ratio, PA diameter, oxygen desaturation during six-minute walk test, and echocardiographic variables. Patients with PA-Ao ratio > 1 had greater mPAP, and a higher risk of death or lung transplantation (log-rank, P < .001) than those with PA-Ao ratio ≤ 1. The PA-Ao ratio measured on CT scan has a potential role as a non-invasive tool to predict the presence of PH and as a prognostic parameter in patients with DCLDs.

show abstract

Computer‐aided diagnosis of cystic lung diseases using CT scans and deep learning

Zhu,

Xing,

Yang

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundAuxiliary diagnosis of different types of cystic lung diseases (CLDs) is important in the clinic and is instrumental in facilitating early and specific treatments. Current clinical methods heavily depend on accumulated experience, restricting their applicability in regions with less developed medical resources. Thus, how to realize the computer‐aided diagnosis of CLDs is of great clinical value.PurposeThis work proposed a deep learning‐based method for automatically segmenting the lung parenchyma in computed tomography (CT) slice images and accurately diagnosing the CLDs using CT scans.MethodsA two‐stage deep learning method was proposed for the automatic classification of normal cases and five different CLDs using CT scans. Lung parenchyma segmentation is the foundation of CT image analysis and auxiliary diagnosis. To meet the requirements of different sizes of the lung parenchyma, an adaptive region‐growing and improved U‐Net model was employed for mask acquisition and automatic segmentation. The former was achieved by a self‐designed adaptive seed point selection method based on similarity measurement, and the latter introduced multiscale input and multichannel output into the original U‐Net model and effectively achieved the lightweight design by adjusting the structure and parameters. After that, the middle 30 consecutive CT slice images of each sample were segmented to obtain lung parenchyma, which was employed for training and testing the proposed multichannel parallel input recursive MLP‐Mixer network (MPIRMNet) model, achieving the computer‐aided diagnosis of CLDs.ResultsA total of 4718 and 16 290 CT slice images collected from 543 patients were employed to validate the proposed segmentation and classification methods, respectively. Experimental results showed that the improved U‐Net model can accurately segment the lung parenchyma in CT slice images, with the Dice, precision, volumetric overlap error, and relative volume difference of 0.96 ± 0.01, 0.93 ± 0.04, 0.05 ± 0.02, and 0.05 ± 0.03, respectively. Meanwhile, the proposed MPIRMNet model achieved appreciable classification effect for normal cases and different CLDs, with the accuracy, sensitivity, specificity, and F1 score of 0.8823 ± 0.0324, 0.8897 ± 0.0325, 0.9746 ± 0.0078, and 0.8831 ± 0.0334, respectively. Compared with classical machine learning and convolutional neural networks‐based methods for this task, the proposed classification method had a preferable performance, with a significant improvement of accuracy of 10.74%.ConclusionsThe work introduced a two‐stage deep learning method, which can achieve the segmentation of lung parenchyma and the classification of CLDs. Compared to previous diagnostic tasks targeting single CLD, this work can achieve various CLDs’ diagnosis in the early stage, thereby achieving targeted treatment and increasing the potential and value of clinical applications.

show abstract

Diffuse Cystic Lung Diseases

Cited by 22 publications

References 127 publications

Anatomic pathology and computed tomography of diffuse cystic lung diseases

Anatomic pathology and computed tomography of diffuse cystic lung diseases

Association between pulmonary artery to aorta diameter ratio with pulmonary hypertension and outcomes in diffuse cystic lung diseases

Computer‐aided diagnosis of cystic lung diseases using CT scans and deep learning

Contact Info

Product

Resources

About