Semantic Segmentation of Pathological Lung Tissue With Dilated Fully Convolutional Networks.

Bronchoalveolar lavage (BAL) is a useful technique for differential diagnosis of various interstitial lung diseases (ILDs) and is usually realized by analysis of the differential cell count. This study was conducted to estimate the value of bronchoalveolar lavage fluid (BALF) total cell count (TCC) in the diagnosis of ILD. We analyzed 237 BAL samples from patients with ILD: sarcoidosis (SA), idiopathic pulmonary fibrosis (IPF), cryptogenic organizing pneumonia (COP), hypersensitivity pneumonitis (HP), chronic eosinophilic pneumonia (CEP), and smoking-related ILD (sr-ILD). The control group consisted of 30 healthy volunteers. The statistical analysis revealed significant differences in the BALF TCC between healthy controls and patients with SA, IPF, HP, COP, sr-ILD, and eosinophilic disorders (mean values 6.9 vs. 14.5, 22.5, 22.8, 20.7, 64.5, and 27.3 × 10(6), respectively). Logistic regression revealed a significant relation between the TCC and ILD diagnosis. We conclude that the TCC, as well as the value of total number of inflammatory cells, should be reported in the description of BAL.

Summary In this paper we describe the goals and the latest outcomes of the TA LISMAN project, the purpose of which is to furnish image-based diagnostic assistance for interstitial lung diseases (ILDs) with secondary data integration. Prototypes of the computer tools are implemented. High correct classification rates of lung tissue regions in high-resolution computed tomography (HRCT), based on a high-quality dataset built from clinical routine, suggests that computerised analysis of HRCT images with integration of the clinical context is ready to be used for computer-aided diagnosis of ILDs. As future tasks, implementation of multimodal retrieval of ILD cases and clinical evaluation of the software are planned to meet clinical needs.

An architecture for automatic lung tissue classification method based on the Deep Learning techniques is designed in this paper. Recent works on Deep Learning techniques achieved impressive results in the field of medical image classification. So, we designed a Convolution Neural Network (CNN) for the classification of five categories of Interstitial Lung Diseases (ILD) patterns in High-Resolution Computed Tomography (HRCT) images. The CNN consists of 3 Convolution layers, Leaky ReLU activation followed by Maximum pooling layer and dense layer. The last Fully Connected (FC) layer has 5 outputs equivalent to the classes considered such as Normal, Ground Glass (GG), Emphysema, Micro Nodules, and Fibrosis. The proposed CNN is trained and evaluated on the publicly available ILD database provided by the University Hospitals of Geneva (HUG). Experimental results are compared with the state-of-art, which shows an outstanding performance of the proposed CNN model giving 94.67% accuracy and 94.65% Favg .

To investigate the value of exhaled nitric oxide (eNO) in the diagnosis and differential diagnosis of interstitial lung disease (ILD). This study was conducted among 45 patients with interstitial lung disease, including 18 with connective tissue disease-related ILD (CTD-ILD) and 27 with non-CTD-ILD, with 68 healthy subjects as the control group. According to European Respiratory Association Guidelines, alveolar nitric oxide (CaNO) concentration and fractional exhaled nitric oxide (FeNO) level were measured at the flow rates of 50 and 200 mL/s. The predictive level of CaNO was analyzed using receiver-operating characteristic curve (ROC), and the correlations between CaNO and pulmonary function indicators were examined in the patients with ILD. CaNO, FeNO50, and FeNO200 levels were significantly higher in patients with ILD than in the healthy controls. Logistic regression analysis showed that lowered levels of CaNO and FeNO200 were risk factors for ILD. ROC curve analysis showed that the area under the curve (AUC) of CaNO combined with FeNO200 was 0.829 (95% CI: 0.752-0.906) for the diagnosis of ILD. In patients with ILD, CaNO levels were negatively correlated with DLCO%pred (r=-0.471, P < 0.05). Subgroup comparison showed a significantly higher CaNO level in CTD-ILD group than in non-CTD-ILD group. The AUC for CaNO to discriminate CTD-ILD from non-CTD-ILD was 0.725 (95% CI: 0.576 to 0.875). CaNO has a potential value in the diagnosis of ILD and differential diagnosis of CTD-ILD.

Current data have shown that lung ultrasound (LUS) is an emerging tool in the diagnosis of interstitial lung disease (ILD) by evaluating numbers of B-lines, pleural irregularities and nodules or consolidations. These features can distinguish between ILD and others different pulmonary conditions (i.e., patients with heart failure or end-stage renal disease accompanied by pulmonary congestion). Although there is not a standardized approach for diagnosis of ILD by LUS examination and most studies has been made on rheumatologic patients, we discuss utility of LUS in detecting ILD and its correlation to classical radiological finding, especially to high-resolution computed tomography (HRCT).

Diagnosis of interstitial lung disease (ILD) is based on multidisciplinary team discussion (MDD) with the incorporation of clinical, radiographical, and histopathologic information if available. We aim to evaluate the diagnostic yield and safety outcomes of transbronchial lung cryobiopsy (TBLC) in the diagnosis of ILD. We conducted a meta-analysis by comprehensive literature search to include all studies that evaluated the diagnostic yields and/or adverse events with TBLC in patients with ILD. We calculated the pooled event rates and their 95% confidence intervals (CIs) for the diagnostic yield by MDD, histopathologic diagnostic yield, and various clinical adverse events. We included 68 articles (44 full texts and 24 abstracts) totaling 6386 patients with a mean age of 60.7±14.1 years and 56% men. The overall diagnostic yield of TBLC to achieve a definite or high-confidence diagnosis based on MDD was 82.3% (95% CI: 78.9%-85.2%) and histopathologic diagnosis of 72.5% (95% CI: 67.7%-76.9%). The overall rate of pneumothorax was 9.6% (95% CI: 7.9%-11%), while the rate of pneumothorax requiring drainage by a thoracostomy tube was 5.3% (95% CI: 4.1%-6.9%). The rate of moderate bleeding was 11.7% (95% CI: 9.1%-14.9%), while the rate of severe bleeding was 1.9% (95% CI: 1.4%-2.6%). The risk of mortality attributed to the procedure was 0.9% (95% CI: 0.7%-1.3%). Among patients with undiagnosed or unclassified ILD requiring tissue biopsy for diagnosis, transbronchial cryobiopsy represents a reliable alternative to surgical lung biopsy with decreased incidence of various clinical adverse events.

Comparison of Video Thoracoscopic Lung Biopsy to Open Lung Biopsy in the Diagnosis of Interstitial Lung Disease

Background Connective Tissue Diseases (CTDs) are systemic autoimmune conditions characterized by frequent lung involvement. Interstitial lung disease (ILD) is a severe pulmonary complication in CTD and associated with significant increased morbidity and mortality, so early detection of ILD is essential. Aim of the Work To find the best modality for early diagnosis of interstitial lung disease in patients with connective tissue disorders by using DLCO, impulse oscillometry and HRCT chest. Patients and Methods This observational, analytical and cross sectional study was conducted upon 60 patients whom were diagnosed as connective tissue disease during the period from march 2022 to march 2023 who were admitted to chest and rheumatology department or outpatient clinics visitors, to Ain Shams University Hospitals. Results regarding our results, there was high statistical significance between DLCO and IOS (Best x5). Sensitivity and specificity of Diffusion lung of CO2; DLCO score in prediction of outcome in CT Chest Findings showing significance in DLCO score; p = 0.024 with CI ranged between 53.9-81.4% and sensitivity 67.6%. Sensitivity and specificity of the impulse oscillation method; R5, R20,and Best-X5 score in prediction of outcome in CT Chest Findings. Showing no significance in all with sensitivity 50.2%, 46.1%, 43.4% and 57.5% respectively Conclusion ILD should always be considered in patients with CTD. Diagnosis of CTD-ILD is challenging so Early diagnosis of ILD using DLCO, HRCT chest or by using IOS is important as it could affect therapy plans.

Aim of the work: a descriptive study including analysis of HRCT chest done for patients known to have collagen diseases for diagnosis and classification of interstitial lung diseases. Patients and methods: forty five patients were included in our study (23 rheumatoid arthritis, 14 systemic lupus erythematosis and 8 scleroderma). This was a retrospective study that included patients with collagen diseases either outpatients or referred from the Rheumatology Departement at Ain Shams University Hospitals to the Radiodiagnosis Department for HRCT chest examination. HRCT chest images were interpreted for identification of lung interstitium architectural abnormalities associated with collagen diseases and they were statistically analyzed. Results: The mean age of the selected patients was about 42 years old. Parenchymal involvement was noted in 30 cases that represented 66.6% of included cases in the study, 15 cases had normal HRCT of the chest representing 33.4% of the cases. Conclusion: HRCT of the chest has a reasonable role in the diagnosis of interstitial lung diseases and has the ability to be classify according to the pattern of involvement, distribution and extent of the disease as well as to estimate the severity and help in prognosis of the disease process.

Background: According to current guidelines, when a high-confidence radiologic diagnosis of usual interstitial pneumonia (UIP) is made on thin-section computed tomography (HRCT), surgical biopsy is rarely required. Nevertheless, the disowning of HRCT-scans diagnoses by biopsy is not a rare event as presumed. Aim of our study is to describe the rate of concordance between HRCT-scans and pathological diagnoses. Methods: Patients who underwent mini-invasive surgical biopsy for interstitial lung diseases, from 2013 to 2017 were analyzed. The HRCT-scans were reviewed by an observer blinded to clinical information of patients. The concordance between histological and HRCT-scan were assessed. Results: Data of 35 patients with uncertain HRCT diagnosis of interstitial lung diseases were analyzed. Most of the patients are male (21-60%). The more frequent HRCT pattern was the UIP inconsistent (17–49%), followed by the UIP possible (12–34%), the consolidation (3–9%), the ground glass opacity (1-3%), the non-specific interstitial pneumonia (NSIP) (1–3%) and others (1-3%). The more common histological diagnosis was the cronic hypersensivity pneumonitis (8–23%), followed by the UIP-like pattern (7–20%), the Sarcoidosis (5-14%), the others (7-20%). In 7 (20%) cases final pathological finding denies HRCT-scans diagnoses; indeed, a moderate agreement between HRCT-scan findings and the final histological diagnosis was observed (kappa index:0.42). Conclusions: HRCT-scan have limitations if the objective is to accurate define interstitial lung diseases. Consequently, pathological assessing should be taken into account, in order to provide more accurate tailored treatment strategies.

Seasonal variation of serum KL-6 levels in patients with interstitial lung diseases

Objective: To evaluate the efficacy and safety of transbronchial lung cryobiopsy (TBCB) and conventional transbronchial lung biopsy (TBLB) in the diagnosis of interstitial lung diseases(ILD). Methods: A prospective, self-control study was conducted during January 2017 and April 2017 in First Affiliated Hospital of Guangzhou Medical University. A total of 25 patients [male 16, female 9; mean age (51±13) years, range 24 to 70 years] with inconclusive diagnosis of interstitial lung diseases were sequentially enrolled. In the study, TBCB (TBCB group) and TBLB (TBLB group) were performed successively under general anesthesia in all patients. The size of biopsy specimens, the duration of procedures, complications and pathological results were recorded. Gaussian distribution data were compared between 2 groups by using Student's t test, while abnormal distribution data were compared by using Wilcoxon rank sum test. The incidences of bleeding and pathologic diagnostic yield between the 2 groups were compared by using Pearson chi-square test. A P-value< 0.05 was assumed to be statistically significant. Results: The specimen sizes of TBCB group and TBLB group were (12.3+ 4.9) and (3.1+ 1.9) mm(2) respectively (t=-18.268, P=0.000). The duration of procedures was (7.8±3.2) and (5.4±2.1)min respectively (Z=-3.001, P=0.003). In TBCB group, the diagnostic yield was 72% (18/25), with valuable pathological results in 2 cases (8%), but in 5 cases (20%) it failed to provide valuable pathological results. In TBLB group, the diagnostic yield was 12% (3/25). There were no useful pathological results in other 22 cases. The difference in the rate of useful pathological results between TBCB group and TBLB group was significant (χ(2)=20.779, P=0.000). There was no pneumothorax or severe bleeding. The rate of mild to moderate bleeding in TBCB group and TBLB group was 47.2%(50/106) and 18.9%(20/106) (χ(2)=19.195, P=0.000) respectively. Conclusion: TBCB is superior to TBLB for lung biopsy as indicated by larger sample size, higher diagnostic yield and less complication. TBCB is valuable for the diagnosis of ILD.

International guidelines and new targeted therapies for idiopathic pulmonary fibrosis have increased the need for accurate diagnosis of interstitial lung disease (ILD), which may lead to more surgical lung biopsies. This study aimed to assess the risk of this procedure in patients from the UK.We used Hospital Episodes Statistics data from 1997 to 2008 to assess the frequency of surgical lung biopsy for ILD in England, UK. We identified cardiothoracic surgical patients using International Classification of Diseases revision 10 codes for ILD and Office of Population Censuses and Surveys Classification of Interventions and Procedures version 4 codes for surgical lung biopsy. We excluded those with lung resections or lung cancer. We estimated in-hospital, 30-day and 90-day mortality following the procedure, and linked to cause of death using data from the UK Office of National Statistics.We identified 2820 patients with ILD undergoing surgical lung biopsy during the 12-year period. The number of biopsies increased over the time period studied. In-hospital, 30-day and 90-day mortality were 1.7%, 2.4% and 3.9%, respectively. Male sex, increasing age, increasing comorbidity and open surgery were risk factors for mortality.Surgical lung biopsy for ILD has a similar mortality to lobectomy for lung cancer, and clinicians and patients should understand the likely risks involved.

Aim and introduction:Diagnosing of interstitial lung disease (ILD) is difficult and expensive. The standard diagnostical approaches to ILD are bronchoalveolar lavage, transbronchial lung biopsy, transbronchial lung cryobiopsy (TBLC) and surgical lung biopsy (SLB). SLB is gold standard for the confident diagnosis of ILD but because of the poor performance of the patients it’s use is limited. We conducted a retrospective study to point out that TBLC plays an important role in diagnosis of ILD and has fewer complications and lower cost than awake video-assisted thoracic surgery (AVATS).Material and methods:132 patients who underwent TBLC and AVATS with a pre-diagnosis of ILD in our hospital between 2015 and 2020 were evaluated retrospectively. Diagnosis rates, complications and costs were recorded.Results:There were no non-diagnostic materials in 44 patients in AVATS arm. Prolonged air leak was observed in 11(25.0%) of the patients, and six of them (13.6%) were discharged with Heimlich Valve (HV). Median length of stay in the hospital was 8 days, while average patient cost was $515.9 (415.2-2662.9) in the AVATS arm. Non-diagnostic material was obtained from 10 (11.3%) of 88 patients in TBLC arm. Six (6.8%) of them had pneumothorax, only one of them required a chest tube. No patient was discharged with HV (p=0.001). Median cost for each patient with a median hospital stay of 2.0 (1.0-21.0) (p<0.001) days was $171.9 (80.8-1493.3) (p<0.001).Discussion:Although TBLC is behind AVATS in terms of diagnostic accuracy, it may be an alternative diagnostic tool in the diagnosis of interstitial lung disease due to its acceptable safety profile and cost-effectiveness.

Early diagnosis of interstitial lung diseases secondary to connective tissue diseases is critical for the treatment and survival of patients. The symptoms, like dry cough and dyspnea, appear late in the clinical history and are not specific, moreover, the current approach to confirm the diagnosis of interstitial lung disease is based on high resolution computer tomography. However, computer tomography involves x-ray exposure for patients and high costs for the Health System, therefore preventing its use for a massive screening campaign in elder people.In this work we investigate the use of deep learning techniques for the classification of pulmonary sounds acquired from patients affected by connective tissue diseases. The novelty of the work consists of a suitably developed pre-processing pipeline for de-noising and data augmentation. The proposed approach is combined with a clinical study where the ground truth is represented by high resolution computer tomography. Various convolutional neural networks have provided an overall accuracy as high as 91% in the classification of lung sounds and have led to an overwhelming diagnostic accuracy in the range 91%−93%. Modern high performance hardware for edge computing can easily support our algorithms. This solution paves the way for a vast screening campaign of interstitial lung diseases in elder people on the basis of a non-invasive and cheap thoracic auscultation.