Using cryoprobes of different sizes combined with cone-beam computed tomography-derived augmented fluoroscopy and endobronchial ultrasound to diagnose peripheral pulmonary lesions: a propensity-matched study.

BACKGROUND: Endobronchial ultrasound (EBUS) and cone-beam computed tomography-derived augmented fluoroscopy (CBCT-AF) are utilized for the diagnosis of peripheral pulmonary lesions (PPLs). Combining them with transbronchial cryobiopsy (TBC) can provide sufficient tissue for genetic analysis. However, cryoprobes of different sizes have varying degrees of flexibility, which can affect their ability to access the target bronchus and potentially impact the accuracy. The aim of this study was to compare the diagnostic efficacy of cryoprobes of varying sizes in CBCT-AF and EBUS for the diagnosis of PPLs. METHODS: Patients who underwent endobronchial ultrasound-guided transbronchial biopsy (EBUS-TBB) and TBC combined with CBCT-AF for PPLs diagnosis between January 2021 and May 2022 were included. Propensity score matching and competing-risks regression were utilized for data analysis. Primary outcome was the diagnostic accuracy of TBC. RESULTS: A total of 284 patients underwent TBC, with 172 using a 1.7-mm cryoprobe (1.7 group) and 112 using a 1.1-mm cryoprobe (1.1 group). Finally, we included 99 paired patients following propensity score matching. The diagnostic accuracy of TBC was higher in the 1.1 group (80.8% vs. 69.7%, P = 0.050), with a similar rate of complications. Subgroup analysis also revealed that the 1.1 group had better accuracy when PPLs were located in the upper lobe (85.2% vs. 66.1%, P = 0.020), when PPLs were smaller than 20 mm (78.8% vs. 48.8%, P = 0.008), and when intra-procedural CBCT was needed to be used (79.5% vs. 42.3%, P = 0.001). TBC obtained larger specimens than TBB in both groups. There is still a trend of larger sample size obtained in the 1.7 group, but there is no statistically different between our two study groups (40.8 mm2 vs. 22.0 mm2, P = 0.283). CONCLUSIONS: The combination of TBC with CBCT-AF and EBUS is effective in diagnosing PPLs, and a thin cryoprobe is preferred when the PPLs located in difficult areas.

TransEBUS: The interpretation of endobronchial ultrasound image using hybrid transformer for differentiating malignant and benign mediastinal lesions.

The purpose of this study is to establish a deep learning automatic assistance diagnosis system for benign and malignant classification of mediastinal lesions in endobronchial ultrasound (EBUS) images. EBUS images are in the form of video and contain multiple imaging modes. Different imaging modes and different frames can reflect the different characteristics of lesions. Compared with previous studies, the proposed model can efficiently extract and integrate the spatiotemporal relationships between different modes and does not require manual selection of representative frames. In recent years, Vision Transformer has received much attention in the field of computer vision. Combined with convolutional neural networks, hybrid transformers can also perform well on small datasets. This study designed a novel deep learning architecture based on hybrid transformer called TransEBUS. By adding learnable parameters in the temporal dimension, TransEBUS was able to extract spatiotemporal features from insufficient data. In addition, we designed a two-stream module to integrate information from three different imaging modes of EBUS. Furthermore, we applied contrastive learning when training TransEBUS, enabling it to learn discriminative representation of benign and malignant mediastinal lesions. The results show that TransEBUS achieved a diagnostic accuracy of 82% and an area under the curve of 0.8812 in the test dataset, outperforming other methods. It also shows that several models can improve performance by incorporating two-stream module. Our proposed system has shown its potential to help physicians distinguishing benign and malignant mediastinal lesions, thereby ensuring the accuracy of EBUS examination.

Incidence and risk factors of postoperative pulmonary complications after oral cancer surgery with free flap reconstruction: A single center study.

BACKGROUND: Postoperative pulmonary complications (PPCs) increase the risk of morbidity and mortality in patients who underwent oral cancer surgery with free flap reconstruction. The association between PPC and preoperative risk factors has been investigated; however, reports on intraoperative factors are limited. Therefore, we investigated PPC incidence and its associated preoperative and intraoperative risk factors in these patients. METHODS: We retrospectively analyzed medical records of patients who underwent free flap reconstruction between 2009 and 2019. PPC was defined as presence of atelectasis, pneumonia, and respiratory failure based on radiological confirmation and clinical symptoms during hospitalization. Mortality, hospital stay, preoperative factors (including age and tumor stages), American Society of Anesthesiologists (ASA) classification, and intraoperative factors (including intraoperative fluids and medications) were recorded. RESULTS: PPC incidence among the 993 patients included in this study was 25.8% (256 patients). Six patients with PPCs died; death was not observed among patients without PPCs (p < 0.001). Patients with PPCs had longer hospitalization than those without PPCs (30.3 vs 23.3 days; p < 0.001). Tumor stage (stage I: reference; stage II [OR]: 3.3, p = 0.019; stage III: 4.4, p = 0.002; stage IV: 4.8, p = 0.002), age (OR: 1.0; p < 0.001), and ASA grade >2 (OR: 1.4; p = 0.020) were independent risk factors of PPC; using labetalol was a borderline significant factor (OR: 1.4; p = 0.050). CONCLUSION: The PPC incidence was 25.8% in patients undergoing oral cancer surgery with free flap reconstruction. Tumor stage, age, and ASA >2 were risk factors of developing PPC.

The changes on anesthetic practice for non-intubated bronchoscopic interventions during Covid-19 pandemic.

Bronchoscopic interventions (BIs) and airway management for bronchoscopy are exceptionally high-risk procedures not only for anesthesiologists, pulmonologists, but also for nursing staff because they expose nurses to COVID-19-containing droplets. However, perioperative changes can be made to the anesthetic management for nonintubated BIs to minimize the spread of COVID-19.

Efficacy and Safety of Cone-Beam Computed Tomography-Derived Augmented Fluoroscopy Combined with Endobronchial Ultrasound in Peripheral Pulmonary Lesions.

BACKGROUND: The diagnostic yield of peripheral pulmonary lesions (PPLs) using radial endobronchial ultrasound (EBUS) remains challenging without navigation systems. Cone-beam computed tomography-derived augmented fluoroscopy (CBCT-AF) represents a recently developed technique, and its clinical utility remains to be investigated. OBJECTIVES: The aim of this study was to investigate the diagnostic yield of transbronchial biopsy (TBB) using a combination of CBCT-AF and radial EBUS. METHODS: We recruited consecutive patients with PPLs who underwent radial EBUS-guided TBB, with or without AF, between October 2018 and July 2019. Following propensity score 1:1 matching, we recorded the procedure-related data and measured their efficacy and safety. RESULTS: While 72 patients received EBUS-plus-AF, 235 patients received EBUS only. We included 53 paired patients following propensity score matching. The median size of lesions was 2.8 and 2.9 cm in the EBUS-plus-AF group and EBUS-only group, respectively. Diagnostic yield was higher in the former group (75.5 vs. 52.8%; p = 0.015). The diagnostic yield for the EBUS-plus-AF group was significantly higher for lesions ≤30 mm (73.5 vs. 36.1%; p = 0.002). Moreover, there was no significant difference in the complication rates (3.8 vs. 5.7%; p = 1.000). Twenty-four nodules (45.3%) were invisible by fluoroscopy in the EBUS-plus-AF group. All of them were identifiable on CBCT images and successfully annotated for AF. The mean radiation dose of total procedure, CBCT, and fluoroscopy was 19.59, 16.4, and 3.17 Gy cm2, respectively. CONCLUSIONS: TBB using a combination of CBCT-AF and EBUS resulted in a satisfactory diagnostic yield and safety.

The correspondence of 3D supporting bone loss and crown-to-root ratio to periodontitis classification.

AIM: Assessing the application of three-dimensional clinical attachment loss (3D-CAL), 3D supporting bone loss (3D-SBL), supracrestal tissue attachment (STA), and crown-to-root ratio (CRR) in evaluating the 2017 periodontitis classification. MATERIALS AND METHODS: We analysed ninety single-rooted human premolars with micro-computed tomography. The amount of 3D-SBL, linear radiographic bone loss (RBL), and CRR corresponding to various periodontitis stages as well as the statistical significance was investigated. RESULTS: From a 3D perspective, the premolars with a 21% of 3D-SBL at 2.0 mm coronal root length (RL) and 15% RBL corresponded to the periodontitis stage I. Premolars with a 44% of 3D-SBL at coronal 4.2-4.4 mm RL and 33% RBL accorded with the periodontitis stage II. Excluding the consideration of STA, CRR = 5:6 and 4:3 were associated with the levels at 15% and 33% RBL, respectively. CONCLUSIONS: A greater percentage of 3D-CAL than that of 2D-CAL is significant at evaluated levels. It is feasible to correlate the 3D-SBL, 3D-CAL, and STA parameters to evaluate the stages of periodontitis severity. However, the current use of RBL and CAL as applied for staging in the 2017 classification might be inconsistent with the evaluated premolar roots length, when STA dimensions are considered.

Rapid on-site cytologic evaluation by pulmonologist improved diagnostic accuracy of endobronchial ultrasound-guided transbronchial biopsy.

BACKGROUND/PURPOSE: Rapid on-site cytologic evaluation (ROSE) has been shown to improve the diagnostic accuracy of endobronchial ultrasound-guided transbronchial biopsy (EBUS-TBB). However, ROSE by a cytopathologist or cytotechnologist is not always available during the procedure. The purposes of this study were to verify that a pulmonologist, after receiving training in cytology, could accurately assess an EBUS-TBB specimen on-site, and to evaluate the contribution of ROSE to EBUS-TBB. METHODS: A retrospective chart review of patients who underwent EBUS-TBB for diagnosis of peripheral pulmonary lesions (PPLs) from January 2014 to June 2017 was performed. PPLs without a malignant diagnosis were excluded. The ROSE result determined by a pulmonologist was compared to the formal imprint cytologic report and pathologic report. The diagnostic accuracy of EBUS-TBB was also compared between those with and without ROSE. RESULTS: Two hundred ninety-three patients who underwent 336 EBUS-TBB procedures for PPL diagnosis and were found to have proven malignancy were enrolled. Eighty-six procedures were performed with ROSE. With the formal imprint cytologic diagnosis as the standard, ROSE had 96.9% sensitivity, 68.2% specificity, 89.9% positive predictive value (PPV), 88.2% negative predictive value (NPV), and 89.5% diagnostic accuracy. With the formal pathologic result as the standard, ROSE had 88.2% sensitivity, 80% specificity, 97.1% PPV, 47.1% NPV, and 87.2% diagnostic accuracy, respectively. The diagnostic accuracy was significantly higher when ROSE was performed during EBUS-TBB (88.4% vs 68.0%, P < 0.001). CONCLUSION: A trained pulmonologist can interpret adequately cytologic smears on-site and effectively improve the accuracy of EBUS-TBB in the diagnosis of PPLs.

Diagnosis of mediastinal tuberculous lymphadenitis using endobronchial ultrasound-guided transbronchial needle aspiration with rinse fluid polymerase chain reaction.

BACKGROUND/PURPOSE: Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) has been gradually introduced in the diagnosis of mediastinal tuberculous (TB) lymphadenitis. The purposes of this study were to evaluate the utility of polymerase chain reaction for Mycobacterium tuberculosis (TB-PCR) using EBUS-TBNA rinse fluid and to explore the factors that influence the accuracy of EBUS-TBNA. METHODS: A retrospective study with prospective data collection was carried out with patients with unselected mediastinal lymphadenopathy who underwent EBUS-TBNA and a TB-PCR study from April 2010 to July 2017. Patients without TB were excluded. The diagnostic accuracy rate for each diagnostic modality (pathology, smear, culture, and TB-PCR) was calculated respectively. The characteristics of the lymph node (LN) and the pathologic findings were analyzed as possible impact factors. RESULTS: 240 consecutive patients who received EBUS-TBNA were enrolled, and in the end, 21 patients with a diagnosis of TB lymphadenitis were included. When combined with histologic results and traditional microbiologic studies, the diagnostic accuracy of EBUS-TBNA was 57.1%. If TB-PCR was also utilized, the diagnostic accuracy would significantly increase to 71.4% (p < 0.001). Univariate and multivariate regression analysis revealed that pathology showing necrosis had a higher positive microbiologic result when using EBUS-TBNA rinse fluid. CONCLUSION: EBUS-TBNA is a valuable tool for diagnosis of mediastinal TB lymphadenitis. Using TB-PCR assay and targeting LNs with a necrotic component would improve the diagnostic performance of EBUS-TBNA.

Differentiating malignant and benign lymph nodes using endobronchial ultrasound elastography.

BACKGROUND/PURPOSE: Endobronchial ultrasound (EBUS) elastography is a new technique that provides information on tissue compressibility during endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA). The purposes of this study were to evaluate the utility of EBUS elastography in differentiating malignant and benign mediastinal lymph nodes (LNs) and to explore the factors that influence its accuracy. METHODS: A retrospective chart review of patients who underwent EBUS-TBNA from October 2016 to July 2017 was performed. EBUS with conventional B-mode features and elastographic patterns were compared with the final pathology results or clinical follow-up. We used the following EBUS elastographic patterns for classification: type 1, predominantly non-blue (green, yellow and red); type 2, part blue, part non-blue; type 3, predominantly blue. The potential impacts of the characteristics of LNs, the underlying lung diseases and obtaining fibrotic components from EBUS-TBNA specimens were evaluated relative to the accuracy of EBUS elastography. RESULTS: A total of 206 LNs from 94 patients were retrospectively evaluated. In classifying type 1 as 'benign' and type 3 as 'malignant,' the sensitivity, specificity, positive predictive value, negative predictive value and diagnostic accuracy rate were 90.6, 82.6, 71.6, 94.7 and 85.2%, respectively. The EBUS elastographic patterns had higher diagnostic yields and negative predictive values than conventional B-mode features. Logistic regression analysis revealed that central necrosis was a factor that influenced the accuracy of elastography in malignant LNs. The fibrotic component within benign LNs could cause an incorrect elastographic pattern. CONCLUSION: EBUS elastography is a valuable tool in discriminating benign and malignant mediastinal LNs.

Passive Magnetic-Flux-Concentrator Based Electromagnetic Targeting System for Endobronchoscopy.

In this paper, we demonstrate an innovative electromagnetic targeting system utilizing a passive magnetic-flux-concentrator for tracking endobronchoscope used in the diagnosis process of lung cancer tumors/lesions. The system consists of a magnetic-flux emitting coil, a magnetic-flux receiving electromagnets-array, and high permeability silicon-steel sheets rolled as a collar (as the passive magnetic-flux-concentrator) fixed in a guide sheath of an endobronchoscope. The emitting coil is used to produce AC magnetic-flux, which is consequently received by the receiving electromagnets-array. Due to the electromagnetic-induction, a voltage is induced in the receiving electromagnets-array. When the endobronchoscope's guide sheath (with the silicon-steel collar) travels between the emitting coil and the receiving electromagnets-arrays, the magnetic flux is concentrated by the silicon-steel collar and thereby the induced voltage is changed. Through analyzing the voltage-pattern change, the location of the silicon-steel collar with the guide sheath is targeted. For testing, a bronchial-tree model for training medical doctors and operators is used to test our system. According to experimental results, the system is successfully verified to be able to target the endobronchoscope in the bronchial-tree model. The targeting errors on the x-, y- and z-axes are 9 mm, 10 mm, and 5 mm, respectively.

Non-intubated bronchoscopic tracheobronchial surgeries with electroencephalogram-monitored intravenous anesthesia: feasibility and outcomes.

Background: Anesthesia remains challenging for bronchoscopic tracheobronchial surgeries (BTS) involving surgical manipulations for central airway obstruction within shared airways. To provide complete airway use through intervention with spontaneous breathing without endotracheal tubes, monitored non-intubated anesthesia has been successfully applied with electroencephalogram-derived monitored total intravenous anesthesia. This study evaluated the feasibility and the outcomes of BTS with monitored non-intubated anesthesia. The factors associated with desaturation and complications were also analyzed. Methods: Data from patients receiving non-intubated BTS performed between October 2019 and August 2022 were retrospectively collected. Intraoperative results and postoperative outcomes were analyzed. Results: Data of 92 patients were collected. Supraglottic airways devices and high-flow nasal oxygen were used in 68 and 24 patients respectively. Surgery was successfully completed in 87 patients (94.6%), whereas three patients required conversion to intubation because of substantial bleeding. In total, 11% of patients experienced desaturation [oxygen saturation (SpO2) <90%] for an average of 9 minutes. Unexpected admission to the intensive care unit (ICU) occurred in 12.2% (5/41) of patients from outpatient department and 7.8% (4/51) of hospitalization settings because of high-grade surgical bleeding. With comparable desaturation incidence, tracheal surgery had significantly longer desaturation times (14.5±6.9 min) than bronchial surgeries (5.8±2.6 min) did. Conclusions: Monitored non-intubated anesthesia with spontaneous breathing is feasible for BTS, with high success rate, few complications, and rapid recovery. High-grade bleeding remains the most unpredictable risk for intraoperative desaturation and postoperative ICU admission, especially in tracheal obstruction cases.

Quality of dental treatments under intravenous sedation among patients with disability: A self-matching study.

Background/purpose: Patients with disabilities usually have difficulties in communication and mobility, and the quality of the dental treatments are often inferior. This study uses the Taiwan National Health Insurance Database to analyze the quality of dental treatment for patients with disabilities who receive intravenous sedation (IVS). Materials and methods: This study selected patients with disabilities who received dental treatment under IVS. Their oral cavity was divided into three major sections: anterior teeth, upper posterior teeth, and lower posterior teeth. Self-matching of the same section was conducted to observe whether operative dental treatment (OD) with or without IVS affected the occurrence of dental retreatment. This study observed the occurrence of refilling and the duration from the end of treatment until retreatment to compare treatment differences with or without IVS. Results: After self-matching, this study found 158 patients who received dental treatment within the same section with and without IVS. During a follow-up period of 17 years, 75.18% of the patients who received OD treatment required refilling, 10.87% required endodontic treatment, and 5.67% required tooth extraction. After OD treatment with IVS, the risks of refilling, endodontic treatment, and tooth extraction were 0.71 (95% CI: 0.58-0.87, P < 0.001), 0.77 (95% CI: 0.48-1.23, P = 0.28), and 0.64 (95% CI: 0.32-1.27, P = 0.20), respectively. Conclusion: For patients with disabilities, OD treatment with IVS significantly reduces the risk of refilling compared with OD treatment without IVS. IVS can be ideal for people with disabilities who receive dental treatment.

Work of breathing and respiratory drive in obesity.

Obesity, particularly severe central obesity, affects respiratory physiology both at rest and during exercise. Reductions in expiratory reserve volume, functional residual capacity, respiratory system compliance and impaired respiratory system mechanics produce a restrictive ventilatory defect. Low functional residual capacity and reductions in expiratory reserve volume increase the risk of expiratory flow limitation and airway closure during quiet breathing. Consequently, obesity may cause expiratory flow limitation and the development of intrinsic positive end expiratory pressure, especially in the supine position. This increases the work of breathing by imposing a threshold load on the respiratory muscles leading to dyspnoea. Marked reductions in expiratory reserve volume may lead to ventilation distribution abnormalities, with closure of airways in the dependent zones of the lungs, inducing ventilation perfusion mismatch and gas exchange abnormalities. Obesity may also impair upper airway mechanical function and neuromuscular strength, and increase oxygen consumption, which in turn, increase the work of breathing and impair ventilatory drive. The combination of ventilatory impairment, excess CO(2) production and reduced ventilatory drive predisposes obese individuals to obesity hypoventilation syndrome.

Compliance and barriers to implementing the sepsis resuscitation bundle for patients developing septic shock in the general medical wards.

BACKGROUND/PURPOSE: This two-part study aimed to investigate compliance with the sepsis resuscitation bundle (SRB) and the barriers to its implementation for patients developing septic shock in the general medical wards. METHODS: In the first part, medical records of patients who were admitted to the intensive care unit from the general medical wards due to septic shock were reviewed. Compliance rates with the six SRB components were assessed. In the second part, responsible junior physicians (first-year and second-year residents) in the general wards and senior physicians (third-year residents and fellows) were randomly invited for questionnaire-based interviews. RESULTS: In the first part, during the 6-month study period, 40 patients were included. Overall compliance with the SRB within 6 h was only 2.5%, mainly due to femoral catheterization (42.5%) and the lack of measuring central venous oxygen saturation (ScvO2). Delayed completion of SRB components contributed little to the low compliance rate. In the second part, based on the questionnaire results of 71 junior physicians and 64 senior physicians, the junior physicians were less familiar with the SRB guidelines, particularly regarding the meaning of ScvO2 (p = 0.01) and management of low ScvO2 (p = 0.04). Junior physicians were also more reluctant to measure the central venous pressure (CVP; p = 0.04) and the ScvO2 (p = 0.01), and were also less confident with internal jugular vein or subclavian vein catheterization (p < 0.001). CONCLUSION: Compliance with the SRB for patients developing septic shock in the general medical wards is very low. Besides providing educational programs to improve awareness and acceptance of the SRB, measures to help in central venous catheterization and completion of SRB may be considered.

Effects of oral exercise on tongue pressure in Taiwanese older adults in community day care centers.

BACKGROUND/PURPOSE: Oral exercise is a training method for swallowing dysfunction in older adults. The study investigated the effect of oral exercise on tongue pressure in older adults in Taiwanese community day care centers over a 3-month period. MATERIALS AND METHODS: Participants over age 50 who were able to communicate and participating for the duration of the 12-week period were recruited from five community day care centers. A 15-min weekly group oral exercise activity was conducted. The tongue pressures were measured and multivariable linear regression models were used to assess the effect of oral exercise intervention on the participants' tongue pressures. RESULTS: A total of 66 older adult participants, among whom the mean age was 78.06 ± 10.74 years. Tongue pressure continued improving during the intervention period, and the mean tongue pressure at the end of the study was 20.63 ± 10.45 kPa, which was significantly higher than the baseline measurement (16.92 ± 10.62 kPa, p < 0.001). Participants exhibited significant improvement in tongue pressure regardless of their age groups. Moreover, participants with one to seven pairs of functional tooth units (FTUs) exhibited significantly more improvement in tongue pressure (16.00 kPa, 95% CI = 2.58-29.43) than those without FTUs (p = 0.021). CONCLUSION: Oral exercise over a 3-month period significantly improved tongue pressure among the study participants regardless of their gender or age group. Oral exercise should be integrated into comprehensive health promotion programs to assist in the improvement and maintenance of oral function among older adults.

Effectiveness of Endobronchial Ultrasound-Guided Transbronchial Biopsy Combined With Tissue Culture for the Diagnosis of Sputum Smear-Negative Pulmonary Tuberculosis.

Background: Microorganisms of tuberculosis (TB) are frequently difficult to identify from the airway specimen; therefore, lung biopsy for further histologic and microbiologic study is required. Endobronchial ultrasound-guided transbronchial biopsy (EBUS-TBB) is used for the diagnosis of pulmonary malignancy, but is rarely in the TB population. The purpose of this study was to verify the effectiveness and safety of EBUS-TBB with histologic study and tissue culture in the diagnosis of sputum smear-negative pulmonary TB. Methods: Patients who underwent EBUS-TBB with histologic study and TB tissue culture for clinically suspected, but sputum smear-negative pulmonary TB from January 2016 to December 2018, were included. The accuracy of each diagnostic modality was calculated, respectively. Factors that might influence the positive rate of TB culture (washing fluid and tissue specimen) were also evaluated. Results: One hundred sixty-one patients who underwent EBUS-TBB for clinically suspected, but sputum smear-negative pulmonary TB, were enrolled, and 43 of them were finally diagnosed as having pulmonary TB. The sensitivity of washing fluid (a combination of smear, culture, and polymerase chain reaction for TB) and tissue specimen (a combination of pathology and tissue culture) via EBUS-TBB for TB diagnosis were 48.8 and 55.8%, respectively. The sensitivity for TB diagnosis would be elevated to 67.4% when both washing fluid and tissue specimens are used. The positive TB culture rate would not statistically increase with a combination of tissue specimens and washing fluid. Univariate analysis revealed that TB microorganisms would be more easily cultivated when lesions had an abscess or cavity on the computed tomography (CT) image (presence vs. absence; 62.5 vs. 26.3%, p = 0.022), heterogeneous echogenicity on the EBUS finding (heterogeneous vs. homogeneous; 93.3 vs. 21.4%, p = 0.001), or a necrotic pattern via histologic study (presence vs. absence; 70.6 vs. 30.8%, p = 0.013). Heterogeneous echogenicity in the EBUS finding was the independent predictor according to the results of multivariate analysis. None of our patients encountered major adverse events or received further intensive care after EBUS-TBB. Conclusion: Endobronchial ultrasound-guided transbronchial biopsy is safe and effective for use in diagnosing sputum smear-negative pulmonary TB. EBUS echoic feature is also a predictor of the positive TB culture rate in pulmonary TB. However, tissue culture via EBUS-TBB has little effect in improving the positive TB culture rate.

Nonintubated bronchoscopic interventions with high-flow nasal oxygen: A retrospective observational study.

ABSTRACT: To determine the feasibility on maintaining oxygenation of high-flow nasal oxygenation (HFNO) with bispectral index-guided intravenous anesthesia for nonintubated interventional bronchoscopy (NIIB). If desaturation happens, the factors influencing intraprocedural desaturation were also analyzed.This is a single-center retrospective study on patients receiving NIIB with HFNO and intravenous anesthesia guided by bispectral index levels to the depth of general anesthesia, which were between 40 and 60. Intraprocedural desaturation (SPO2 < 90%) and complications (bleeding, delayed discharge, unexpected admission) were collected. Factors affecting desaturation and complications were analyzed including patients' factors (age, American Society of Anesthesiologists classification, body mass index [BMI]), procedural factors (procedural time, with or without use of cryoprobe), and setting (outpatient or hospitalized).Records of 223 patients receiving NIIB were collected. The NIIB procedures time was 56.1 ±â€Š26.8 minute. Sixty patients (26.9%) presented desaturation events. Higher BMI, but not procedure time or setting, was significantly associated with desaturation. The desaturation were resolved after relieving upper airway obstruction but 1 patient required bag-valve-mask ventilation to restore oxygenation. Accidental massive bleeding and intraprocedural desaturation during tracheal and bronchial recannulation with cryoprobes happened in 2 patients and 1 of them was admitted to intensive care unit.HFNO is feasible to maintain oxygenation during NIIB only if there is effective upper airway management especially for patients with higher BMI. Longer procedural time and different setting did not affect the desaturation rate. Complications and unexpected admission were associated with the use of cryoprobes.

Using DeepLab v3 + -based semantic segmentation to evaluate platelet activation.

This research used DeepLab v3 + -based semantic segmentation to automatically evaluate the platelet activation process and count the number of platelets from scanning electron microscopy (SEM) images. Current activated platelet recognition and counting methods include (a) using optical microscopy or SEM images to identify and manually count platelets at different stages, or (b) using flow cytometry to automatically recognize and count platelets. However, the former is time- and labor-consuming, while the latter cannot be employed due to the complicated morphology of platelet transformation during activation. Additionally, because of how complicated the transformation of platelets is, current blood-cell image analysis methods, such as logistic regression or convolution neural networks, cannot precisely recognize transformed platelets. Therefore, this study used DeepLab v3 + , a powerful learning model for semantic segmentation of image analysis, to automatically recognize and count platelets at different activation stages from SEM images. Deformable convolution, a pretrained model, and deep supervision were added to obtain additional platelet transformation features and higher accuracy. The number of activated platelets was predicted by dividing the segmentation predicted platelet area by the average platelet area. The results showed that the model counted the activated platelets at different stages from the SEM images, achieving an error rate within 20%. The error rate was approximately 10% for stages 2 and 4. The proposed approach can thus save labor and time for evaluating platelet activation and facilitate related research.

Effectiveness of convolutional neural networks in the interpretation of pulmonary cytologic images in endobronchial ultrasound procedures.

BACKGROUND: Rapid on-site cytologic evaluation (ROSE) helps to improve the diagnostic accuracy in endobronchial ultrasound (EBUS) procedures. However, cytologists are seldom available to perform ROSE in many institutions. Recent studies have investigated the application of deep learning in cytologic image analysis. As such, the present study analyzed lung cytologic images obtained by EBUS procedures, and employed deep-learning methods to distinguish between benign and malignant cells and to semantically segment malignant cells. METHODS: Ninety-seven patients who underwent 104 EBUS procedures were enrolled. Four hundred and ninety-nine lung cytologic images obtained via ROSE, including 425 malignant and 74 benign, and most malignant were lung adenocarcinoma (64.3%). All the images were used to train a residual network model with 101 layers (ResNet101), with suitable hyperparameters selected to classify benign and malignant lung cytologic images. An HRNet model was also employed to mark the area of malignant cells. Automatic patch-cropping was adopted to facilitate dataset preparation. RESULTS: Malignant cells were successfully classified by ResNet101 with 98.8% classification accuracy, 98.8% sensitivity, and 98.8% specificity in patch-based classification; 95.5% classification accuracy in image-based classification; and 92.9% classification accuracy in patient-based classification. Malignant cell area was successfully marked by HRNet with a mean intersection over union of 89.2%. The automatic cropping method enabled the system to complete diagnosis within 1 s. CONCLUSIONS: This is the first study to combine lung cytologic image deep-learning classification with semantic segmentation. The model was optimized for high accuracy and the automatic cropping facilitates the clinical application of our model. The success in both lung cytologic images classification and semantic segmentation on our dataset shows a promising result for clinical application in the future.