Lung Scan Research Articles

AI-enabled automated cardiac chambers volumetry in non-contrast ECG-gated cardiac scans vs. non-contrast non-gated lung scans

Abstract Introduction We have developed an AI-enabled automated volume measurement of cardiac chambers (AutoChamber) that works on ECG-gated coronary artery calcium scans and correlates well with contrast enhanced coronary CT angiography scans. We have recently reported that increased left atrial volume measured by AutoChamber is a strong predictor of new onset atrial fibrillation (AF) in asymptomatic individuals of Multi-Ethnic Study of Atherosclerosis (MESA). In this study, we compare the volumetry results in ECG- gated CAC scans with those of non-gated full-chest lung cancer screening scans in the same individuals. Methods We have studied 169 cases of paired ECG-gated cardiac CT scans and non-gated lung scans obtained from Harbor UCLA. Mean±SD for age was 62.1±10.0 years with 52% female participants. All cases were asymptomatic and were scanned for preventive health assessment. AutoChamber was run on all cases by an independent operator who was not involved in data analysis. P value was calculated using a two-tailed test of significance with α=0.05. Results AutoChamber in cardiac scans vs lung scans reported volume (Mean±SD) for left atrium (LA) was 63.8 ± 18.5 vs. 65.5 ± 19.4, left ventricle (LV) 102.8 ± 25.3 vs. 105.5 ± 25.2, right atrium (RA) 81.9 ± 20.5 vs. 85.7 ± 21.9 right ventricle (RV), 140.7 ± 34.2 vs. 134.2 ± 33.7, left ventricle wall (LVW) 113.0 ± 26.6 vs. 109.7 ± 27.0 respectively (P < 0.0001). Strong correlation was shown between cardiac and lung scans for each cardiac chamber: LA (R = 0.92), LV (R = 0.93), RA (R = 0.91), RV (R = 0.92), and left ventricular wall (LVW) R = 0.95. Conclusions AutoChamber volumetry results are similar in ECG-gated cardiac scans vs non-gated full-chest lung scans. This AI-enabled automated tool is promising as it can provide added value to patients undergoing coronary calcium and lung cancer screening scans flagging enlarged cardiac chambers at risk of AF and heart failure.

Feasibility of quantitative evaluation of hemodynamics using SPECT/CT in patients with chronic thromboembolic pulmonary hypertension

Abstract Background A ventilation/perfusion (V/Q) lung scan is recommended in the diagnostic work-up of patients with newly diagnosed pulmonary hypertension to rule out chronic thromboembolic pulmonary hypertension (CTEPH). V/Q single-photon emission computed tomography (SPECT) is considered the method of choice for diagnosis in CTEPH because it allows more precise evaluation than planar imaging. However, the evaluation of lung perfusion using V/Q SPECT imaging remains mainly a qualitative evaluation, and no quantitative method has been established. We hypothesized that the standardized uptake value (SUV) technique in Positron Emission Tomography (PET)-CT, a nuclear imaging technique well suited for quantitative of tumor biology, could be applied to quantitative assessment of lung perfusion. Purpose The purpose of this study was to evaluate the correlation between pulmonary perfusion distribution and hemodynamic data in Tc-labeled large-assembly albumin (99mTc-MAA) SPECT images in order to determine the feasibility of SPECT/CT for quantitative assessment of lung perfusion. Methods Twenty-five patients with CTEPH who underwent BPA and received SPECT-CT were included. Since the injected 99mTc-MAA selectively accumulates only in the lungs, SUV normalization was conducted using each patient’s lung volume, calculated by SPECT/CT and defined as SUV lung volume (LV) . The percentage of lung volume below each SUVLV value in total lung volume on SPECT/CT was examined before BPA, after two procedures of BPA, and six months after a series of BPA, and the correlations with hemodynamic parameters on right heart catheterization at each time point were evaluated. Results The Percent lung volume below SUVLV of 0.7 in total lung volume before BPA, after two procedures of BPA, and six months after a series of BPA had the strongest correlation with mean pulmonary artery pressure (mPAP) (rs; 0.727, p<0.001, Figure 1). The percent lung volume below SUVLV of 0.7 decreased with the BPA procedure in each patient with CTEPH (Figure 2). Furthermore, receiver operating characteristic analysis revealed that a threshold for the percent lung volume below SUVLV of 0.7 of 50.3% or greater could identify mPAP greater than 21 mmHg for right heart catheterization (area under the curve = 0.86, 95% CI 0.78-0.94, p<0.001). Conclusion Percent lung volume below SUVLV of 0.7 in total lung volume using SPECT/CT might reflect the severity of hemodynamics in patients with CTEPH. This method would be feasible for quantitative assessment of lung perfusion, even inter-patient and intra-patient.Figure 1Figure 2

A Review on Venous Thrombosis: Management with anticoagulants

Thrombosis is the most common condition and the world's leading cause of death due to blood clot development in blood arteries. Thromboembolism includes classification based on where the thrombus gets attached to the blood vessels. Deep vein thrombosis (DVT) and pulmonary embolism (PE) are two of the main causes of vascular death globally, making up venous thromboembolism (VTE). According to estimates, the yearly incidence rates of VTE in individuals with European ancestry vary from 104 to 183 per 100,000 person-years. Thrombus development and propagation are dependent upon the existence of anomalies in blood flow, blood vessel wall, and blood clotting components, which are together referred to as Virchow's triad. A comprehensive diagnostic approach, which includes clinical evaluation, D-dimer testing, ultrasonography, and lung scan, provided a non-invasive diagnosis for most outpatients with suspected venous thromboembolism. Anticoagulant medication is the primary and established treatment for people who have acute venous thromboembolism (VTE). Among the treatment options available, UFH & LMWH are found to be safe for the growing fetus as they appear to not cross the placenta. Oral anticoagulants targeting thrombin or factor Xa have been introduced, replacing vitamin K antagonists. In a study involving DOACs vs VKAs in patients with pre-existing heart conditions, patients receiving DOACs for non-valvular atrial fibrillation had predominantly superior efficacy and safety. Keywords: Venous thromboembolism, Anticoagulants, Deep vein thrombosis, Pulmonary embolism, Thrombus

Development of Quantitative Norms for Normal Lung Uptake Based on Three-Dimensional Gallium-67 Single Photon Emission Computed Tomography/Computed Tomography

Abstract Purpose Gallium-67 (Ga-67) lung scans assess alveolitis and interstitial lung disease, with Ga-67 accumulation correlating with inflammation intensity as seen in lung biopsy sections. Both semi-quantitative and quantitative methods have been used, with the latter providing an inflammatory activity index linked to lung lavage and histopathological scores. However, differing reference points result in varying outcomes. This study aimed to establish standard Ga-67 index parameters using semi-quantitative analysis and a linear regression model based on planar and SPECT/CT images. Methods Twenty subjects without lung disease received a 5–6 mCi Ga-67 injection via the ankle. Both planar and SPECT/CT images were analyzed, with semi-quantitative values assessed using GraphPad Prism 9.5.1. Results Compared to planar images, SPECT/CT acquisitions for the lung-to-arm uptake ratio proved the most reliable indicator for assessing lung inflammation. Increased lung Ga-67 uptake was defined as greater than 2 standard deviations from the average Ga-67 uptake for healthy subjects. The normal range was 0.065 ± 0.049 for the right side and 0.076 ± 0.070 for the left side. Conclusion Lung-to-arm ratios in SPECT/CT images are more accurate than those in planar images. This method should be adopted as a standard clinical practice, providing more reliable diagnostic information and improving patient management. Future studies should compare patients without lung disease to those with lung disease to determine the diagnostic benefit of these norms.

Human lung cancer classification and comprehensive analysis using different machine learning techniques.

Lung cancer is the most common causes of death among all cancer-related diseases. A lung scan examination of the patient is the primary diagnostic technique. This scan analysis pertains to an MRI, CT, or X-ray. The automated classification of lung cancer is difficult due to the involvement of multiple steps in imaging patients' lungs. In this manuscript, human lung cancer classification and comprehensive analysis using different machine learning techniques is proposed. Initially, the input images are gathered using lung cancer dataset. The proposed method processes these images using image-processing techniques, and further machine learning techniques are utilized for categorization. Seven different classifiers including the k-nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), multinomial naive Bayes (MNB), stochastic gradient descent (SGD), random forest (RF), and multi-layer perceptron (MLP) classifier are used, which classifies the lung cancer as malignant and benign. The performance of the proposed approach is examined using performances metrics, like positive predictive value, accuracy, sensitivity, and f-score are evaluated. Among them, the performance of the MLP classifier provides 25.34%, 45.39%, 15.39%, 41.28%, 22.17%, and 12.12% higher accuracy than other KNN, SVM, DT, MNB, SGD, and RF respectively. RESEARCH HIGHLIGHTS: Lung cancer is a leading cause of cancer-related death. Imaging (MRI, CT, and X-ray) aids diagnosis. Automated classification of lung cancer faces challenges due to complex imaging steps. This study proposes human lung cancer classification using diverse machine learning techniques. Input images from lung cancer dataset undergo image processing and machine learning. Classifiers like k-nearest neighbors, support vector machine, decision tree, multinomial naive Bayes, stochastic gradient descent, random forest, and multi-layer perceptron (MLP) classify cancer types; MLP excels in accuracy.

Optimizing pulmonary carcinoma detection through image segmentation using evolutionary algorithms

<span lang="EN-US">This paper’s goal is to suggest an image segmentation technique for use with medical images, specifically computer tomography scan images, to aid doctors in understanding the images. To address a variety of picture segmentation issues, it is necessary to investigate and apply novel evolutionary algorithms. The study focuses on pulmonary carcinoma, which is the cancer that affects males the most frequently across the globe. For proper treatment and life-saving measures, early identification of lung cancer is essential. To identify lung cancer, doctors frequently employ the computed tomography imaging technique. In order to extract tumours from lung scans, the study analyses the effectiveness of three optimization algorithms: k-means clustering, particle swarm optimization, and modified guaranteed convergence particle swarm optimization. The study also examines the pre-processing performance of four filters, namely the mean, bilateral, gaussian, and laplacian filters, shows that the bilateral filter is best suited for CT scans of the body. To test the proposed technique on 30 examples of lung scans. The proposed algorithm is tested on 30 sample lung images. The results show that the modified guaranteed convergence particle swarm optimization algorithm has the highest accuracy of 96.01%.</span>

Choosing the optimal combination of lungs lobe evaluation during focused pulmonary ultrasonography in calves

Bovine respiratory disease (BRD) poses significant challenges on beef and dairy farms, impacting mortality rates, animal welfare, and production efficiency. Although pulmonary ultrasonography is highly sensitive and specific for monitoring lung lesions and diagnosing BRD, its practical application could be optimized by focusing on the most commonly affected lung lobes. This study first evaluated the efficacy of focused lung ultrasonography for diagnosing BRD in calves, examining individual lung lobes and their associations versus the extensive lung scanning under various disease prevalence scenarios. Then, the relationship between individual and combined clinical respiratory signs vs lung consolidation was analyzed. In a combined analysis, 193 Holstein calves from a longitudinal study and 112 Angus calves from a cross-sectional study underwent a total of 1265 complete bilateral thoracic ultrasonographic evaluations from 1 to 6 mo of age. Then, it was assessed the agreement and sensitivity of specific lung lobe combinations compared with the findings from total lung ultrasonography. The Classification and Regression Tree (CART) algorithm was used to suggest an optimal examination sequence, and logistic regression was applied to associate specific clinical signs with the presence of lung consolidation adjusting for breed and calf age. Findings reveal that the most sensitive areas are cranial (K: 0.867; Se: 84.7%) and the caudal (K: 0.433; Se: 40.3%) portions of the right cranial lobe, the caudal portion (K: 0.235; Se: 20.6%) of the left cranial lobe, and the middle lobe (K: 0.25; Se: 22%). The optimal lobe combinations for focused lung ultrasonography were identified as the right cranial lobe paired with either the left cranial lobe or the middle lobe. Focused techniques achieved sensitivity over 94% and maintained good agreement. Using these focused techniques were relatively robust to various true lung consolidation scenarios. CART analysis recommended initiating examinations with the right cranial lobe, proceeding to the left cranial lobe, and concluding with the middle lobe. While spontaneous cough was linked to pneumonia presence, reliance on a single clinical sign is not advised due to low sensitivity (26.8%) and high specificity (85.4%); it should merely prompt further ultrasound assessment. In conclusion, focused lung ultrasonography, especially utilizing the right cranial lobe in conjunction with the left cranial lobe or the middle lobe, emerged as effective strategies for focused pulmonary ultrasonography, preserving the accuracy of the results.

Diagnostic management of acute pulmonary embolism

Straightforward, accurate diagnostic management in patients presenting with clinically suspected pulmonary embolism (PE) is essential, since starting anticoagulant treatment may give important adverse effects of bleeding, while false exclusion of the disease may lead to recurrent VTE, with associated morbidity and mortality. In the past three decades, considerable improvement in the diagnostic management of PE has been made. Computed tomography pulmonary angiography (CTPA) has largely replaced conventional pulmonary angiography and ventilation-perfusion lung scanning as the imaging methods of choice. Several diagnostic algorithms, all able to minimize the need for radiological imaging have been developed and validated. Lastly, within the diagnostic algorithms, varying d-dimer cut-off levels have successfully been introduced to further downsize the need for radiological imaging.

Diagnostic value of antibody testing in comparison with lung scan and PCR in patients suspected of having COVID-19.

SARS-CoV-2 is a newly discovered viral infection. It's still unclear how antibodies react in infected individuals, and there is not enough evidence to support the clinical use of antibody examination. This study evaluates the diagnostic value of serologic tests for diagnosing COVID-19. 32 patients for whom serologic testing was performed within 7 to 21 days from symptom onset and whether they were diagnosed with COVID-19 by both PCR and lung HRCT as gold standard tests at the same time, were included in the study. Serologic tests (IgM / IgG) compared to PCR and lung HRCT scan to diagnose COVID-19, were 89.3% specific and 59.6% sensitive. Positive predictive value (PPV) was 95% and negative predictive value (NPV) was 37%. The diagnostic accuracy index of the serologic test was 0.745 (CI 0.651-0.838) (p-value <0.001). Serologic testing can be a complementary alternative for SARA-CoV-2 nucleic acid RT-PCR, although it cannot replace it completely. IgG/IgM combo test kits and RT-PCR together can give more insight into the diagnosis of SARS-CoV-2.

Radiosynthesis of 99MTc-Montelukast as a Novel Potential Radiopharmaceutical Model for Lung Scanning

Radiosynthesis of 99MTc-Montelukast as a Novel Potential Radiopharmaceutical Model for Lung Scanning

Impact of COVID-19 on Ventilation-Perfusion (V/Q) Scans: A Comparative Analysis of Pre-COVID-19 Era V/Q Scans and Post-COVID-19 Era Perfusion Scans.

Introduction The COVID-19 pandemic has profoundly impacted medical practices, including nuclear medicine. To minimize aerosol transmission risks, lung perfusion scintigraphy was preferred over traditional ventilation-perfusion (V/Q) scintigraphy during the pandemic. This study compares lung perfusion scans performed during COVID-19 with V/Q scans from the pre-COVID era. After reviewing this study, the reader will learn about V/Q scintigraphy and lung perfusion. Methods This retrospective observational study, conducted from December 2018 to July 2021, involved 868 patients - 511 in the pre-COVID era and 357 in the post-COVID era - at a single tertiary care center. The pretest probability of pulmonary embolism (PE) was determined using Wells' criteria, and data including demographics, clinical findings, and diagnostic test results (V/Q or lung perfusionscintigraphy) were collected. Results A 30% decline in lung scans was observed during the pandemic. In the pre-COVID era, 68.3% of scans had low, 27.8% had intermediate, and 3.9% had high probability for PE. During the pandemic, perfusion-only scans showed 57.3% low, 32.9% indeterminate, and 9.8% high probability for PE. Among COVID-19-positive patients, 48.9% had intermediate, and 11.1% had high probability scans. The rise in indeterminate and high-probability scans during the pandemic is attributed to COVID-19-related lung changes and hypercoagulability. Conclusion The perfusion component of lung scans is typically sufficient for evaluating acute PE. Omitting the ventilation part of the V/Q scan had minimal impact, with only a 5.1% increase in indeterminate/non-diagnostic scans using perfusion-only modified Prospective Investigation of Pulmonary Embolism Diagnosis II (PIOPED II) criteria during the post-COVID-19 era, likely due to underlying lung parenchymal involvement in COVID-19 patients. Additionally, there was a 5.9% rise in high-probability scans, attributed to the hypercoagulability and vascular complications associated with COVID-19.

Lung Ultrasound Score in Neonatal RDS: Agreement between Sonography Expert and Neonatologists with Varying Levels of Experience.

This study aimed to assess interrater agreement in lung ultrasound scores (LUS) among neonatologists with varying experience levels and an expert sonographer. A post hoc analysis was conducted on data from a prospective multicenter study involving 155 infants born <34 weeks' gestation, all with respiratory distress syndrome. A total of 629 lung scans were performed and video-recorded by 21 point-of-care sonographers, including both experienced (n = 7) and inexperienced (n = 14) evaluators. Subsequently, a blinded expert sonographer re-evaluated the assigned LUS values. The Cohen's kappa statistic for individual pulmonary field assessments ranged from 0.89 to 0.93, indicating nearly perfect agreement. The interclass correlation coefficient (ICC) confirmed excellent reliability on total LUS values, demonstrating similar performance of experienced (ICC = 0.92, 95% CI 0.90-0.94) and inexperienced sonographers (ICC = 0.93, 95% CI 0.92-0.94). This study underscores that lung ultrasound is easily learned, and LUS exhibits outstanding reproducibility, irrespective of the sonographer's level of experience.

Lung Volume and Pneumatization Changes in Children in Early Post-Surgical Period After Correction of Severe Neuromuscular Scoliosis Complicated with Respiratory Failure: Cohort Study

Background. The effect of spinal deformity surgical correction in children with severe neuromuscular scoliosis (NMS) on lung function remains unexplored. Objective. The aim of the study is to — to survey the dynamics of volume and structure of lungs pneumatization in children after surgical correction of severe neuromuscular deformities of the spine complicated by respiratory disorders. Methods. CT scans of lungs from 5 children with right-sided NMS, grade IV (Cobb angle &gt; 50°) and functional respiratory disorders (lung capacity &lt; 30% of normal value according to spirometry data and/or clinical signs of respiratory failure) were retrospectively studied. Right and left lungs volumes, their ratio (asymmetry index), indicators of distribution of tissue density of each lung (as a percentage of total volume) before (not earlier than 2 months) and after (not later than 3 months) surgical correction of scoliosis were determined via the data processing from CT scans of the thoracic spine. Results. All children had both lung volumes below reference values (healthy peers) before surgery. The right lung volume increased by 11% (6.4–40.6%), the left lung — by 41% (22.5–90%) with the asymmetry index approaching the reference values for the corresponding age after correction of spinal deformity (the value of scoliotic deformity decreased (median) from 94 to 68°). The volume of normal ventilation zones increased from 30 to 50% on the right side, and from 41 to 55% on the left side, primarily due to decrease in the volume of hypoventilation zones, but not atelectasis and emphysema. Conclusion. Surgical correction of spinal deformity in children with NMS, grade IV, complicated with respiratory failure led to normalization of lungs volume and tissue density characteristics already in the early postoperative period.

An optimized convolutional neural network architecture for lung cancer detection.

Lung cancer, the treacherous malignancy affecting the respiratory system of a human body, has a devastating impact on the health and well-being of an individual. Due to the lack of automated and noninvasive diagnostic tools, healthcare professionals look forward toward biopsy as a gold standard for diagnosis. However, biopsy could be traumatizing and expensive process. Additionally, the limited availability of dataset and inaccuracy in diagnosis is a major drawback experienced by researchers. The objective of the proposed research is to develop an automated diagnostic tool for screening of lung cancer using optimized hyperparameters such that convolutional neural network (CNN) model generalizes well for universally obtained computerized tomography (CT) slices of lung pathologies. The aforementioned objective is achieved in the following ways: (i) Initially, a preprocessing methodology specific to lung CT scans is formulated to avoid the loss of information due to random image smoothing, and (ii) a sine cosine algorithm optimization algorithm (SCA) is integrated in the CNN model, to optimally select the tuning parameters of CNN. The error rate is used as an objective function, and the SCA algorithm tries to minimize. The proposed method successfully achieved an average classification accuracy of 99% in classification of lung scans in normal, benign, and malignant classes. Further, the generalization ability of the proposed model is tested on unseen dataset, thereby achieving promising results. The quantitative results prove the efficacy of the system to be used by radiologists in a clinical scenario.

An Enhanced Lung Cancer Identification and Classification Based on Advanced Deep Learning and Convolutional Neural Network

In this research, a fast, accurate, and stable system of lung cancer detection based on novel deep learning techniques is proposed. Lung cancer continues to be one of the most monumental global health concerns, which is why there is an urgent need for low-cost and non-invasive screening. Though the diagnostic methods that are most commonly in use include CTscan, X-ray etc. The interpretation by the human eye varies and errors are bound to occur. In response to this challenge, we outline a more automated approach that is based on deep learning models and can be used to classify lung pictures with high levels of accuracy. This research makes use of a large data set of lung scans categorised as normal, malignant, and benign. The first look what the data had in store threw up some correlation with picture size and what seemed to be category differences. Realizing that live feed requires constant input, each picture underwent grayscale conversion and dimensionality reduction. In order to effectively deal with the unbalanced nature of the dataset that was discovered in the study, the Synthetic Minority Oversampling Technique (SMOTE) was applied as a technique. In this presentation, three new designs were introduced: Model I, Model 2, and Model 3. Additionally, one architecture was developed with the purpose of merging the predictions of all three models. Furthermore, out of all the models created, the best model emerged as model 1 with approximately an accuracy of 84%. 7%. But the ensemble strategy which was intended to make the best of each of the models, produced an astounding 82. 5% accuracy. The specific advantages and misclassification behaviors of Model 2 and 3, although less accurate than Model 1 but are currently under evaluation for future Model ensemble improvements. The technique developed using deep learning addresses the challenges at a faster, efficient, and contactless approach to lung cancer analysis. The fact that it is capable of operating in tandem with others diagnostic instruments may help reduce diagnostic errors and enhance patient care. We have addressed this issue so that the various practitioners would be able to read this paper and we can go to the next generation of diagnostic technologies.

The Role of POCUS to Face COVID-19: A Narrative Review.

COVID-19 has been a challenging outbreak to face, with millions of deaths among the globe. Acute respiratory failure due to interstitial pneumonia was the leading cause of death other than prothrombotic activation and complications. Lung ultrasound (LUS) and point-of-care ultrasound (POCUS) are widely used not only to triage, to identify, and to monitor lungs involvement but also to assess hemodynamic status and thrombotic and hemorrhagic complications, mainly in critically ill patients. POCUS has gained growing consideration due to its bedside utilization, reliability, and reproducibility even in emergency settings especially in unstable patients. In this narrative review, we aim to describe LUS and POCUS utilization in COVID-19 infection based on the literature found on this topic. We reported the LUS patterns of COVID-19 pulmonary infection, the diagnostic accuracy with respect to CT lung scan, its prognostic value, the variety of scores and protocols proposed, and the utilization of POCUS to investigate the extra-lung complications.

Estimation of maternal and foetal risk of radiation-induced cancer from a survey of computed tomography pulmonary angiography and ventilation/perfusion lung scanning for diagnosing pulmonary embolism during pregnancy.

While there are many papers on maternal and foetal radiation doses from computed tomography pulmonary angiography (CTPA) and ventilation/perfusion (V/Q) lung scanning examinations for diagnosing pulmonary embolism in pregnant patients, few have used clinical data to examine the patient lifetime attributable risk (LAR) of different cancer types. This paper aims to estimate the cancer risk from maternal radiation doses from CTPA and V/Q examinations and associated foetal doses. Dosimetric data were determined for 267 pregnant patients who received CTPA and/or V/Q examinations over 8 years. Organ and foetal doses were determined using software allowing patient size variations for CTPA and using two different activity-to-organ dose conversion methods for V/Q scans. The LAR of cancer incidence was estimated using International Commission on Radiological Protection (ICRP) modelling including estimates of detriment. Estimated total cancer incidence was 23 and 22 cases per 100,000 for CTPA and V/Q examinations, respectively, with detriment estimates of 18 and 20 cases. Cancer incidence was evenly divided between lung and breast cancer for CTPA with lung cancer being 80% of all cancer for V/Q. The median foetal doses were 0.03 mSv for CTPA and 0.29 mSv for V/Q. Significant differences in estimated foetal dose for V/Q scans were obtained by the two different methods used. The differences in dose between the modes of CTPA scan acquisition highlight the importance of optimisation. Maternal cancer incidence and detriment were remarkably similar for each examination. Optimisation of examinations is critical for low-dose outcomes, particularly for CTPA examination.

Ultrasound Guided Phrenic Nerve Block for Percutaneous Computer Tomography Guided Lung Biopsy

Abstract The aim of this paper is to present the technique of the ultrasound (US) guided phrenic nerve block (PNB). This is an important adjuvant technique for percutaneous computer-tomography (CT) lung biopsy of nodules situated in the lower lobes, in proximity of the diaphragm, with a diameter of less than 2 cm. These types of nodules have a high location variability during respiration, which makes them hard to be approached for a successful biopsy. US visualization of the nerve is possible after identifying specific landmarks as the sternocleidomastoid and scalene muscle, interval jugular vein and brachial plexus. The phrenic nerve is seen as an oval hypoechogenic structure with no Doppler signal, superficial to the anterior scalene muscle. Ropivacaine can be used as a local anesthetic to induce the PNB. Results: Success of the phrenic nerve block can be assessed by CT scanogram, which shows the ipsilateral hemidiaphragm elevated, and by subsequent lung scans that show little to no location variability of the target lesion. Conclusion. US-guided PNB is a safe and efficient procedure that can help during percutaneous CT-guided lung biopsy of small basal nodules.

Evaluation of filtering and contrast in X-ray and computerized tomography scan lung classification

Deep learning provides many convenient methods to help medical practitioners take informed decisions about diverse ailments. The goal of this project is to measure the effectiveness of filters and contrast enhancement techniques qualitatively and quantitatively in classifying lung scan images. Transfer deep learning was used to obtain the necessary results, with DenseNet 121 being the base model. Salt and pepper filter was used to introduce noise, and 3×3 mean and 5×5 mean with contrast limited adaptive histogram equalization (CLAHE) was used to minimize the effect of noise. All layers excluding the rearmost were frozen, and new dense and dropout layers were added to identify features of computerized tomography (CT) scan images of lungs. The resultant models were of comparable accuracy, where the model with no filter gave the accurate results for the given data, and the one using the 5×5 mean filter gave better adaptability in classification of unseen data. The misclassification between normal and pneumonia affected lungs is relatively higher, because of the lack of distinct features between them.

DENG ENTROPY AND INFORMATION DIMENSION FOR COVID-19 AND COMMON PNEUMONIA CLASSIFICATION

Motivated by previous authors’ work, where Shannon entropy, box covering and information dimension were applied to quantify pulmonary lesions, this paper extends such a contribution in two fashions: (i) Following the approach to quantify pulmonary lesions with Deng entropy and Deng information dimension obtained through box covering method; (ii) exploiting the Shannon and Deng lesion quantification for pulmonary illnesses classification with a bidirectional Long Short Term Memory (bLSTM). The referred pulmonary illnesses are Common Pneumonia (CP) and COVID-19. Shannon entropy and information dimension are performed here and called the Shannon sequence. Then, Deng entropy and Deng information dimension are computed for chest Computed Tomography (CT) images to obtain and combine two data sequences to quantify the pulmonary lesions. The data sequence resulting from the data combination is called the Deng sequence. Both Shannon and Deng sequences are independently used as input for the bLSTM. CT lung scans of 531 healthy subjects, 497 confirmed COVID-19 diagnoses and 516 with CP were analyzed to obtain the Shannon and Deng sequences. The results demonstrate that Deng entropy and Deng information dimension of CT images can differentiate similar lung lesions between COVID-19 and CP. Besides, a statistical analysis shows that: (a) Classification by the bLSTM is better when using the Deng sequence than the Shannon sequence; (b) Deng sequences plus bLSTM significantly outperform DenseNet-201, GoogLeNet and MobileNet-v2 in classifying COVID-19, CP and Normal CT (healthy subjects) in time and accuracy. Hence, the Deng sequence and bLSTM are fast and accurate tools for helping in diagnosing CP and COVID-19.