RESUMEN

Background The use of computational technology in medicine has allowed for an increase in the accuracy of clinical diagnosis, reducing errors through additional layers of oversight. Artificial intelligence technologies present the potential to further augment and expedite the accuracy, quality, and efficiency at which diagnosis can be made when used as an adjunctive tool. Such techniques, if found to be accurate and reliable in their diagnostic acuity, can be implemented to foster better clinical decision-making, improving patient quality of care while reducing healthcare costs. Methodology This study implemented convolution neural networks to develop a deep learning model capable of differentiating normal chest X-rays from those indicating pneumonia, tuberculosis, cardiomegaly, and COVID-19. There were 3,063 normal chest X-rays, 3,098 pneumonia chest X-rays, 2,920 COVID-19 chest X-rays, 2,214 chest X-rays, and 554 tuberculosis chest X-rays from Kaggle that were used for training and validation. The model was trained to recognize patterns within the chest X-rays to efficiently recognize these diseases within patients to be treated on time. Results The results indicated a success rate of 98.34% incorrect detections, exemplifying a high degree of accuracy. There are limitations to this study. Training models require hundreds to thousands of samples, and due to potential variability in image scanning equipment and techniques from which the images are sourced, the model could have learned to interpret external noise and unintended details which can adversely impact accuracy. Conclusions Further studies that implement more universal database-sourced images with similar image scanning techniques, assess diverse but related medical conditions, and the utilization of repeat trials can help assess the reliability of the model. These results highlight the potential of machine learning algorithms for disease detection with chest X-rays.

RESUMEN

Ectopic thyroid tissue (ETT) is a rare finding on mediastinoscopy which could be attributed to a defect early in thyroid gland embryogenesis, as the glandular tissue makes its way to a pre-tracheal position. The more distal the location of the ectopic tissue from typically neighboring structures, such as the recurrent laryngeal nerves or the superior thyroid artery, the greater the likelihood for issues such as hyperthyroidism, compression of nearby neurovascular structures, and malignancy. Depending on the exact anatomical location and hormonal activity of the tissue, management can range from administration of iodine to surgical resection. This report discusses a case of ETT discovered during the resection of an anterior mediastinal mass, possible treatment, and management plans.

RESUMEN

Electromagnetic navigational bronchoscopy (ENB) has emerged as an innovative technique for diagnosing peripheral and central nodules, offering an improved diagnostic yield compared to conventional bronchoscopy with fewer complications. That being said, pneumothorax remains a frequent complication. This retrospective study conducted at Castle Hill Hospital, UK, analysed ENB procedures over four years to assess the diagnostic yield and pneumothorax rates, exploring learning curves and procedural improvements specifically focusing on the diagnostic yield and pneumothorax rate as markers of change. A total of 246 patients underwent 358 peripheral lung biopsies, revealing an overall diagnostic yield of 61.3%. The diagnostic yield increased from 58.2% in 2020-2021 to 66.0% in 2022-2023 while the pneumothorax rate decreased significantly from 9.8% to 3.4% (p = 0.021*). The majority of pneumothorax cases occurred following upper lobe procedures. The study depicts the importance of procedural experience in improving outcomes, suggesting a learning curve effect. Additionally, it emphasizes the potential for technological advancements, such as robotic assistance, to mitigate operator-dependent variability and improve reproducibility in ENB procedures. These findings contribute to optimizing diagnostic pathways for lung lesions and improving patient safety in ENB interventions.

RESUMEN

Granulomatosis with polyangiitis (GPA), formerly known as Wegener's granulomatosis, is a rare and potentially life-threatening autoimmune disease characterized by antineutrophil cytoplasmic antibody (ANCA)-associated vasculature inflammation. It presents as a systemic autoimmune disease with necrotizing granulomatous inflammation and pauci-immune small vessel vasculitis. This case initially posed a diagnostic challenge due to its atypical presentation and was misdiagnosed as hypersensitivity pneumonitis. The avian precipitin screening assay was positive in our patient, which may be consistent with bird breeder's lung disease or a non-specific reactivity of the chicken antigen test. However, the presence of positive c-ANCA was pivotal for the GPA diagnosis. Here, we describe in detail the clinical manifestations, diagnostic approach, and treatment of GPA in a 54-year-old female who presented with alveolar hemorrhage, but no renal involvement. Treatment involved the use of high-dose corticosteroids to suppress the autoimmune response. Finally, we discuss the striking response of this unique form of granulomatosis with polyangiitis to corticosteroid treatment and emphasize the importance of early initiation of treatment.

RESUMEN

We depict a unique case of a 34-year-old woman who presents to the emergency department with complaints of dyspnea and chest pain for the past month. A chest x-ray (CXR) from an earlier urgent care visit was concerning for large fluid opacity in the left lung and follow-up imaging revealed a cystic mass suspicious of a pulmonary cystic abscess. The patient underwent complete lobectomy and resection. Post-surgical biopsy confirmed pulmonary hydatid cystic mass and signs of rupture or seeding to liver tissue. The patient was discharged with adjuvant therapy and recommended imaging follow-up for the next decade. The diagnosis, treatment, and maintenance guidelines are discussed in this report which reveals controversy between experts given the lack of complete literature regarding echinococcosis. Our purpose in putting forward this case is to present a rare diagnosis of pulmonary echinococcosis in the United States and to emphasize the importance of early imaging and diagnosis to prevent cystic rupture and secondary organ dissemination.

RESUMEN

Empyema necessitans is characterized by an empyema that extends from the lung pleura into the chest wall and underlying tissue. We present a rare case of Streptococcus agalactiae (Group B) empyema necessitans in an adult male. This case highlights the diagnosis and management of empyema necessitans in the modern era.

RESUMEN

INTRODUCTION: Chest radiographs are the most performed radiographic procedure, but suboptimal technical factors can impact clinical interpretation. A deep learning model was developed to assess technical and inspiratory adequacy of anteroposterior chest radiographs. METHODS: Adult anteroposterior chest radiographs (n = 2375) were assessed for technical adequacy, and if otherwise technically adequate, for adequacy of inspiration. Images were labelled by an experienced radiologist with one of three ground truth labels: inadequate technique (n = 605, 25.5 %), adequate inspiration (n = 900, 37.9 %), and inadequate inspiration (n = 870, 36.6 %). A convolutional neural network was then iteratively trained to predict these labels and evaluated using recall, precision, F1 and micro-F1, and Gradient-weighted Class Activation Mapping analysis on a hold-out test set. Impact of kyphosis on model accuracy was assessed. RESULTS: The model performed best for radiographs with adequate technique, and worst for images with inadequate technique. Recall was highest (89 %) for radiographs with both adequate technique and inspiration, with recall of 81 % for images with adequate technique and inadequate inspiration, and 60 % for images with inadequate technique, although precision was highest (85 %) for this category. Per-class F1 was 80 %, 81 % and 70 % for adequate inspiration, inadequate inspiration, and inadequate technique respectively. Weighted F1 and Micro F1 scores were 78 %. Presence or absence of kyphosis had no significant impact on model accuracy in images with adequate technique. CONCLUSION: This study explores the promising performance of a machine learning algorithm for assessment of inspiratory adequacy and overall technical adequacy for anteroposterior chest radiograph acquisition. IMPLICATIONS FOR PRACTICE: With further refinement, machine learning can contribute to education and quality improvement in radiology departments.

Asunto(s)

RESUMEN

Schwannomas are benign slow-growing tumors arising from the embryonic neural crest cells of the nerve sheaths of peripheral and cranial nerves, and they are a rare type of soft tissue mass that is usually always solitary. Generally, it grows in the head, neck, and flexor portions of the limbs, where many nerves are located. Schwannomas of the lung are extremely rare. Fewer than ten cases of schwannomas in this organ region have been reported in the existing literature. In this case report, a 40-year-old male non-smoker was hospitalized with occasional chest pain. His chest computed tomographic scan revealed a 3.8 cm space occupying lesion in the upper lobe of the right lung. This lesion has clear boundaries and uneven internal density. And it was concluded as a benign lesion possibility, it is preferred to be considered as a haematoma. This space occupying lesion was eventually confirmed as a schwannoma by needle biopsy tissues. Due to the presence in rare locations, such as the lung, the clinical presentation of this space occupying lesion is non-specific, making diagnosis difficult. The data presented in this case report can help clinicians to obtain information on the identification of this disease, which highlighted lung schwannoma as a differential diagnosis for patients with intermittent pain. It can also alert clinicians and radiologists to observe every detail of the radiology imaging findings.

RESUMEN

Introduction Despite the fact that smoking has been identified as a risk factor for respiratory diseases and lung infections, the relationship between smoking and coronavirus severity remains ambiguous. It is believed that smoking is a risk factor for pulmonary infections. However, the effect of smoking on COVID-19 patients is still controversial. Objective The aim of the study was to identify and analyze the distinct radiological features in COVID-19 patients with different smoking statuses. Additionally, the study sought to examine the association between smoking and the severity of pulmonary changes. Methods A retrospective cohort study of 111 patients who were referred to Al-Salt/Hussein Hospital, Al-Salt, Jordan, from January to June 2021, with a confirmed COVID-19 diagnosis and smoking status recorded. Patients' demographics, medical history, age, gender, comorbidity, and length of hospitalization were obtained from their medical records. Results Study groups were similar in median age, prevalence of chosen chronic diseases, and median length of hospital stay. Based on the median scores of the radiological findings in each lung lobe, no statistically significant differences were found between the scores and smoking status (p-values of >0.05; Mann-Whitney test). Conclusion Smoking is an independent risk factor for the severity of COVID-19. Smoking has no noticeable impact on interstitial manifestation in COVID-19 patients.

RESUMEN

Bronchocutaneous fistula (BCF) is a pathologic communication between the bronchus and the subcutaneous tissue. Its diagnosis is made mainly by chest imaging, and bronchoscopy can help in accurately localizing the fistula. Treatment options include conservative and non-conservative approaches. We report a case of iatrogenic bronchocutaneous fistula occurring after traumatic chest tube placement in an 81-year-old man, treated efficiently with conservative management.

RESUMEN

Computed tomography (CT)-guided percutaneous core needle biopsy of the lung is a frequently performed interventional radiological procedure. Most complications are minor and self-resolving. However, a rare but potentially fatal complication is that of systemic air embolism, especially when to the cerebral or coronary arteries. This study reports a case of delayed (12 hours after initial biopsy) air embolism in the cerebral arteries that resulted from an otherwise uncomplicated biopsy of a lung nodule. It is vital for early diagnostic confirmation and appropriate treatment if possible, though maximal efforts at prevention are still recommended.

RESUMEN

The objective of this article is to automatically segment organs at risk (OARs) for thoracic radiology in computed tomography (CT) scan images. The OARs in the thoracic anatomical region during the radiotherapy treatment are mainly the neighbouring organs such as the esophagus, heart, trachea, and aorta. The dataset of 40 patients was used in the proposed work by splitting it into three parts: training, validation, and test sets. The implementation was performed on the Google Colab Pro+ framework with 52 GB of RAM and 265 GB of storage space. An ensemble model was evolved for the automatic segmentation of four OARs in thoracic CT images. U-Net with InceptionV3 as the backbone was used, and different hyperparameters were used during the training of the model. The proposed model achieved precise accuracy for OARs segmentation with an average dice coefficient of 0.9413, Hausdorff value of 0.1838, sensitivity of 0.9783, and specificity of 0.9895 on the Test dataset. An ensembled U-Net InceptionV3 model has been proposed, improving the segmentation results compared with the state-of-the-art techniques such as U-Net, ResNet, Vgg16, etc. The results of the experiments revealed that the proposed model effectively improved the performance of the segmentation of the esophagus, heart, trachea, and aorta.

Asunto(s)

RESUMEN

OBJECTIVES: The aims of this study were to describe the radiographic features of cardiogenic pulmonary oedema (CPE) in a large group of cats with left-sided cardiac disease, and to determine the association between the radiographic features of CPE and the underlying cardiac disease. METHODS: Thoracic radiographs of cats with CPE and echocardiographic evidence of left-sided cardiac disease and left atrial enlargement (LAE) were reviewed, and cardiac silhouette, pulmonary vessels and pulmonary parenchyma evaluation were performed. Interstitial and/or alveolar patterns were classified according to their distribution (ie, diffuse, multifocal or focal) and location (ie, craniodorsal, cranioventral, caudodorsal, caudoventral and perihilar). A Student's t-test and Mann-Whitney U-test, or the two-proportion z-test, were used to compare continuous or categorical variables, respectively, between cats affected by the two most represented cardiac diseases, namely hypertrophic cardiomyopathy (HCM) and restrictive cardiomyopathy (RCM). RESULTS: Seventy-one cats were included; among them, 46 (64.7%) and 13 (18.3%) had presented for HCM and RCM, respectively. Subjective and objective cardiomegaly, and subjective and objective LAE were detected in 97.2% and 91.9% of cats and in 80.3% and 40.6% of cats, respectively. Pulmonary artery abnormalities, in particular caudal pulmonary artery dilation, were found in 77.5% of cats. Pulmonary artery to pulmonary vein ratio = 1 was found in 71.8% and 55% cats on right lateral and ventrodorsal or dorsoventral views, respectively. Interstitial (57.8%) and mixed interstitial-alveolar (38%) pattern, multifocal (84.5%) and symmetrical (75%) distribution with prevalent ventrocaudal (65.6% of cats) and ventrocranial (60.9% of cats) locations were most frequently observed. No difference was found for any of these radiographic features between cats with HCM and RCM. CONCLUSIONS AND RELEVANCE: Moderate-to-severe cardiomegaly and LAE, caudal pulmonary artery and vein dilation, as well as a ventral, multifocal and symmetrical interstitial pulmonary pattern, were the main radiographic features of CPE in evaluated cats. Underlying cardiac disease did not influence the aforementioned radiographic features.

Asunto(s)

RESUMEN

A wide spectrum of pathology, both congenital and acquired, can affect the pulmonary arteries. While some of these are commonly seen in everyday clinical practice, some are rare. These entities may be discovered incidentally at imaging for other reasons in an asymptomatic patient, however patients may go on to develop symptoms over the course of their lifetime. Although an enlarged pulmonary artery can be visualized on chest X-ray (CXR), for the most part, CXR is insensitive for detecting abnormalities of the pulmonary arteries. Contrast-enhanced chest CT (CECT) is a better test to evaluate the pulmonary arteries as it is readily available, quick to perform, able to provide multiplanar reformatted images, and noninvasive. CECT is not only able to assess the lumen and wall of the pulmonary artery, but also provides a detailed evaluation of the entire thorax, including the heart, mediastinal structures, and lungs, often times picking up associated findings, and is the mainstay for evaluating disorders of the pulmonary vasculature. MRI allows for detailed evaluation of the vessel wall which can be especially helpful in cases where malignancy or vasculitis are suspected, and is also able to provide useful physiologic data such as quantification of flow. It is important for the radiologist to be aware of the many conditions which affect the pulmonary arteries, as some may require urgent treatment. This article will review normal pulmonary artery anatomy and physiology, as well as the various imaging findings of pulmonary vascular pathologies.

Asunto(s)

RESUMEN

Rasmussen's aneurysm is a pseudoaneurysm caused by tuberculosis, when cavitation occurs adjacent to a pulmonary artery, which can be lethal. It is a rare complication usually affecting adults. This is a case of an 9-year-old boy initially admitted for pneumonia that developed hemoptysis during admission. Chest X-ray done after this episode showed development of a left hilar mass not present in the previous studies. A chest CT with contrast subsequently revealed a saccular aneurysm arising from the left lower lobe pulmonary artery adjacent to a cavity, a Rasmussen's aneurysm. The patient was treated conservatively with continuation of anti-TB medication and serial monitoring due to the size of the aneurysm being less than 6 cm and spontaneous resolution of the hemoptysis. This report stresses that a Rasmussen's aneurysm should always be in the differential diagnosis of a hilar mass in a patient with hemoptysis, regardless of the patient's age.

RESUMEN

RATIONALE AND OBJECTIVES: The burden of coronavirus disease 2019 (COVID-19) airspace opacities is time consuming and challenging to quantify on computed tomography. The purpose of this study was to evaluate the ability of a deep convolutional neural network (dCNN) to predict inpatient outcomes associated with COVID-19 pneumonia. MATERIALS AND METHODS: A previously trained dCNN was tested on an external validation cohort of 241 patients who presented to the emergency department and received a chest computed tomography scan, 93 with COVID-19 and 168 without. Airspace opacity scoring systems were defined by the extent of airspace opacity in each lobe, totaled across the entire lungs. Expert and dCNN scores were concurrently evaluated for interobserver agreement, while both dCNN identified airspace opacity scoring and raw opacity values were used in the prediction of COVID-19 diagnosis and inpatient outcomes. RESULTS: Interobserver agreement for airspace opacity scoring was 0.892 (95% CI 0.834-0.930). Probability of each outcome behaved as a logistic function of the opacity scoring (25% intensive care unit admission at score of 13/25, 25% intubation at 17/25, and 25% mortality at 20/25). Length of hospitalization, intensive care unit stay, and intubation were associated with larger airspace opacity score (p = 0.032, 0.039, 0.036, respectively). CONCLUSION: The tested dCNN was highly predictive of inpatient outcomes, performs at a near expert level, and provides added value for clinicians in terms of prognostication and disease severity.

Asunto(s)

RESUMEN

Although many of the thoracic infections endemic to Africa are also present around the world, this article focuses on entities that are emerging or disproportionately affect populations living in sub-Saharan Africa. Important emerging or reemerging viral and bacterial diseases that commonly affect the lung include dengue fever, plague, leptospirosis, and rickettsioses. Most parasitic infections endemic to Africa can also manifest within the thorax, including malaria, amebiasis, hydatid disease, schistosomiasis, paragonimiasis, ascariasis, strongyloidiasis and cysticercosis. Level of sanitation, interaction between humans and host animals, climate change, political instability, and global travel all affect the distribution and burden of these diseases.

Asunto(s)

RESUMEN

CLINICAL ISSUE: Chest x­ray is a projection technique which reduces a three-dimensional body to a two-dimensional image. Inevitably, this leads to loss of information. Hence, it is much more difficult to determine anatomy and pathology in chest ray than in computed tomography. PERFORMANCE: The so-called "lines and stripes" are prominent landmarks. Knowledge of these lines and stripes eases interpretation of chest x­rays. ACHIEVEMENTS: This review describes anatomy and normal morphology of all relevant lines and stripes and gives differential diagnoses in case of pathologic morphology.

Asunto(s)

RESUMEN

Although echocardiography is the gold standard for the diagnosis of cardio-structural disease, thoracic radiography is a rapid, cost-effective, and widely accessible method for evaluating cardiac size in dogs. The vertebral heart score (VHS) and the vertebral left atrial size (VLAS) are established as objective measures of cardiomegaly on thoracic radiographs. However, several studies have shown significant variations in the VHS among different breeds. The Chihuahua is predisposed to both congenital and acquired cardiac diseases. The aim of this prospective, single-center, cross sectional study was thus to evaluate the VHS and the VLAS in healthy adult Chihuahua dogs. A total of 30 Chihuahuas were included. The VHS values in our sample population of Chihuahuas were 10.0 ± 0.6 (95% range, 8.9-11.0). This was significantly greater than the canine reference value of 9.7 ± 0.5 established by Buchanan and Bücheler (P = .002). The VLAS of Chihuahuas in our study was 1.8 ± 0.2 (95% range, 1.3-2.1). This was significantly lower than the values previously reported by Malcolm et al (2.07 ± 0.25; P = .0004). The VHS and the VLAS were not influenced by sex, body weight, short or long hair, and body condition score in normal Chihuahuas. Our results indicated that breed-specific reference values for radiographic VHS and VLAS are needed. In Chihuahuas, the values found in this study can be used as a normal reference in order to help avoid overinterpretation of cardiomegaly in these dogs.

Asunto(s)

RESUMEN

Lung cancer is currently the most common malignancy in the world. A lobectomy is the standard of care for most patients with operable lung cancer and accounts for 60% to 70% of lung resection. The chest radiograph may appear normal after a lobectomy, particularly in uncomplicated cases. However, lobectomy usually involves leaving surgical staples at the bronchial stump and causes various changes in the intra- and extrapulmonary thoracic structures on plain radiographs. These changes may differ according to the resected lobe. We retrospectively evaluated the plain radiographic appearances of the postlobectomy chest, free of postoperative complications or recurrent/metastatic lung cancer. On the basis of our observations, the changes that occur in pulmonary and extrapulmonary anatomy can differ according to the resected lobe. Recognition of these changes will make it easier to identify which lobe has been removed surgically.

Asunto(s)