Chest X-ray Research Articles

A Diagnostic Challenge in the Biopsy of a Mammographic Abnormality

Abstract Introduction/Objective Primary breast marginal zone lymphoma (MZL) is an uncommon subtype of extranodal lymphoma, and its diagnosis presents challenges, particularly in distinguishing it from lymphoplasmacytic lymphoma (LPL). MYD88 L265P mutation has been identified in a subset of marginal zone lymphomas, comprising 6-9% of cases. This genetic alteration further complicates the differentiation between MZL and LPL in breast tumors. We present a case highlighting the diagnostic complexities associated with primary breast MZL. Methods/Case Report A 71-year-old female patient underwent mammographic screening, which revealed a suspicious lesion in her left breast. Subsequent PET scan showed a hypermetabolic area consistent with a primary breast lesion. Biopsy histology exhibited a diffuse atypical lymphoid infiltration with varying proportions of neoplastic lymphocytes. Immunohistochemical analysis revealed positivity for CD20, PAX5, BCL2, CD138, MUM1, and negativity for CD3, CD5, Cyclin D1, CD10, CD23, CD34, BCL6, TDT, CD30, GATA3, and CK AE1/3. Additionally, there was lambda light chain restriction, and the Ki67 proliferation rate index was approximately 50%. Fish analysis indicated abnormal BCL6 gene rearrangement. Molecular genetic testing confirmed the presence of MYD88 mutation with c.794T>C p.L265P. Notably, bone marrow biopsy showed no abnormalities, with normal hematopoiesis. Serum electrophoresis and immunofixation detected an IgM monoclonal protein with lambda light chain specificity. Results (if a Case Study enter NA) NA Conclusion The diagnosis of primary breast MZL was favored over LPL due to the absence of common LPL- associated symptoms such as bone marrow involvement. However, the distinction between these entities remains challenging, underscoring the importance of comprehensive diagnostic approaches integrating histopathology, immunohistochemistry, and molecular genetics. Further research is warranted to enhance diagnostic certainty in such cases, particularly as the management of MZL and LPL becomes increasingly specific with the advent of novel therapeutic agents and ongoing clinical trials.

Gastric cyst of the posterior mediastinum in a child: An unusual presentation

Gastric cyst of the posterior Mediastinum is a rare congenital anomaly of the gastrointestinal tract. They are classified according to their embryological origin, epithelial lining and location, as thymic cyst, cystic hygroma, mesothelial cysts, thoracic duct cyst and cystic malformation of the primitive foregut. They usually present in neonates or in infancy and are discovered incidentally on radiological examination or gastric endoscopy. Accurate diagnosis of these cysts before resection is difficult and differential diagnosis are varied. This case report presents a 6-year-old boy who complained of fever for 3 weeks. Chest X-ray revealed right para median oval shaped opacity. HRCT showed a well-defined cystic lesion measuring 9x4.4x3.3 cm in the right side of the posterior mediastinum in the perihilar location. There was also noted vertebral segmentation anomaly in the cervicothoracic spine. Cystectomy was and Gastric cyst was diagnosed through histopathological examination. This case report is presented for its rarity and an unusual delayed clinical presentation.

Features of children with critical asthma hospitalized in a pediatric intensive care unit: Results from the ICU-3A study.

Despite improvements in long-term asthma treatment, an increasing number of children are being hospitalized in pediatric intensive care units (PICU) for asthma. The main objective of this study was to describe a recent cohort of children hospitalized in PICU for asthma to identify risk factors associated with a need for respiratory support, and multiple PICU stays. We conducted a retrospective cohort study in three PICUs in Paris (intensive care units 3A Study), using medical files of children hospitalized for asthma between February 2019 and October 2020. Need for respiratory support was defined by the need for high-flow nasal cannula or mechanical ventilation (MV) (either noninvasive [NIV] or invasive [IMV]). During the study period, 252 stays corresponding to 234 patients were analyzed. MV was required in 17.5% of stays, for significantly younger patients (2.37 vs. 4.18 years, p = 0.002). On multivariate analysis, a higher risk of progression to a need for respiratory support was found for children requiring magnesium sulfate or oxygen therapy ≥6 L/mn before PICU admission (RR 4.48; CI95% [1.85-10.89]; p = 0.001, and RR 2.86; CI95% [1.13-7.22]; p = 0.03, respectively), and those with atelectasis detected on chest radiography (RR 3.38; CI95% [1.43-8.00]; p < 0.01). Multiple PICU stays were associated with greater social deprivation (RR for French Deprivation Index 1.25; CI95% [1.03-1.51]; p = 0.03). Children experiencing social deprivation are at greater risk of multiple PICU stays for severe asthma. After transfer to PICU, children with chest radiograph detected atelectasis on admission are at higher risk of needing respiratory support.

A Novel Deep Learning Framework Enhanced by Hybrid Optimization Using Dung Beetle and Fick’s Law for Superior Pneumonia Detection

Pneumonia is an inflammation of lung tissue caused by various infectious microorganisms and noninfectious factors. It affects people of all ages, but vulnerable age groups are more susceptible. Imaging techniques, such as chest X-rays (CXRs), are crucial in early detection and prompt action. CXRs for this condition are characterized by radiopaque appearances or sometimes a consolidation in the affected part of the lung caused by inflammatory secretions that replace the air in the infected alveoli. Accurate early detection of pneumonia is essential to avoid its potentially fatal consequences, particularly in children and the elderly. This paper proposes an enhanced framework based on convolutional neural network (CNN) architecture, specifically utilizing a transfer-learning-based architecture (MobileNet V1), which has outperformed recent models. The proposed framework is improved using a hybrid method combining the operation of two optimization algorithms: the dung beetle optimizer (DBO), which enhances exploration by mimicking dung beetles’ navigational strategies, and Fick’s law algorithm (FLA), which improves exploitation by guiding solutions toward optimal areas. This hybrid optimization effectively balances exploration and exploitation, significantly enhancing model performance. The model was trained on 7750 chest X-ray images. The framework can distinguish between healthy and pneumonia, achieving an accuracy of 98.19 ± 0.94% and a sensitivity of 98 ± 0.99%. The results are promising, indicating that this new framework could be used for the early detection of pneumonia with a low cost and high accuracy, especially in remote areas that lack expertise in radiology, thus reducing the mortality rate caused by pneumonia.

Clinical features, treatment, and outcome of granulocyte colony stimulating factor-induced sweet syndrome.

Sweet syndrome (SS) is a rare dermatological adverse reaction caused by granulocyte colony-stimulating factor (G-CSF), but the characteristics of G-CSF-induced SS are unclear. This study aims to elucidate the characteristics of G-CSF-induced SS and offer guidance for its prevention and management. We collected relevant case reports of G-CSF-induced SS by searching pertinent databases until June 30, 2024, and synthesized the data for retrospective analysis. A total of fifty patients were analyzed, with a median age of 44 years (1.7-77). The onset of SS occurred between 2 and 90 days post-administration, with a median onset time of 7 days. The predominant cutaneous manifestations included papules/plaques (74.0%), nodules (32.0%), and vesicles/bullae (24.0%). Fever presented in 74.0% of cases, while extra-cutaneous symptoms appeared in 32% of patients. Skin biopsy revealed key findings such as dermal diffuse neutrophil infiltration (97.8%), leukocytoclasis (19.1%), and dermal papillary edema (27.7%). Following both the cessation of G-CSF and systemic corticosteroids treatment, patients showed symptomatic improvement at a median interval of 7 days (2-70). Clinicians should remain vigilant for the risk of SS during G-CSF administration. Skin biopsy plays a crucial role in confirming SS diagnosis. G-CSF-induced SS exhibits a favorable response to corticosteroids, and re-administration of G-CSF should be avoided due to the risk of symptom recurrence.

Enhanced COVID-19 Detection from X-ray Images with Convolutional Neural Network and Transfer Learning.

The global spread of Coronavirus (COVID-19) has prompted imperative research into scalable and effective detection methods to curb its outbreak. The early diagnosis of COVID-19 patients has emerged as a pivotal strategy in mitigating the spread of the disease. Automated COVID-19 detection using Chest X-ray (CXR) imaging has significant potential for facilitating large-scale screening and epidemic control efforts. This paper introduces a novel approach that employs state-of-the-art Convolutional Neural Network models (CNNs) for accurate COVID-19 detection. The employed datasets each comprised 15,000 X-ray images. We addressed both binary (Normal vs. Abnormal) and multi-class (Normal, COVID-19, Pneumonia) classification tasks. Comprehensive evaluations were performed by utilizing six distinct CNN-based models (Xception, Inception-V3, ResNet50, VGG19, DenseNet201, and InceptionResNet-V2) for both tasks. As a result, the Xception model demonstrated exceptional performance, achieving 98.13% accuracy, 98.14% precision, 97.65% recall, and a 97.89% F1-score in binary classification, while in multi-classification it yielded 87.73% accuracy, 90.20% precision, 87.73% recall, and an 87.49% F1-score. Moreover, the other utilized models, such as ResNet50, demonstrated competitive performance compared with many recent works.

Pulmonary hyalinizing granuloma: literature review and case presentation

Pulmonary hyalinizing granuloma (PHG) is an extremely rare condition. Only 170-200 cases have been described until now all over the world. There have been no reports in the Russian medical literature. Etiology of the disease is unknown. The X-ray picture is very unspecific. Tumors of lungs and pleura and infectious diseases are included in the differential line. Patients with pulmonary hyalinizing granuloma have long stabile progression of the disease, and the treatment with glucocorticoids can lead to the long lasting remission.The aim of the review was to inform pulmonologists, general practitioners, infectious disease specialists, thoracic surgeons, and oncologists about the existence of pulmonary hyalinizing granuloma, its diagnosis, clinical course, and treatment. Also we present one clinical case of patient with pulmonary hyalinizing granuloma.Conclusion. Because of very low incidence of PHG, an internist or a pulmonologist can never encounter it in their professional life. However it is worth keeping this condition in mind and including it into the diagnostic process when focal and focused shadows are identified in the lungs during chest X-ray. Probably, the disease is caused by different immune-mediatory processes, but the exact pathogenesis is still unknown. Biopsy of the lung tissue by means of lung resection is crucial for the morphological verification of the diagnosis. The prognosis of the disease is favorable. The timely initiation of treatment can sufficiently prolong the remission.

Study of Co-relation between Clinical and Diagnostic Profile of Pediatric Tuberculosis in a Tertiary Care Hospital

Objective: Study of Co-relation between Clinical and Diagnostic profile of Pediatric Tuberculosis in a tertiary care hospital. Methods: This hospital-based observational study was conducted at the Department of Pediatrics, Muzaffarnagar Medical College and Hospital, covering a population of children aged &lt;18 years diagnosed with TB. Data collection spanned 18 months, with a sample size of 100 children. Results: The study identified a predominant TB incidence in children aged 11-17 years (73%) with more females affected (66%) than males. Common symptoms included fever, cough, weight loss, and loss of appetite. Diagnostic findings showed a high use of Chest X-rays and Molecular tests. PTB was the most common form, accounting for 47 cases, EPTB accounting for 48 cases and Disseminated form was seen in 5 cases. Conclusions: Chest X-ray, Tuberculin Skin Test, Molecular Tests, and Blood Tests were universally performed on all patients. Microbiological confirmation is more common in pulmonary tuberculosis cases, while radiology, FNAC/Biopsy, and body fluid analysis are more utilized for extrapulmonary/disseminated cases. Diagnosing tuberculosis (TB) in children is often challenging due to several factors, including the difficulty in obtaining specimens and the typical paucibacillary nature.

The peritumoral brain zone in glioblastoma: a review of the pretreatment approach.

Glioblastomas are the most common and aggressive form of malignant primary brain tumors in adults. The standard treatment is surgical resection followed by radiotherapy and chemotherapy. Despite optimal treatment methods, the prognosis for patients remains poor. Preoperative determination of glioblastoma margins remains beneficial for the complete removal of the tumor mass. Radiotherapy is essential for post-surgery treatment, but radioresistance is a significant challenge contributing to high mortality rates. Advanced imaging technologies are used to analyze the changes in the peritumoral brain zone (PTZ). Consequently, they may lead to the development of novel therapeutic options, especially targeting the marginal parts of a tumor, which could improve the prognosis of glioblastoma patients. The clinical presentation of glioblastoma is heterogeneous and mostly depends on the location and size of a tumor. Glioblastomas are characterized by both intratumoral cellular heterogeneity and an extensive, diffuse infiltration into the normal tissue bordering a tumor called the PTZ. Neuroimaging techniques, such as diffusion-weighted imaging (DWI), diffusion tensor imaging (DTI), perfusion-weighted imaging (PWI), proton magnetic resonance spectroscopy (1H MRS), and chemical exchange saturation transfer (CEST) are useful methods in the evaluation of the tumor infiltration and thus the resection margin.

Pneumocystis jirovecii pneumonia in hemato-oncological patients; 10 years of experience at Hospital Infantil Teletón de Oncología

Abstract Background Pneumocystis jirovecii pneumonia is an opportunistic infection that most frequently affects immunocompromised people, especially patients with HIV; clinical presentation is nonspecific and mortality rate in patients without HIV ranges are between 30% and 75%. In the international literature, there are few case reports of pediatric oncology patients. A series of cases is presented with the objective of describing the epidemiological characteristics, clinical presentation, treatment, and outcomes of Pneumocystis jirovecii pneumonia in this population group. Methods An observational, descriptive, and retrospective study was carried out in cancer patients under 18 years, with clinically compatible symptoms, an imaging study suggestive of the pneumonia, and identification of P. jirovecii using a PCR test of bronchial aspirate at Hospital Infantil Teletón de Oncología in Querétaro Mexico, since November 2014 to June 2023. Results A total of 17 events were reported with a median age of 9.8 years, 14/17 (82%) with a diagnosis of acute leukemias, 1/17 (6%) Ewing sarcoma, 1/17 (6%) lymphoma large cell anaplastic and 1/17 (6%) neuroblastoma. Regarding their therapeutic phases, 7/17 (41%) were in consolidation, 4/17 (23%) induction, 3/17 (18%) allogeneic HSCT (Hematopoietic stem-cell transplantation), 2/17 (12%) in surveillance, and 1/17 (6%) in maintenance. The clinical presentation in our patients was characterized by the presence of fever in 15/17 (88%), dry cough in 10/17 (59%) and 17/17 (100%) developed acute respiratory distress syndrome, which was classified as mild in 7/17 (41%), moderate in 5/17 (29%) and severe in 5/17 (29%). 13/17 (75%) presented distributive shock. All our patients underwent chest x-rays, 12/17 (70.5%) presented bilateral interstitial infiltrate, 4/17 (23.5%) consolidation, and 1/17 (6%) pleural effusion. Lung CT (computed tomography) was performed in 4/17 (23.5%), and 4/4 (100%) presented ground glass opacities. All of our patients were admitted to the PICU (Pediatric intensive care unit) and 16/17 (94%) required invasive mechanical ventilation. All receive treatment with TMP-SMX (Trimethoprim-sulfamethoxazole). 4/17 patients died (23%) of whom none received prophylaxis. 3/17 patients (18%) received prophylaxis with trimethoprim-sulfamethoxazole (TMP-SMX). Conclusion The present study is the first study in Mexico that compiles cases of Pneumocystis Jirovecii pneumonia in pediatric oncology patients. P. jirovecii pneumonia remains a rare cause, but represents a potentially fatal cause in oncology patients, so it is important to have a high clinical suspicion during the evaluation of an immunocompromised patient with evidence of pneumonia during all treatment phases with chemotherapy, in order to start treatment promptly. Thus, we also emphasize the importance of adequate prophylaxis as the most important preventive measure.

Real-World evaluation of an AI triaging system for chest X-rays: A prospective clinical study

Chest X-rays (CXRs) are crucial for diagnosing and managing lung conditions. While CXR is a common and cost-effective diagnostic tool, interpreting the high volume of CXRs is challenging due to workforce limitations. Artificial intelligence (AI) offers promise in enhancing efficiency and accuracy. However, real-world applicability and generalizability across diverse patient cohorts remain areas of concerns. In our study, the LUNIT INSIGHT CXR Triage software was evaluated in a diverse patient cohort. Forty-three radiologists, blinded to AI results, assessed CXRs categorized into normal, non-urgent, and urgent using a 3-tier classification system. Performance metrics and turnaround times were analyzed.The AI system demonstrated sensitivity of 89% for normal CXRs, specificity of 93%, PPV of 83%, and NPV of 95%, with an F1 score of 0.86 and an AUC of 0.91. For non-urgent CXRs, sensitivity and specificity were 93% and 91%, with PPV and NPV at 94% and 89%, respectively, and an F1 score of 0.94 and an AUC of 0.92. In the urgent category, sensitivity was 82%, specificity 99%, PPV 90%, and NPV 98%. Subgroup analysis revealed consistently high accuracy across various age groups (Young, Adult, Senior), genders, and ethnicities (Chinese, Malay, Indian, Others), with sensitivity, specificity, and AUC consistently above 84%. The AI system also significantly reduced turnaround times across all subgroups, indicating its robust performance and generalizability in diverse healthcare settings.

Proteome Signature for Differential Diagnosis of Patients with Bilateral Lung Infiltrates

BackgroundThe differential diagnosis of bilateral lung infiltrates and prognosis prediction can be challenging for clinicians in the intensive care unit (ICU). We analyzed the proteome from bronchoalveolar lavage fluid (BALF) and determine their usefulness for evaluating the infectious causes and mortality associated with bilateral lung infiltrates.MethodsIn the ICU cohort, 136 patients with bilateral infiltrate on chest radiographs were selected, and bronchoscopy with bronchoalveolar lavage (BAL) was performed. Proteomics profiling of the exosomes in the BALF (n=20) was conducted to identify candidate protein biomarkers potentially associated with infection or mortality. The BAL samples (n=116) were used to measure the candidate biomarker levels.ResultsThe candidate biomarkers, CD20, CLIC4, SCFD1, and TAP1, were selected for the differential diagnosis of infection or mortality. The levels of CD20 were significantly elevated in patients with non-infectious causes compared to those with infectious causes (248.6±154.5versus177.6±150.9 ng·mL−1, p=0.014). The levels of CLIC4, SCFD1, and TAP1 did not differ between the two groups. As per the receiver operating characteristic analysis, CD20 was a significant predictor of non-infectious causes (area under curve, 0.668; 95% CI, 0.567–0.769; p=0.002; cut off value, 167.6 ng·mL−1; sensitivity, 74.1%; specificity, 63.2%). There were no significant differences in the concentrations of the biomarkers between survivors and non-survivors.ConclusionsOur results suggested that CD20 levels in BALF might be a useful biomarker for differentiating non-infectious and infectious diseases in patients with bilateral lung infiltrates.

Characteristics and Management of Children with Appendiceal Neuroendocrine Neoplasms: A Single-Center Study.

Appendiceal neuroendocrine neoplasms (ANENs) are usually found incidentally during histology examination after appendectomy for appendicitis. Due to their rarity in pediatric populations, there is no consensus on treatment or follow-up. The analysis of patients with ANENs of our and other studies will increase the understanding of this tumor. Pediatric patients with ANENs were uniformly managed at our center between 1998 and 2023. Patients' presenting symptoms, surgery, tumor histology, post-surgical work-up, follow-up and outcome were analyzed. Our report describes 17 patients with a diagnosis of ANEN after appendectomy. The median age was 14 years (range of 4-17 years). Tumors were located at the tip of the appendix in 58.8% of cases and only one had a diameter >1 cm. All were well-differentiated tumors with free resection margins. The submucosa was invaded in five cases, muscularis propria in eight and subserosa in four. Post-appendectomy work-up included tumor marker measurement, abdominal ultrasound and computed tomography or magnetic resonance imaging, chest X-ray and octreotide scintigraphy. No residual tumors or metastases were detected. Additional surgery was not necessary. Follow-up was carried out for a median duration of 6 years (range of 1-10 years). Only one patient was lost to follow-up and all other patients are alive without tumor recurrence. The tumor characteristics of our patients confirmed data from the literature. With the lack of a sufficient number of large prospective trials, it is important to add more information to confirm the benign nature and excellent outcome of this tumor, even without additional surgery. Consensus guidelines are needed for ANENs in pediatric populations.

Automatic structuring of radiology reports with on-premise open-source large language models.

Structured reporting enhances comparability, readability, and content detail. Large language models (LLMs) could convert free text into structured data without disrupting radiologists' reporting workflow. This study evaluated an on-premise, privacy-preserving LLM for automatically structuring free-text radiology reports. We developed an approach to controlling the LLM output, ensuring the validity and completeness of structured reports produced by a locally hosted Llama-2-70B-chat model. A dataset with de-identified narrative chest radiograph (CXR) reports was compiled retrospectively. It included 202 English reports from a publicly available MIMIC-CXR dataset and 197 German reports from our university hospital. Senior radiologist prepared a detailed, fully structured reporting template with 48 question-answer pairs. All reports were independently structured by the LLM and two human readers. Bayesian inference (Markov chain Monte Carlo sampling) was used to estimate the distributions of Matthews correlation coefficient (MCC), with [-0.05, 0.05] as the region of practical equivalence (ROPE). The LLM generated valid structured reports in all cases, achieving an average MCC of 0.75 (94% HDI: 0.70-0.80) and F1 score of 0.70 (0.70-0.80) for English, and 0.66 (0.62-0.70) and 0.68 (0.64-0.72) for German reports, respectively. The MCC differences between LLM and humans were within ROPE for both languages: 0.01 (-0.05 to 0.07), 0.01 (-0.05 to 0.07) for English, and -0.01 (-0.07 to 0.05), 0.00 (-0.06 to 0.06) for German, indicating approximately comparable performance. Locally hosted, open-source LLMs can automatically structure free-text radiology reports with approximately human accuracy. However, the understanding of semantics varied across languages and imaging findings. Question Why has structured reporting not been widely adopted in radiology despite clear benefits and how can we improve this? Findings A locally hosted large language model successfully structured narrative reports, showing variation between languages and findings. Critical relevance Structured reporting provides many benefits, but its integration into the clinical routine is limited. Automating the extraction of structured information from radiology reports enables the capture of structured data while allowing the radiologist to maintain their reporting workflow.

Assessment of Emphysema on X-ray Equivalent Dose Photon-Counting Detector CT

Objectives The aim of this study was to evaluate the feasibility and efficacy of visual scoring, low-attenuation volume (LAV), and deep learning methods for estimating emphysema extent in x-ray dose photon-counting detector computed tomography (PCD-CT), aiming to explore future dose reduction potentials. Methods One hundred one prospectively enrolled patients underwent noncontrast low- and chest x-ray dose CT scans in the same study using PCD-CT. Overall image quality, sharpness, and noise, as well as visual emphysema pattern (no, trace, mild, moderate, confluent, and advanced destructive emphysema; as defined by the Fleischner Society), were independently assessed by 2 experienced radiologists for low- and x-ray dose images, followed by an expert consensus read. In the second step, automated emphysema quantification was performed using an established LAV algorithm with a threshold of −950 HU and a commercially available deep learning model for automated emphysema quantification. Automated estimations of emphysema extent were converted and compared with visual scoring ratings. Results X-ray dose scans exhibited a significantly lower computed tomography dose index than low-dose scans (low-dose: 0.66 ± 0.16 mGy, x-ray dose: 0.11 ± 0.03 mGy, P &lt; 0.001). Interreader agreement between low- and x-ray dose for visual emphysema scoring was excellent (κ = 0.83). Visual emphysema scoring consensus showed good agreement between low-dose and x-ray dose scans (κ = 0.70), with significant and strong correlation (Spearman ρ = 0.79). Although trace emphysema was underestimated in x-ray dose scans, there was no significant difference in the detection of higher-grade (mild to advanced destructive) emphysema (P = 0.125) between the 2 scan doses. Although predicted emphysema volumes on x-ray dose scans for the LAV method showed strong and the deep learning model excellent significant correlations with predictions on low-dose scans, both methods significantly overestimated emphysema volumes on lower quality scans (P &lt; 0.001), with the deep learning model being more robust. Further, deep learning emphysema severity estimations showed higher agreement (κ = 0.65) and correlation (Spearman ρ = 0.64) with visual scoring for low-dose scans than LAV predictions (κ = 0.48, Spearman ρ = 0.45). Conclusions The severity of emphysema can be reliably estimated using visual scoring on CT scans performed with x-ray equivalent doses on a PCD-CT. A deep learning algorithm demonstrated good agreement and strong correlation with the visual scoring method on low-dose scans. However, both the deep learning and LAV algorithms overestimated emphysema extent on x-ray dose scans. Nonetheless, x-ray equivalent radiation dose scans may revolutionize the detection and monitoring of disease in chronic obstructive pulmonary disease patients.

Risk factors for non-isolation of patients admitted for pulmonary tuberculosis in a high-incidence department: a single-centre retrospective study

Pulmonary tuberculosis (PT) is an airborne disease, justifying the identification of suspect patients on admission, and their hospitalization in individual rooms with the implementation of Airborne Supplementary Precautions (ASP). The aim of this study was to identify, in a high-prevalence hospital, the frequency of non-isolated PT and the factors associated with the delay in implementing ASP.This was a retrospective observational study, including patients with at least one Mycobacterium tuberculosis-positive specimen. Patient demographic and clinical data, as well as data related to the mode of admission, were collected. Univariate and multivariate statistical analyses were performed.During the study period, 256 patients were included. Among them 134 (52.3%) had PT. These included 100 (75%) men, median age 39, 70% foreign-born. Among these patients, 46 (34%) were isolated beyond the 24th hour of admission. The average time to implement ASP was 4.3 days, and 7 patients (5.2%) were not isolated throughout their stay. Three classes of factors were associated by multivariate analysis with isolation. Previous consultation with a general practitioner was protective whereas admission through emergency department was not. Presence of so-called cardinal clinical signs and a suggestive chest X-ray were protective factors. Finally, European patients were less frequently isolated.In our study, 34% of patients admitted with PT were not isolated on admission. The risk of non-isolation was 3 times higher in cases of admission via the emergency department, and European patients were less well isolated. The presence of cardinal signs and prior consultation with a general practitioner were associated with a higher frequency of isolation.

Deep Learning Methods for Detecting Chest X-Ray and CT Scan Abnormalities

Deep learning's quick development has created new opportunities to improve medical image analysis, especially in the identification of anomalies in chest CT and X-ray scans. This work investigates several deep learning techniques designed for this particular purpose to enhance the efficiency and accuracy of diagnosis in medical settings. We explore the use of 3D CNNs, transfer learning, and convolutional neural networks, or CNNs, for the analysis of volumetric CT scan information as well as 2D chest X-ray pictures. Comparative analyses show the benefits and drawbacks of various deep learning architectures for identifying a variety of anomalies, including tumors, tumors in the lungs, pneumonia, and other diseases. We also go over the significance of preprocessing methods, assessment metrics specifically designed for medical picture analysis, and dataset preparation. The results highlight how deep learning has the potential to revolutionize chest imaging diagnostics by facilitating the quicker and more accurate identification of anomalies, which will enhance patient outcomes and the effectiveness of healthcare delivery. To spur additional developments in the deep learning-powered analysis of medical images for chest problems, future research topics, and obstacles in this area are also covered.

Concordance of Chest Radiography and Chest Computed Tomography Findings in Patients with Hematologic Malignancy and Invasive Mucormycosis: What Are the Prognostic Implications?

Invasive pulmonary mucormycosis (IPM) is a deadly opportunistic mold infection in patients with hematological malignancies (HM). Radiologic imaging is essential for its timely diagnosis. Here, we compared IPM lesions visualized by chest computed tomography (CCT) and chest X-ray (CXR) and determined the prognostic significance of discordant imaging. Therefore, we reviewed 44 consecutive HM patients with probable/proven IPM at MD Anderson Cancer Center in 2000-2020 who had concurrent CCT and CXR studies performed. All 44 patients had abnormal CCTs and 39 (89%) had anormal CXR findings at IPM diagnosis. However, only 26 patients (59%) showed CCT-matching IPM-suspicious lesions on CXR. Acute Physiology and Chronic Health Evaluation II score > 18 at IPM diagnosis and breakthrough infection to Mucorales-active antifungals were the only independent risk factors for 42-day and/or 84-day mortality. Absence of neutropenia at IPM diagnosis, neutrophil recovery in neutropenic patients, and surgical revision of mucormycosis lesions were protective factors. Although not reaching significance on multivariable analysis, visualization of CCT-matching lesions on CXR was associated with significantly increased 84-day mortality (log-rank test, p = 0.033), possibly as a surrogate of extensive lesions and tissue necrosis. This observation supports the exploration of radiologic lesion kinetics as a prognostic staging tool in IPM patients.

Potential of Chest Radiography in Primary Diagnosis of Lung Cancer

Objective: to evaluate the effectiveness of diagnostics for non-small cell lung cancer (LC) based on chest radiography/fluorography data for LC screening diagnostics during preventive medical examination and check-ups.Material and methods. The work was organized as a retrospective cohort study. The starting point of the study was chest radiography, the final point was the diagnosis of LC based on the results of low-dose computed tomography (LDCT) and tumor morphological examination. The patient sample was composed using inclusion and exclusion criteria and initially included 800 patients, then narrowed down to 788. Patients were divided into groups according to LC stage and depending on whether radiography during preventive measures made it possible to suspect LC verified within 3 months via LDCT for any reasons not related to the suspicion of a tumor process. The diagnostic coefficient and informative value of radiography were calculated for each stage of the established LC diagnosis.Results. The study showed that chest radiography does not allow establishing stage I LC diagnosis (J=0.00; p&lt;0.05), it is low informative for stage II LC (J=0.25; p&lt;0.05), and medium informative for stage III LC (J=0.80; p&lt;0.05). Chest radiography does not reliably detect LC signs at early stages in 84.3% of cases.Conclusion. The obtained results indicate an insufficient sensitivity of radiography as a screening method, primarily for early LC diagnosis. The introduction of chest LDCT instead of radiography into the procedure for preventive medical examination and check-ups of the adult population approved by the Ministry of Health of the Russian Federation will increase LC detection at early stages by 5.37 times (95% confidence interval 3,77–7,64).

Evaluating Explainable Artificial Intelligence (XAI) techniques in chest radiology imaging through a human-centered Lens.

The field of radiology imaging has experienced a remarkable increase in using of deep learning (DL) algorithms to support diagnostic and treatment decisions. This rise has led to the development of Explainable AI (XAI) system to improve the transparency and trust of complex DL methods. However, XAI systems face challenges in gaining acceptance within the healthcare sector, mainly due to technical hurdles in utilizing these systems in practice and the lack of human-centered evaluation/validation. In this study, we focus on visual XAI systems applied to DL-enabled diagnostic system in chest radiography. In particular, we conduct a user study to evaluate two prominent visual XAI techniques from the human perspective. To this end, we created two clinical scenarios for diagnosing pneumonia and COVID-19 using DL techniques applied to chest X-ray and CT scans. The achieved accuracy rates were 90% for pneumonia and 98% for COVID-19. Subsequently, we employed two well-known XAI methods, Grad-CAM (Gradient-weighted Class Activation Mapping) and LIME (Local Interpretable Model-agnostic Explanations), to generate visual explanations elucidating the AI decision-making process. The visual explainability results were shared through a user study, undergoing evaluation by medical professionals in terms of clinical relevance, coherency, and user trust. In general, participants expressed a positive perception of the use of XAI systems in chest radiography. However, there was a noticeable lack of awareness regarding their value and practical aspects. Regarding preferences, Grad-CAM showed superior performance over LIME in terms of coherency and trust, although concerns were raised about its clinical usability. Our findings highlight key user-driven explainability requirements, emphasizing the importance of multi-modal explainability and the necessity to increase awareness of XAI systems among medical practitioners. Inclusive design was also identified as a crucial need to ensure better alignment of these systems with user needs.