4.6 Article

Reduced Perfusion in Pulmonary Infiltrates of High-risk Hematologic Patients Is a Possible Discriminator of Pulmonary Angioinvasive Mycosis: A Pilot Volume Perfusion Computed Tomography (VPCT) Study

期刊

ACADEMIC RADIOLOGY
卷 19, 期 7, 页码 842-850

出版社

ELSEVIER SCIENCE INC
DOI: 10.1016/j.acra.2012.03.002

关键词

Volume perfusion CT (VPCT); hypoperfusion sign; angioinvasive pulmonary mycosis; aspergillosis; mucormycosis; candidiasis

向作者/读者索取更多资源

Rationale and Objectives: The aim of this study was to assess perfusion parameters in atypical pneumonia of heavily immunocompromised hematologic patients suspected of having invasive mycosis using volume perfusion computed tomography and establish their diagnostic role. Materials and Methods: Volume perfusion computed tomographic data from 21 consecutive immunocompromised patients presenting with atypical parenchymal opacity of consolidation were analyzed with respect to the degree of perfusion of their pneumonias. All patients presented with clinical and laboratory signs of infection. Seventeen patients (10 men, seven women; mean age, 57 years; age range, 19-76 years) were found with proven (n = 9), probable (n = 2), or possible (n = 6) angioinvasive mycosis. One patient was diagnosed with bronchoinvasive aspergillosis. Four patients (all men; mean age, 71 years; age range, 67-79 years) were diagnosed with bacterial pneumonia. Volume perfusion computed tomography of the involved pulmonary areas was performed at 80 kV and 60 mAs, with 26 measurement points distributed over 65.9 seconds. Fifty milliliters of contrast material was injected at a rate of 5 mL/s, followed by a 50-mL saline chaser. Entire coverage of the pneumonic parenchymal consolidation was obtained in all patients, with the generation of parametric maps of blood flow (BF) using the maximal slope model and blood volume (BV) using Patlak analysis. The results of perfusion measurements were then analyzed and evaluated for all patients. Results: Patients with proven, probable, or possible angioinvasive pulmonary fungal infection revealed very low levels of perfusion of their parenchymal consolidations, with BFs ranging from 0.01 to 23.86 mL/100 mL tissue/min and BVs ranging from 0.88 to 10.67 mL/100 mL tissue, lower than those of the adjacent thoracic musculature and of bacterial pneumonias. Bacterial pneumonias showed all increased perfusion parameters, with BFs ranging from 30.49 to 41.65 mL/100 mL tissue/min and BVs ranging from 10.07 to 49.90 mL/100 mL tissue. The cutoff BF value for differentiation was 23.89 mL/100 mL tissue/min, and the cutoff BV value was 9.6 mL/100 mL tissue. Conclusions: Patients with angioinvasive pulmonary mycosis showed lower perfusion parameters on volume perfusion computed tomography compared to those experiencing bacterial pneumonia.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

Article Radiology, Nuclear Medicine & Medical Imaging

Towards automated generation of curated datasets in radiology: Application of natural language processing to unstructured reports exemplified on CT for pulmonary embolism

Thomas Weikert, Ivan Nesic, Joshy Cyriac, Jens Bremerich, Alexander W. Sauter, Gregor Sommer, Bram Stieltjes

EUROPEAN JOURNAL OF RADIOLOGY (2020)

Article Radiology, Nuclear Medicine & Medical Imaging

Automated detection of pulmonary embolism in CT pulmonary angiograms using an AI-powered algorithm

Thomas Weikert, David J. Winkel, Jens Bremerich, Bram Stieltjes, Victor Parmar, Alexander W. Sauter, Gregor Sommer

EUROPEAN RADIOLOGY (2020)

Article Radiology, Nuclear Medicine & Medical Imaging

Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic: The synergetic effect of an open, clinically embedded software development platform and machine learning

Constantin Anastasopoulos, Thomas Weikert, Shan Yang, Ahmed Abdulkadir, Lena Schmuelling, Claudia Buehler, Fabiano Paciolla, Raphael Sexauer, Joshy Cyriac, Ivan Nesic, Raphael Twerenbold, Jens Bremerich, Bram Stieltjes, Alexander W. Sauter, Gregor Sommer

EUROPEAN JOURNAL OF RADIOLOGY (2020)

Article Radiology, Nuclear Medicine & Medical Imaging

Machine learning automatically detects COVID-19 using chest CTs in a large multicenter cohort

Eduardo J. Mortani Barbosa, Bogdan Georgescu, Shikha Chaganti, Gorka Bastarrika Aleman, Jordi Broncano Cabrero, Guillaume Chabin, Thomas Flohr, Philippe Grenier, Sasa Grbic, Nakul Gupta, Francois Mellot, Savvas Nicolaou, Thomas Re, Pina Sanelli, Alexander W. Sauter, Youngjin Yoo, Valentin Ziebandt, Dorin Comaniciu

Summary: The study investigates machine learning and deep learning classifiers to accurately differentiate COVID-19 from other types of pneumonia, ILD, and normal CTs using interpretable features and quantitative imaging features.

EUROPEAN RADIOLOGY (2021)

Article Medicine, General & Internal

Vascular Abnormalities Detected with Chest CT in COVID-19: Spectrum, Association with Parenchymal Lesions, Cardiac Changes, and Correlation with Clinical Severity (COVID-CAVA Study)

Salah D. Qanadli, Alexander W. Sauter, Hatem Alkadhi, Andreas Christe, Pierre-Alexandre Poletti, Lukas Ebner, David C. Rotzinger

Summary: The Swiss national registry CAVA is a multicentric cohort study aimed at evaluating vascular and non-vascular-related CT findings in COVID-19 patients and their correlation with clinical outcomes. The main objective is to assess the prevalence of cardiovascular abnormalities, while secondary objectives include studying the predictive value of cardiovascular abnormalities in terms of disease severity and fatal outcomes.

DIAGNOSTICS (2021)

Article Medicine, General & Internal

Automated Detection of Pancreatic Cystic Lesions on CT Using Deep Learning

Lorraine Abel, Jakob Wasserthal, Thomas Weikert, Alexander W. Sauter, Ivan Nesic, Marko Obradovic, Shan Yang, Sebastian Manneck, Carl Glessgen, Johanna M. Ospel, Bram Stieltjes, Daniel T. Boll, Bjoern Friebe

Summary: An algorithm based on a two-step nnU-Net architecture was developed for automated detection of pancreatic cystic lesions on CT scans, showing comparable performance to human readers. The algorithm had high sensitivity for large lesions and those located in the distal pancreas.

DIAGNOSTICS (2021)

Article Medicine, General & Internal

Automated CT Lung Density Analysis of Viral Pneumonia and Healthy Lungs Using Deep Learning-Based Segmentation, Histograms and HU Thresholds

Andrej Romanov, Michael Bach, Shan Yang, Fabian C. Franzeck, Gregor Sommer, Constantin Anastasopoulos, Jens Bremerich, Bram Stieltjes, Thomas Weikert, Alexander Walter Sauter

Summary: The study demonstrated that imaging biomarkers derived from deep learning segmentation-based histogram and HU threshold analysis can effectively differentiate healthy lungs from lungs with viral pneumonia. The absolute high attenuation area [600-0 HU] showed the strongest correlation with disease severity.

DIAGNOSTICS (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep learning-based automated detection of pulmonary embolism on CT pulmonary angiograms: No significant effects on report communication times and patient turnaround in the emergency department nine months after technical implementation

Lena Schmuelling, Fabian C. Franzeck, Christian H. Nickel, Gregory Mansella, Roland Bingisser, Noemi Schmidt, Bram Stieltjes, Jens Bremerich, Alexander W. Sauter, Thomas Weikert, Gregor Sommer

Summary: This study aimed to investigate the role of deep learning algorithm in detecting PE in CTPAs and improving communication efficiency with the emergency department through an ENS. The research found that while the algorithm performed well, the introduction of these tools alone was not sufficient to significantly impact clinical performance measures.

EUROPEAN JOURNAL OF RADIOLOGY (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Fully automated guideline-compliant diameter measurements of the thoracic aorta on ECG-gated CT angiography using deep learning

Maurice Pradella, Thomas Weikert, Jonathan Sperl, Rainer Kaergel, Joshy Cyriac, Rita Achermann, Alexander W. Sauter, Jens Bremerich, Bram Stieltjes, Philipp Brantner, Gregor Sommer

Summary: The research found that in a clinical setting, the DL algorithm provided coherent results to radiologists at almost 90% of measurement locations, with the majority of discrepent cases located at the aortic root. In total, the DL algorithm assisted radiologists in performing AHA-compliant measurements by saving 50% of time per case.

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY (2021)

Article Medicine, General & Internal

Automated Detection, Segmentation, and Classification of Pericardial Effusions on Chest CT Using a Deep Convolutional Neural Network

Adrian Jonathan Wilder-Smith, Shan Yang, Thomas Weikert, Jens Bremerich, Philip Haaf, Martin Segeroth, Lars C. Ebert, Alexander Sauter, Raphael Sexauer

Summary: This study developed an automatic PEF detection, segmentation, and classification tool that can reliably detect and diagnose PEF on CT scans with high sensitivity and specificity. The tool has the potential to improve the efficiency and quality of CT diagnosis.

DIAGNOSTICS (2022)

Article Biochemistry & Molecular Biology

Acute Pulmonary Embolism in COVID-19: A Potential Connection between Venous Congestion and Thrombus Distribution

Franck Nevesny, David C. Rotzinger, Alexander W. Sauter, Laura Loebelenz, Lena Schmuelling, Hatem Alkadhi, Lukas Ebner, Andreas Christe, Alexandra Platon, Pierre-Alexandre Poletti, Salah D. Qanadli

Summary: Vascular abnormalities, including venous congestion and pulmonary embolism, are common in COVID-19 patients. Pulmonary embolism is primarily associated with venous congestion and not affected by alveolar opacities in the absence of venous congestion.

BIOMEDICINES (2022)

Article Computer Science, Artificial Intelligence

Utilization of Artificial Intelligence-based Intracranial Hemorrhage Detection on Emergent Noncontrast CT Images in Clinical Workflow

Muhannad Seyam, Thomas Weikert, Alexander Sauter, Alex Brehm, Marios-Nikos Psychogios, Kristine A. Blackham

Summary: Authors implemented an AI-based detection tool for intracranial hemorrhage and evaluated its diagnostic performance and impact on clinical workflow. While the overall diagnostic accuracy was 93.0%, lower detection rates were observed for specific types of ICH. Workflow metrics showed a reduction in average time for communicating critical findings post-implementation, but further improvements are needed to streamline the entire workflow chain.

RADIOLOGY-ARTIFICIAL INTELLIGENCE (2022)

Article Cardiac & Cardiovascular Systems

Atri-U: assisted image analysis in routine cardiovascular magnetic resonance volumetry of the left atrium

Constantin Anastasopoulos, Shan Yang, Maurice Pradella, Tugba Akinci D'Antonoli, Sven Knecht, Joshy Cyriac, Marco Reisert, Elias Kellner, Rita Achermann, Philip Haaf, Bram Stieltjes, Alexander W. Sauter, Jens Bremerich, Gregor Sommer, Ahmed Abdulkadir

Summary: The study achieved a substantial reduction in time required to read a cardiovascular magnetic resonance (CMR) study for estimating left atrial volume by combining automated LA volumetry with human interaction in image analysis. The assistance of Atri-U led to a significant reduction in reading time in a clinical setting and provided measurement results close to those of experts.

JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Prediction of Patient Management in COVID-19 Using Deep Learning-Based Fully Automated Extraction of Cardiothoracic CT Metrics and Laboratory Findings

Thomas Weikert, Saikiran Rapaka, Sasa Grbic, Thomas Re, Shikha Chaganti, David J. Winkel, Constantin Anastasopoulos, Tilo Niemann, Benedikt J. Wiggli, Jens Bremerich, Raphael Twerenbold, Gregor Sommer, Dorin Comaniciu, Alexander W. Sauter

Summary: Automated image analysis of chest CTs from COVID-19 patients allows for the extraction of pulmonary and cardiovascular metrics, which can aid in predicting patient management. Combining demographic parameters, CT metrics, and laboratory findings showed excellent performance in predicting the need for intensive care. Application of the model on a different hospital dataset demonstrated its external validity.

KOREAN JOURNAL OF RADIOLOGY (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Assessment of a Deep Learning Algorithm for the Detection of Rib Fractures on Whole-Body Trauma Computed Tomography

Thomas Weikert, Luca Andre Noordtzij, Jens Bremerich, Bram Stieltjes, Victor Parmar, Joshy Cyriac, Gregor Sommer, Alexander Walter Sauter

KOREAN JOURNAL OF RADIOLOGY (2020)

暂无数据