Polish journal of radiology最新文献

Purpose: To evaluate the feasibility of using a deep learning (DL) model to generate fat-suppression images and detect abnormalities on knee magnetic resonance imaging (MRI) through the fat-suppression image-subtraction method.

Material and methods: A total of 45 knee MRI studies in patients with knee disorders and 12 knee MRI studies in healthy volunteers were enrolled. The DL model was developed using 2-dimensional convolutional neural networks for generating fat-suppression images and subtracting generated fat-suppression images without any abnormal findings from those with normal/abnormal findings and detecting/classifying abnormalities on knee MRI. The image qualities of the generated fat-suppression images and subtraction-images were assessed. The accuracy, average precision, average recall, F-measure, sensitivity, and area under the receiver operator characteristic curve (AUROC) of DL for each abnormality were calculated.

Results: A total of 2472 image datasets, each consisting of one slice of original T1WI, original intermediate-weighted images, generated fat-suppression (FS)-intermediate-weighted images without any abnormal findings, generated FS-intermediate-weighted images with normal/abnormal findings, and subtraction images between the generated FS-intermediate-weighted images at the same cross-section, were created. The generated fat-suppression images were of adequate image quality. Of the 2472 subtraction-images, 2203 (89.1%) were judged to be of adequate image quality. The accuracies for overall abnormalities, anterior cruciate ligament, bone marrow, cartilage, meniscus, and others were 89.5-95.1%. The average precision, average recall, and F-measure were 73.4-90.6%, 77.5-89.4%, and 78.4-89.4%, respectively. The sensitivity was 57.4-90.5%. The AUROCs were 0.910-0.979.

Conclusions: The DL model was able to generate fat-suppression images of sufficient quality to detect abnormalities on knee MRI through the fat-suppression image-subtraction method.

Purpose: Ileocolonoscopy aids in the diagnosis of ileocecal region pathologies when typical mucosal lesions are seen. However, in many cases the mucosal lesions of the ileocaecal region are atypical, rendering themselves to diagnostic dilemma. The present study aimed to study the role of computed tomography (CT) enterography in the evaluation of symptomatic patients who demonstrated ileocecal mucosal lesions of uncertain diagnosis on ileocolonoscopy.

Material and methods: Symptomatic patients who had ileocolonoscopy documented ileocecal mucosal lesions of uncertain diagnosis were enrolled. Patients were subjected to CT enterography within 10 days of ileocolonoscopy. On CT enterography a diagnosis of Crohn's disease (CD) or ileocaecal tuberculosis (ITB) was made. The diagnosis obtained by CT enterography was correlated with the final diagnosis obtained from histopathology. Using descriptive statistics, the diagnostic performance of CT enterography was evaluated.

Results: A total of 153 cases were enrolled in the study. CT enterography findings were present in 147 cases, resulting in a diagnostic yield of 96%. Out of these, 58.16% (89/153) had CD, 26.14% (40/153) had ITB, 6.5% (10/153) had infectious ileitis, and 9.15% (14/153) were indeterminate on histopathology. CT enterography correctly identified 78.65% (70/89) of CD and 75% (30/40) of ITB. CT enterography had a sensitivity of 78.65% and 75%, specificity of 67.19% and 87.61%, positive predictive value of 76.92% and 68.18%, and diagnostic accuracy of 73.86% and 84.31% for diagnosing CD and ITB, respectively.

Conclusions: CT enterography provided a high diagnostic yield in ileocaecal mucosal lesions of uncertain significance on endoscopy. CD and ITB were the predominant diseases detected in these individuals. CT enterography had a good diagnostic performance in the detection of these 2 disorders.

Purpose: To assess the efficacy and safety of a low-dose, computed tomography (CT)-guided transthoracic biopsy of lung and pleural lesions.

Material and methods: A total of 135 low-dose, CT-guided transthoracic lung and pleural lesions biopsies were performed. A cutting needle was utilized in 124 cases, and fine needle aspiration biopsy was performed in 14 cases. In all cases, 14- to 22-gauge biopsy needles were used.

Results: Diagnostic material was obtained in 111 (82.2%) patients. In 97 (71.8%) cases neoplastic lesions were found, predominantly adenocarcinoma and non-small cell carcinoma. In 14 (12.6%) cases non atypical cells were reported. Biopsy failed to obtain material suitable for histopathological examination in 24 (17.7%) cases. Complications occurred in 31 patients, including pneumothorax in 28 patients and haematoma in 3 cases.

Conclusions: Based on the obtained results, it can be stated that low-dose, CT-guided transthoracic biopsy of lung and pleural tissues is an accurate and safe procedure. Also, it is linked to a low risk of complications such as a small pneumothorax.

In recent years, imaging studies have become increasingly used at various stages in the management of patients with various conditions and disorders. This process results in a necessity to provide an increasing number of exams, which involves a growing role of radiologists in assessing and reporting those exams. The article discusses tele-radiology as a method that can improve access to radiology services, presenting its potential benefits, as well as the risks involved. It analyses access to radiology healthcare services in Poland in the context of the international and Polish legal provisions concerning the right to healthcare. While funding for imaging studies for patients is widely available and imaging equipment in Poland is improving despite some shortages, the main barrier is identified in the number of specialists capable of assessing the exams. Teleradiology can alleviate this shortage, so the article presents legal provisions and international good practice guidelines in this area, focusing on documents issued by the European Society of Radiology, the American College of Radiology, and the British Royal College of Radiologists. The guidelines concerning such aspects as patients' rights, teleradiologists' qualifications, communication and reporting, responsibility, and technical requirements may help make teleradiology a safe and valuable component of the healthcare system in Poland.

Purpose: The aim of the study was to analyse the usefulness of core biopsy in the diagnosis of malignant neoplasms of the pancreas - sensitivity and accuracy of diagnosis, safety of the procedure, indication of factors that may increase the risk of complications after biopsy.

Material and methods: A retrospective analysis of data was performed in a group of 100 patients diagnosed with a focal lesion of the pancreas, qualified for a core biopsy.

Results: The results are a sensitivity of 92%, a specificity of 100%, and an accuracy of 93.3%. The incidence of more severe complications according to the Clavien-Dindo classification was 1% (one case in the material studied). The results of the analysis were compared with the results of other authors, showing similar values for the sensitivity and specificity of the method and low rates of serious complications; it also seems that the tissue material obtained by core biopsy has higher diagnostic potential than that obtained by endoscopic ultrasound-guided fine needle aspiration (EUS-FNA), currently considered the method of choice. In addition, the costs of transabdominal biopsy and endoscopic biopsy were compared; the lower cost of the former may be an important economic issue when choosing the biopsy method.

Conclusions: The results show core biopsy to be a sensitive, accurate, and safe method for obtaining the tissue necessary to plan treatment in patients with pancreatic cancer.

Purpose: Our aim was to distinguish between low-grade and high-grade brain tumours on the basis of dynamic susceptibility contrast (DSC) magnetic resonance imaging (MRI) perfusion and arterial spin labelling (ASL) perfusion and to compare DSC and ASL techniques.

Material and methods: Forty-one patients with brain tumours were evaluated by 3-Tesla MRI. Conventional and perfusion MRI imaging with a 3D pseudo-continuous ASL (PCASL) and DSC perfusion maps were evaluated. Three ROIs were placed to obtain cerebral blood value (CBV) and cerebral blood flow (CBF) in areas of maximum perfusion in brain tumour and normal grey matter. Histopathological diagnosis was considered as the reference. ROC analysis was performed to compare the diagnostic performance and to obtain a feasible cut-off value of perfusion parameters to differentiate low-grade and high-grade brain tumours.

Results: Normalised perfusion parameters with grey matter (rCBF or rCBV lesion/NGM) of malignant lesions were significantly higher than those of benign lesions in both DSC (normalised rCBF of 2.16 and normalised rCBV of 2.63) and ASL (normalised rCBF of 2.22) perfusion imaging. The normalised cut-off values of DSC (rCBF of 1.1 and rCBV of 1.4) and ASL (rCBF of 1.3) showed similar specificity and near similar sensitivity in distinguishing low-grade and high-grade brain tumours.

Conclusions: Quantitative analysis of perfusion parameters obtained by both DSC and ASL perfusion techniques can be reliably used to distinguish low-grade and high-grade brain tumours. Normalisation of these values by grey matter gives us more reliable parameters, eliminating the different technical parameters involved in both the techniques.

Colorectal cancer (CRC) is one of the most common malignancies in the world. Nowadays many treatments are available to help control CRC, including surgery, radiation therapy, interventional radiology, and drug treatments. A multidisciplinary approach and the role of radiologists is needed to assist the surgeon in the management thanks to emerging technology and strategies. The Response Evaluation Criteria in Solid Tumours (RECIST) has been created to objectify and standardize cancer response assessment. Thus, in this article specific presumptions and practical aspects of evaluating responses according to the RECIST 1.1 are discussed. Furthermore, examples of possible response to systemic treatment of colorectal liver metastases (CRLM), including tumour necrosis, apparent diffusion coefficient (ADC) values, tumour calcification, tumour fibrosis and intratumoural fat deposition observed on cross-sectional imaging, are described. Disappearing liver metastases (DLM) presents a therapeutic dilemma. The optimal management of DLM remains controversial due to the uncertainty of residual microscopic disease and effective long-term outcomes. The article provides an overview of the CRLM phenomenon and current possible assessment methods of the response to systemic treatment.

Purpose: Early depiction of bony erosions in sacroiliac (SI) joints increases the diagnostic accuracy of spondyloarthritis. The new 3D magnetic resonance imaging (MRI) sequence THRIVE (T1-weighted high-resolution isotropic volume examination) can depict cartilage erosions in sacroiliac joints. The aim of the study was to compare the diagnostic capacity of the new MRI sequence 3D THRIVE (T1-weighted high-resolution isotropic volume examination) with the routinely used T1 TSE pulse sequence in the depiction of structural erosions in sacroiliac joints by using MRI sequence zero echo time (zero ET) as a reference standard.

Material and methods: Seventy five adult patients were included in this study. They underwent MRI sacroiliac joints examination using routine T1 TSE and STIR pulse sequences with the addition of the new 3D THRIVE and zero echo time (zero ET) sequences. Images of T1 TSE, 3D THRIVE, and zero ET sequences were evaluated by 2 radiolo-gists separately for the detection of sacroiliac joints erosions, then a comparison between T1 TSE and 3D THRIVE sequences was done using a CT-like image MRI sequence zero ET as a reference standard. Sensitivity, specificity, and accuracy for each sequence were calculated by the 2 readers.

Results: Sensitivity, specificity, and accuracy of 3D THRIVE were higher than those of T1 TSE for reader 1 (sensitivity: 94.5% vs. 86.2%; specificity: 93.4% vs. 85.1%; and accuracy 95.2% vs. 88.5%) and for reader 2 (sensitivity: 93.3% vs. 79.9%; specificity: 94.7% vs. 86.2%; and accuracy 95.8% vs. 82.1%).

Conclusions: Using CT-like image MRI sequence zero ET as the reference standard, 3D THRIVE pulse sequencing of the sacroiliac joints has much better diagnostic value in the depiction of bony erosions in patients suspected having spondyloarthritis as compared to the routinely used T1 TSE sequence.

Purpose: X-ray images are viewed as a vital component in emergency diagnosis. They are often used by deep learning applications for disease prediction, especially for thoracic pathologies. Pneumonia, a fatal thoracic disease induced by bacteria or viruses, generates a pleural effusion where fluids are accumulated inside lungs, leading to breathing difficulty. The utilization of X-ray imaging for pneumonia detection offers several advantages over other modalities such as computed tomography scans or magnetic resonance imaging. X-rays provide a cost-effective and easily accessible method for screening and diagnosing pneumonia, allowing for quicker assessment and timely intervention. However, interpretation of chest X-ray images depends on the radiologist's competency. Within this study, we aim to suggest new elements leading to good interpretation of chest X-ray images for pneumonia detection, especially for distinguishing between viral and bacterial pneumonia.

Material and methods: We proposed an interpretation model based on convolutional neural networks (CNNs) and extreme gradient boosting (XGboost) for pneumonia classification. The experimental study is processed through various scenarios, using Python as a programming language and a public database obtained from Guangzhou Women and Children's Medical Centre.

Results: The results demonstrate an acceptable accuracy of 87% within a mere 7 seconds, thereby endorsing its effectiveness compared to similar existing works.

Conclusions: Our study provides a model based on CNN and XGboost to classify images of viral and bacterial pneumonia. The work is a challenging task due to the lack of appropriate data. The experimental process allows a better accuracy of 87%, a specificity of 89%, and a sensitivity of 85%.