Article
Pediatrics
Edward Y. Lee, Sara O. Vargas, Halley J. Park, Domen Plut, Katie A. Krone, Abbey J. Winant
Summary: The characteristic thoracic MDCT findings of a combined BA-CPAM congenital lung lesion are a solitary, well-circumscribed solid and multicystic mass, with a nonenhancing nodule, reflecting the BA component, adjacent to a cystic mass, representing the CPAM component. Accurate recognition of these characteristic MDCT findings has the potential to differentiate this combined congenital lung lesion from other thoracic pathology in children. Interobserver agreement for detecting abnormalities on thoracic MDCT studies was almost perfect (k = 0.98).
PEDIATRIC PULMONOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiaohan Bai, Lingyu Wu, Jie Dai, Kexin Wang, Hongyuan Shi, Zipeng Lu, Guwei Ji, Jing Yu, Qing Xu
Summary: This study identified radiological features and clinical biomarkers, including rim enhancement, peripancreatic fat stranding, tumor size, tumor resectability, and level of CA125, as predictors of occult metastasis (OM) in pancreatic ductal adenocarcinoma (PDAC). A combined model incorporating these factors showed the highest performance in predicting OM.
ACADEMIC RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yong Chen, Jingyu Zhong, Lan Wang, Xiaomeng Shi, Wei Lu, Jianying Li, Jianxing Feng, Yihan Xia, Rui Chang, Jing Fan, Liwei Chen, Ying Zhu, Fuhua Yan, Weiwu Yao, Huan Zhang
Summary: This study evaluated the repeatability and reproducibility of radiomics features within and between single-energy CT (SECT) and dual-energy CT (DECT), as well as different scan modes and scanners. The majority of radiomics features were found to be non-reproducible within and between SECT and DECT.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
F. Zanca, H. G. Brat, P. Pujadas, D. Racine, B. Dufour, D. Fournier, B. Rizk
Summary: The study aimed to determine a personalized and optimized contrast injection protocol for liver parenchymal enhancement. Results showed that the protocol based on 600 mgI/kg FFM achieved diagnostically optimized liver enhancement, improved patient-to-patient enhancement uniformity, and significantly reduced iodine load.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Stefanie J. Bette, Franziska M. Braun, Mark Haerting, Josua A. Decker, Jan H. Luitjens, Christian Scheurig-Muenkler, Thomas J. Kroencke, Florian Schwarz
Summary: In this study comparing PCD-CT and EID-CT in mouse specimens, PCD-CT demonstrated lower image noise, higher SNR, and better edge sharpness compared to EID-CT. Radiologists consistently preferred PCD-CT for visualizing bone details, even in SNR-matched pairs.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Haoting Wu, Chenqing Wu, Hui Zheng, Lei Wang, Wenbin Guan, Shaofeng Duan, Dengbin Wang
Summary: A CT-based radiomics signature was constructed and showed great performance in predicting MYCN amplification in pediatric patients with neuroblastoma. The clinical radiomics nomogram, incorporating radiomics signature and clinical factors, outperformed the clinical model alone for predicting MNA.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Antoine Topolsky, Olivier Pantet, Lucas Liaudet, Christine Sempoux, Alban Denys, Jean-Francois Knebel, Sabine Schmidt
Summary: This study evaluated the influence of vasoconstrictor agents on vasoconstriction and bowel ischemia detected by MDCT in patients with non-occlusive mesenteric ischemia. The results showed that patients treated with vasoconstrictor agents had more severe mesenteric artery vasoconstriction and more frequent abdominal organ infarcts compared to patients not treated with vasoconstrictor agents. The use of vasoconstrictor agents also led to lower blood pressure and hemoglobin levels, indicating worse clinical condition.
EUROPEAN RADIOLOGY
(2023)
Article
Computer Science, Interdisciplinary Applications
Syed Ahmed Nadeem, Eric A. Hoffman, Jessica C. Sieren, Alejandro P. Comellas, Surya P. Bhatt, Igor Z. Barjaktarevic, Fereidoun Abtin, Punam K. Saha
Summary: This study introduces a novel approach for automated segmentation of pulmonary airway trees to explore COPD sub-phenotypes, assess disease progression, and intervention outcomes. Both CT intensity- and deep learning-based algorithms show high reproducibility and accuracy, with the deep learning-based FG algorithm being a promising option for large multi-site studies.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Medicine, General & Internal
Jiyeon Park, Chohee Kim, Yoon Ki Cha, Myung Jin Chung
Summary: This study aimed to examine how often radiologists miss or detect incidental breast cancers on chest CT and compare the CT features between the two groups. By evaluating chest CT scans and medical records of breast cancer patients, it was found that 64.3% of incidental breast cancer lesions were missed by radiologists. Smaller lesions and those with lower enhancement ratios were more likely to be missed. However, when radiologists re-read the CTs with a focus on the breast area, they had higher accuracy in detecting breast cancers (90.1%, 87.9%, and 81.3%).
Article
Radiology, Nuclear Medicine & Medical Imaging
Choong Guen Chee, Min A. Yoon, Kyung Won Kim, Yusun Ko, Su Jung Ham, Young Chul Cho, Bumwoo Park, Hye Won Chung
Summary: The combined radiomics-clinical model showed good calibration and discrimination in predicting malignancy of vertebral compression fractures on CT. It outperformed both the radiomics score and clinical predictor model in terms of discrimination performance and accurately stratified patients into low and high risk groups.
EUROPEAN RADIOLOGY
(2021)
Article
Medicine, General & Internal
Laura Andreea Bolintineanu (Ghenciu), Sorin Lucian Bolintineanu, Nicoleta Iacob, Delia-Elena Zahoi
Summary: The purpose of this study was to determine the prevalence of normal hepatic vascularization and variations in the common hepatic arteries using multidetector computer tomography angiography. The study identified various variants of hepatic arteries and analyzed their clinical and surgical implications. The findings have important implications in surgical planning for hepatic transplantation, liver and pancreatic resection, and upper abdominal surgeries.
Article
Radiology, Nuclear Medicine & Medical Imaging
Johan Jendeberg, Per Thunberg, Marcin Popiolek, Mats Liden
Summary: The study validated a quantitative SE-CT method (kNN-ppLapl-maxHU) that can classify UA stones with accuracy comparable to DE-CT.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Giovanni Foti, Ronaldo Silva, Niccolo Faccioli, Alessandro Fighera, Rossella Menghini, Arianna Campagnola, Giovanni Carbognin
Summary: In a selected, high-prevalence population, VP-DECT is considered an accurate imaging tool for diagnosing PE compared to CTPA. The sensitivity of VP-DECT images in per-patient analysis was 90.0%, with 100% specificity; while in per-lobe analysis, sensitivity ranged from 100% for the right lower lobe to 50% for the left upper lobe.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Sebastian Ruehling, Fernando Navarro, Anjany Sekuboyina, Malek El Husseini, Thomas Baum, Bjoern Menze, Rickmer Braren, Claus Zimmer, Jan S. Kirschke
Summary: This study evaluated the accuracy of an artificial neural network for automated detection of iodinated contrast agent in MDCT scans and the effect of contrast correction for osteoporosis screening. The results showed that the 2D DenseNet model with anatomy-guided slice selection outperformed others and successfully reduced the bias in bone mineral density measurements after contrast application.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ieun Yoon, Jae Seok Bae, Jeongin Yoo, Dong Ho Lee, Se Hyung Kim
Summary: Studies suggest that compared to MDCT alone, MDCT combined with [F-18]FDG PET/MRI can improve the diagnostic accuracy for preoperative M staging and resectability in patients with recurrent gastric cancer, with a significant advantage in evaluating M staging.
EUROPEAN RADIOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Anna Fabijanska
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2018)
Article
Agriculture, Multidisciplinary
Anna Fabijanska, Malgorzata Danek
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2018)
Article
Engineering, Biomedical
Anna Fabijanska
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2019)
Article
Automation & Control Systems
Mariusz Chybicki, Wiktor Kozakiewicz, Dawid Sielski, Anna Fabijanska
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2019)
Article
Computer Science, Interdisciplinary Applications
Konrad Olejnik, Anna Fabijanska, Pawel Pelczynski, Anna Stanislawska
COMPUTERS & CHEMICAL ENGINEERING
(2019)
Article
Agriculture, Multidisciplinary
Anna Fabijanska, Malgorzata Danek, Joanna Barniak
Summary: This paper introduces a convolutional neural network method for automatic tree species identification from scanned wood core images, achieving high accuracy in wood patch classification and wood core classification tasks. The model outperformed the state-of-the-art methods and the study also analyzed the impact of model parameters and training settings on performance to ensure the highest recognition rates.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Engineering, Biomedical
Adrian Kucharski, Anna Fabijanska
Summary: The study proposes a fully automatic pipeline combining the watershed algorithm and an encoder-decoder convolutional neural network for corneal endothelial cell segmentation. It achieves promising results on a heterogeneous dataset, outperforming the competitor in terms of cell detection accuracy and other metrics.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Interdisciplinary Applications
Maciej Czepita, Anna Fabijanska
Summary: An automated pipeline was proposed for analyzing blood flow through retinal vessels to replace time-consuming manual methods. Using convolutional neural networks and full width at half maximum analysis, blood flow was successfully detected in 18 retinal blood vessels. The average difference between manual and automatic measurements was 4.96%, with an average relative error of 8% for single vessel measurements.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Chemistry, Multidisciplinary
Abir Affane, Adrian Kucharski, Paul Chapuis, Samuel Freydier, Marie-Ange Lebre, Antoine Vacavant, Anna Fabijanska
Summary: Accurate liver vessel segmentation is crucial for hepatic diseases, with recent methods using deep learning like U-Net. This study compares 3D U-Net, Dense U-Net, and MultiRes U-Net on the IRCAD dataset, finding that full 3D processing is most accurate overall but slab-based MultiRes U-Net performs best among specific models.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Anna Fabijanska, Robert Banasiak
Summary: This study proposes using graph convolutional networks (GCN) to enhance the quality of 3D ECT images by effectively utilizing specific geometrical relationships hidden in unstructured grids, resulting in improved tomographic image quality and spatial resolution.
APPLIED SOFT COMPUTING
(2021)
Article
Multidisciplinary Sciences
Anna Fabijanska, Gabriel D. Cahalan
Summary: This study proposes a new fully automatic pipeline that quantifies the properties of resin ducts and tree-ring boundaries in Pinus trees. A convolutional neural network is used to detect the ducts and boundaries, and a region merging procedure is applied to identify connected components corresponding to successive rings. The proposed method achieves high detection sensitivity and precision for both resin ducts and tree-ring boundaries.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Biomedical
Adrian Kucharski, Anna Fabijanska
Summary: Currently, corneal endothelial image segmentation relies on convolutional neural networks, but the scarcity of labeled corneal endothelial data due to expensive cell delineation process limits their potential. This study proposes a method of synthesizing cell edges and corresponding images using generative adversarial neural networks, which has not been reported before. Experimental results on three datasets show that our solution provides a cost-effective and diverse source of training data for corneal endothelial image segmentation.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Information Systems
Anna Fabijanska
Summary: The problem of image segmentation is crucial in computer vision, and deep-learning methods have become dominant in providing solutions. However, they require a large amount of costly training data. This paper proposes a semi-supervised image segmentation method using graph convolutional networks, which achieved good performance in binary and multi-label segmentation tasks.
Article
Computer Science, Interdisciplinary Applications
Anna Fabijanska, Andrew Feder, John Ridge
COMPUTERS & GEOSCIENCES
(2020)
Article
Computer Science, Information Systems
Anna Fabijanska, Szymon Grabowski
