Article
Radiology, Nuclear Medicine & Medical Imaging
Jong Hyuk Lee, Hyunsook Hong, Gunhee Nam, Eui Jin Hwang, Chang Min Park
Summary: This study assessed the impact of AI diagnostic performance and reader characteristics on the detection of malignant lung nodules during AI-assisted reading of chest radiographs. The use of a high accuracy AI model improved readers' detection performance to a greater extent than a low accuracy AI model, and readers using the high accuracy AI showed a higher susceptibility to changing their diagnosis based on AI suggestions.
Article
Biochemistry & Molecular Biology
Hwa-Yen Chiu, Rita Huan-Ting Peng, Yi-Chian Lin, Ting-Wei Wang, Ya-Xuan Yang, Ying-Ying Chen, Mei-Han Wu, Tsu-Hui Shiao, Heng-Sheng Chao, Yuh-Min Chen, Yu-Te Wu
Summary: This study presents a machine learning method for early lung cancer detection using chest X-rays and demonstrates its effectiveness in assisting radiologists in the early detection of lung nodules.
Article
Radiology, Nuclear Medicine & Medical Imaging
Eline Langius-Wiffen, Pim A. de Jong, Firdaus Mohamed A. Hoesein, Lisette Dekker, Andor F. Van den Hoven, Ingrid M. Nijholt, Martijn F. Boomsma, Wouter B. Veldhuis
Summary: This study evaluated the incremental value of artificial intelligence (AI) compared to radiologists alone in diagnosing incidental acute pulmonary embolism (PE) on routine chest CT scans. CT scans of 3089 patients were retrospectively analyzed using an AI algorithm. The AI algorithm showed higher sensitivity and comparable specificity to the initial report, detecting 25 cases of initially unreported PE.
EUROPEAN RADIOLOGY
(2023)
Article
Oncology
Chengdi Wang, Jun Shao, Xiuyuan Xu, Le Yi, Gang Wang, Congchen Bai, Jixiang Guo, Yanqi He, Lei Zhang, Zhang Yi, Weimin Li
Summary: The DeepLN algorithm based on deep learning shows competitive performance in predicting imaging characteristics, malignancy, and pathologic subtypes of pulmonary nodules based on non-invasive CT images.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Jiajun Deng, Mengmeng Zhao, Qiuyuan Li, Yikai Zhang, Minjie Ma, Chuanyi Li, Jun Wang, Yunlang She, Yan Jiang, Yunzeng Zhang, Tingting Wang, Chunyan Wu, Likun Hou, Sheng Zhong, Shengxi Jin, Dahong Qian, Dong Xie, Yuming Zhu, Yasmeen K. Tandon, Annemiek Snoeckx, Feng Jin, Bentong Yu, Guofang Zhao, Chang Chen
Summary: The AI diagnostic system SSNet showed comparable performance to doctors in differentiating invasive adenocarcinoma, improving sensitivity for junior doctors and specificity for senior doctors. In the external test, SSNet outperformed doctors in AUC, with doctors' AUC improving with SSNet assistance. Furthermore, SSNet achieved better performance than doctors in histological subtype classifications, enhancing the overall diagnostic efficiency in evaluating SSNs.
TRANSLATIONAL LUNG CANCER RESEARCH
(2021)
Article
Cardiac & Cardiovascular Systems
Michal Cohen-Shelly, Zachi Attia, Paul A. Friedman, Saki Ito, Benjamin A. Essayagh, Wei-Yin Ko, Dennis H. Murphree, Hector Michelena, Maurice Enriquez-Sarano, Rickey E. Carter, Patrick W. Johnson, Peter A. Noseworthy, Francisco Lopez-Jimenez, Jae K. Oh
Summary: The study showed that AI-ECG has a certain degree of accuracy and reliability in identifying patients with moderate to severe AS, especially showing differences among patients of different ages and genders. For patients with false-positive AI-ECGs, the risk of developing moderate or severe AS within the next 15 years is twice that of true negative AI-ECGs.
EUROPEAN HEART JOURNAL
(2021)
Article
Cardiac & Cardiovascular Systems
Michal Cohen-Shelly, Zachi Attia, Paul A. Friedman, Saki Ito, Benjamin A. Essayagh, Wei-Yin Ko, Dennis H. Murphree, Hector Michelena, Maurice Enriquez-Sarano, Rickey E. Carter, Patrick W. Johnson, Peter A. Noseworthy, Francisco Lopez-Jimenez, Jae K. Oh
Summary: The study aimed to develop an artificial intelligence-enabled electrocardiogram (AI-ECG) to identify patients with moderate to severe aortic stenosis (AS). The AI-ECG showed promising results in detecting AS, especially in a community screening setting.
EUROPEAN HEART JOURNAL
(2021)
Article
Medicine, General & Internal
Philippe A. Grenier, Angela Ayobi, Sarah Quenet, Maxime Tassy, Michael Marx, Daniel S. Chow, Brent D. Weinberg, Peter D. Chang, Yasmina Chaibi
Summary: We developed a deep learning-based application to automatically detect acute pulmonary embolism (PE) on chest computed tomography angiograms (CTAs) and alert radiologists for urgent interpretation. The algorithm demonstrated a high level of diagnostic accuracy with balanced sensitivity and specificity for PE detection on CTAs.
Review
Oncology
Anton Schreuder, Ernst T. Scholten, Bram van Ginneken, Colin Jacobs
Summary: Lung cancer CT screening has shown a reduction in deaths but faces challenges such as false positives, cost-effectiveness, and radiologist availability. AI can enhance efficiency in screening, but more research is needed to fully integrate it into the analysis of lung CT scans.
TRANSLATIONAL LUNG CANCER RESEARCH
(2021)
Article
Biochemistry & Molecular Biology
Mayidili Nijiati, Jie Ma, Chuling Hu, Abudouresuli Tuersun, Abudoukeyoumujiang Abulizi, Abudoureyimu Kelimu, Dongyu Zhang, Guanbin Li, Xiaoguang Zou
Summary: This study developed an artificial intelligence system based on deep convolutional neural network (DCNN) to accurately diagnose tuberculosis (TB) on chest X-ray photographs. The system achieved a diagnostic accuracy of 96.73% and was able to mark the precise TB regions on the radiographs.
FRONTIERS IN MOLECULAR BIOSCIENCES
(2022)
Article
Oncology
Dalia Fahmy, Heba Kandil, Adel Khelifi, Maha Yaghi, Mohammed Ghazal, Ahmed Sharafeldeen, Ali Mahmoud, Ayman El-Baz
Summary: This manuscript discusses the applications of artificial intelligence (AI) in lung segmentation, pulmonary nodule segmentation, and classification. It highlights the importance of early detection of pulmonary nodules for lung cancer treatment and saving lives, and how AI technology can improve diagnostic accuracy.
Article
Engineering, Biomedical
Guozheng Sui, Xuefeng Liu, Shuang Chen, Shunli Liu, Zaixian Zhang
Summary: This paper proposes a segmentation method based on adversarial domain adaptation and background masking for medical image segmentation. By constructing networks and updating parameters for both source and target data, the segmentation accuracy is improved. Experimental results show that this method has a potential prospect in the segmentation of pulmonary nodules in computed tomography images.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Article
Medicine, General & Internal
Placido Gomes, Helder Novais e Bastos, Andre Carvalho, Andre Lobo, Alan Guimaraes, Rosana Souza Rodrigues, Walter Araujo Zin, Alysson Roncally S. Carvalho
Summary: This study evaluated the association between emphysema extent and regional distribution quantified by chest CT with clinical and functional severity in COPD patients. Results showed that emphysema volume should be referenced to predicted lung volume, not measured lung volume, for assessment. Pulmonary function impairments were greater in patients with higher emphysema volumes and more homogenous distribution of emphysema.
FRONTIERS IN MEDICINE
(2021)
Article
Multidisciplinary Sciences
Eduardo P. Reis, Joselisa P. Q. de Paiva, Maria C. B. da Silva, Guilherme A. S. Ribeiro, Victor F. Paiva, Lucas Bulgarelli, Henrique M. H. Lee, Paulo V. Santos, Vanessa M. Brito, Lucas T. W. Amaral, Gabriel L. Beraldo, Jorge N. Haidar Filho, Gustavo B. S. Teles, Gilberto Szarf, Tom Pollard, Alistair E. W. Johnson, Leo A. Celi, Edson Amaro
Summary: This paper describes a automatically labeled Brazilian chest x-ray dataset, BRAX, designed to assist researchers in validating machine learning models. The dataset includes a large number of chest radiography studies from a Brazilian general hospital, totaling 40,967 images.
Article
Radiology, Nuclear Medicine & Medical Imaging
Florian Jungmann, Lukas Mueller, Felix Hahn, Maximilian Weustenfeld, Ann-Kathrin Dapper, Aline Maehringer-Kunz, Dirk Graafen, Christoph Dueber, Darius Schafigh, Daniel Pinto dos Santos, Peter Mildenberger, Roman Kloeckner
Summary: This study evaluated the performance of commercial AI solutions in differentiating COVID-19 pneumonia from other lung conditions, revealing variable specificity and low positive predictive value. One solution showed acceptable sensitivity values, suggesting the potential integration of commercial AI solutions as alert tools in clinical routine workflow with further improvement. Randomized trials are needed to fully assess the benefits and risks of AI in image analysis.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jeremy R. Burt, Jeffrey Waltz, Ashley Ramirez, Andres Abadia, Basel Yacoub, Sydney A. Burt, Fiona Tissavirasingham, Madison R. Kocher
Summary: The majority of young adult patients presented with large tumors on imaging, increasing the likelihood of identification on CT. Tumors initially presenting in the rectum with enlarged lymph nodes and/or with distant metastases on CT were more often associated with advanced surgical stage and poorer prognosis. A majority of patients presented at an advanced stage, most commonly stage 4A, and had progression of disease at follow-up.
ABDOMINAL RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Basel Yacoub, Adam Spandorfer, U. Joseph Sehoepf, Sheldon E. Litwin
Summary: The study found a weak but significant inverse correlation between fat content in the liver, spleen, and erector spinae muscle and body mass index, but not in the myocardial septum. Furthermore, there were differences in mean attenuation values between the obese and nonobese groups in different tissues. The study did not find a relationship between myocardial CT attenuation and obesity or other cardiovascular risk factors, suggesting that the degree of myocardial fat accumulation in obesity or metabolic syndrome may be too small to be detected with this modality.
JOURNAL OF THORACIC IMAGING
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Basel Yacoub, Ismail M. Kabakus, U. Joseph Schoepf, Vincent M. Giovagnoli, Andreas M. Fischer, Julian L. Wichmann, John D. Martinez, Puneet Sharma, Saikiran Rapaka, Pooyan Sahbaee, Philipp Hoelzer, Jeremy R. Burt, Akos Varga-Szemes, Tilman Emrich
Summary: This study evaluates the implementation of an AI platform in evaluating noncontrast chest CT scans compared to clinical radiology reports. The results demonstrate a significant added value to clinical radiology reporting when incorporating AI support platforms into radiology workflows. The AI platform showed better performance in identifying aortic dilatation and coronary artery calcifications, while the clinical radiology reports performed better in identifying pulmonary lesions and vertebral compression fractures. The performance in identifying pulmonary emphysema was comparable between AI and clinical radiology reports.
ACADEMIC RADIOLOGY
(2022)
Article
Cardiac & Cardiovascular Systems
Pengpeng Xu, Yi Xue, U. Joseph Schoepf, Akos Varga-Szemes, Joseph Griffith, Basel Yacoub, Fan Zhou, Changsheng Zhou, Yuting Yang, Wei Xing, Longjiang Zhang
Summary: Radiomics utilizes advanced image analysis to extract quantitative information, revealing correlations between imaging features and clinical endpoints. Cardiac CT radiomics analysis shows diagnostic potential and benefits for patients and physicians.
CIRCULATION-CARDIOVASCULAR IMAGING
(2021)
Article
Cardiac & Cardiovascular Systems
Akos Varga-Szemes, U. Joseph Schoepf, Pal Maurovich-Horvat, Rui Wang, Lei Xu, Danielle M. Dargis, Tilman Emrich, Andrew J. Buckler
Summary: The study evaluated the feasibility of using plaque morphology assessment from CCTA to estimate non-invasive FFR, which outperformed traditional stenosis interpretation and showed comparable sensitivity and specificity. The results suggest that non-invasive plaque morphology-based FFR assessment may be a useful tool for predicting lesion-specific ischemia in hemodynamically significant CAD.
INTERNATIONAL JOURNAL OF CARDIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Akos Varga-Szemes, Pascale Aouad, U. Joseph Schoepf, Tilman Emrich, Basel Yacoub, Thomas M. Todoran, Ioannis Koktzoglou, Robert R. Edelman
Summary: The 3D prototype thin-slab stack-of-stars (tsSOS) quiescent-interval slice-selective (QISS) MRA technique showed better image quality for branch vessels compared to the standard 2D-QISS technique in diagnosing peripheral artery disease (PAD). However, there was no significant difference in objective image quality between the two techniques.
MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Josua A. Decker, Laura-Marie Brill, Ulrich Orlowski, Akos Varga-Szemes, Tilman Emrich, U. Joseph Schoepf, Florian Schwarz, Thomas J. Kroncke, Christian Scheurig-Munkler
Summary: This retrospective study investigated the predictors of mortality in patients with spontaneous iliopsoas muscle hemorrhage (SIPH). The results showed that only active bleeding was associated with shorter survival, while hematoma volume and extramuscular retroperitoneal hematoma had no significant influence on short-term mortality.
ACADEMIC RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Gilberto J. Aquino, Andres F. Abadia, U. Joseph Schoepf, Tilman Emrich, Basel Yacoub, Ismail Kabakus, Alexis Violette, Courtney Wiley, Andreina Moreno, Pooyan Sahbaee, Chris Schwemmer, Richard R. Bayer, Akos Varga-Szemes, Daniel Steinberg, Nicholas Amoroso, Madison Kocher, Jeffrey Waltz, Thomas J. Ward, Jeremy R. Burt
Summary: This study evaluated the predictive value of machine learning-based CT-FFR in candidates for TAVR. The results demonstrated that CT-FFR had independent predictive value for MACE and improved the predictive value of coronary CT angiography assessment.
Article
Cardiac & Cardiovascular Systems
Song Luo, Wei Qiang Dou, U. Joseph Schoepf, Akos Varga-Szemes, Wanya T. Pridgen, Long Jiang Zhang
Summary: This article systematically reviews the pathology, clinical features, and diagnosis of myocardial involvement in systemic lupus erythematosus (SLE), while illustrating the clinical role of cardiovascular magnetic resonance (CMR) imaging in SLE-associated cardiomyopathy.
TRENDS IN CARDIOVASCULAR MEDICINE
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Verena Brandt, Raffi Bekeredjian, U. Joseph Schoepf, Akos Varga-Szemes, Tilman Emrich, Gilberto J. Aquino, Josua Decker, Richard R. Bayer, Lauren Ellis, Ullrich Ebersberger, Christian Tesche
Summary: This study aimed to determine the prognostic implication of EAT volume, CCTA-derived plaque quantification, and CT-FFR for major adverse cardiac events (MACE) and found that a combination of these parameters significantly improved the prediction performance. EAT volume, CCTA >= 50% stenosis, and CT-FFR were significantly different in patients who developed MACE, highlighting their potential as predictors for adverse cardiac events.
EUROPEAN JOURNAL OF RADIOLOGY
(2022)
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
Akos Varga-Szemes, Tilman Emrich
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Gilberto J. Aquino, Josua A. Decker, U. Joseph Schoepf, Landin Carson, Namrata Paladugu, Basel Yacoub, Verena Brandt, Anna Lena Emrich, Florian Schwarz, Jeremy R. Burt, Richard Bayer II, Akos Varga-Szemes, Tilman Emrich
Summary: This study evaluated the value of using left ventricular long-axis shortening (LV-LAS) derived from coronary CT angiography (CCTA) to predict mortality in patients with severe aortic stenosis (AS) undergoing transcatheter aortic valve replacement (TAVR). The results showed that LV-LAS can independently predict mortality in patients undergoing TAVR, including those with a normal left ventricular ejection fraction (LVEF).
RADIOLOGY-CARDIOTHORACIC IMAGING
(2022)
Review
Radiology, Nuclear Medicine & Medical Imaging
Martin J. Willemink, Akos Varga-Szemes, U. Joseph Schoepf, Marina Codari, Koen Nieman, Dominik Fleischmann, Domenico Mastrodicasa
Summary: Emerging imaging methods offer a more detailed picture of postischemic myocardial phenomena, potentially advancing the understanding and clinical practice of ischemic heart disease.
EUROPEAN RADIOLOGY EXPERIMENTAL
(2021)
Article
Cardiac & Cardiovascular Systems
Basel Yacoub, Robert E. Stroud, Davide Piccini, U. Joseph Schoepf, John Heerfordt, Jerome Yerly, Lorenzo Di Sopra, Jonathan D. Rollins, D. Alan Turner, Tilman Emrich, Fei Xiong, Pal Suranyi, Akos Varga-Szemes
Summary: The radial whole-heart CMRA technique combined with respiratory motion-resolved reconstruction provides comparable anatomical measurements of the thoracic aorta and cardiac structures as the reference standard CTA. It could potentially be used to diagnose and monitor patients with thoracic aortic dilatation without exposing them to radiation or contrast media.
JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE
(2021)
