Article
Radiology, Nuclear Medicine & Medical Imaging
Hossein Arabi, Habib Zaidi
Summary: This study implemented deep learning-based metal artefact reduction to minimize metal artefacts in CT images, with DLI-MAR approach showing superior performance compared to DLP-MAR and NMAR. Metal artefacts in CT images can lead to quantitative bias and image artefacts in PET images, but DLI-MAR technique effectively reduced these adverse effects.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Francesca Marturano, Priscilla Guglielmo, Andrea Bettinelli, Fabio Zattoni, Giacomo Novara, Alessandra Zorz, Matteo Sepulcri, Michele Gregianin, Marta Paiusco, Laura Evangelista
Summary: Radiomic analysis can assist in predicting biochemical recurrence in intermediate and high-risk prostate cancer patients. Combining clinical data with radiomic features improves the accuracy of prediction.
EUROPEAN RADIOLOGY
(2023)
Article
Oncology
Marcus Unterrainer, Christophe M. Deroose, Ken Herrmann, Markus Moehler, Lennart Blomqvist, Roberto Cannella, Caroline Caramella, Damiano Caruso, Manil D. Chouhan, Timm Denecke, Carolina De la Pinta, Lioe-Fee De Geus-Oei, Audrius Dulskas, Michel Eisenblatter, Kieran G. Foley, Sofia Gourtsoyianni, Frederic E. Lecouvet, Egesta Lopci, Monique Maas, Markus M. Obmann, Daniela E. Oprea-Lager, Joost J. C. Verhoeff, Ines Santiago, Sylvain Terraz, Melvin D'Anastasi, Daniele Regge, Andrea Laghi, Regina G. H. Beets-Tan, Volker Heinemann, Florian Lordick, Elizabeth C. Smyth, Jens Ricke, Wolfgang G. Kunz
Summary: This study aimed to establish an imaging protocol for colorectal cancer that promotes standardization and reduces variations. Through the formation of a multidisciplinary panel and the use of the Delphi method, the EORTC-ESOI-ESGAR core imaging protocol was identified.
EUROPEAN JOURNAL OF CANCER
(2022)
Review
Oncology
Nasim Vahidfar, Saeed Farzanefar, Hojjat Ahmadzadehfar, Eoin N. Molloy, Elisabeth Eppard
Summary: This literature review provides a brief overview of the role of nuclear medicine in the diagnosis of obstetric and gynecological cancers. Nuclear medicine has proven to be reliable in diagnostic imaging in nuclear medicine and cancer treatment. [F-18]FDG PET/CT imaging plays a crucial role in investigating gynecological cancer.
Article
Radiology, Nuclear Medicine & Medical Imaging
Chenggong Yan, Lingfeng Wang, Jie Lin, Jun Xu, Tianjing Zhang, Jin Qi, Xiangying Li, Wei Ni, Guangyao Wu, Jianbin Huang, Yikai Xu, Henry C. Woodruff, Philippe Lambin
Summary: This study developed an AI-based fully automated CT image analysis system for detection, diagnosis, and burden quantification of pulmonary TB, achieving human-level diagnostic performance through deep learning technology.
EUROPEAN RADIOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Xiaowei Xu, Qianjun Jia, Haiyun Yuan, Hailong Qiu, Yuhao Dong, Wen Xie, Zeyang Yao, Jiawei Zhang, Zhiqaing Nie, Xiaomeng Li, Yiyu Shi, James Y. Zou, Meiping Huang, Jian Zhuang
Summary: In this study, an artificial intelligence system was developed for diagnosing 17 types of congenital heart disease. Experimental results demonstrate that the system achieves comparable accuracy to junior cardiovascular radiologists and higher sensitivity. The system, combined with senior radiologists, also achieves similar results to the current clinical routine. Additionally, the system provides 3D visualization of hearts for interpretation and review, aiding surgeons in understanding heart structures and clinicians in predicting outcomes more accurately.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Automation & Control Systems
Siqi Cai, Yizhi Liao, Lixuan Lai, Haiyu Zhou, Longhan Xie
Summary: This article introduces a computer-aided diagnosis method based on convolutional neural networks for generating corrective solutions for patients with pectus excavatum. By training a CNN model to predict the corrected sternum contours for patients, the effectiveness of the approach was validated through experiments.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Chemistry, Multidisciplinary
Pierpaolo Alongi, Alessandro Stefano, Albert Comelli, Alessandro Spataro, Giuseppe Formica, Riccardo Laudicella, Helena Lanzafame, Francesco Panasiti, Costanza Longo, Federico Midiri, Viviana Benfante, Ludovico La Grutta, Irene Andrea Burger, Tommaso Vincenzo Bartolotta, Sergio Baldari, Roberto Lagalla, Massimo Midiri, Giorgio Russo
Summary: By analyzing the textural features of [F-18]FDG PET/CT images, radiomics models can be proposed to predict disease progression and survival outcome in metastatic colorectal cancer patients.
APPLIED SCIENCES-BASEL
(2022)
Article
Oncology
Jun Lv, Jianhui Li, Yanzhen Liu, Hong Zhang, Xiangfeng Luo, Min Ren, Yufan Gao, Yanhe Ma, Shuo Liang, Yapeng Yang, Zhenchun Song, Guangming Gao, Guozheng Gao, Yusheng Jiang, Ximing Li
Summary: The study evaluated the value of AI-assisted software in the diagnosis of lung nodules using a combination of low-dose and high-resolution computed tomography. Significant differences were observed in nodule volume and malignancy probability for subsolid nodules between the improved and identical visibility groups. The combined scanning scheme may be beneficial for screening high-risk populations under the operation and decision of AI.
FRONTIERS IN ONCOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Antoine Girard, Laurent Dercle, Helena Vila-Reyes, Lawrence H. Schwartz, Astrid Girma, Marc Bertaux, Camelia Radulescu, Thierry Lebret, Olivier Delcroix, Mathieu Rouanne
Summary: By using machine learning, we developed a combination of criteria that accurately identifies pelvic lymph node involvement in bladder cancer patients. The diagnostic performance of this combination is comparable to that of a consensus of experts on [F-18]FDG PET/CT scans.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Mourtaza Karimdjee, Gauthier Delaby, Damien Huglo, Clio Baillet, Alexandre Willaume, Simon Dujardin, Alban Bailliez
Summary: New PET data-processing tools using artificial intelligence (AI) provide automated lesion selection and segmentation, allowing for the routine acquisition of total metabolic tumor volume (TMTV) and total lesion glycolysis (TLG) at the clinical workstation. This study evaluated the implementation of AI in commercial software, demonstrating its reproducibility, time savings, and reliable performance. The results showed that AI-enabled software offers an automated, fast, and consistently performing tool for obtaining TMTV and TLG.
EUROPEAN RADIOLOGY
(2023)
Article
Biology
Anca Emanuela Musetescu, Florin Liviu Gherghina, Lucian-Mihai Florescu, Liliana Streba, Paulina Lucia Ciurea, Alesandra Florescu, Ioana Andreea Gheonea
Summary: The study used CAD technology to detect lung nodules in patients with rheumatoid arthritis, and found that CAD can play a role in reducing the interpretation time of CT examinations, but there are also certain false positive and false negative rates.
Article
Microbiology
Zhaotong Li, Fengliang Wu, Fengze Hong, Xiaoyan Gai, Wenli Cao, Zeru Zhang, Timin Yang, Jiu Wang, Song Gao, Chao Peng
Summary: The new deep learning method proposed effectively fuses four elaborate image features, showing optimal performance in accuracy, specificity, sensitivity, and area under curve when using VGG-11 and virtual data augmentation. There is an inverse relationship between model size and test accuracy.
FRONTIERS IN MICROBIOLOGY
(2022)
Review
Radiology, Nuclear Medicine & Medical Imaging
Wanting Li, Haiyan Liu, Feng Cheng, Yanhua Li, Sijin Li, Jiangwei Yan
Summary: PET-based radiomics and artificial intelligence play significant roles in oncology for disease diagnosis, predicting histological subtype, gene mutation status, tumor metastasis, etc. The development of AI in PET imaging offers promising prospects for future clinical studies and treatments.
EUROPEAN JOURNAL OF RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Beibei Jiang, Yaping Zhang, Lu Zhang, Geertruida H. de Bock, Rozemarijn Vliegenthart, Xueqian Xie
Summary: The study developed CNN models to classify SSNs on CT images and investigated image features associated with the CNN classification. The study found that smooth margins and ground-glass components were primary features in the benign and PL group, while part-solid and solid components, lobulated shapes, and air bronchograms were activated areas in the IA group.
EUROPEAN RADIOLOGY
(2021)