Unit of Endocrinology, Department of Medical Specialties, Azienda Ospedaliero-Universitaria, Modena, Italy
Search for other papers by Giulia Brigante in
Google Scholar
PubMed
Search for other papers by Clara Lazzaretti in
Google Scholar
PubMed
Search for other papers by Elia Paradiso in
Google Scholar
PubMed
Search for other papers by Federico Nuzzo in
Google Scholar
PubMed
Search for other papers by Martina Sitti in
Google Scholar
PubMed
Search for other papers by Frank Tüttelmann in
Google Scholar
PubMed
Search for other papers by Gabriele Moretti in
Google Scholar
PubMed
Search for other papers by Roberto Silvestri in
Google Scholar
PubMed
Search for other papers by Federica Gemignani in
Google Scholar
PubMed
Division of Pediatric Neurooncology, German Cancer Research Center (DKFZ), German Cancer Consortium (DKTK), Heidelberg, Germany
Search for other papers by Asta Försti in
Google Scholar
PubMed
Division of Cancer Epidemiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
Search for other papers by Kari Hemminki in
Google Scholar
PubMed
Search for other papers by Rossella Elisei in
Google Scholar
PubMed
Search for other papers by Cristina Romei in
Google Scholar
PubMed
Search for other papers by Eric Adriano Zizzi in
Google Scholar
PubMed
Search for other papers by Marco Agostino Deriu in
Google Scholar
PubMed
Unit of Endocrinology, Department of Medical Specialties, Azienda Ospedaliero-Universitaria, Modena, Italy
Center for Genomic Research, University of Modena and Reggio Emilia, Modena, Italy
Search for other papers by Manuela Simoni in
Google Scholar
PubMed
Search for other papers by Stefano Landi in
Google Scholar
PubMed
Center for Genomic Research, University of Modena and Reggio Emilia, Modena, Italy
Search for other papers by Livio Casarini in
Google Scholar
PubMed
, gene–gene interactions are likely too complex to be explained by simple additive or weighted models and alternative methods are under exploration. Machine learning (ML) is increasingly used for predicting individuals’ inherited genomic susceptibility
Search for other papers by Roberto Negro in
Google Scholar
PubMed
Search for other papers by Matteo Rucco in
Google Scholar
PubMed
Search for other papers by Annalisa Creanza in
Google Scholar
PubMed
Search for other papers by Alberto Mormile in
Google Scholar
PubMed
Search for other papers by Paolo Piero Limone in
Google Scholar
PubMed
Search for other papers by Roberto Garberoglio in
Google Scholar
PubMed
Search for other papers by Stefano Spiezia in
Google Scholar
PubMed
Search for other papers by Salvatore Monti in
Google Scholar
PubMed
Search for other papers by Christian Cugini in
Google Scholar
PubMed
Search for other papers by Ghassan El Dalati in
Google Scholar
PubMed
Search for other papers by Maurilio Deandrea in
Google Scholar
PubMed
additional treatment session. For this purpose, we trained a machine learning model and tested its ability to predict the 12-month VRR of nodules treated with RF. Methods The machine learning model was trained with a dataset consisting of 402 Italian
Amsterdam Gastroenterology, Endocrinology and Metabolism, Amsterdam, The Netherlands
Department of Laboratory Medicine, Endocrine Laboratory, Amsterdam UMC location University of Amsterdam, Meibergdreef, Amsterdam, The Netherlands
Search for other papers by Heleen I Jansen in
Google Scholar
PubMed
Department of Computer Science, Vrije Universiteit, Boelelaan, Amsterdam, The Netherlands
Search for other papers by Marije van Haeringen in
Google Scholar
PubMed
Search for other papers by Marelle J Bouva in
Google Scholar
PubMed
Amsterdam Public Health, Amsterdam, The Netherlands
Search for other papers by Wendy P J den Elzen in
Google Scholar
PubMed
Department of Endocrinology and Metabolism, Amsterdam UMC location University of Amsterdam, Meibergdreef, Amsterdam, The Netherlands
Search for other papers by Eveline Bruinstroop in
Google Scholar
PubMed
Search for other papers by Catharina P B van der Ploeg in
Google Scholar
PubMed
Department of Paediatric Endocrinology, Emma Children’s Hospital, Amsterdam UMC, University of Amsterdam, Meibergdreef, Amsterdam, The Netherlands
Search for other papers by A S Paul van Trotsenburg in
Google Scholar
PubMed
Department of Paediatric Endocrinology, Emma Children’s Hospital, Amsterdam UMC, University of Amsterdam, Meibergdreef, Amsterdam, The Netherlands
Search for other papers by Nitash Zwaveling-Soonawala in
Google Scholar
PubMed
Amsterdam Gastroenterology, Endocrinology and Metabolism, Amsterdam, The Netherlands
Department of Laboratory Medicine, Endocrine Laboratory, Amsterdam UMC location University of Amsterdam, Meibergdreef, Amsterdam, The Netherlands
Amsterdam Reproduction & Development Research Institute, Amsterdam, The Netherlands
Search for other papers by Annemieke C Heijboer in
Google Scholar
PubMed
Department of Pediatrics, Division of Metabolic Disorders, Emma Children’s Hospital, Amsterdam UMC, University of Amsterdam, Meibergdreef, Amsterdam, The Netherlands
Search for other papers by Annet M Bosch in
Google Scholar
PubMed
Department of Laboratory Medicine, Amsterdam UMC, Vrije Universiteit, Boelelaan, Amsterdam, The Netherlands
Department of Laboratory Medicine, Amsterdam UMC, University of Amsterdam, Meibergdreef, Amsterdam, The Netherlands
Search for other papers by Robert de Jonge in
Google Scholar
PubMed
Search for other papers by Mark Hoogendoorn in
Google Scholar
PubMed
Department of Laboratory Medicine, Endocrine Laboratory, Amsterdam UMC location University of Amsterdam, Meibergdreef, Amsterdam, The Netherlands
Amsterdam Reproduction & Development Research Institute, Amsterdam, The Netherlands
Search for other papers by Anita Boelen in
Google Scholar
PubMed
4 and TBG and thereby refining the cutoff value for a (partial) TBG deficiency ( 3 ) and by using machine learning ( 8 ). The latter study used a dataset containing almost all children with a referral in the historical CH screening from 2007 to 2017
Xi’an Hospital of Traditional Chinese Medicine, Xi’an, China
Search for other papers by Lei Xu in
Google Scholar
PubMed
Search for other papers by Junling Gao in
Google Scholar
PubMed
Search for other papers by Quan Wang in
Google Scholar
PubMed
Search for other papers by Jichao Yin in
Google Scholar
PubMed
Search for other papers by Pengfei Yu in
Google Scholar
PubMed
Search for other papers by Bin Bai in
Google Scholar
PubMed
Search for other papers by Ruixia Pei in
Google Scholar
PubMed
Search for other papers by Dingzhang Chen in
Google Scholar
PubMed
Search for other papers by Guochun Yang in
Google Scholar
PubMed
Search for other papers by Shiqi Wang in
Google Scholar
PubMed
Search for other papers by Mingxi Wan in
Google Scholar
PubMed
diagnostic accuracy and efficiency, machine learning-based computer-aided diagnosis (CAD) systems are being introduced in the diagnosis process. Currently, two types of machine learning method are adopted: (1) the classic machine learning method, which is
Department of Radiology, Jichi Medical University, School of Medicine, Shimotsuke, Tochigi, Japan
Search for other papers by Tomohiro Kikuchi in
Google Scholar
PubMed
Search for other papers by Shouhei Hanaoka in
Google Scholar
PubMed
Search for other papers by Takahiro Nakao in
Google Scholar
PubMed
Center for Frontier Medical Engineering, Chiba University, Yayoicho, Inage–ku, Chiba, Japan
Search for other papers by Yukihiro Nomura in
Google Scholar
PubMed
Search for other papers by Takeharu Yoshikawa in
Google Scholar
PubMed
Search for other papers by Ashraful Alam in
Google Scholar
PubMed
Search for other papers by Harushi Mori in
Google Scholar
PubMed
Search for other papers by Naoto Hayashi in
Google Scholar
PubMed
Objective
This study aimed to determine a standardized cut-off value for abnormal 18F-fluorodeoxyglucose (FDG) accumulation in the thyroid gland.
Methods
Herein, 7013 FDG–PET/CT scans were included. An automatic thyroid segmentation method using two U-nets (2D- and 3D-U-net) was constructed; mean FDG standardized uptake value (SUV), CT value, and volume of the thyroid gland were obtained from each participant. The values were categorized by thyroid function into three groups based on serum thyroid-stimulating hormone levels. Thyroid function and mean SUV with increments of 1 were analyzed, and risk for thyroid dysfunction was calculated. Thyroid dysfunction detection ability was examined using a machine learning method (LightGBM, Microsoft) with age, sex, height, weight, CT value, volume, and mean SUV as explanatory variables.
Results
Mean SUV was significantly higher in females with hypothyroidism. Almost 98.9% of participants in the normal group had mean SUV < 2 and 93.8% participants with mean SUV < 2 had normal thyroid function. The hypothyroidism group had more cases with mean SUV ≥ 2. The relative risk of having abnormal thyroid function was 4.6 with mean SUV ≥ 2. The sensitivity and specificity for detecting thyroid dysfunction using LightGBM (Microsoft) were 14.5 and 99%, respectively.
Conclusions
Mean SUV ≥ 2 was strongly associated with abnormal thyroid function in this large cohort, indicating that mean SUV with FDG–PET/CT can be used as a criterion for thyroid evaluation. Preliminarily, this study shows the potential utility of detecting thyroid dysfunction based on imaging findings.
Search for other papers by Kristine Z Swan in
Google Scholar
PubMed
Search for other papers by Johnson Thomas in
Google Scholar
PubMed
Search for other papers by Viveque E Nielsen in
Google Scholar
PubMed
Search for other papers by Marie Louise Jespersen in
Google Scholar
PubMed
Search for other papers by Steen J Bonnema in
Google Scholar
PubMed
Fairness, Accountability and Transparency , pp. 77 – 91 . Eds Sorelle AF Christo W . Proceedings of Machine Learning Research: PMLR , 2018 . 21 Thomas J Ledger GA Mamillapalli CK . Use of artificial intelligence and machine learning for
Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
Search for other papers by Haiyang Zhang in
Google Scholar
PubMed
Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
Search for other papers by Shuo Wu in
Google Scholar
PubMed
Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
Search for other papers by Shuyu Hu in
Google Scholar
PubMed
Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
Search for other papers by Xianqun Fan in
Google Scholar
PubMed
Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
Search for other papers by Xuefei Song in
Google Scholar
PubMed
Search for other papers by Tienan Feng in
Google Scholar
PubMed
Shanghai Key Laboratory of Orbital Diseases and Ocular Oncology, Shanghai, China
Search for other papers by Huifang Zhou in
Google Scholar
PubMed
heterogeneity profiling through high-dimensional quantitative data extracted from radiological images ( 27 , 36 ). Furthermore, the application of advanced modeling techniques like machine learning and artificial intelligence ( 37 ) empowers the construction of
Search for other papers by Roberto Negro in
Google Scholar
PubMed
Biomedical Sciences, Università della Svizzera Italiana (USI), Lugano, Switzerland
Search for other papers by Pierpaolo Trimboli in
Google Scholar
PubMed
percutaneous laser ablation: a pilot study . Med Ultrason . 2017 Apr ; 19 ( 2 ): 172 – 8 . 10.11152/mu-1039 28440351 1844-4172 20 Negro R , Rucco M , Creanza A , Mormile A , Limone PP , Garberoglio R , et al. Machine learning
Department of Medicine, Autonomous University of Barcelona, Barcelona, Spain
Search for other papers by J L Reverter in
Google Scholar
PubMed
Department of Medicine, Autonomous University of Barcelona, Barcelona, Spain
Search for other papers by L Ferrer-Estopiñan in
Google Scholar
PubMed
Department of Medicine, Autonomous University of Barcelona, Barcelona, Spain
Search for other papers by F Vázquez in
Google Scholar
PubMed
Department of Medicine, Autonomous University of Barcelona, Barcelona, Spain
Search for other papers by S Ballesta in
Google Scholar
PubMed
Department of Medicine, Autonomous University of Barcelona, Barcelona, Spain
Search for other papers by S Batule in
Google Scholar
PubMed
Department of Medicine, Autonomous University of Barcelona, Barcelona, Spain
Search for other papers by A Perez-Montes de Oca in
Google Scholar
PubMed
Department of Medicine, Autonomous University of Barcelona, Barcelona, Spain
Search for other papers by C Puig-Jové in
Google Scholar
PubMed
Department of Medicine, Autonomous University of Barcelona, Barcelona, Spain
Search for other papers by M Puig-Domingo in
Google Scholar
PubMed
inevitable and the diagnostic performance of US is highly related with the experience of the clinician who performs the image acquisition ( 6 ). To improve the diagnostic accuracy and efficiency, machine learning-based computer-aided diagnosis (CAD) systems
Search for other papers by Nianting Ju in
Google Scholar
PubMed
Search for other papers by Liying Hou in
Google Scholar
PubMed
Search for other papers by Hongjun Song in
Google Scholar
PubMed
Search for other papers by Zhongling Qiu in
Google Scholar
PubMed
Search for other papers by Yang Wang in
Google Scholar
PubMed
Search for other papers by Zhenkui Sun in
Google Scholar
PubMed
Search for other papers by Quanyong Luo in
Google Scholar
PubMed
Search for other papers by Chentian Shen in
Google Scholar
PubMed
M & McGrath M . Clinical predictors of I-131 therapy failure in differentiated thyroid cancer by machine learning: a single-center experience . World Journal of Nuclear Medicine 2021 20 253 – 259 . ( https://doi.org/10.4103/wjnm.WJNM_104