Maria Elena Laino1, Luca Viganò2, Angela Ammirabile3, Ludovica Lofino4, Elena Generali5, Marco Francone6, Ana Lleo7, Luca Saba8, Victor Savevski9. 1. Artificial Intelligence Center, IRCCS Humanitas Research Hospital, via Manzoni 56, Rozzano, 20089 Milan, Italy. Electronic address: mariaelena.laino@humanitas.it. 2. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20072 Milan, Italy; Humanitas Clinical and Research Center-IRCCS, Via Manzoni 56, 20089 Rozzano, Italy. Electronic address: luca.vigano@hunimed.eu. 3. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20072 Milan, Italy; Humanitas Clinical and Research Center-IRCCS, Via Manzoni 56, 20089 Rozzano, Italy. Electronic address: angela.ammirabile@humanitas.it. 4. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20072 Milan, Italy; Humanitas Clinical and Research Center-IRCCS, Via Manzoni 56, 20089 Rozzano, Italy. Electronic address: ludovica.lofino@humanitas.it. 5. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20072 Milan, Italy; Humanitas Clinical and Research Center-IRCCS, Via Manzoni 56, 20089 Rozzano, Italy. Electronic address: elena.generali@humanitasresearch.it. 6. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20072 Milan, Italy; Humanitas Clinical and Research Center-IRCCS, Via Manzoni 56, 20089 Rozzano, Italy. Electronic address: marco.francone@hunimed.eu. 7. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20072 Milan, Italy; Humanitas Clinical and Research Center-IRCCS, Via Manzoni 56, 20089 Rozzano, Italy. Electronic address: ana.lleo@humanitas.it. 8. Department of Radiology, Policlinico Universitario, Via Ospedale, 54, 09124 Cagliari, Italy. Electronic address: lucasabamd@gmail.com. 9. Artificial Intelligence Center, IRCCS Humanitas Research Hospital, via Manzoni 56, Rozzano, 20089 Milan, Italy. Electronic address: victor.savevski@humanitas.it.
Abstract
PURPOSE: The objective of this systematic review was to critically assess the available literature on deep learning (DL) and radiomics applied to the Liver Imaging Reporting and Data System (LI-RADS) in terms of 1) automatic LI-RADS classification of liver nodules; 2) the contribution of DL and radiomics to human evaluation in the classification of liver nodules following LI-RADS protocol. MATERIALS AND METHODS: A literature search was conducted to identify original research studies published up to April 2021. The inclusion criteria were: English language, focus on computed tomography (CT) and/or magnetic resonance (MR) with specified number of patients and lesions, adoption of LI-RADS classification for the detected hepatic lesions, and application of AI in the classification of liver nodules. Review articles, conference papers, editorials and commentaries, animal studies or studies with absence of AI and/or LI-RADS were excluded. After screening 221 articles, 11 studies were included in this review. RESULTS: All the included studies proved that DL and radiomics have high performances in liver nodules classification, sometimes similar or better than human evaluation. The best performances of DL was an AUC of 0.95 on MR and the best performance of radiomics was AUC of 0.98 either on CT and MR, while the lower ones were respectively AUC of 0.63 either on CT and MR for DL and AUC of 0.70 on CT for radiomics. CONCLUSION: DL and radiomics could be a useful tool in assisting radiologists in the diagnosis and classification of liver nodules according to LI-RADS.
PURPOSE: The objective of this systematic review was to critically assess the available literature on deep learning (DL) and radiomics applied to the Liver Imaging Reporting and Data System (LI-RADS) in terms of 1) automatic LI-RADS classification of liver nodules; 2) the contribution of DL and radiomics to human evaluation in the classification of liver nodules following LI-RADS protocol. MATERIALS AND METHODS: A literature search was conducted to identify original research studies published up to April 2021. The inclusion criteria were: English language, focus on computed tomography (CT) and/or magnetic resonance (MR) with specified number of patients and lesions, adoption of LI-RADS classification for the detected hepatic lesions, and application of AI in the classification of liver nodules. Review articles, conference papers, editorials and commentaries, animal studies or studies with absence of AI and/or LI-RADS were excluded. After screening 221 articles, 11 studies were included in this review. RESULTS: All the included studies proved that DL and radiomics have high performances in liver nodules classification, sometimes similar or better than human evaluation. The best performances of DL was an AUC of 0.95 on MR and the best performance of radiomics was AUC of 0.98 either on CT and MR, while the lower ones were respectively AUC of 0.63 either on CT and MR for DL and AUC of 0.70 on CT for radiomics. CONCLUSION: DL and radiomics could be a useful tool in assisting radiologists in the diagnosis and classification of liver nodules according to LI-RADS.
Authors: Róbert Stollmayer; Bettina Katalin Budai; Aladár Rónaszéki; Zita Zsombor; Ildikó Kalina; Erika Hartmann; Gábor Tóth; Péter Szoldán; Viktor Bérczi; Pál Maurovich-Horvat; Pál Novák Kaposi Journal: Cells Date: 2022-05-05 Impact factor: 6.600