Isabella Castiglioni1, Leonardo Rundo2, Marina Codari3, Giovanni Di Leo4, Christian Salvatore5, Matteo Interlenghi6, Francesca Gallivanone7, Andrea Cozzi8, Natascha Claudia D'Amico9, Francesco Sardanelli10. 1. Department of Physics, Università degli Studi di Milano-Bicocca, Piazza della Scienza 3, 20126 Milano, Italy; Institute of Biomedical Imaging and Physiology, National Research Council, Via Fratelli Cervi 93, 20090 Segrate, Italy. Electronic address: isabella.castiglioni@unimib.it. 2. Department of Radiology, Box 218, Cambridge Biomedical Campus, Cambridge CB2 0QQ, United Kingdom; Cancer Research UK Cambridge Centre, University of Cambridge Li Ka Shing Centre, Robinson Way, Cambridge CB2 0RE, United Kingdom. Electronic address: lr495@cam.ac.uk. 3. Department of Radiology, Stanford University School of Medicine, Stanford University, 300 Pasteur Drive, Stanford, CA, USA. Electronic address: mcodari@stanford.edu. 4. Unit of Radiology, IRCCS Policlinico San Donato, Via Rodolfo Morandi 30, 20097 San Donato Milanese, Italy. Electronic address: gianni.dileo77@gmail.com. 5. Scuola Universitaria Superiore IUSS Pavia, Piazza della Vittoria 15, 27100 Pavia, Italy; DeepTrace Technologies S.r.l., Via Conservatorio 17, 20122 Milano, Italy. Electronic address: salvatore@deeptracetech.com. 6. DeepTrace Technologies S.r.l., Via Conservatorio 17, 20122 Milano, Italy. Electronic address: interlenghi@deeptracetech.com. 7. Institute of Biomedical Imaging and Physiology, National Research Council, Via Fratelli Cervi 93, 20090 Segrate, Italy. Electronic address: francesca.gallivanone@ibfm.cnr.it. 8. Department of Biomedical Sciences for Health, Università degli Studi di Milano, Via Luigi Mangiagalli 31, 20133 Milano, Italy. Electronic address: andrea.cozzi1@unimi.it. 9. Department of Diagnostic Imaging and Stereotactic Radiosurgery, Centro Diagnostico Italiano S.p.A., Via Saint Bon 20, 20147 Milano, Italy; Unit of Computer Systems and Bioinformatics, Department of Engineering, Università Campus Bio-Medico di Roma, Via Alvaro del Portillo 21, 00128 Roma, Italy. Electronic address: nataschaclaudia.damico@cdi.it. 10. Unit of Radiology, IRCCS Policlinico San Donato, Via Rodolfo Morandi 30, 20097 San Donato Milanese, Italy; Department of Biomedical Sciences for Health, Università degli Studi di Milano, Via Luigi Mangiagalli 31, 20133 Milano, Italy. Electronic address: francesco.sardanelli@unimi.it.
Abstract
PURPOSE: Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context. METHODS: A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections. RESULTS: We first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way. CONCLUSIONS: Biomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.
PURPOSE: Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context. METHODS: A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections. RESULTS: We first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way. CONCLUSIONS:Biomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.
Authors: Chengyue Wu; Guillermo Lorenzo; David A Hormuth; Ernesto A B F Lima; Kalina P Slavkova; Julie C DiCarlo; John Virostko; Caleb M Phillips; Debra Patt; Caroline Chung; Thomas E Yankeelov Journal: Biophys Rev (Melville) Date: 2022-05-17
Authors: Jun Jie Ong; Brais Muñiz Castro; Simon Gaisford; Pedro Cabalar; Abdul W Basit; Gilberto Pérez; Alvaro Goyanes Journal: Int J Pharm X Date: 2022-06-09