Empowering PET: harnessing deep learning for improved clinical insight
Abstract This review aims to take a journey into the transformative impact of artificial intelligence (AI) on positron emission tomography (PET) imaging. To this scope, a broad overview of AI applications in the field of nuclear medicine and a thorough exploration of deep learning (DL) implementatio...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-02-01
|
| Series: | European Radiology Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41747-023-00413-1 |
| _version_ | 1797275932499640320 |
|---|---|
| author | Alessia Artesani Alessandro Bruno Fabrizia Gelardi Arturo Chiti |
| author_facet | Alessia Artesani Alessandro Bruno Fabrizia Gelardi Arturo Chiti |
| author_sort | Alessia Artesani |
| collection | DOAJ |
| description | Abstract This review aims to take a journey into the transformative impact of artificial intelligence (AI) on positron emission tomography (PET) imaging. To this scope, a broad overview of AI applications in the field of nuclear medicine and a thorough exploration of deep learning (DL) implementations in cancer diagnosis and therapy through PET imaging will be presented. We firstly describe the behind-the-scenes use of AI for image generation, including acquisition (event positioning, noise reduction though time-of-flight estimation and scatter correction), reconstruction (data-driven and model-driven approaches), restoration (supervised and unsupervised methods), and motion correction. Thereafter, we outline the integration of AI into clinical practice through the applications to segmentation, detection and classification, quantification, treatment planning, dosimetry, and radiomics/radiogenomics combined to tumour biological characteristics. Thus, this review seeks to showcase the overarching transformation of the field, ultimately leading to tangible improvements in patient treatment and response assessment. Finally, limitations and ethical considerations of the AI application to PET imaging and future directions of multimodal data mining in this discipline will be briefly discussed, including pressing challenges to the adoption of AI in molecular imaging such as the access to and interoperability of huge amount of data as well as the “black-box” problem, contributing to the ongoing dialogue on the transformative potential of AI in nuclear medicine. Relevance statement AI is rapidly revolutionising the world of medicine, including the fields of radiology and nuclear medicine. In the near future, AI will be used to support healthcare professionals. These advances will lead to improvements in diagnosis, in the assessment of response to treatment, in clinical decision making and in patient management. Key points • Applying AI has the potential to enhance the entire PET imaging pipeline. • AI may support several clinical tasks in both PET diagnosis and prognosis. • Interpreting the relationships between imaging and multiomics data will heavily rely on AI. Graphical Abstract |
| first_indexed | 2024-03-07T15:21:07Z |
| format | Article |
| id | doaj.art-9abcae3996ca416fa4daaa397f099604 |
| institution | Directory Open Access Journal |
| issn | 2509-9280 |
| language | English |
| last_indexed | 2024-03-07T15:21:07Z |
| publishDate | 2024-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Radiology Experimental |
| spelling | doaj.art-9abcae3996ca416fa4daaa397f0996042024-03-05T17:38:14ZengSpringerOpenEuropean Radiology Experimental2509-92802024-02-018111310.1186/s41747-023-00413-1Empowering PET: harnessing deep learning for improved clinical insightAlessia Artesani0Alessandro Bruno1Fabrizia Gelardi2Arturo Chiti3Department of Biomedical Sciences, Humanitas UniversityDepartment of Business, Law, Economics and Consumer Behaviour “Carlo A. Ricciardi”, IULM Libera Università Di Lingue E ComunicazioneDepartment of Biomedical Sciences, Humanitas UniversityVita-Salute San Raffaele UniversityAbstract This review aims to take a journey into the transformative impact of artificial intelligence (AI) on positron emission tomography (PET) imaging. To this scope, a broad overview of AI applications in the field of nuclear medicine and a thorough exploration of deep learning (DL) implementations in cancer diagnosis and therapy through PET imaging will be presented. We firstly describe the behind-the-scenes use of AI for image generation, including acquisition (event positioning, noise reduction though time-of-flight estimation and scatter correction), reconstruction (data-driven and model-driven approaches), restoration (supervised and unsupervised methods), and motion correction. Thereafter, we outline the integration of AI into clinical practice through the applications to segmentation, detection and classification, quantification, treatment planning, dosimetry, and radiomics/radiogenomics combined to tumour biological characteristics. Thus, this review seeks to showcase the overarching transformation of the field, ultimately leading to tangible improvements in patient treatment and response assessment. Finally, limitations and ethical considerations of the AI application to PET imaging and future directions of multimodal data mining in this discipline will be briefly discussed, including pressing challenges to the adoption of AI in molecular imaging such as the access to and interoperability of huge amount of data as well as the “black-box” problem, contributing to the ongoing dialogue on the transformative potential of AI in nuclear medicine. Relevance statement AI is rapidly revolutionising the world of medicine, including the fields of radiology and nuclear medicine. In the near future, AI will be used to support healthcare professionals. These advances will lead to improvements in diagnosis, in the assessment of response to treatment, in clinical decision making and in patient management. Key points • Applying AI has the potential to enhance the entire PET imaging pipeline. • AI may support several clinical tasks in both PET diagnosis and prognosis. • Interpreting the relationships between imaging and multiomics data will heavily rely on AI. Graphical Abstracthttps://doi.org/10.1186/s41747-023-00413-1Artificial intelligenceDeep learningNuclear medicinePositron emission tomography |
| spellingShingle | Alessia Artesani Alessandro Bruno Fabrizia Gelardi Arturo Chiti Empowering PET: harnessing deep learning for improved clinical insight European Radiology Experimental Artificial intelligence Deep learning Nuclear medicine Positron emission tomography |
| title | Empowering PET: harnessing deep learning for improved clinical insight |
| title_full | Empowering PET: harnessing deep learning for improved clinical insight |
| title_fullStr | Empowering PET: harnessing deep learning for improved clinical insight |
| title_full_unstemmed | Empowering PET: harnessing deep learning for improved clinical insight |
| title_short | Empowering PET: harnessing deep learning for improved clinical insight |
| title_sort | empowering pet harnessing deep learning for improved clinical insight |
| topic | Artificial intelligence Deep learning Nuclear medicine Positron emission tomography |
| url | https://doi.org/10.1186/s41747-023-00413-1 |
| work_keys_str_mv | AT alessiaartesani empoweringpetharnessingdeeplearningforimprovedclinicalinsight AT alessandrobruno empoweringpetharnessingdeeplearningforimprovedclinicalinsight AT fabriziagelardi empoweringpetharnessingdeeplearningforimprovedclinicalinsight AT arturochiti empoweringpetharnessingdeeplearningforimprovedclinicalinsight |