A review of machine learning applications for the proton MR spectroscopy workflow

A review of machine learning applications for the proton MR spectroscopy workflow. van de Sande, D. M. J., Merkofer, J. P., Amirrajab, S., Veta, M., van Sloun, R. J. G., Versluis, M. J., Jansen, J. F. A., van den Brink, J. S., & Breeuwer, M. Magn Reson Med, 2023. van de Sande, Dennis M J Merkofer, Julian P Amirrajab, Sina Veta, Mitko van Sloun, Ruud J G Versluis, Maarten J Jansen, Jacobus F A van den Brink, Johan S Breeuwer, Marcel eng 20209/Spectralligence project (EUREKA AI Call 2020), project number/ Review Magn Reson Med. 2023 Jul 4. doi: 10.1002/mrm.29793.

Paper doi abstract bibtex

This literature review presents a comprehensive overview of machine learning (ML) applications in proton MR spectroscopy (MRS). As the use of ML techniques in MRS continues to grow, this review aims to provide the MRS community with a structured overview of the state-of-the-art methods. Specifically, we examine and summarize studies published between 2017 and 2023 from major journals in the MR field. We categorize these studies based on a typical MRS workflow, including data acquisition, processing, analysis, and artificial data generation. Our review reveals that ML in MRS is still in its early stages, with a primary focus on processing and analysis techniques, and less attention given to data acquisition. We also found that many studies use similar model architectures, with little comparison to alternative architectures. Additionally, the generation of artificial data is a crucial topic, with no consistent method for its generation. Furthermore, many studies demonstrate that artificial data suffers from generalization issues when tested on in vivo data. We also conclude that risks related to ML models should be addressed, particularly for clinical applications. Therefore, output uncertainty measures and model biases are critical to investigate. Nonetheless, the rapid development of ML in MRS and the promising results from the reviewed studies justify further research in this field.

@article{RN333,
   author = {van de Sande, D. M. J. and Merkofer, J. P. and Amirrajab, S. and Veta, M. and van Sloun, R. J. G. and Versluis, M. J. and Jansen, J. F. A. and van den Brink, J. S. and Breeuwer, M.},
   title = {A review of machine learning applications for the proton MR spectroscopy workflow},
   journal = {Magn Reson Med},
   note = {van de Sande, Dennis M J
Merkofer, Julian P
Amirrajab, Sina
Veta, Mitko
van Sloun, Ruud J G
Versluis, Maarten J
Jansen, Jacobus F A
van den Brink, Johan S
Breeuwer, Marcel
eng
20209/Spectralligence project (EUREKA AI Call 2020), project number/
Review
Magn Reson Med. 2023 Jul 4. doi: 10.1002/mrm.29793.},
   abstract = {This literature review presents a comprehensive overview of machine learning (ML) applications in proton MR spectroscopy (MRS). As the use of ML techniques in MRS continues to grow, this review aims to provide the MRS community with a structured overview of the state-of-the-art methods. Specifically, we examine and summarize studies published between 2017 and 2023 from major journals in the MR field. We categorize these studies based on a typical MRS workflow, including data acquisition, processing, analysis, and artificial data generation. Our review reveals that ML in MRS is still in its early stages, with a primary focus on processing and analysis techniques, and less attention given to data acquisition. We also found that many studies use similar model architectures, with little comparison to alternative architectures. Additionally, the generation of artificial data is a crucial topic, with no consistent method for its generation. Furthermore, many studies demonstrate that artificial data suffers from generalization issues when tested on in vivo data. We also conclude that risks related to ML models should be addressed, particularly for clinical applications. Therefore, output uncertainty measures and model biases are critical to investigate. Nonetheless, the rapid development of ML in MRS and the promising results from the reviewed studies justify further research in this field.},
   keywords = {MR spectroscopic imaging
MR spectroscopy
deep learning
machine learning},
   ISSN = {1522-2594 (Electronic)
0740-3194 (Linking)},
   DOI = {10.1002/mrm.29793},
   url = {https://www.ncbi.nlm.nih.gov/pubmed/37402235},
   year = {2023},
   type = {Journal Article}
}

Downloads: 0

{"_id":"MwxFMBLLZxaFQYor3","bibbaseid":"vandesande-merkofer-amirrajab-veta-vansloun-versluis-jansen-vandenbrink-etal-areviewofmachinelearningapplicationsfortheprotonmrspectroscopyworkflow-2023","author_short":["van de Sande, D. M. J.","Merkofer, J. P.","Amirrajab, S.","Veta, M.","van Sloun, R. J. G.","Versluis, M. J.","Jansen, J. F. A.","van den Brink, J. S.","Breeuwer, M."],"bibdata":{"bibtype":"article","type":"Journal Article","author":[{"propositions":["van","de"],"lastnames":["Sande"],"firstnames":["D.","M.","J."],"suffixes":[]},{"propositions":[],"lastnames":["Merkofer"],"firstnames":["J.","P."],"suffixes":[]},{"propositions":[],"lastnames":["Amirrajab"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Veta"],"firstnames":["M."],"suffixes":[]},{"propositions":["van"],"lastnames":["Sloun"],"firstnames":["R.","J.","G."],"suffixes":[]},{"propositions":[],"lastnames":["Versluis"],"firstnames":["M.","J."],"suffixes":[]},{"propositions":[],"lastnames":["Jansen"],"firstnames":["J.","F.","A."],"suffixes":[]},{"propositions":["van","den"],"lastnames":["Brink"],"firstnames":["J.","S."],"suffixes":[]},{"propositions":[],"lastnames":["Breeuwer"],"firstnames":["M."],"suffixes":[]}],"title":"A review of machine learning applications for the proton MR spectroscopy workflow","journal":"Magn Reson Med","note":"van de Sande, Dennis M J Merkofer, Julian P Amirrajab, Sina Veta, Mitko van Sloun, Ruud J G Versluis, Maarten J Jansen, Jacobus F A van den Brink, Johan S Breeuwer, Marcel eng 20209/Spectralligence project (EUREKA AI Call 2020), project number/ Review Magn Reson Med. 2023 Jul 4. doi: 10.1002/mrm.29793.","abstract":"This literature review presents a comprehensive overview of machine learning (ML) applications in proton MR spectroscopy (MRS). As the use of ML techniques in MRS continues to grow, this review aims to provide the MRS community with a structured overview of the state-of-the-art methods. Specifically, we examine and summarize studies published between 2017 and 2023 from major journals in the MR field. We categorize these studies based on a typical MRS workflow, including data acquisition, processing, analysis, and artificial data generation. Our review reveals that ML in MRS is still in its early stages, with a primary focus on processing and analysis techniques, and less attention given to data acquisition. We also found that many studies use similar model architectures, with little comparison to alternative architectures. Additionally, the generation of artificial data is a crucial topic, with no consistent method for its generation. Furthermore, many studies demonstrate that artificial data suffers from generalization issues when tested on in vivo data. We also conclude that risks related to ML models should be addressed, particularly for clinical applications. Therefore, output uncertainty measures and model biases are critical to investigate. Nonetheless, the rapid development of ML in MRS and the promising results from the reviewed studies justify further research in this field.","keywords":"MR spectroscopic imaging MR spectroscopy deep learning machine learning","issn":"1522-2594 (Electronic) 0740-3194 (Linking)","doi":"10.1002/mrm.29793","url":"https://www.ncbi.nlm.nih.gov/pubmed/37402235","year":"2023","bibtex":"@article{RN333,\n author = {van de Sande, D. M. J. and Merkofer, J. P. and Amirrajab, S. and Veta, M. and van Sloun, R. J. G. and Versluis, M. J. and Jansen, J. F. A. and van den Brink, J. S. and Breeuwer, M.},\n title = {A review of machine learning applications for the proton MR spectroscopy workflow},\n journal = {Magn Reson Med},\n note = {van de Sande, Dennis M J\nMerkofer, Julian P\nAmirrajab, Sina\nVeta, Mitko\nvan Sloun, Ruud J G\nVersluis, Maarten J\nJansen, Jacobus F A\nvan den Brink, Johan S\nBreeuwer, Marcel\neng\n20209/Spectralligence project (EUREKA AI Call 2020), project number/\nReview\nMagn Reson Med. 2023 Jul 4. doi: 10.1002/mrm.29793.},\n abstract = {This literature review presents a comprehensive overview of machine learning (ML) applications in proton MR spectroscopy (MRS). As the use of ML techniques in MRS continues to grow, this review aims to provide the MRS community with a structured overview of the state-of-the-art methods. Specifically, we examine and summarize studies published between 2017 and 2023 from major journals in the MR field. We categorize these studies based on a typical MRS workflow, including data acquisition, processing, analysis, and artificial data generation. Our review reveals that ML in MRS is still in its early stages, with a primary focus on processing and analysis techniques, and less attention given to data acquisition. We also found that many studies use similar model architectures, with little comparison to alternative architectures. Additionally, the generation of artificial data is a crucial topic, with no consistent method for its generation. Furthermore, many studies demonstrate that artificial data suffers from generalization issues when tested on in vivo data. We also conclude that risks related to ML models should be addressed, particularly for clinical applications. Therefore, output uncertainty measures and model biases are critical to investigate. Nonetheless, the rapid development of ML in MRS and the promising results from the reviewed studies justify further research in this field.},\n keywords = {MR spectroscopic imaging\nMR spectroscopy\ndeep learning\nmachine learning},\n ISSN = {1522-2594 (Electronic)\n0740-3194 (Linking)},\n DOI = {10.1002/mrm.29793},\n url = {https://www.ncbi.nlm.nih.gov/pubmed/37402235},\n year = {2023},\n type = {Journal Article}\n}\n\n","author_short":["van de Sande, D. M. J.","Merkofer, J. P.","Amirrajab, S.","Veta, M.","van Sloun, R. J. G.","Versluis, M. J.","Jansen, J. F. A.","van den Brink, J. S.","Breeuwer, M."],"key":"RN333","id":"RN333","bibbaseid":"vandesande-merkofer-amirrajab-veta-vansloun-versluis-jansen-vandenbrink-etal-areviewofmachinelearningapplicationsfortheprotonmrspectroscopyworkflow-2023","role":"author","urls":{"Paper":"https://www.ncbi.nlm.nih.gov/pubmed/37402235"},"keyword":["MR spectroscopic imaging MR spectroscopy deep learning machine learning"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://raw.githubusercontent.com/jansenjfa1/bibbase.github.io/master/jansenjfa.bib","dataSources":["TCkfRWJAZvbLAZi29"],"keywords":["mr spectroscopic imaging mr spectroscopy deep learning machine learning"],"search_terms":["review","machine","learning","applications","proton","spectroscopy","workflow","van de sande","merkofer","amirrajab","veta","van sloun","versluis","jansen","van den brink","breeuwer"],"title":"A review of machine learning applications for the proton MR spectroscopy workflow","year":2023}