Enhancing paranasal sinus disease detection with AutoML: efficient AI development and evaluation via magnetic resonance imaging.
- Resource Type
- Academic Journal
- Authors
- Cheong RCT; Royal National ENT and Eastman Dental Hospitals, University College London Hospitals NHS, London, UK.; Jawad S; Royal National ENT and Eastman Dental Hospitals, University College London Hospitals NHS, London, UK.; Adams A; Barts Health NHS Trust, London, UK.; Campion T; Barts Health NHS Trust, London, UK.; Lim ZH; University College London, London, UK.; Papachristou N; Medical Physics and Digital Innovation Laboratory, School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, Greece.; Unadkat S; Royal National ENT and Eastman Dental Hospitals, University College London Hospitals NHS, London, UK.; Randhawa P; Royal National ENT and Eastman Dental Hospitals, University College London Hospitals NHS, London, UK.; Joseph J; Royal National ENT and Eastman Dental Hospitals, University College London Hospitals NHS, London, UK.; Andrews P; Royal National ENT and Eastman Dental Hospitals, University College London Hospitals NHS, London, UK.; Taylor P; University College London, London, UK.; Kunz H; University College London, London, UK. h.kunz@ucl.ac.uk.; School of Public Health, Imperial College London, London, UK. h.kunz@ucl.ac.uk.
- Source
- Publisher: Springer International Country of Publication: Germany NLM ID: 9002937 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1434-4726 (Electronic) Linking ISSN: 09374477 NLM ISO Abbreviation: Eur Arch Otorhinolaryngol Subsets: MEDLINE
- Subject
- Language
- English
Purpose: Artificial intelligence (AI) in the form of automated machine learning (AutoML) offers a new potential breakthrough to overcome the barrier of entry for non-technically trained physicians. A Clinical Decision Support System (CDSS) for screening purposes using AutoML could be beneficial to ease the clinical burden in the radiological workflow for paranasal sinus diseases.
Methods: The main target of this work was the usage of automated evaluation of model performance and the feasibility of the Vertex AI image classification model on the Google Cloud AutoML platform to be trained to automatically classify the presence or absence of sinonasal disease. The dataset is a consensus labelled Open Access Series of Imaging Studies (OASIS-3) MRI head dataset by three specialised head and neck consultant radiologists. A total of 1313 unique non-TSE T2w MRI head sessions were used from the OASIS-3 repository.
Results: The best-performing image classification model achieved a precision of 0.928. Demonstrating the feasibility and high performance of the Vertex AI image classification model to automatically detect the presence or absence of sinonasal disease on MRI.
Conclusion: AutoML allows for potential deployment to optimise diagnostic radiology workflows and lay the foundation for further AI research in radiology and otolaryngology. The usage of AutoML could serve as a formal requirement for a feasibility study.
(© 2024. The Author(s).)