Image-Based Search in Radiology: Identification of Brain Tumor Subtypes within Databases Using MRI-Based Radiomic Features
We introduce an image-based search method for exploring historical MR images of primary brain tumors and fetching reference cases closely resembling queried ones. Assessment involving comparison of tumor types and visual similarity Likert scoring by expert neuroradiologists validates the effectiveness of this method.
Authors
- Marc von Reppert (ORCID: https://orcid.org/0000-0003-4623-7401)
- Sanjay Aneja (ORCID: https://orcid.org/0000-0001-5681-7528)
- Arman Avesta (ORCID: https://orcid.org/0000-0002-6847-9818)
- Nazanin Maleki
- MingDe Lin (ORCID: https://orcid.org/0000-0001-7641-2595)
- Sara Merkaj (ORCID: https://orcid.org/0000-0003-1147-4968)
- Karl‐Titus Hoffmann (ORCID: https://orcid.org/0000-0001-7693-887X)
- Tal Zeevi (ORCID: https://orcid.org/0000-0001-8917-7061)
- Leon Jekel (ORCID: https://orcid.org/0000-0001-9954-3328)
- Jan Lost (ORCID: https://orcid.org/0000-0001-6098-6746)
- Niklas Tillmanns (ORCID: https://orcid.org/0000-0002-9366-7183)
- Saahil Chadha (ORCID: https://orcid.org/0009-0002-8519-7895)
- Mariam Aboian (ORCID: https://orcid.org/0000-0002-4877-8271)
- Klara Willms
Institutions
- Yale New Haven Hospital (US)
- Children's Hospital of Philadelphia (US)
- Leipzig University of Applied Sciences (DE)
- Universität Ulm (DE)
- Yale University (US)
- Massachusetts General Hospital (US)
- Düsseldorf University Hospital (DE)
- Yale New Haven Health System (US)
- Laboratoire d’Imagerie Biomédicale (FR)
- Essen University Hospital (DE)
- University Hospital Leipzig (DE)
- Sage Technologies (United States) (US)
- Technische Hochschule Ulm (DE)
- Heinrich Heine University Düsseldorf (DE)
- University of Duisburg-Essen (DE)
- Leipzig University (DE)
Publication Details
- Journal
- American Journal of Neuroradiology
- Published
- 2025-04-18
- DOI
- https://doi.org/10.3174/ajnr.a8805
- Citations
- 3
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 4.08