Advancing prediction of bone marrow biopsy results from MRI in myeloma patients: A Neural Network Approach
Motivation: While Radiomics analysis has shown predictive power for plasma cell infiltration (PCI) from MRI in Myeloma patients, convolutional neural networks (CNNs) offer an opportunity for improved performance and generalizability. Goal(s): Our objective was to develop a predictive model for PCI using CNNs while addressing the challenges posed by limited dataset size. Approach: CNNs were trained on MRI data of the pelvic bone marrow and its predictive capabilities were enriched by concatenating radiomic features in the latent space. Results: The findings revealed limitations due to the small dataset size. However, incorporating radiomic features enhanced prediction accuracy, aligning with radiomics and random forest-based methods. Impact: This study highlights the limitations of deep learning when using a small dataset. It underlines the importance of feature extraction and the need of dedicating substantial efforts to create large annotated datasets.
Authors
- Marc‐Steffen Raab
- Juliane Bernhard
- Klaus Maier‐Hein (ORCID: https://orcid.org/0000-0002-6626-2463)
- Tassilo Wald (ORCID: https://orcid.org/0009-0007-5222-2683)
- Jessica Kächele (ORCID: https://orcid.org/0000-0003-3851-2848)
- Stefan Delorme (ORCID: https://orcid.org/0000-0002-1000-2582)
- Niels Weinhold (ORCID: https://orcid.org/0000-0002-5464-3234)
- Hartmut Goldschmidt (ORCID: https://orcid.org/0000-0003-0961-0035)
- Maximilian Fischer (ORCID: https://orcid.org/0009-0001-8305-6370)
- Jens Hillengaß (ORCID: https://orcid.org/0000-0002-1778-0010)
- Fabian Bauer (ORCID: https://orcid.org/0000-0002-0896-5734)
- Sandra Sauer (ORCID: https://orcid.org/0000-0001-5552-3149)
- Peter Neher (ORCID: https://orcid.org/0000-0002-5285-7554)
- Markus Wennmann (ORCID: https://orcid.org/0000-0002-8092-8380)
- Robin Peretzke (ORCID: https://orcid.org/0000-0002-6187-3636)
- Elias Mai
- Heinz-Peter Schlemmer
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2024-11-26
- DOI
- https://doi.org/10.58530/2024/3799
- Primary Topic
- Digital Imaging for Blood Diseases
- Type
- article
- Field-Weighted Citation Impact
- 0.00