Similar Posts
- Gratuit | MedToolBox | Neuro | Non certifié | Tier 2
Multiple Sclerosis Diagnostic Tool
Multiple sclerosis diagnostic criteria lack optimal specificity, leading to potential misdiagnosis. Advanced magnetic resonance imaging (MRI) biomarkers like the central vein sign, cortical lesions, and paramagnetic rim lesions are highly specific to multiple sclerosis and could potentially improve diagnostic accuracy. In this study, we applied machine learning techniques to a retrospective, multicentric dataset of 322…
TEF-Health
Testing and Experimentation Validation Evaluation Facilities for health ai and robotics
MCsquare
The use of Monte Carlo dose calculation instead of typical analytical algorithms can improve the accuracy of proton therapy treatment planning. Especially, range uncertainties are significantly reduced in heterogeneous anatomies. MCsquare, a new fast Monte Carlo code, has been developed to simulate proton PBS treatments with the accuracy and calculation speed required in the clinic….
LiblineaR
LiblineaR is an R package for large-scale linear modeling supporting classification and regression of large datasets. The original software in C/C++ was developed by Prof. Chih-Jen Lin and his team at the Machine Learning Group of the Taiwan University. As most of our developments are done in the open source R language, we have developed the R library LiblineaR, making all the…
Orthanc
Orthanc est un écosystème libre et open-source destiné à la gestion et au partage d’images médicales. Orthanc implémente le standard international DICOM qui régule l’imagerie médicale numérique dans tout établissement de santé. Cela permet à Orthanc de recevoir, de stocker et de transmettre des images en provenance de n’importe quel équipement de radiologie (scanners, IRM,…
Exploring Foundation Models Fine-Tuning for Cytology Tasks
> Github repository
In this paper, we explore the application of existing foundation models to cytological classification tasks, focusing on low-rank adaptation (LoRA), a parameter-efficient fine-tuning method well-suited to few-shot learning scenarios. We evaluate five foundation models across four cytological classification datasets. Our results demonstrate that fine-tuning the pre-trained backbones with LoRA significantly enhances model performance compared to merely fine-tuning the classifier head, achieving state-of-the-art results on both simple and complex classification tasks while requiring fewer data samples.
