Development of robust deep learning techniques for DDLS. Development of trustworthy and explainable AI approaches for practical use in biomedical and medical image data analysis. PI for several research projects aiming to exploit the power of modern data driven image analysis for use in biomedicine and healthcare, with a particular focus on AI-supported cytology, early cancer detection and diagnostics. Self supervised and multimodal learning from weakly labeled image data.
Joakim Lindblad
Uppsala University
Key Publications
Early Detection of Oral Potentially Malignant Disorders: A Review on Prospective Screening Methods with Regard to Global Challenges
Journal of Maxillofacial and Oral Surgery, 2024
INSPIRE: Intensity and spatial information-based deformable image registration
PLOS ONE, 2023
End-to-End Learning and Analysis of Infant Engagement During Guided Play: Prediction and Explainability
2022
Fast computation of mutual information in the frequency domain with applications to global multimodal image alignment
Pattern Recognition Letters, 2022
Cross-Sim-NGF: FFT-Based Global Rigid Multimodal Alignment of Image Volumes Using Normalized Gradient Fields
2022