5 papers
FedProIn: Mitigating Client Drift for Learnable Prototypes in Federated Medical Imaging
Harsh Kumar, Tarun Kumar Garg, Vaanathi Sundaresan
Federated learning (FL) is severely hindered by statistical heterogeneity due to variations in scanners, acquisition protocols, and patient populations. Such non-IID data induces c…
Mutually Exclusive Multiclass Lesion Segmentation in Neuroimaging: Binary-Guided Weak Supervision with Inter-Class Orthogonality
Ashutosh Kumar, Vivek Dhamale, Vaanathi Sundaresan
Weakly supervised segmentation of co-occurring neuroimaging lesion subclasses remains challenging due to overlapping activations, noisy pseudo-labels, and the absence of explicit i…
MARVEL: Margin-Aware Robust von Mises-Fischer Expert Learning for Long-Tailed Out-of-Distribution Detection
A. S. Anudeep, Vaanathi Sundaresan
For clinical deployment, it is essential that automated diagnostic systems remain reliable when confronted with previously unseen cases, yet deep models routinely misclassify out-o…
Traumatic Brain Injury Segmentation using an Ensemble of Encoder-decoder Models
Ghanshyam Dhamat, Vaanathi Sundaresan
The identification and segmentation of moderate-severe traumatic brain injury (TBI) lesions pose a significant challenge in neuroimaging. This difficulty arises from the extreme he…
Automated quality assessment using appearance-based simulations and hippocampus segmentation on low-field paediatric brain MR images
Vaanathi Sundaresan, Nicola K Dinsdale
Understanding the structural growth of paediatric brains is a key step in the identification of various neuro-developmental disorders. However, our knowledge is limited by many fac…