MedGuards introduces a multi-agent in-context learning framework for medical error detection and correction plus the KPCS metric, reporting improvements on four multilingual clinical note datasets.
Out-of-distribution detection in medical image analysis: A survey
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
MaRS improves reconstruction-based OOD detection by replacing L2 residual norms with variance-aware Mahalanobis scoring on autoencoder outputs.
MahaVar augments the Mahalanobis OOD score with class-wise distance variance, which is theoretically higher for in-distribution samples under relaxed Neural Collapse geometry.
MMIR-TCM is a multimodal framework using MLLM, memory-SAM, and RAG that claims to outperform GPT-4o and Gemini on TCM tongue diagnosis tasks via a new dataset and custom metric.
A Temporal Fusion Transformer with CORAL ordinal layer and autoregressive Mixture Density Network generates multi-horizon probabilistic trajectories and decomposed uncertainty estimates for Alzheimer's progression on ADNI data.
Noise injection during training reduces the ID-OOD performance gap in COVID-19 CXR classification from 0.10-0.20 to 0.01-0.06.
citing papers explorer
-
MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction
MedGuards introduces a multi-agent in-context learning framework for medical error detection and correction plus the KPCS metric, reporting improvements on four multilingual clinical note datasets.
-
MaRS: Robust Out-of-Distribution Detection via Mahalanobis Residual Scoring
MaRS improves reconstruction-based OOD detection by replacing L2 residual norms with variance-aware Mahalanobis scoring on autoencoder outputs.
-
MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
MahaVar augments the Mahalanobis OOD score with class-wise distance variance, which is theoretically higher for in-distribution samples under relaxed Neural Collapse geometry.
-
MMIR-TCM: Memory-Integrated Multimodal Inference and Retrieval for TCM Clinical Decision Support
MMIR-TCM is a multimodal framework using MLLM, memory-SAM, and RAG that claims to outperform GPT-4o and Gemini on TCM tongue diagnosis tasks via a new dataset and custom metric.
-
Uncertainty-Aware Longitudinal Forecasting of Alzheimer's Disease Progression Using Deep Learning
A Temporal Fusion Transformer with CORAL ordinal layer and autoregressive Mixture Density Network generates multi-horizon probabilistic trajectories and decomposed uncertainty estimates for Alzheimer's progression on ADNI data.
-
Noise Injection: Improving Out-of-Distribution Generalization for Limited Size Datasets
Noise injection during training reduces the ID-OOD performance gap in COVID-19 CXR classification from 0.10-0.20 to 0.01-0.06.