5 papers
In-batch Relational Features Enhance Precision in An Unsupervised Medical Anomaly Detection Task
P. Bilha Githinji, Ijaz Gul, Lian Zhang +3
Confounding pathology with normal anatomical variation remains a significant challenge in unsupervised medical-image anomaly detection, resulting in numerous false positives. To en…
Making Knowledge Accessible: Divergent Readability-Accuracy Strategies of Mistral and QWen in Biomedical Text Simplification
P. Bilha Githinji, Aikaterini Melliou, Zeming Liang +2
The growing public demand for accessible biomedical information calls for scalable text simplification. While large language models (LLMs) offer solutions, they too struggle with b…
External Prompt Features Enhanced Parameter-efficient Fine-tuning for Salient Object Detection
Wen Liang, Peipei Ran, Mengchao Bai +4
Salient object detection (SOD) aims at finding the most salient objects in images and outputs pixel-level binary masks. Transformer-based methods achieve promising performance due…
Harnessing Intra-group Variations Via a Population-Level Context for Pathology Detection
P. Bilha Githinji, Xi Yuan, Zhenglin Chen +8
Realizing sufficient separability between the distributions of healthy and pathological samples is a critical obstacle for pathology detection convolutional models. Moreover, these…
IRFundusSet: An Integrated Retinal Fundus Dataset with a Harmonized Healthy Label
P. Bilha Githinji, Keming Zhao, Jiantao Wang +1
Ocular conditions are a global concern and computational tools utilizing retinal fundus color photographs can aid in routine screening and management. Obtaining comprehensive and s…