Publication Archive
Browse publication mini-blog pages by year, type, and topic. Missing manuscript details are intentionally marked as TODO placeholders.
Showing 21 publications
conference / 2026
Breast MRI + Explainable AI
BE-WISE studies weakly informed slice-level explanation for breast MRI, focusing on interpretable evidence localization within volumetric exams.
conference / 2026
Mammography + Vision-Language Pretraining
LA-CLIP studies lesion-aware mammography vision-language pretraining through ROI-guided contrastive representation learning.
conference / 2026
Low-dose CT + Risk Stratification
This BVM 2026 work investigates opportunistic breast cancer risk stratification from low-dose chest CT using multiple-instance learning.
PatchCLIP extends CLIP-style medical image-text training with patch-level alignment to improve region-specific evidence localization.
This retrospective study evaluates AI-assisted malignant breast cancer detection in a cohort enriched for high breast density.
This retrospective breast MRI study evaluates lesion-level AI performance in an external Chinese cohort, with emphasis on sensitivity and false-positive burden.
AGE uses self-supervised attention maps to guide stochastic erasing, preserving task-relevant mammography regions during transfer learning.
conference / 2025
Mammography + Lesion Detection
Exemplar Med-DETR uses learned exemplar representations to improve lesion localization under dense anatomy, domain shift, and cross-modality variation.
MammoBLIP investigates end-to-end mammography report generation by aligning breast images with standardized radiology-style language.
workshop / 2025
Mammography + Mass Detection
MM-DETR models paired mammography views jointly, using cross-view information rather than independent single-image detection.
DITL investigates how source-dataset selection influences mammography transfer learning for breast cancer screening and lesion diagnosis.
journal / 2025
Mammography + Vision-Language Models
This work investigates mammography foundation models for radiological reasoning using vision-language representation learning.
journal / 2025
Mammography + Quality Control
This study investigates CNN-based detection of skin-fold positioning errors for mammography quality control.
Attention-Guided Erasing improves breast-density transfer learning by preserving attention-derived tissue regions while stochastically suppressing less informative background.
This work studies representation learning for contrast-enhanced spectral mammography to improve downstream abnormality classification.
This clinical validation study evaluates whether AI-assisted mammography reading improves sensitivity in a Vietnamese cohort with high breast-density prevalence.
AUCReshaping optimizes classifier behavior near clinically relevant high-specificity operating points rather than treating the full ROC curve uniformly.
preprint / 2023
Mammography + Transfer Learning
This preprint evaluates whether full-field mammograms contain signal for luminal subtype classification using image-level supervision.
journal / 2023
Hematology + Deep Learning
This study applies deep learning to unstained white blood cell classification, extending medical image analysis into laboratory hematology.
workshop / 2022
Mammography + Calcification
This BVM study evaluates random histogram equalization as an augmentation strategy for deep-learning-based breast calcification analysis.
patent / 2020
Medical Devices + Patent
This patent entry documents earlier medical-device workflow engineering related to secure device unlocking.