7 papers · 1 filter
SelfCue: Making a 3D CT Report Generator Say What It Already Knows
Renjie Liang, Yang Yang, Jinqian Pan +3
Progress in 3D CT report generation is usually sought in increasingly sophisticated architectures and larger pools of training data. We find instead that a 3D CT report generator a…
When Do Cheap Probes Predict Expensive Training? Probing 3D-CT Encoders for Text Generation
Renjie Liang, Zijian Xu, Jinqian Pan +6
Building a 3D CT vision language model begins with a choice of which image encoder to build on. Today that choice is made by fine-tuning every candidate through the full language m…
ORCA: ORgan-Centroid Aggregation for Training-Free 3D CT Visual Token Compression
Renjie Liang, Zijian Xu, Jinqian Pan +6
A 3D CT scan entering a vision-language model produces a long sequence of visual tokens, often thousands to tens of thousands per volume, and this sequence must be compressed befor…
Multi-Granularity 3D Kidney Lesion Characterization from CT Volumes
Renjie Liang, Zhengkang Fan, Jinqian Pan +4
Radiology reports describe kidney lesions by type, size, enhancement, and attenuation, yet existing 3D methods predict only at the patient or organ level. We reformulate kidney CT…
OphMAE: Bridging Volumetric and Planar Imaging with a Foundation Model for Adaptive Ophthalmological Diagnosis
Tienyu Chang, Zhen Chen, Renjie Liang +9
The advent of foundation models has heralded a new era in medical artificial intelligence (AI), enabling the extraction of generalizable representations from large-scale unlabeled…
Beyond the Embedding Bottleneck: Adaptive Retrieval-Augmented 3D CT Report Generation
Renjie Liang, Yiling Ma, Yang Xing +6
Automated radiology report generation from 3D CT volumes often suffers from incomplete pathology coverage. We provide empirical evidence that this limitation stems from a represent…
DTC: A Deformable Transposed Convolution Module for Medical Image Segmentation
Chengkun Sun, Jinqian Pan, Renjie Liang +4
In medical image segmentation, particularly in UNet-like architectures, upsampling is primarily used to transform smaller feature maps into larger ones, enabling feature fusion bet…