112 citations · 243 across the 23 of their papers we have counts for
29 papers
Diagnostic Loss: Asymmetric Supervision for Radiology Report Generation
Ignacy Kolton, Wenxuan Li, Zongwei Zhou +4
Automated radiology report generation requires models to do more than produce fluent clinical narratives: they must explicitly state supported diagnoses while avoiding unsupported…
DART: Scaling a Shape Representation Across Anatomical Classes and Imaging Modalities
Koushik Swarna, Pedro R. A. S. Bassi, Lam Ngo +4
Current state-of-the-art segmentation models still produce anatomically implausible shapes, such as broken vessels and fragmented glands, on the structures that are hardest to segm…
Merlin Plus: A Large-Scale, Multi-Cancer, Image-Mask-Report Dataset
Pedro R. A. S. Bassi, Wenxuan Li, Szymon Plotka +10
Multi-cancer segmentation in computed tomography (CT) is fundamentally limited by the scarcity of tumor masks across different organs. We present Merlin Plus, the first large-scale…
RT-Super: Learning Tumor Segmentation from Longitudinal Images and Reports
Pedro R. A. S. Bassi, Wenxuan Li, Hanxue Gu +11
Multi-tumor segmentation is important for early cancer detection and allows radiologists to visualize, verify, and understand AI predictions. However, tumor segmentation masks are…
Report Supervision
Pedro R. A. S. Bassia, Wenxuan Li, Jakob Wasserthal +10
Segmentation models can surpass radiologists, classification models, and vision-language models in tumor detection. Importantly, segmentation models outline tumors, allowing radiol…
BenchX: Benchmarking AI Models for Cancer Detection and Localization with Demographic and Protocol Biases
Qi Chen, Wenxuan Li, Pedro R. A. S. Bassi +14
Artificial intelligence (AI) has achieved remarkable success in medical imaging, but it is widely recognized that these models often perform inconsistently across real-world clinic…
RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology
Wenxuan Li, Pedro R. A. S. Bassi, Xinze Zhou +3
Cancer screening is a reasoning task. A radiologist observes findings, compares them to prior scans, integrates clinical context, and reaches a diagnostic conclusion confirmed by p…
DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents
Yixiong Chen, Wenjie Xiao, Pedro R. A. S. Bassi +7
Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, existing medical visual questio…
Early and Prediagnostic Detection of Pancreatic Cancer from Computed Tomography
Wenxuan Li, Pedro R. A. S. Bassi, Lizhou Wu +34
Pancreatic ductal adenocarcinoma (PDAC), one of the deadliest solid malignancies, is often detected at a late and inoperable stage. Retrospective reviews of prediagnostic CT scans,…
Auditing Significance, Metric Choice, and Demographic Fairness in Medical AI Challenges
Ariel Lubonja, Pedro R. A. S. Bassi, Wenxuan Li +4
Open challenges have become the de facto standard for comparative ranking of medical AI methods. Despite their importance, medical AI leaderboards exhibit three persistent limitati…
See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement
Junqi Liu, Zejun Wu, Pedro R. A. S. Bassi +15
Image enhancement improves visual quality and helps reveal details that are hard to see in the original image. In medical imaging, it can support clinical decision-making, but curr…
Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks
Pedro R. A. S. Bassi, Xinze Zhou, Wenxuan Li +20
Early tumor detection save lives. Each year, more than 300 million computed tomography (CT) scans are performed worldwide, offering a vast opportunity for effective cancer screenin…
Learning Segmentation from Radiology Reports
Pedro R. A. S. Bassi, Wenxuan Li, Jieneng Chen +8
Tumor segmentation in CT scans is key for diagnosis, surgery, and prognosis, yet segmentation masks are scarce because their creation requires time and expertise. Public abdominal…
PanTS: The Pancreatic Tumor Segmentation Dataset
Wenxuan Li, Xinze Zhou, Qi Chen +15
PanTS is a large-scale, multi-institutional dataset curated to advance research in pancreatic CT analysis. It contains 36,390 CT scans from 145 medical centers, with expert-validat…
Are Vision Language Models Ready for Clinical Diagnosis? A 3D Medical Benchmark for Tumor-centric Visual Question Answering
Yixiong Chen, Wenjie Xiao, Pedro R. A. S. Bassi +5
Vision-Language Models (VLMs) have shown promise in various 2D visual tasks, yet their readiness for 3D clinical diagnosis remains unclear due to stringent demands for recognition…
Text2CT: Towards 3D CT Volume Generation from Free-text Descriptions Using Diffusion Model
Pengfei Guo, Can Zhao, Dong Yang +9
Generating 3D CT volumes from descriptive free-text inputs presents a transformative opportunity in diagnostics and research. In this paper, we introduce Text2CT, a novel approach…
RadGPT: Constructing 3D Image-Text Tumor Datasets
Pedro R. A. S. Bassi, Mehmet Can Yavuz, Kang Wang +7
Cancers identified in CT scans are usually accompanied by detailed radiology reports, but publicly available CT datasets often lack these essential reports. This absence limits the…
Expectation-Maximization as the Engine of Scalable Medical Intelligence
Wenxuan Li, Pedro R. A. S. Bassi, Tianyu Lin +19
Large, high-quality, annotated datasets are the foundation of medical AI research, but constructing even a small, moderate-quality, annotated dataset can take years of effort from…
Text-Driven Tumor Synthesis
Xinran Li, Yi Shuai, Chen Liu +11
Tumor synthesis can generate examples that AI often misses or over-detects, improving AI performance by training on these challenging cases. However, existing synthesis methods, wh…
Label Critic: Design Data Before Models
Pedro R. A. S. Bassi, Qilong Wu, Wenxuan Li +4
As medical datasets rapidly expand, creating detailed annotations of different body structures becomes increasingly expensive and time-consuming. We consider that requesting radiol…
Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
Pedro R. A. S. Bassi, Wenxuan Li, Yucheng Tang +50
How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified…
AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarking
Wenxuan Li, Chongyu Qu, Xiaoxi Chen +18
We introduce the largest abdominal CT dataset (termed AbdomenAtlas) of 20,460 three-dimensional CT volumes sourced from 112 hospitals across diverse populations, geographies, and f…
Training with Explanations Alone: A New Paradigm to Prevent Shortcut Learning
Pedro R. A. S. Bassi, Haydr A. H. Ali, Andrea Cavalli +1
Application of Artificial Intelligence (AI) in critical domains, like the medical one, is often hampered by shortcut learning, which hinders AI generalization to diverse hospitals…
Faster ISNet for Background Bias Mitigation on Deep Neural Networks
Pedro R. A. S. Bassi, Sergio Decherchi, Andrea Cavalli
Bias or spurious correlations in image backgrounds can impact neural networks, causing shortcut learning (Clever Hans Effect) and hampering generalization to real-world data. ISNet…