An official website of the United States government
Medical Large Vision-Language Models (Med-LVLMs) have shown promising results in clinical applications, but often suffer from hallucinated outputs due to misaligned visual understanding. In this work, we identify two fundamental limitations contributing to this issue: insufficient visual representation learning and poor visual attention alignment. To address these problems, we propose MedAlign, a simple, lightweight alignment distillation framework that transfers visual alignment knowledge from a domain-specific Contrastive Language-Image Pre-training (CLIP) model to Med-LVLMs. MedAlign introduces two distillation losses: a spatial-aware visual alignment loss based on visual token-level similarity structures, and an attention-aware distillation loss that guides attention toward diagnostically relevant regions. Extensive experiments on medical report generation and medical visual question answering (VQA) benchmarks show that MedAlign consistently improves both performance and interpretability, yielding more visually grounded outputs.
more »
« less
This content will become publicly available on March 17, 2027
A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation
Radiology report generation from chest X-rays is an important task in artificial intelligence with the potential to greatly reduce radiologists' workload and shorten patient wait times. Despite recent advances, existing approaches often lack sufficient disease-awareness in visual representations and adequate vision-language alignment to meet the specialized requirements of medical image analysis. As a result, these models usually overlook critical pathological features on chest X-rays and struggle to generate clinically accurate reports. To address these limitations, we propose a novel dual-stage disease-aware framework for chest X-ray report generation. In Stage~1, our model learns Disease-Aware Semantic Tokens (DASTs) corresponding to specific pathology categories through cross-attention mechanisms and multi-label classification, while simultaneously aligning vision and language representations via contrastive learning. In Stage~2, we introduce a Disease-Visual Attention Fusion (DVAF) module to integrate disease-aware representations with visual features, along with a Dual-Modal Similarity Retrieval (DMSR) mechanism that combines visual and disease-specific similarities to retrieve relevant exemplars, providing contextual guidance during report generation. Extensive experiments on benchmark datasets (i.e., CheXpert Plus, IU X-ray, and MIMIC-CXR) demonstrate that our disease-aware framework achieves state-of-the-art performance in chest X-ray report generation, with significant improvements in clinical accuracy and linguistic quality.
more »
« less
- Award ID(s):
- 2145640
- PAR ID:
- 10674686
- Publisher / Repository:
- AAAI
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 40
- Issue:
- 40
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 33953 to 33961
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Manual examination of chest x-rays is a time consuming process that involves significant effort by expert radiologists. Recent work attempts to alleviate this problem by developing learning-based automated chest x-ray analysis systems that map images to multi-label diagnoses using deep neural net- works. These methods are often treated as black boxes, or they output attention maps but don’t explain why the attended areas are important. Given data consisting of a frontal-view x-ray, a set of natural language findings, and one or more diagnostic impressions, we propose a deep neural network model that during training simultaneously 1) constructs a topic model which clusters key terms from the findings into meaningful groups, 2) predicts the presence of each topic for a given input image based on learned visual features, and 3) uses an image’s predicted topic encoding as features to predict one or more diagnoses. Since the net learns the topic model jointly with the classifier, it gives us a powerful tool for understanding which semantic concepts the net might be ex- ploiting when making diagnoses, and since we constrain the net to predict topics based on expert-annotated reports, the net automatically encodes some higher-level expert knowledge about how to make diagnoses.more » « less
-
null (Ed.)Coronavirus Disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 virus (SARS-CoV-2). The virus transmits rapidly; it has a basic reproductive number (R0) of 2.2-2.7. In March 2020, the World Health Organization declared the COVID-19 outbreak a pandemic. COVID-19 is currently affecting more than 200 countries with 6M active cases. An effective testing strategy for COVID-19 is crucial to controlling the outbreak but the demand for testing surpasses the availability of test kits that use Reverse Transcription Polymerase Chain Reaction (RT-PCR). In this paper, we present a technique to screen for COVID-19 using artificial intelligence. Our technique takes only seconds to screen for the presence of the virus in a patient. We collected a dataset of chest X-ray images and trained several popular deep convolution neural network-based models (VGG, MobileNet, Xception, DenseNet, InceptionResNet) to classify the chest X-rays. Unsatisfied with these models, we then designed and built a Residual Attention Network that was able to screen COVID-19 with a testing accuracy of 98% and a validation accuracy of 100%. A feature maps visual of our model show areas in a chest X-ray which are important for classification. Our work can help to increase the adaptation of AI-assisted applications in clinical practice. The code and dataset used in this project are available at https://github.com/vishalshar/covid-19-screening-using-RAN-on-X-ray-images.more » « less
-
Creating a large-scale dataset of abnormality annotation on medical images is a labor-intensive and costly task. Leveraging weak supervision from readily available data such as radiology reports can compensate lack of large-scale data for anomaly detection methods. However, most of the current methods only use image-level pathological observations, failing to utilize the relevant anatomy mentions in reports. Furthermore, Natural Language Processing (NLP)-mined weak labels are noisy due to label sparsity and linguistic ambiguity. We propose an Anatomy-Guided chest X-ray Network (AGXNet) to address these issues of weak annotation. Our framework consists of a cascade of two net- works, one responsible for identifying anatomical abnormalities and the second responsible for pathological observations. The critical component in our framework is an anatomy-guided attention module that aids the downstream observation network in focusing on the relevant anatomical regions generated by the anatomy network. We use Positive Unlabeled (PU) learning to account for the fact that lack of mention does not nec- essarily mean a negative label. Our quantitative and qualitative results on the MIMIC-CXR dataset demonstrate the effectiveness of AGXNet in disease and anatomical abnormality localization. Experiments on the NIH Chest X-ray dataset show that the learned feature representations are transferable and can achieve the state-of-the-art performances in dis- ease classification and competitive disease localization results. Our code is available at https://github.com/batmanlab/AGXNet.more » « less
-
Temporal Context Matters: Enhancing Single Image Prediction With Disease Progression RepresentationsClinical outcome or severity prediction from medical images has largely focused on learning representations from single-timepoint or snapshot scans. It has been shown that disease progression can be better characterized by temporal imaging. We therefore hypothesized that outcome predictions can be improved by utilizing the disease progression information from sequential images. We present a deep learning approach that leverages temporal progression information to improve clinical outcome predictions from single-timepoint images. In our method, a self-attention based Temporal Convolutional Network (TCN) is used to learn a representation that is most reflective of the disease trajectory. Meanwhile, a Vision Transformer is pretrained in a self-supervised fashion to extract features from single-timepoint images. The key contribution is to design a recalibration module that employs maximum mean discrepancy loss (MMD) to align distributions of the above two contextual representations. We train our system to predict clinical outcomes and severity grades from single-timepoint images. Experiments on chest and osteoarthritis radiography datasets demonstrate that our approach outperforms other state-of-the-art techniques.more » « less
