Medical report generation can be treated as a process of doctors' observing, understanding, and describing images from different perspectives. Following this process, this paper innovatively proposes a Transformer-based Semantic Query learning paradigm (TranSQ). Briefly, this paradigm is to learn an intention embedding set and make a semantic query to the visual features, generate intent-compliant sentence candidates, and form a coherent report. We apply a bipartite matching mechanism during training to realize the dynamic correspondence between the intention embeddings and the sentences to induct medical concepts into the observation intentions. Experimental results on two major radiology reporting datasets (i.e., IU X-ray and MIMIC-CXR) demonstrate that our model outperforms state-of-the-art models regarding generation effectiveness and clinical efficacy. In addition, comprehensive ablation experiments fully validate the TranSQ model's innovation and interpretation. The code is available at https://github.com/zjukongming/TranSQ.
Keyphrases
- healthcare
- high resolution
- randomized controlled trial
- systematic review
- deep learning
- artificial intelligence
- emergency department
- machine learning
- optical coherence tomography
- computed tomography
- magnetic resonance
- magnetic resonance imaging
- electron microscopy
- adverse drug
- atrial fibrillation
- electronic health record