Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations
This work addresses the challenge of enhancing prediction accuracy for clinicians by integrating temporal context into single-image analysis, representing an incremental improvement over existing methods.
The paper tackled the problem of clinical outcome prediction from single-timepoint medical images by incorporating disease progression information from sequential scans, resulting in improved performance over state-of-the-art methods on chest and osteoarthritis radiography datasets.
Clinical 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.