From Single-Visit to Multi-Visit Image-Based Models: Single-Visit Models are Enough to Predict Obstructive Hydronephrosis
This work addresses patient risk stratification in medical imaging, but it is incremental as it builds on existing single-visit models.
The study tackled the problem of predicting obstructive hydronephrosis using kidney ultrasound images and found that incorporating multiple past visits provides only a small benefit, with prediction based on the latest ultrasound being sufficient for patient risk stratification.
Previous work has shown the potential of deep learning to predict renal obstruction using kidney ultrasound images. However, these image-based classifiers have been trained with the goal of single-visit inference in mind. We compare methods from video action recognition (i.e. convolutional pooling, LSTM, TSM) to adapt single-visit convolutional models to handle multiple visit inference. We demonstrate that incorporating images from a patient's past hospital visits provides only a small benefit for the prediction of obstructive hydronephrosis. Therefore, inclusion of prior ultrasounds is beneficial, but prediction based on the latest ultrasound is sufficient for patient risk stratification.