This website requires JavaScript.

From Single-Visit to Multi-Visit Image-Based Models: Single-Visit Models are Enough to Predict Obstructive Hydronephrosis

Stanley Bryan Z. HuaMandy RickardJohn Weaver ...+7 Lauren Erdman
Dec 2022
摘要
Previous work has shown the potential of deep learning to predict renalobstruction using kidney ultrasound images. However, these image-basedclassifiers 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 visitinference. We demonstrate that incorporating images from a patient's pasthospital visits provides only a small benefit for the prediction of obstructivehydronephrosis. Therefore, inclusion of prior ultrasounds is beneficial, butprediction based on the latest ultrasound is sufficient for patient riskstratification.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答