NTU-HTC Deep Learning Competition: Weakly Supervised Learning for Findings Detection in Medical Images
weekly supervised leanring medical image densenet grad-cam
Introduction:
Deep convolutional neural networks have been widely adopted in various applications. Applications on medical researches attracted attention and demonstrated remarkable progress. In this task, we applied convolutional neural networks to fulfill the requirements. Further-more, we experimented a variety of models and mechanisms.
About the Task:
In this task, we have to plot bounding boxes for each disease finding in a single chest X-ray without goundtruth (X, Y, width, height) in training set. The task description is detailed in PDF1 and PDF2. Our work flow could be summarized as 
