Automatic Diagnosis of Pulmonary Embolism Using an Attention-guided Framework: A Large-scale Study

no code implementations • MIDL 2019 • Luyao Shi, Deepta Rajan, Shafiq Abedin, Manikanta Srikar Yellapragada, David Beymer, Ehsan Dehghan

In addition to the classification loss, an attention loss was added during training to help the network focus attention on PE.

Pi-PE: A Pipeline for Pulmonary Embolism Detection using Sparsely Annotated 3D CT Images

no code implementations • 5 Oct 2019 • Deepta Rajan, David Beymer, Shafiqul Abedin, Ehsan Dehghan

Pulmonary embolisms (PE) are known to be one of the leading causes for cardiac-related mortality.

Pulmonary Embolism Detection

Disease Detection in Weakly Annotated Volumetric Medical Images using a Convolutional LSTM Network

no code implementations • 3 Dec 2018 • Nathaniel Braman, David Beymer, Ehsan Dehghan

We explore a solution for learning disease signatures from weakly, yet easily obtainable, annotated volumetric medical imaging data by analyzing 3D volumes as a sequence of 2D images.

Multiple Instance Learning