Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms
This addresses misdiagnosis and delays in PE detection, which can be fatal, but is incremental as it builds on existing deep learning methods for medical imaging.
The paper tackles pulmonary embolism detection in CT pulmonary angiograms by introducing a deep learning approach that combines computer vision and neural networks, achieving state-of-the-art results on the RSNA dataset.
Pulmonary Embolisms (PE) represent a leading cause of cardiovascular death. While medical imaging, through computed tomographic pulmonary angiography (CTPA), represents the gold standard for PE diagnosis, it is still susceptible to misdiagnosis or significant diagnosis delays, which may be fatal for critical cases. Despite the recently demonstrated power of deep learning to bring a significant boost in performance in a wide range of medical imaging tasks, there are still very few published researches on automatic pulmonary embolism detection. Herein we introduce a deep learning based approach, which efficiently combines computer vision and deep neural networks for pulmonary embolism detection in CTPA. Our method features novel improvements along three orthogonal axes: 1) automatic detection of anatomical structures; 2) anatomical aware pretraining, and 3) a dual-hop deep neural net for PE detection. We obtain state-of-the-art results on the publicly available multicenter large-scale RSNA dataset.