RADNET: Radiologist Level Accuracy using Deep Learning for HEMORRHAGE detection in CT Scans

TL;DR

RADnet is a deep learning model that emulates radiologists' analysis of CT scans for hemorrhage detection, achieving accuracy comparable to experts and higher recall in identifying hemorrhages.

Contribution

The paper introduces RADnet, a novel deep learning architecture combining DenseNet, attention mechanisms, and recurrent layers for improved hemorrhage detection in CT scans.

Findings

RADnet achieves 81.82% accuracy at CT level.

RADnet has higher recall than two radiologists.

Performance is comparable to senior radiologists.

Abstract

We describe a deep learning approach for automated brain hemorrhage detection from computed tomography (CT) scans. Our model emulates the procedure followed by radiologists to analyse a 3D CT scan in real-world. Similar to radiologists, the model sifts through 2D cross-sectional slices while paying close attention to potential hemorrhagic regions. Further, the model utilizes 3D context from neighboring slices to improve predictions at each slice and subsequently, aggregates the slice-level predictions to provide diagnosis at CT level. We refer to our proposed approach as Recurrent Attention DenseNet (RADnet) as it employs original DenseNet architecture along with adding the components of attention for slice level predictions and recurrent neural network layer for incorporating 3D context. The real-world performance of RADnet has been benchmarked against independent analysis performed by three senior radiologists for 77 brain CTs. RADnet demonstrates 81.82% hemorrhage prediction accuracy at CT level that is comparable to radiologists. Further, RADnet achieves higher recall than two of the three radiologists, which is remarkable.