Ischemic Stroke Lesion Segmentation in CT Perfusion Scans using Pyramid Pooling and Focal Loss

11/02/2018
by   S. Mazdak Abulnaga, et al.
0

We present a fully convolutional neural network for segmenting ischemic stroke lesions in CT perfusion images for the ISLES 2018 challenge. Treatment of stroke is time sensitive and current standards for lesion identification require manual segmentation, a time consuming and challenging process. Automatic segmentation methods present the possibility of accurately identifying lesions and improving treatment planning. Our model is based on the PSPNet, a network architecture that makes use of pyramid pooling to provide global and local contextual information. To learn the varying shapes of the lesions, we train our network using focal loss, a loss function designed for the network to focus on learning the more difficult samples. We compare our model to networks trained using the U-Net and V-Net architectures. Our approach demonstrates effective performance in lesion segmentation and ranked among the top performers at the challenge conclusion.

READ FULL TEXT

page 2

page 9

research
10/18/2018

A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation

We propose a generalized focal loss function based on the Tversky index ...
research
05/09/2019

Liver Lesion Segmentation with slice-wise 2D Tiramisu and Tversky loss function

At present, lesion segmentation is still performed manually (or semi-aut...
research
06/05/2018

MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Images

The analysis of glandular morphology within colon histopathology images ...
research
09/23/2018

Leveraging Transfer Learning for Segmenting Lesions and their Attributes in Dermoscopy Images

Computer-aided diagnosis systems for classification of different type of...
research
09/15/2023

3D SA-UNet: 3D Spatial Attention UNet with 3D ASPP for White Matter Hyperintensities Segmentation

White Matter Hyperintensity (WMH) is an imaging feature related to vario...
research
11/02/2018

Classification of Findings with Localized Lesions in Fundoscopic Images using a Regionally Guided CNN

Fundoscopic images are often investigated by ophthalmologists to spot ab...
research
05/22/2017

GP-Unet: Lesion Detection from Weak Labels with a 3D Regression Network

We propose a novel convolutional neural network for lesion detection fro...

Please sign up or login with your details

Forgot password? Click here to reset