Deep-FExt: Deep Feature Extraction for Vessel Segmentation and Centerline Prediction
This work addresses vessel analysis in biomedical imaging, offering improved accuracy for medical diagnosis, though it appears incremental as it builds on existing deep learning architectures.
The authors tackled vessel segmentation and centerline prediction in biomedical images by developing Deep-FExt, a deep feature extraction method using inception models and fully convolutional networks. Their approach achieved an average maximum Dice score of 0.85 on both DRIVE and STARE datasets, outperforming existing hand-crafted feature schemes and matching human annotator performance.
Feature extraction is a very crucial task in image and pixel (voxel) classification and regression in biomedical image modeling. In this work we present a machine learning based feature extraction scheme based on inception models for pixel classification tasks. We extract features under multi-scale and multi-layer schemes through convolutional operators. Layers of Fully Convolutional Network are later stacked on this feature extraction layers and trained end-to-end for the purpose of classification. We test our model on the DRIVE and STARE public data sets for the purpose of segmentation and centerline detection and it out performs most existing hand crafted or deterministic feature schemes found in literature. We achieve an average maximum Dice of 0.85 on the DRIVE data set which out performs the scores from the second human annotator of this data set. We also achieve an average maximum Dice of 0.85 and kappa of 0.84 on the STARE data set. Though these datasets are mainly 2-D we also propose ways of extending this feature extraction scheme to handle 3-D datasets.