Vessel-CAPTCHA: an efficient learning framework for vessel annotation and segmentation

by   Vien Ngoc Dang, et al.

The use of deep learning techniques for 3D brain vessel image segmentation has not been as widespread as for the segmentation of other organs and tissues. This can be explained by two factors. First, deep learning techniques tend to show poor performances at the segmentation of relatively small objects compared to the size of the full image. Second, due to the complexity of vascular trees and the small size of vessels, it is challenging to obtain the amount of annotated training data typically needed by deep learning methods. To address these problems, we propose a novel annotation-efficient deep learning vessel segmentation framework. The framework avoids pixel-wise annotations, only requiring patch-level labels to discriminate between vessel and non-vessel 2D patches in the training set, in a setup similar to the CAPTCHAs used to differentiate humans from bots in web applications. The user-provided annotations are used for two tasks: 1) to automatically generate pixel-wise labels for vessels and background in each patch, which are used to train a segmentation network, and 2) to train a classifier network. The classifier network allows to generate additional weak patch labels, further reducing the annotation burden, and it acts as a noise filter for poor quality images. We use this framework for the segmentation of the cerebrovascular tree in Time-of-Flight angiography (TOF) and Susceptibility-Weighted Images (SWI). The results show that the framework achieves state-of-the-art accuracy, while reducing the annotation time by up to 80 segmentation methods using pixel-wise labels for training


page 5

page 7

page 10

page 12

page 14

page 15

page 16


A multi-task U-net for segmentation with lazy labels

The need for labour intensive pixel-wise annotation is a major limitatio...

A Simplified Approach to Deep Learning for Image Segmentation

Leaping into the rapidly developing world of deep learning is an excitin...

Embracing Annotation Efficient Learning (AEL) for Digital Pathology and Natural Images

Jitendra Malik once said, "Supervision is the opium of the AI researcher...

Learning with less labels in Digital Pathology via Scribble Supervision from natural images

A critical challenge of training deep learning models in the Digital Pat...

Effects of annotation granularity in deep learning models for histopathological images

Pathological is crucial to cancer diagnosis. Usually, Pathologists draw ...

Learning under Distributed Weak Supervision

The availability of training data for supervision is a frequently encoun...

Efficient Annotation of Medieval Charters

Diplomatics, the analysis of medieval charters, is a major field of rese...

Please sign up or login with your details

Forgot password? Click here to reset