Atlas-based segmentation using deep-learning

Abstract

Techniques for enhancing image segmentation with the integration of deep learning are disclosed herein. An example method for atlas-based segmentation using deep learning includes: applying a deep learning model to a subject image to identify an anatomical feature, registering an atlas image to the subject image, using the deep learning segmentation data to improve a registration result, generating a mapped atlas, and identifying the feature in the subject image using the mapped atlas. Another example method for training and use of a trained machine learning classifier, in an atlas-based segmentation process using deep learning, includes: applying a deep learning model to an atlas image, training a machine learning model classifier using data from applying the deep learning model, estimating structure labels of areas of the subject image, and defining structure labels by combining the estimated structure labels with labels produced from atlas-based segmentation on the subject image.

Description

[0001] priority claim [0002] This application claims the benefit of priority to US Application Serial No. 15 / 896,895, filed February 14, 2018, which is hereby incorporated by reference in its entirety. technical field [0003] Embodiments of the present disclosure relate generally to medical image and artificial intelligence processing techniques. In particular, the present disclosure relates to the use of deep learning models in image segmentation and structure labeling workflows. Background technique [0004] In radiotherapy or radiosurgery, treatment planning is usually performed based on medical images of a patient, and treatment planning requires delineation of target volumes and normal key organs in the medical images. Therefore, structural segmentation or contouring of various patient anatomy in medical images is a prerequisite and important step in radiotherapy treatment planning; if performed manually, contouring and segmentation is one of the most tedious and ti...

AI Technical Summary

Problems solved by technology

Second, different medical devices may use different imaging protocols and / or different contouring protocols for segmentation; therefore, a model trained using data from one device and manual delineation may not work well for data from a different device and may leading to deviations in segmentation results

Third, training deep learning models often requires deep expertise, so it may be difficult for individual medical users to retrain models on private datasets or adapt deep learning models to specific needs

Thus, although deep learning offers a variety of techniques that seem promising for identifying anatomical features in medical imaging, it has not yet been successfully adopted in many real-world settings

Images