Enforcing temporal consistency in Deep Learning segmentation of brain MR images

by   Malav Bateriwala, et al.

Longitudinal analysis has great potential to reveal developmental trajectories and monitor disease progression in medical imaging. This process relies on consistent and robust joint 4D segmentation. Traditional techniques are dependent on the similarity of images over time and the use of subject-specific priors to reduce random variation and improve the robustness and sensitivity of the overall longitudinal analysis. This is however slow and computationally intensive as subject-specific templates need to be rebuilt every time. The focus of this work to accelerate this analysis with the use of deep learning. The proposed approach is based on deep CNNs and incorporates semantic segmentation and provides a longitudinal relationship for the same subject. The proposed approach is based on deep CNNs and incorporates semantic segmentation and provides a longitudinal relationship for the same subject. The state of art using 3D patches as inputs to modified Unet provides results around 0.91 ± 0.5 Dice and using multi-view atlas in CNNs provide around the same results. In this work, different models are explored, each offers better accuracy and fast results while increasing the segmentation quality. These methods are evaluated on 135 scans from the EADC-ADNI Harmonized Hippocampus Protocol. Proposed CNN based segmentation approaches demonstrate how 2D segmentation using prior slices can provide similar results to 3D segmentation while maintaining good continuity in the 3D dimension and improved speed. Just using 2D modified sagittal slices provide us a better Dice and longitudinal analysis for a given subject. For the ADNI dataset, using the simple UNet CNN technique gives us 0.84 ± 0.5 and while using modified CNN techniques on the same input yields 0.89 ± 0.5. Rate of atrophy and RMS error are calculated for several test cases using various methods and analyzed.


A Longitudinal Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis

In this paper we propose a novel method for the segmentation of longitud...

Comparative Evaluation of 3D and 2D Deep Learning Techniques for Semantic Segmentation in CT Scans

Image segmentation plays a pivotal role in several medical-imaging appli...

A Comparison of Deep Learning Convolution Neural Networks for Liver Segmentation in Radial Turbo Spin Echo Images

Motion-robust 2D Radial Turbo Spin Echo (RADTSE) pulse sequence can prov...

How You Split Matters: Data Leakage and Subject Characteristics Studies in Longitudinal Brain MRI Analysis

Deep learning models have revolutionized the field of medical image anal...

PlasmoID: A dataset for Indonesian malaria parasite detection and segmentation in thin blood smear

Indonesia holds the second-highest-ranking country for the highest numbe...

Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems

Automatic segmentation methods based on deep learning have recently demo...

Segmentation of 3D Dental Images Using Deep Learning

3D image segmentation is a recent and crucial step in many medical analy...

Please sign up or login with your details

Forgot password? Click here to reset