Published on Wed Jun 26 2019

Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentations

Reuben R Shamir, Yuval Duchin, Jinyoung Kim, Guillermo Sapiro, Noam Harel

Overlapping measures are often utilized to quantify the similarity between two binary regions. Modern segmentation algorithms output a probabilities or confidence map with continuous values in the zero-to-one interval. These binary overlapping measures are biased to structure size. Addressing these challenges is the objective of this work.

0
0
0
Abstract

Objective: Overlapping measures are often utilized to quantify the similarity between two binary regions. However, modern segmentation algorithms output a probability or confidence map with continuous values in the zero-to-one interval. Moreover, these binary overlapping measures are biased to structure size. Addressing these challenges is the objective of this work. Methods: We extend the definition of the classical Dice coefficient (DC) overlap to facilitate the direct comparison of a ground truth binary image with a probabilistic map. We call the extended method continuous Dice coefficient (cDC) and show that 1) cDC is less or equal to 1 and cDC = 1 if-and-only-if the structures overlap is complete, and, 2) cDC is monotonically decreasing with the amount of overlap. We compare the classical DC and the cDC in a simulation of partial volume effects that incorporates segmentations of common targets for deep-brainstimulation. Lastly, we investigate the cDC for an automatic segmentation of the subthalamic-nucleus. Results: Partial volume effect simulation on thalamus (large structure) resulted with DC and cDC averages (SD) of 0.98 (0.006) and 0.99 (0.001), respectively. For subthalamic-nucleus (small structure) DC and cDC were 0.86 (0.025) and 0.97 (0.006), respectively. The DC and cDC for automatic STN segmentation were 0.66 and 0.80, respectively. Conclusion: The cDC is well defined for probabilistic segmentation, less biased to structure size and more robust to partial volume effects in comparison to DC. Significance: The proposed method facilitates a better evaluation of segmentation algorithms. As a better measurement tool, it opens the door for the development of better segmentation methods.

Mon Mar 11 2019
Computer Vision
Joint inference on structural and diffusion MRI for sequence-adaptive Bayesian segmentation of thalamic nuclei with probabilistic atlases
Some brain structures (e.g.,globus pallidus, thalamus and its nuclei) can be extracted more accurately by combining the two modalities. Using a recently published atlas derived from histology, we apply our method to thalamic nuclei segmentation on two datasets.
0
0
0
Fri Jul 27 2018
Computer Vision
A multi-contrast MRI approach to thalamus segmentation
accurate delineation of grey matter thalamic subregions is of the most clinical importance. Thalamic alterations are relevant to many neurological disorders including Alzheimer's, Parkinson's and multiple sclerosis. MRI is highly appropriate for structural segmentation as it provides different views of the anatomy from a single scan.
0
0
0
Mon Apr 01 2019
Computer Vision
Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge
Quantification of cerebral white matter hyperintensities (WMH) is of key importance in many neurological research studies. Automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their method on a standardized multi-center/-scanner image dataset.
0
0
0
Thu Jul 18 2019
Machine Learning
Exploiting bilateral symmetry in brain lesion segmentation
Brain lesions have a high degree of variability in terms of location, size, intensity and form, making automatic segmentation difficult. We propose an improvement to existing segmentation methods by exploiting the bilateral quasi-symmetry of healthy brains.
0
0
0
Thu Apr 19 2018
Computer Vision
Inherent Brain Segmentation Quality Control from Fully ConvNet Monte Carlo Sampling
We introduce inherent measures for effective quality control of brain segmentation based on a Bayesian fully convolutional neural network. Monte Carlo samples from the posterior distribution are generated using dropout at test time.
0
0
0
Wed Sep 16 2020
Computer Vision
Hierarchical brain parcellation with uncertainty
Brain parcellation methods tend to ignore this structure and treat labels as if they are flat. We introduce a hierarchically-aware brain parcellation method that works by predicting the decisions at each branch in the label tree. Our method exceeds the performance of flat uncertainty methods.
1
10
30