Enhancing Foreground Boundaries for Medical Image Segmentation

05/29/2020
by   Dong Yang, et al.
9

Object segmentation plays an important role in the modern medical image analysis, which benefits clinical study, disease diagnosis, and surgery planning. Given the various modalities of medical images, the automated or semi-automated segmentation approaches have been used to identify and parse organs, bones, tumors, and other regions-of-interest (ROI). However, these contemporary segmentation approaches tend to fail to predict the boundary areas of ROI, because of the fuzzy appearance contrast caused during the imaging procedure. To further improve the segmentation quality of boundary areas, we propose a boundary enhancement loss to enforce additional constraints on optimizing machine learning models. The proposed loss function is light-weighted and easy to implement without any pre- or post-processing. Our experimental results validate that our loss function are better than, or at least comparable to, other state-of-the-art loss functions in terms of segmentation accuracy.

READ FULL TEXT
03/23/2021

Roughness Index and Roughness Distance for Benchmarking Medical Segmentation

Medical image segmentation is one of the most challenging tasks in medic...
09/19/2019

Deep learning architectures for automated image segmentation

Image segmentation is widely used in a variety of computer vision tasks,...
10/22/2019

Penalizing small errors using an Adaptive Logarithmic Loss

Loss functions are error metrics that quantify the difference between a ...
07/28/2022

Extraction of Vascular Wall in Carotid Ultrasound via a Novel Boundary-Delineation Network

Ultrasound imaging plays an important role in the diagnosis of vascular ...
07/17/2020

Superpixel-Guided Label Softening for Medical Image Segmentation

Segmentation of objects of interest is one of the central tasks in medic...
11/16/2020

High-level Prior-based Loss Functions for Medical Image Segmentation: A Survey

Today, deep convolutional neural networks (CNNs) have demonstrated state...
04/11/2022

Segmentation Network with Compound Loss Function for Hydatidiform Mole Hydrops Lesion Recognition

Pathological morphology diagnosis is the standard diagnosis method of hy...