Universal Loss Reweighting to Balance Lesion Size Inequality in 3D Medical Image Segmentation

07/20/2020
by   Boris Shirokikh, et al.
0

Target imbalance affects the performance of recent deep learning methods in many medical image segmentation tasks. It is a twofold problem: class imbalance - positive class (lesion) size compared to negative class (non-lesion) size; lesion size imbalance - large lesions overshadows small ones (in the case of multiple lesions per image). While the former was addressed in multiple works, the latter lacks investigation. We propose a loss reweighting approach to increase the ability of the network to detect small lesions. During the learning process, we assign a weight to every image voxel. The assigned weights are inversely proportional to the lesion volume, thus smaller lesions get larger weights. We report the benefit from our method for well-known loss functions, including Dice Loss, Focal Loss, and Asymmetric Similarity Loss. Additionally, we compare our results with other reweighting techniques: Weighted Cross-Entropy and Generalized Dice Loss. Our experiments show that inverse weighting considerably increases the detection quality, while preserves the delineation quality on a state-of-the-art level. We publish a complete experimental pipeline for two publicly available datasets of CT images: LiTS and LUNA16 (https://github.com/neuro-ml/inverse_weighting). We also show results on a private database of MR images for the task of multiple brain metastases delineation.

READ FULL TEXT
research
02/08/2021

A Mixed Focal Loss Function for Handling Class Imbalanced Medical Image Segmentation

Automatic segmentation methods are an important advancement in medical i...
research
09/29/2020

Geometric Loss for Deep Multiple Sclerosis lesion Segmentation

Multiple sclerosis (MS) lesions occupy a small fraction of the brain vol...
research
03/30/2022

The impact of using voxel-level segmentation metrics on evaluating multifocal prostate cancer localisation

Dice similarity coefficient (DSC) and Hausdorff distance (HD) are widely...
research
03/15/2023

DeDA: Deep Directed Accumulator

Chronic active multiple sclerosis lesions, also termed as rim+ lesions, ...
research
09/13/2022

On the Optimal Combination of Cross-Entropy and Soft Dice Losses for Lesion Segmentation with Out-of-Distribution Robustness

We study the impact of different loss functions on lesion segmentation f...
research
01/26/2022

Joint Liver and Hepatic Lesion Segmentation using a Hybrid CNN with Transformer Layers

Deep learning-based segmentation of the liver and hepatic lesions therei...
research
06/25/2019

Learning a sparse database for patch-based medical image segmentation

We introduce a functional for the learning of an optimal database for pa...

Please sign up or login with your details

Forgot password? Click here to reset