Improve Global Glomerulosclerosis Classification with Imbalanced Data using CircleMix Augmentation

01/16/2021
by   Yuzhe Lu, et al.
0

The classification of glomerular lesions is a routine and essential task in renal pathology. Recently, machine learning approaches, especially deep learning algorithms, have been used to perform computer-aided lesion characterization of glomeruli. However, one major challenge of developing such methods is the naturally imbalanced distribution of different lesions. In this paper, we propose CircleMix, a novel data augmentation technique, to improve the accuracy of classifying globally sclerotic glomeruli with a hierarchical learning strategy. Different from the recently proposed CutMix method, the CircleMix augmentation is optimized for the ball-shaped biomedical objects, such as glomeruli. 6,861 glomeruli with five classes (normal, periglomerular fibrosis, obsolescent glomerulosclerosis, solidified glomerulosclerosis, and disappearing glomerulosclerosis) were employed to develop and evaluate the proposed methods. From five-fold cross-validation, the proposed CircleMix augmentation achieved superior performance (Balanced Accuracy=73.0 with the EfficientNet-B0 baseline (Balanced Accuracy=69.4

READ FULL TEXT

page 2

page 4

research
08/01/2019

GANs 'N Lungs: improving pneumonia prediction

We propose a novel method to improve deep learning model performance on ...
research
01/26/2023

Experimenting with an Evaluation Framework for Imbalanced Data Learning (EFIDL)

Introduction Data imbalance is one of the crucial issues in big data ana...
research
01/07/2021

Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification

Although deep convolutional neural networks (DCNNs) have achieved signif...
research
03/10/2020

Computer Aided Diagnosis for Spitzoid lesions classification using Artificial Intelligence techniques

Spitzoid lesions may be largely categorized into Spitz Nevus, Atypical S...
research
08/29/2023

From SMOTE to Mixup for Deep Imbalanced Classification

Given imbalanced data, it is hard to train a good classifier using deep ...
research
07/13/2022

Efficient Augmentation for Imbalanced Deep Learning

Deep learning models memorize training data, which hurts their ability t...
research
10/24/2022

GradMix for nuclei segmentation and classification in imbalanced pathology image datasets

An automated segmentation and classification of nuclei is an essential t...

Please sign up or login with your details

Forgot password? Click here to reset