The Effect of the Loss on Generalization: Empirical Study on Synthetic Lung Nodule Data

08/10/2021
by   Vasileios Baltatzis, et al.
16

Convolutional Neural Networks (CNNs) are widely used for image classification in a variety of fields, including medical imaging. While most studies deploy cross-entropy as the loss function in such tasks, a growing number of approaches have turned to a family of contrastive learning-based losses. Even though performance metrics such as accuracy, sensitivity and specificity are regularly used for the evaluation of CNN classifiers, the features that these classifiers actually learn are rarely identified and their effect on the classification performance on out-of-distribution test samples is insufficiently explored. In this paper, motivated by the real-world task of lung nodule classification, we investigate the features that a CNN learns when trained and tested on different distributions of a synthetic dataset with controlled modes of variation. We show that different loss functions lead to different features being learned and consequently affect the generalization ability of the classifier on unseen data. This study provides some important insights into the design of deep learning solutions for medical imaging tasks.

READ FULL TEXT
research
11/21/2016

Deep Learning for the Classification of Lung Nodules

Deep learning, as a promising new area of machine learning, has attracte...
research
02/21/2018

Smooth Loss Functions for Deep Top-k Classification

The top-k error is a common measure of performance in machine learning a...
research
08/24/2019

Deriving a Quantitative Relationship Between Resolution and Human Classification Error

For machine learning perception problems, human-level classification per...
research
06/23/2022

A novel adversarial learning strategy for medical image classification

Deep learning (DL) techniques have been extensively utilized for medical...
research
03/21/2022

CNN Attention Guidance for Improved Orthopedics Radiographic Fracture Classification

Convolutional neural networks (CNNs) have gained significant popularity ...
research
07/06/2023

The Role of Subgroup Separability in Group-Fair Medical Image Classification

We investigate performance disparities in deep classifiers. We find that...
research
03/11/2019

Multi-Representational Learning for Offline Signature Verification using Multi-Loss Snapshot Ensemble of CNNs

Offline Signature Verification (OSV) is a challenging pattern recognitio...

Please sign up or login with your details

Forgot password? Click here to reset