Evaluation of Complexity Measures for Deep Learning Generalization in Medical Image Analysis

by   Aleksandar Vakanski, et al.

The generalization performance of deep learning models for medical image analysis often decreases on images collected with different devices for data acquisition, device settings, or patient population. A better understanding of the generalization capacity on new images is crucial for clinicians' trustworthiness in deep learning. Although significant research efforts have been recently directed toward establishing generalization bounds and complexity measures, still, there is often a significant discrepancy between the predicted and actual generalization performance. As well, related large empirical studies have been primarily based on validation with general-purpose image datasets. This paper presents an empirical study that investigates the correlation between 25 complexity measures and the generalization abilities of supervised deep learning classifiers for breast ultrasound images. The results indicate that PAC-Bayes flatness-based and path norm-based measures produce the most consistent explanation for the combination of models and data. We also investigate the use of multi-task classification and segmentation approach for breast images, and report that such learning approach acts as an implicit regularizer and is conducive toward improved generalization.


Unified Representation Learning for Efficient Medical Image Analysis

Medical image analysis typically includes several tasks such as image en...

A Tour of Unsupervised Deep Learning for Medical Image Analysis

Interpretation of medical images for diagnosis and treatment of complex ...

Deep Learning for Computational Cytology: A Survey

Computational cytology is a critical, rapid-developing, yet challenging ...

Few-shot medical image classification with simple shape and texture text descriptors using vision-language models

In this work, we investigate the usefulness of vision-language models (V...

Towards understanding deep learning with the natural clustering prior

The prior knowledge (a.k.a. priors) integrated into the design of a mach...

MedAL: Deep Active Learning Sampling Method for Medical Image Analysis

Deep learning models have been successfully used in medical image analys...

Predicting Generalization in Deep Learning via Local Measures of Distortion

We study generalization in deep learning by appealing to complexity meas...

Code Repositories


Empirical study that reports the correlation between complexity measures and generalization performance by deep learning models on medical images

view repo

Please sign up or login with your details

Forgot password? Click here to reset