An Analysis of the Influence of Transfer Learning When Measuring the Tortuosity of Blood Vessels

TL;DR

This paper investigates how transfer learning affects the measurement of blood vessel tortuosity in medical images, revealing potential biases and proposing data augmentation to improve downstream analysis accuracy.

Contribution

It demonstrates that pre-trained CNNs can introduce bias in tortuosity measurements and shows that data augmentation can mitigate these biases even if segmentation performance remains unchanged.

Findings

Pre-trained CNNs may produce biased tortuosity values.

Fine-tuning does not always improve tortuosity estimation.

Data augmentation helps reduce bias in measurements.

Abstract

Characterizing blood vessels in digital images is important for the diagnosis of many types of diseases as well as for assisting current researches regarding vascular systems. The automated analysis of blood vessels typically requires the identification, or segmentation, of the blood vessels in an image or a set of images, which is usually a challenging task. Convolutional Neural Networks (CNNs) have been shown to provide excellent results regarding the segmentation of blood vessels. One important aspect of CNNs is that they can be trained on large amounts of data and then be made available, for instance, in image processing software for wide use. The pre-trained CNNs can then be easily applied in downstream blood vessel characterization tasks such as the calculation of the length, tortuosity, or caliber of the blood vessels. Yet, it is still unclear if pre-trained CNNs can provide robust, unbiased, results on downstream tasks when applied to datasets that they were not trained on. Here, we focus on measuring the tortuosity of blood vessels and investigate to which extent CNNs may provide biased tortuosity values even after fine-tuning the network to the new dataset under study. We show that the tortuosity values obtained by a CNN trained from scratch on a dataset may not agree with those obtained by a fine-tuned network that was pre-trained on a dataset having different tortuosity statistics. In addition, we show that the improvement in segmentation performance when fine-tuning the network does not necessarily lead to a respective improvement on the estimation of the tortuosity. To mitigate the aforementioned issues, we propose the application of specific data augmentation techniques even in situations where they do not improve segmentation performance.