Spark in the Dark: Evaluating Encoder-Decoder Pairs for COVID-19 CT's Semantic Segmentation

TL;DR

This paper presents the largest benchmark to date, evaluating 120 encoder-decoder architectures across five COVID-19 CT segmentation datasets using extensive cross-validation, aiming to standardize performance comparisons.

Contribution

It provides an extensive, standardized benchmark of multiple encoder-decoder pairs for COVID-19 CT segmentation, covering the largest number of architectures and datasets to date.

Findings

120 architectures evaluated

5 datasets used for validation

3,000 experiments conducted

Abstract

With the COVID-19 global pandemic, computerassisted diagnoses of medical images have gained a lot of attention, and robust methods of Semantic Segmentation of Computed Tomography (CT) turned highly desirable. Semantic Segmentation of CT is one of many research fields of automatic detection of Covid-19 and was widely explored since the Covid19 outbreak. In the robotic field, Semantic Segmentation of organs and CTs are widely used in robots developed for surgery tasks. As new methods and new datasets are proposed quickly, it becomes apparent the necessity of providing an extensive evaluation of those methods. To provide a standardized comparison of different architectures across multiple recently proposed datasets, we propose in this paper an extensive benchmark of multiple encoders and decoders with a total of 120 architectures evaluated in five datasets, with each dataset being validated through a five-fold cross-validation strategy, totaling 3.000 experiments. To the best of our knowledge, this is the largest evaluation in number of encoders, decoders, and datasets proposed in the field of Covid-19 CT segmentation.