A Closer Look at Spatial-Slice Features Learning for COVID-19 Detection

TL;DR

This work tackles CT-based COVID-19 detection challenges arising from variable scan resolutions and many OOD slices by introducing SSFL++, an unsupervised spatial-slice feature learning framework that identifies RoIs and reduces redundancy by about 70%. Complementing SSFL++, Kernel-Density-based Slice Sampling (KDS) uses Kernel Density Estimation to select the most informative slices while preserving global sequence information, stabilizing training and inference for a 2D EfficientNet backbone. Through extensive experiments on the COVID-19-CT-DB dataset (DEF-AI-MIA CVPR 2024), the authors show that 2D CNNs with SSFL++ and KDS can achieve strong performance, even with limited data, and surpass baseline and heavier 3D approaches. The approach emphasizes data efficiency, explainability via ROI-focused processing, and potential generalizability to other CT-related tasks, offering a practical path for rapid, reliable CT-based diagnosis. All mathematical notation is presented in $...$ to ensure precise representation.

Abstract

Conventional Computed Tomography (CT) imaging recognition faces two significant challenges: (1) There is often considerable variability in the resolution and size of each CT scan, necessitating strict requirements for the input size and adaptability of models. (2) CT-scan contains large number of out-of-distribution (OOD) slices. The crucial features may only be present in specific spatial regions and slices of the entire CT scan. How can we effectively figure out where these are located? To deal with this, we introduce an enhanced Spatial-Slice Feature Learning (SSFL++) framework specifically designed for CT scan. It aim to filter out a OOD data within whole CT scan, enabling our to select crucial spatial-slice for analysis by reducing 70% redundancy totally. Meanwhile, we proposed Kernel-Density-based slice Sampling (KDS) method to improve the stability when training and inference stage, therefore speeding up the rate of convergence and boosting performance. As a result, the experiments demonstrate the promising performance of our model using a simple EfficientNet-2D (E2D) model, even with only 1% of the training data. The efficacy of our approach has been validated on the COVID-19-CT-DB datasets provided by the DEF-AI-MIA workshop, in conjunction with CVPR 2024. Our source code is available at https://github.com/ming053l/E2D

Figures (7)

• Figure 1: The brief illustration for SSFL++. It aim to reduce redundancy in spatial and slice dimension on whole CT-scan to improve model and data quality. (1)Left: original CT-scan. (2)Middle: after reduction at spatial. (3)Right: after reduction at slices.
• Figure 2: The illustration of spatial steps in proposed SSFL++.
• Figure 3: The illustration of slice steps in proposed SSFL++. The line graph in the bottom right corner represents the area of each slice in a CT scan. The blue area denotes OOD data that have been removed, while the red area represents the CT slices that have been selected.
• Figure 4: The GradCAM++ gradcam++ visualization before and after proposed SSFL++. By reducing redundancy on the spatial scale, we can implicitly enhance the visual effectiveness of Explainable AI, thereby facilitating clinical applications.
• Figure 5: The comparison between random sampling, systematic sampling, and the proposed KDS method is noteworthy. As illustrated, random sampling fails to uniformly sample CT slices of varying area sizes, tending to select larger areas while neglecting global information. This results in greater bias and randomness during training and inference. On the other hand, systematic sampling divides the area into equally lengthened sub-intervals before randomly selecting samples from them. Although this approach can capture global information, it is ineffective at sampling the most crucial CT slices. Our proposed KDS method combines the advantages of both methods without their drawbacks, achieving a better balance. KDS can implicitly improve data efficiency, thereby enhancing the model's few-shot capability.