ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging

by   Alessandro Fontanella, et al.

In some medical imaging tasks and other settings where only small parts of the image are informative for the classification task, traditional CNNs can sometimes struggle to generalise. Manually annotated Regions of Interest (ROI) are sometimes used to isolate the most informative parts of the image. However, these are expensive to collect and may vary significantly across annotators. To overcome these issues, we propose a framework that employs saliency maps to obtain soft spatial attention masks that modulate the image features at different scales. We refer to our method as Adversarial Counterfactual Attention (ACAT). ACAT increases the baseline classification accuracy of lesions in brain CT scans from 71.39 findings in lung CT scans from 67.71 competing methods. We investigate the best way to generate the saliency maps employed in our architecture and propose a way to obtain them from adversarially generated counterfactual images. They are able to isolate the area of interest in brain and lung CT scans without using any manual annotations. In the task of localising the lesion location out of 6 possible regions, they obtain a score of 65.05 of 61.29


page 4

page 5

page 8

page 14

page 15


Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention

Lesion detection from computed tomography (CT) scans is challenging comp...

MosMedData: Chest CT Scans With COVID-19 Related Findings Dataset

This dataset contains anonymised human lung computed tomography (CT) sca...

Survey of the Detection and Classification of Pulmonary Lesions via CT and X-Ray

In recent years, the prevalence of several pulmonary diseases, especiall...

Class-Aware Adversarial Lung Nodule Synthesis in CT Images

Though large-scale datasets are essential for training deep learning sys...

Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification

Mammogram benign or malignant classification with only image-level label...

GAN-based Medical Image Small Region Forgery Detection via a Two-Stage Cascade Framework

Using generative adversarial network (GAN)<cit.> for data enhancement of...

Explaining the Black-box Smoothly- A Counterfactual Approach

We propose a BlackBox Counterfactual Explainer that is explicitly develo...

Please sign up or login with your details

Forgot password? Click here to reset