Detecting Spurious Correlations With Sanity Tests for Artificial Intelligence Guided Radiology Systems

Mahmood, Usman; Shrestha, Robik; Bates, ‬David D. B.; Mannelli, Lorenzo; Corrias, Giuseppe; Erdi, Yusuf E.; Kanan, Christopher

doi:10.3389/fdgth.2021.671015

Cited by 9 publications

(6 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spurious correlation can affect the performance of deep neural networks and has been actively studied in computer vision [17,22,29] and in medical imaging [18,9].…”

Section: Resultsmentioning

confidence: 99%

Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification

Xia¹,

Sánchez²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Data augmentation has been widely used in deep learning to reduce over-fitting and improve the robustness of models. However, traditional data augmentation techniques, e.g., rotation, cropping, flipping, etc., do not consider semantic transformations, e.g., changing the age of a brain image. Previous works tried to achieve semantic augmentation by generating counterfactuals, but they focused on how to train deep generative models and randomly created counterfactuals with the generative models without considering which counterfactuals are most effective for improving downstream training. Different from these approaches, in this work, we propose a novel adversarial counterfactual augmentation scheme that aims to find the most effective counterfactuals to improve downstream tasks with a pre-trained generative model. Specifically, we construct an adversarial game where we update the input conditional factor of the generator and the downstream classifier with gradient backpropagation alternatively and iteratively. The key idea is to find conditional factors that can result in hard counterfactuals for the classifier. This can be viewed as finding the 'weakness' of the classifier and purposely forcing it to overcome its weakness via the generative model. To demonstrate the effectiveness of the proposed approach, we validate the method with the classification of Alzheimer's Disease (AD) as the downstream task based on a pre-trained brain ageing synthesis model. We show the proposed approach improves test accuracy and can alleviate spurious correlations. Code will be released upon acceptance.

show abstract

“…Spurious correlation can affect the performance of deep neural networks and has been actively studied in computer vision [17,22,29] and in medical imaging [18,9].…”

Section: Resultsmentioning

confidence: 99%

Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification

Xia¹,

Sánchez²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Including nonliver tissue increases the risk of learning to correlate features unrelated to the target task with the class labels. As a result, systems presumed to be working would fail to generalize when used clinically, or they would appear to be working, but for the wrong reasons [55]. In addition to stricter quality control standards and reporting criteria for training datasets, we identify the need for medical institutions' to acceptance test or evaluate AI systems before they are used on patients.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning and Domain-Specific Knowledge to Segment the Liver from Synthetic Dual Energy CT Iodine Scans

et al. 2022

Self Cite

View full text Add to dashboard Cite

We map single energy CT (SECT) scans to synthetic dual-energy CT (synth-DECT) material density iodine (MDI) scans using deep learning (DL) and demonstrate their value for liver segmentation. A 2D pix2pix (P2P) network was trained on 100 abdominal DECT scans to infer synth-DECT MDI scans from SECT scans. The source and target domain were paired with DECT monochromatic 70 keV and MDI scans. The trained P2P algorithm then transformed 140 public SECT scans to synth-DECT scans. We split 131 scans into 60% train, 20% tune, and 20% held-out test to train four existing liver segmentation frameworks. The remaining nine low-dose SECT scans tested system generalization. Segmentation accuracy was measured with the dice coefficient (DSC). The DSC per slice was computed to identify sources of error. With synth-DECT (and SECT) scans, an average DSC score of 0.93±0.06 (0.89±0.01) and 0.89±0.01 (0.81±0.02) was achieved on the held-out and generalization test sets. Synth-DECT-trained systems required less data to perform as well as SECT-trained systems. Low DSC scores were primarily observed around the scan margin or due to non-liver tissue or distortions within ground-truth annotations. In general, training with synth-DECT scans resulted in improved segmentation performance with less data.

show abstract

“…However, most of these tools are not yet ready for clinical deployment. It is of paramount importance that any AI-driven clinical tool undergo proper training and rigorous validation of its generalizability and robustness before being adopted into patient clinical care [15,[19][20][21].…”

Section: Ai In Ct and Mri For Oncological Imagingmentioning

confidence: 99%

“…Reproducibility assesses measurement uncertainty, which in measurement typically arises from multiple sources. It is critical that the results of AI systems are both reproducible and reliable to enable the development of personalized cancer care strategies [21,91,125].…”

Section: Bias In Ai Modelsmentioning

confidence: 99%

Artificial Intelligence in CT and MR Imaging for Oncological Applications

Paudyal

Shah

Akın

et al. 2023

Cancers

Self Cite

View full text Add to dashboard Cite

Cancer care increasingly relies on imaging for patient management. The two most common cross-sectional imaging modalities in oncology are computed tomography (CT) and magnetic resonance imaging (MRI), which provide high-resolution anatomic and physiological imaging. Herewith is a summary of recent applications of rapidly advancing artificial intelligence (AI) in CT and MRI oncological imaging that addresses the benefits and challenges of the resultant opportunities with examples. Major challenges remain, such as how best to integrate AI developments into clinical radiology practice, the vigorous assessment of quantitative CT and MR imaging data accuracy, and reliability for clinical utility and research integrity in oncology. Such challenges necessitate an evaluation of the robustness of imaging biomarkers to be included in AI developments, a culture of data sharing, and the cooperation of knowledgeable academics with vendor scientists and companies operating in radiology and oncology fields. Herein, we will illustrate a few challenges and solutions of these efforts using novel methods for synthesizing different contrast modality images, auto-segmentation, and image reconstruction with examples from lung CT as well as abdome, pelvis, and head and neck MRI. The imaging community must embrace the need for quantitative CT and MRI metrics beyond lesion size measurement. AI methods for the extraction and longitudinal tracking of imaging metrics from registered lesions and understanding the tumor environment will be invaluable for interpreting disease status and treatment efficacy. This is an exciting time to work together to move the imaging field forward with narrow AI-specific tasks. New AI developments using CT and MRI datasets will be used to improve the personalized management of cancer patients.

show abstract

Detecting Spurious Correlations With Sanity Tests for Artificial Intelligence Guided Radiology Systems

Cited by 9 publications

References 53 publications

Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification

Adversarial Counterfactual Augmentation: Application in Alzheimer's Disease Classification

Deep Learning and Domain-Specific Knowledge to Segment the Liver from Synthetic Dual Energy CT Iodine Scans

Artificial Intelligence in CT and MR Imaging for Oncological Applications

Contact Info

Product

Resources

About