ICAM-Reg: Interpretable Classification and Regression With Feature Attribution for Mapping Neurological Phenotypes in Individual Scans

Bass, Cher; Silva, Mariana da; Sudre, Carole H.; Williams, Logan Z. J.; Sousa, Helena Sofia; Tudosiu, Petru-Daniel; Alfaro-Almagro, Fidel; Fitzgibbon, Sean; Glasser, Matthew F.; Smith, Stephen M.

doi:10.1109/tmi.2022.3221890

Cited by 22 publications

(13 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since Varela et al showed that LA anatomy is a significant factor in prediction of AF recurrence post ablation ( Varela et al, 2017a ), the DL approach of the study should be extended to 3D LA images and simulations. Future work should also focus on using exclusively real patient LA data and investigating intrinsically interpretable DL models such as ICAM ( Bass et al, 2022 ).…”

Section: Discussionmentioning

confidence: 99%

Exploring interpretability in deep learning prediction of successful ablation therapy for atrial fibrillation

Ogbomo-Harmitt

Muffoletto²,

Zeidan³

et al. 2023

Front. Physiol.

View full text Add to dashboard Cite

Background: Radiofrequency catheter ablation (RFCA) therapy is the first-line treatment for atrial fibrillation (AF), the most common type of cardiac arrhythmia globally. However, the procedure currently has low success rates in dealing with persistent AF, with a reoccurrence rate of ∼50% post-ablation. Therefore, deep learning (DL) has increasingly been applied to improve RFCA treatment for AF. However, for a clinician to trust the prediction of a DL model, its decision process needs to be interpretable and have biomedical relevance.Aim: This study explores interpretability in DL prediction of successful RFCA therapy for AF and evaluates if pro-arrhythmogenic regions in the left atrium (LA) were used in its decision process.Methods: AF and its termination by RFCA have been simulated in MRI-derived 2D LA tissue models with segmented fibrotic regions (n = 187). Three ablation strategies were applied for each LA model: pulmonary vein isolation (PVI), fibrosis-based ablation (FIBRO) and a rotor-based ablation (ROTOR). The DL model was trained to predict the success of each RFCA strategy for each LA model. Three feature attribution (FA) map methods were then used to investigate interpretability of the DL model: GradCAM, Occlusions and LIME.Results: The developed DL model had an AUC (area under the receiver operating characteristic curve) of 0.78 ± 0.04 for predicting the success of the PVI strategy, 0.92 ± 0.02 for FIBRO and 0.77 ± 0.02 for ROTOR. GradCAM had the highest percentage of informative regions in the FA maps (62% for FIBRO and 71% for ROTOR) that coincided with the successful RFCA lesions known from the 2D LA simulations, but unseen by the DL model. Moreover, GradCAM had the smallest coincidence of informative regions of the FA maps with non-arrhythmogenic regions (25% for FIBRO and 27% for ROTOR).Conclusion: The most informative regions of the FA maps coincided with pro-arrhythmogenic regions, suggesting that the DL model leveraged structural features of MRI images to identify such regions and make its prediction. In the future, this technique could provide a clinician with a trustworthy decision support tool.

show abstract

Section: Discussionmentioning

confidence: 99%

Exploring interpretability in deep learning prediction of successful ablation therapy for atrial fibrillation

Ogbomo-Harmitt

Muffoletto²,

Zeidan³

et al. 2023

Front. Physiol.

View full text Add to dashboard Cite

show abstract

“…In recent time, approaches to simultaneous classification and feature attribution are being developed using a shared latent space of attributes with a classification layer: VA-GAN [ 148 ], ICAM [ 149 ]. These methods imply learning on the basis of generative networks being not always successful on a small data sample of medical tasks.…”

Section: Section 3 Utilizing Data Analysis and Machine Lear...mentioning

confidence: 99%

Diagnosis of Schizophrenia Based on the Data of Various Modalities: Biomarkers and Machine Learning Techniques (Review)

Sharaev¹,

Malashenkova²,

Maslennikova³

et al. 2022

Sovrem Tehnol Med

View full text Add to dashboard Cite

Schizophrenia is a socially significant mental disorder resulting frequently in severe forms of disability. Diagnosis, choice of treatment tactics, and rehabilitation in clinical psychiatry are mainly based on the assessment of behavioral patterns, socio-demographic data, and other investigations such as clinical observations and neuropsychological testing including examination of patients by the psychiatrist, self-reports, and questionnaires. In many respects, these data are subjective and therefore a large number of works have appeared in recent years devoted to the search for objective characteristics (indices, biomarkers) of the processes going on in the human body and reflected in the behavioral and psychoneurological patterns of patients. Such biomarkers are based on the results of instrumental and laboratory studies (neuroimaging, electro-physiological, biochemical, immunological, genetic, and others) and are successfully being used in neurosciences for understanding the mechanisms of the emergence and development of nervous system pathologies.

show abstract

“…For example, Bass, Silva, Sudre, et al . [19], [20] used a VAE-GAN [21], with separate content and attribute encodings, to disentangle class specific features of disease, from class irrelevant features of cortical shape variation, to map patterns of disease related brain atrophy in individuals with mild cognitive impairment (MCI) or Alzheimer’s disease (AD). Others models have sought to improve interpretability by incorporating confounding factors, such as age: for example, Ravi, Alexander, Oxtoby, et al .…”

Section: Introductionmentioning

confidence: 99%

Surface Generative Modelling of Neurodevelopmental Trajectories

Fawaz,

Masui,

Williams

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Cortical neurodevelopment is sensitive to disruption following preterm birth, with lasting impact on cognitive outcomes. The creation of generative models of neurodevelopment could aid clinicians in identifying at-risk subjects but is complicated by the degree of subject variability in cortical folding, and significant heterogeneity in the effect of preterm birth. In this work, we propose a graph convolutional generative adversarial network (GAN) and a training scheme to simulate neonatal cortical surface developmental trajectories. The proposed model is used to smoothly modify two cortical phenotypes: post-menstrual age at scan (PMA) and gestational age at birth (GA) on data from the developing Human Connectome Project (dHCP). The synthetic images were validated with an independently trained regression network, and compared against follow up scans, indicating that the model can realistically age individuals whilst preserving subject-specific cortical morphology. Deviation between simulated healthy scans, and preterm follow up scans generated a metric of individual atypicality, which improved prediction of 18-month cognitive outcome over GA alone.

show abstract

ICAM-Reg: Interpretable Classification and Regression With Feature Attribution for Mapping Neurological Phenotypes in Individual Scans

Cited by 22 publications

References 77 publications

Exploring interpretability in deep learning prediction of successful ablation therapy for atrial fibrillation

Exploring interpretability in deep learning prediction of successful ablation therapy for atrial fibrillation

Diagnosis of Schizophrenia Based on the Data of Various Modalities: Biomarkers and Machine Learning Techniques (Review)

Surface Generative Modelling of Neurodevelopmental Trajectories

Contact Info

Product

Resources

About