A Structural Causal Model for MR Images of Multiple Sclerosis

Reinhold, Jacob C.; Carass, Aaron; Prince, Jerry L.

doi:10.1007/978-3-030-87240-3_75

Cited by 17 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Open Sci. 9: 220638 such as medical imaging [14][15][16] and pharmacology [2]. In this section, we will elaborate on how causality can be used for improving medical decision-making.…”

Section: Why Should We Consider a Causal Framework In Healthcare?mentioning

confidence: 99%

“…CI has made several contributions over the last few decades to fields such as social sciences, econometrics, epidemiology and aetiology [ 4 , 5 ], and it has recently spread to other healthcare fields such as medical imaging [ 14 – 16 ] and pharmacology [ 2 ]. In this section, we will elaborate on how causality can be used for improving medical decision-making.…”

Section: Why Should We Consider a Causal Framework In Healthcare?mentioning

confidence: 99%

“…Aglietti et al [ 98 ] evaluate their method with using a model of the causal effect of statin drugs on the levels of prostate specific antigen [ 100 ] while Pawlowski et al [ 15 ] and Wang et al [ 101 ] model the data generation process of the MRI images of the brain. Reinhold et al [ 102 ] extend Pawlowski et al [ 15 ] by adding pathological information about multiple sclerosis lesions.…”

Section: Research Directions In Causal Machine Learningmentioning

confidence: 99%

See 2 more Smart Citations

Causal machine learning for healthcare and precision medicine

et al. 2022

View full text Add to dashboard Cite

Causal machine learning (CML) has experienced increasing popularity in healthcare. Beyond the inherent capabilities of adding domain knowledge into learning systems, CML provides a complete toolset for investigating how a system would react to an intervention (e.g. outcome given a treatment). Quantifying effects of interventions allows actionable decisions to be made while maintaining robustness in the presence of confounders. Here, we explore how causal inference can be incorporated into different aspects of clinical decision support systems by using recent advances in machine learning. Throughout this paper, we use Alzheimer’s disease to create examples for illustrating how CML can be advantageous in clinical scenarios. Furthermore, we discuss important challenges present in healthcare applications such as processing high-dimensional and unstructured data, generalization to out-of-distribution samples and temporal relationships, that despite the great effort from the research community remain to be solved. Finally, we review lines of research within causal representation learning, causal discovery and causal reasoning which offer the potential towards addressing the aforementioned challenges.

show abstract

“…Open Sci. 9: 220638 such as medical imaging [14][15][16] and pharmacology [2]. In this section, we will elaborate on how causality can be used for improving medical decision-making.…”

Section: Why Should We Consider a Causal Framework In Healthcare?mentioning

confidence: 99%

Section: Why Should We Consider a Causal Framework In Healthcare?mentioning

confidence: 99%

Section: Research Directions In Causal Machine Learningmentioning

confidence: 99%

See 1 more Smart Citation

Causal machine learning for healthcare and precision medicine

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Causality in Medical Image Analysis: Recently, causality receives increasing attention in the context of medical image analysis [2]. Reinhold et al [29] use causal ideas to generate MRI images with a Deep Structural Causal Model [25]. Lenis et al [17] use the concept of counterfactuals to analyze and interpret medical image classifiers.…”

Section: Related Workmentioning

confidence: 99%

CaRTS: Causality-driven Robot Tool Segmentation from Vision and Kinematics Data

Ding¹,

Jin-tan²,

Kazanzides³

et al. 2022

Preprint

View full text Add to dashboard Cite

Vision-based segmentation of the robotic tool during robotassisted surgery enables downstream applications, such as augmented reality feedback, while allowing for inaccuracies in robot kinematics. With the introduction of deep learning, many methods were presented to solve instrument segmentation directly and solely from images. While these approaches made remarkable progress on benchmark datasets, fundamental challenges pertaining to their robustness remain. We present CaRTS, a causality-driven robot tool segmentation algorithm, that is designed based on a complementary causal model of the robot tool segmentation task. Rather than directly inferring segmentation masks from observed images, CaRTS iteratively aligns tool models with image observations by updating the initially incorrect robot kinematic parameters through forward kinematics and differentiable rendering to optimize image feature similarity end-to-end. We benchmark CaRTS with competing techniques on both synthetic as well as real data from the dVRK, generated in precisely controlled scenarios to allow for counterfactual synthesis.On training-domain test data, CaRTS achieves a Dice score of 93.4 that is preserved well (Dice score of 91.8) when tested on counterfactually altered test data, exhibiting low brightness, smoke, blood, and altered background patterns. This compares favorably to Dice scores of 95.0 and 62.8, respectively, of a purely image-based method trained and tested on the same data. Future work will involve accelerating CaRTS to achieve video framerate and estimating the impact occlusion has in practice. Despite these limitations, our results are promising: In addition to achieving high segmentation accuracy, CaRTS provides estimates of the true robot kinematics, which may benefit applications such as force estimation.

show abstract

“…Interventions empower counterfactuals that enable imagined spaces [181,195]. They are potentially vital in medical applications [99,238,258] to answer questions such as, what would be the evolution of a damaged lung if the patient had followed a different treatment? What would happen to a human lung if the treatment only consisted of clinical trials on non-human primates and mice?.…”

Section: Ai Learning Principles With Emphasis In Lung Analysismentioning

confidence: 99%

Tuberculosis Lesions in CT Images Inferred using 3D-CNN and Multi-Task Learning

Gordaliza

Vaquero

Sharpe

et al. 2019

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

View full text Add to dashboard Cite

Author contributions: Pedro M. Gordaliza was responsible for conception of the study and the design of the experimental framework, software development, data analysis, writing, editing and reviewing the paper. A.M.B and J.J.V contribute to the conception of the study and interpretation of the results. S.S. provided the CT data and contributed to the revision of the manuscript. All authors were responsible for writing, editing and reviewing the paper.Contribution completely included in Chapter 2.

show abstract

A Structural Causal Model for MR Images of Multiple Sclerosis

Cited by 17 publications

References 14 publications

Causal machine learning for healthcare and precision medicine

Causal machine learning for healthcare and precision medicine

CaRTS: Causality-driven Robot Tool Segmentation from Vision and Kinematics Data

Tuberculosis Lesions in CT Images Inferred using 3D-CNN and Multi-Task Learning

Contact Info

Product

Resources

About