A novel Multi-Level feature selection method for radiomics

Wang, Ke; Yushkov, A. N.; Zhou, Jing; Long, Yong; Chen, Xianlai

doi:10.1016/j.aej.2022.10.069

“…LASSO exactly does this by shrinking the near zero coefficients to zero. However, LASSO does not consider features that are weakly correlated ( 31 ). Ridge regression on the other hand addresses this problem by not forcing the near zero coefficients to zero but penalizes the loss function by adding quadratic terms of coefficient values.…”

Section: Discussionmentioning

confidence: 99%

Comparing quantitative image parameters between animal and clinical CT-scanners: a translational phantom study analysis

Vellala,

Mogler,

Haag

et al. 2024

Front. Med.

0

View full text Add to dashboard Cite

PurposeThis study compares phantom-based variability of extracted radiomics features from scans on a photon counting CT (PCCT) and an experimental animal PET/CT-scanner (Albira II) to investigate the potential of radiomics for translation from animal models to human scans. While oncological basic research in animal PET/CT has allowed an intrinsic comparison between PET and CT, but no 1:1 translation to a human CT scanner due to resolution and noise limitations, Radiomics as a statistical and thus scale-independent method can potentially close the critical gap.MethodsTwo phantoms were scanned on a PCCT and animal PET/CT-scanner with different scan parameters and then the radiomics parameters were extracted. A Principal Component Analysis (PCA) was conducted. To overcome the limitation of a small dataset, a data augmentation technique was applied. A Ridge Classifier was trained and a Feature Importance- and Cluster analysis was performed.ResultsPCA and Cluster Analysis shows a clear differentiation between phantom types while emphasizing the comparability of both scanners. The Ridge Classifier exhibited a strong training performance with 93% accuracy, but faced challenges in generalization with a test accuracy of 62%.ConclusionThese results show that radiomics has great potential as a translational tool between animal models and human routine diagnostics, especially using the novel photon counting technique. This is another crucial step towards integration of radiomics analysis into clinical practice.

show abstract

“…Interestingly, it appears that in the presence of a high noise-to-signal ratio, conventional feature selection techniques outperform methods that are based on machine learning models. Future studies would benefit from evaluating alternative approaches, such as Coe-Thr-Lasso method, that facilitate a more holistic analysis of variable importance 47 .…”

Section: Discussionmentioning

confidence: 99%

A novel radiomics approach for predicting TACE outcomes in hepatocellular carcinoma patients using deep learning for multi-organ segmentation

Bartnik,

Krzyziński,

Bartczak

et al. 2024

Sci Rep

0

View full text Add to dashboard Cite

Transarterial chemoembolization (TACE) represent the standard of therapy for non-operative hepatocellular carcinoma (HCC), while prediction of long term treatment outcomes is a complex and multifactorial task. In this study, we present a novel machine learning approach utilizing radiomics features from multiple organ volumes of interest (VOIs) to predict TACE outcomes for 252 HCC patients. Unlike conventional radiomics models requiring laborious manual segmentation limited to tumoral regions, our approach captures information comprehensively across various VOIs using a fully automated, pretrained deep learning model applied to pre-TACE CT images. Evaluation of radiomics random survival forest models against clinical ones using Cox proportional hazard demonstrated comparable performance in predicting overall survival. However, radiomics outperformed clinical models in predicting progression-free survival. Explainable analysis highlighted the significance of non-tumoral VOI features, with their cumulative importance superior to features from the largest liver tumor. The proposed approach overcomes the limitations of manual VOI segmentation, requires no radiologist input and highlight the clinical relevance of features beyond tumor regions. Our findings suggest the potential of this radiomics models in predicting TACE outcomes, with possible implications for other clinical scenarios.

show abstract

“…Interestingly, it appears that in the presence of a high noise-to-signal ratio, conventional feature selection techniques outperform methods that are based on machine learning models. Future studies would bene t from evaluating alternative approaches, such as Coe-Thr-Lasso method, that facilitate a more holistic analysis of variable importance 43 .…”

Section: Discussionmentioning

confidence: 99%

A Novel Radiomics Approach for Predicting TACE Outcomes in Hepatocellular Carcinoma Patients Using Deep Learning for Multi-organ Segmentation

Bartnik,

Krzyziński,

Bartczak

et al. 2023

Preprint

0

View full text Add to dashboard Cite

Transarterial chemoembolization (TACE) represent the standard of therapy for non-operative hepatocellular carcinoma (HCC), while prediction of long term treatment outcomes is a complex and multifactorial task. In this study, we present a novel machine learning approach utilizing radiomics features from multiple organ volumes of interest (VOIs) to predict TACE outcomes for 252 HCC patients. Unlike conventional radiomics models requiring laborious manual segmentation limited to tumoral regions, our approach captures information comprehensively across various VOIs using a fully automated, pretrained deep learning model applied to pre-TACE CT images. Evaluation of radiomics random survival forest models against clinical ones using Cox proportional hazard demonstrated comparable performance in predicting overall survival. However, radiomics outperformed clinical models in predicting progression-free survival. Explainable analysis highlighted the significance of non-tumoral VOI features, with their cumulative importance superior to features from the largest liver tumor. The proposed approach overcomes the limitations of manual VOI segmentation, requires no radiologist input and highlight the clinical relevance of features beyond tumor regions. Our findings suggest the potential of this radiomics models in predicting TACE outcomes, with possible implications for other clinical scenarios.

show abstract

A novel Multi-Level feature selection method for radiomics

Cited by 9 publications

References 28 publications

Comparing quantitative image parameters between animal and clinical CT-scanners: a translational phantom study analysis

Comparing quantitative image parameters between animal and clinical CT-scanners: a translational phantom study analysis

A novel radiomics approach for predicting TACE outcomes in hepatocellular carcinoma patients using deep learning for multi-organ segmentation

A Novel Radiomics Approach for Predicting TACE Outcomes in Hepatocellular Carcinoma Patients Using Deep Learning for Multi-organ Segmentation

Contact Info

Product

Resources

About