Machine learning-based radiomics for amyotrophic lateral sclerosis diagnosis

Tafuri, Benedetta; Milella, Giammarco; Filardi, Marco; Giugno, Alessia; Zoccolella, Stefano; Tamburrino, Ludovica; Gnoni, Valentina; Urso, Daniele; De Blasi, Roberto; Nigro, Salvatore; Logroscino, Giancarlo

doi:10.1016/j.eswa.2023.122585

Cited by 4 publications

(2 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since high-dimensional data suffer from noise and redundant attributes that may weaken the performance of model training, multivariate logistic regression with the least absolute shrinkage and selection operator (LASSO) and Boruta algorithms with cross-validation were applied to reduce the high dimensionality of features and to select the radiomics features significantly associated with TLE ( 22 ). To discern crucial features from less significant ones, we initially utilized the Boruta feature selection algorithm to identify pertinent attributes within the training dataset.…”

Section: Methodsmentioning

confidence: 99%

Machine learning techniques based on 18F-FDG PET radiomics features of temporal regions for the classification of temporal lobe epilepsy patients from healthy controls

Liao,

Wu,

Jiang

et al. 2024

Front. Neurol.

View full text Add to dashboard Cite

BackgroundThis study aimed to investigate the clinical application of 18F-FDG PET radiomics features for temporal lobe epilepsy and to create PET radiomics-based machine learning models for differentiating temporal lobe epilepsy (TLE) patients from healthy controls.MethodsA total of 347 subjects who underwent 18F-FDG PET scans from March 2014 to January 2020 (234 TLE patients: 25.50 ± 8.89 years, 141 male patients and 93 female patients; and 113 controls: 27.59 ± 6.94 years, 48 male individuals and 65 female individuals) were allocated to the training (n = 248) and test (n = 99) sets. All 3D PET images were registered to the Montreal Neurological Institute template. PyRadiomics was used to extract radiomics features from the temporal regions segmented according to the Automated Anatomical Labeling (AAL) atlas. The least absolute shrinkage and selection operator (LASSO) and Boruta algorithms were applied to select the radiomics features significantly associated with TLE. Eleven machine-learning algorithms were used to establish models and to select the best model in the training set.ResultsThe final radiomics features (n = 7) used for model training were selected through the combinations of the LASSO and the Boruta algorithms with cross-validation. All data were randomly divided into a training set (n = 248) and a testing set (n = 99). Among 11 machine-learning algorithms, the logistic regression (AUC 0.984, F1-Score 0.959) model performed the best in the training set. Then, we deployed the corresponding online website version (https://wane199.shinyapps.io/TLE_Classification/), showing the details of the LR model for convenience. The AUCs of the tuned logistic regression model in the training and test sets were 0.981 and 0.957, respectively. Furthermore, the calibration curves demonstrated satisfactory alignment (visually assessed) for identifying the TLE patients.ConclusionThe radiomics model from temporal regions can be a potential method for distinguishing TLE. Machine learning-based diagnosis of TLE from preoperative FDG PET images could serve as a useful preoperative diagnostic tool.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine learning techniques based on 18F-FDG PET radiomics features of temporal regions for the classification of temporal lobe epilepsy patients from healthy controls

Liao,

Wu,

Jiang

et al. 2024

Front. Neurol.

View full text Add to dashboard Cite

show abstract

“…In a similar vein, clinical trials for drugs targeting specific proteins would ideally want to recruit patients whose symptoms aren’t driven by a copathology, or at least account for this copathology in stratification. While there has been some work showing radiomics features can be helpful for differential diagnosis in Parkinson’s disease 73 and amylotrophic lateral sclerosis, 74 there is little work exploring potential applications in identifying common copathologies in AD. Finally, radiomics analysis may provide opportunities for validation studies when used in combination with multimodal data where biologically relevant information such as ground truth histopathology ratings are available.…”

Section: The Promise Of Machine Learningmentioning

confidence: 99%