Radiomics for clinical decision support in radiation oncology

Hippocampal functional imaging-derived radiomics features for diagnosing cognitively impaired patients with Parkinson's disease

PURPOSE

The aim of this retrospective study was to investigate whether radiomics features derived from hippocampal functional imaging can effectively differentiate cognitively impaired patients from cognitively preserved patients with Parkinson's disease (PD).

METHODS

The study included a total of 89 clinically definite PD patients, comprising 55 who werecognitively impaired and 34 who were cognitively preserved. All participants underwent functional magnetic resonance imaging and clinical assessments. Preprocessed functional data were utilized to derive the amplitude of the low-frequency fluctuations (ALFF), regional homogeneity (ReHo), voxel-mirrored homotopic connectivity (VMHC), and degree centrality (DC). A standardized set of radiomics features was subsequently extracted from the bilateral hippocampi, resulting in a total of 819 features. Following feature selection, the radiomics score (rad-score) and logistic regression (LR) models were trained. Additionally, the Shapley additive explanations (SHAP) algorithm was employed to elucidate and interpret the predictions made by the LR models. Finally, the relationships between the radiomics features derived from hippocampal functional imaging and the scores of the clinical measures were explored to assess their clinical significance.

RESULTS

The rad-score and LR algorithm models constructed using a combination of wavelet features extracted from ReHo and VMHC data exhibited superior classification efficiency. These models demonstrated exceptional accuracy, sensitivity, and specificity in distinguishing cognitively impaired PD patients (CI-PD) from cognitively preserved PD (CP-PD) patients, with values of 0.889, 0.900, and 0.882, respectively. Furthermore, SHAP values indicated that wavelet features derived from ReHo and VMHC were critical for classifying CI-PD patients. Importantly, our findings revealed significant associations between radiomics wavelet features and scores on the Hamilton Anxiety Scale, Non-Motor Symptom Scale, and Montreal Cognitive Assessment in CI-PD patients (P < 0.05, with Bonferroni correction).

CONCLUSIONS

Our novel rad-score model and LR model, which utilize radiomics features derived from hippocampal functional imaging, have demonstrated their value in diagnosing CI-PDpatients. These models can enhance the accuracy and efficiency of functional MRI diagnosis, suggesting potential clinical applications.

CLINICAL TRIAL NUMBER

Not applicable.

Predictive value of CT radiomics and inflammatory markers for pulmonary adenocarcinoma spread through air spaces

OBJECTIVES

To evaluate the predictive value of combining CT radiomics features and inflammatory markers for the preoperative prediction of spread through air spaces (STAS) in pulmonary adenocarcinoma.

METHODS

In this retrospective study, we analyzed data from 256 patients diagnosed with pulmonary adenocarcinoma between 2021 and 2023. Patients were categorized into two groups based on the presence (n = 115) or absence (n = 141) of STAS, as confirmed by histopathological examination. CT imaging data and routine blood test results, including inflammatory markers, were collected. A validation cohort of 233 patients was included for external validation. Statistical analyses, including univariate and multivariate logistic regression, were performed to identify independent predictors of STAS. Model performance was assessed using Receiver Operating Characteristic curve analysis.

RESULTS

Key CT radiomics features, such as density, satellite lesions, irregular shape, spiculation, vascular convergence, and the vacuole sign, were significantly associated with STAS. Among inflammatory markers, a lower lymphocyte-to-monocyte ratio (LMR) and higher neutrophil-to-lymphocyte (NLR) and platelet-to-lymphocyte ratios (PLR) were predictive of STAS. The combined predictive model, integrating CT radiomics and inflammatory markers, demonstrated a high discriminatory ability, achieving an area under the curve of 0.915, which was externally validated with an AUC of 0.847.

CONCLUSIONS

The combination of CT radiomics and inflammatory markers provides an effective, non-invasive preoperative tool for predicting STAS in pulmonary adenocarcinoma, aiding in early prognostication and treatment planning.

Study of prediction model for high-grade meningioma using fractal geometry combined with radiological features

PURPOSE

To establish a prediction model combining fractal geometry and radiological features, which consider the complexity of tumour morphology advancing beyond the limitations of previous models.

METHODS

A total of 227 patients at the First Affiliated Hospital of Harbin Medical University from July 2021 to November 2023 were included. Fractal geometry was calculated and the radiomics features were extracted from regions of interest (ROIs). Weighted Gene Co-Expression Network Analysis (WGCNA) was employed for preliminary screening to identify those that were significantly associated with high-grade meningioma. In the training cohort, the least absolute shrinkage and selection operator (LASSO) regression was employed for further screening the radiomics features. Area under curve (AUC) was to evaluate models' performance.

RESULTS

In entire patient cohort, low-grade meningiomas had significantly lower fractal dimensions (P = 0.01), while high-grade meningiomas had higher lacunarity (P = 0.049). Fractal dimension (OR 6.8, 95% CI 1.49-36.51, P = 0.017), lacunarity (OR 3.7, 95% CI 1.36-11.75, P = 0.014), and Rscore (OR 2.8, 95% CI 1.55-5.75, P = 0.002) were independent risk factors for high-grade meningiomas. The final results demonstrated that the "fractal geometry + radiological features (semantic features + radiomics features)" model exhibited the most optimal performance in predicting high-grade meningioma, with an AUC of 0.854 in the training cohort and 0.757 in the validation cohort.

CONCLUSION

Significant differences in fractal dimension and lacunarity exist between high-grade and low-grade meningiomas, which can be potential predictive factors. The developed predictive model demonstrated good performance in predicting high-grade meningiomas.

Advancing ischemic stroke diagnosis and clinical outcome prediction using improved ensemble techniques in DSC-PWI radiomics

Ischemic stroke is a leading global cause of death and disability and is expected to rise in the future. The present diagnostic techniques, like CT and MRI, have some limitations in distinguishing acute from chronic ischemia and in early ischemia detection. This study investigates the function of ensemble models based on the dynamic radiomics features (DRF) from the dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) ischemic stroke diagnosis, neurological impairment assessment, and modified Rankin Scale (mRS) outcome prediction). DRF is extracted from the 3D images, features are selected, and dimensionality is reduced. After that, ensemble models are applied. Two model structures were developed: a voting classifier with 6 bagging classifiers and a stacking classifier based on 4 bagging classifiers. The ensemble models were evaluated on three core tasks. The Stacking_ens_LR model performed best for ischemic stroke detection, the LR Bagging model for NIH Stroke Scale (NIHSS) prediction, and the NB Bagging model for outcome prediction. These outcomes illustrate the strength of ensemble models. The work showcases the role of ensemble models and DRF in the stroke management process.