Abstract Purpose To investigate the relationship between the Diffusion Kurtosis Imaging (DKI) parameters and conventional metrics provided by Diffusion-weighted imaging (DWI) in patients affected by ...Brain or Head and Neck (HN) cancer. Methods Ten patients affected by brain tumor and nine patients with HN tumor underwent a pre-treatment MR examination at 3 T. The largest tumor section was manually contoured by two expert neuroradiologists. The apparent diffusion coefficient (Dapp ) and apparent diffusional kurtosis (Kapp ) parameters were determined at the voxel level by using the DKI model, and compared to the apparent diffusion coefficient (ADC) and the tissue diffusion coefficient (Dmono ) obtained from mono-exponential fitting methods. The Akaike Information Criteria (AIC) was calculated to assess the quality of the fitting methods. Cross-correlations between all the variables were assessed using the Spearman rank test. Results Increased Kapp values were found in each lesion. All parameters were strongly related, in particular an inverse relationship emerged between median values of Kapp and Dapp /Dmono /ADC in both patient groups, while Dapp showed positive correlations with Dmono and ADC. From the analysis at the voxel level, significant inverse associations were found between Kapp and Dmono within the lesions, while a weak or moderate association emerged between Kapp and ADC or Dapp. Conclusions A significant association between the apparent diffusional kurtosis Kapp and the tissue diffusion coefficient Dmono emerged for both brain and HN tumors at 3 T, suggesting that both variables may consistently reflect deeper insight into the microstructural characteristics of tumors.
Highlights • The predictive role of IVIM-DWI on cervical nodal response to chemo-radiotherapy was investigated. • Pre- and mid-treatment IVIM-DWI correlated significantly with the status of lymph ...nodes. • D values at baseline and at mid-RT had greater diagnostic accuracy than ADC values. • Perfusion-related parameters showed potential to further improve the predictive power.
The differentiation between benign and malignant parotid lesions is crucial to defining the treatment plan, which highly depends on the tumor histology. We aimed to evaluate the role of MRI-based ...radiomics using both T2-weighted (T2-w) images and Apparent Diffusion Coefficient (ADC) maps in the differentiation of parotid lesions, in order to develop predictive models with an external validation cohort.
A sample of 69 untreated parotid lesions was evaluated retrospectively, including 37 benign (of which 13 were Warthin's tumors) and 32 malignant tumors. The patient population was divided into three groups: benign lesions (24 cases), Warthin's lesions (13 cases), and malignant lesions (32 cases), which were compared in pairs. First- and second-order features were derived for each lesion. Margins and contrast enhancement patterns (CE) were qualitatively assessed. The model with the final feature set was achieved using the support vector machine binary classification algorithm.
Models for discriminating between Warthin's and malignant tumors, benign and Warthin's tumors and benign and malignant tumors had an accuracy of 86.7%, 91.9% and 80.4%, respectively. After the feature selection process, four parameters for each model were used, including histogram-based features from ADC and T2-w images, shape-based features and types of margins and/or CE. Comparable accuracies were obtained after validation with the external cohort.
Radiomic analysis of ADC, T2-w images, and qualitative scores evaluating margins and CE allowed us to obtain good to excellent diagnostic accuracies in differentiating parotid lesions, which were confirmed with an external validation cohort.
Radiomic models outperform clinical data for outcome prediction in high-grade gliomas (HGG). However, lack of parameter standardization limits clinical applications. Many machine learning (ML) ...radiomic models employ single classifiers rather than ensemble learning, which is known to boost performance, and comparative analyses are lacking in the literature. We aimed to compare ML classifiers to predict clinically relevant tasks for HGG: overall survival (OS), isocitrate dehydrogenase (IDH) mutation, O-6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation, epidermal growth factor receptor vIII (EGFR) amplification, and Ki-67 expression, based on radiomic features from conventional and advanced magnetic resonance imaging (MRI). Our objective was to identify the best algorithm for each task. One hundred fifty-six adult patients with pathologic diagnosis of HGG were included. Three tumoral regions were manually segmented: contrast-enhancing tumor, necrosis, and non-enhancing tumor. Radiomic features were extracted with a custom version of Pyradiomics and selected through Boruta algorithm. A Grid Search algorithm was applied when computing ten times K-fold cross-validation (K=10) to get the highest mean and lowest spread of accuracy. Model performance was assessed as AUC-ROC curve mean values with 95% confidence intervals (CI). Extreme Gradient Boosting (xGB) obtained highest accuracy for OS (74,5%), Adaboost (AB) for IDH mutation (87.5%), MGMT methylation (70,8%), Ki-67 expression (86%), and EGFR amplification (81%). Ensemble classifiers showed the best performance across tasks. High-scoring radiomic features shed light on possible correlations between MRI and tumor histology.
This study aimed to develop a clinical-radiomic model based on radiomic features extracted from digital breast tomosynthesis (DBT) images and clinical factors that may help to discriminate between ...benign and malignant breast lesions.
A total of 150 patients were included in this study. DBT images acquired in the setting of a screening protocol were used. Lesions were delineated by two expert radiologists. Malignity was always confirmed by histopathological data. The data were randomly divided into training and validation set with an 80:20 ratio. A total of 58 radiomic features were extracted from each lesion using the LIFEx Software. Three different key methods of feature selection were implemented in Python: (1) K best (KB), (2) sequential (S), and (3) Random Forrest (RF). A model was therefore produced for each subset of seven variables using a machine-learning algorithm, which exploits the RF classification based on the Gini index.
All three clinical-radiomic models show significant differences (p < 0.05) between malignant and benign tumors. The area under the curve (AUC) values of the models obtained with three different feature selection methods were 0.72 0.64,0.80, 0.72 0.64,0.80 and 0.74 0.66,0.82 for KB, SFS, and RF, respectively.
The clinical-radiomic models developed by using radiomic features from DBT images showed a good discriminating power and hence may help radiologists in breast cancer tumor diagnoses already at the first screening.
Under therapeutic pressure aggressive tumors evolve rapidly. Herein, a luminal B/HER2-low breast cancer was tracked for >3 years during a total of 6 largely unsuccessful therapy lines, from adjuvant ...to advanced settings. Targeted next generation sequencing (NGS) of the primary lesion, two metastases and 14 blood drawings suggested a striking, unprecedented coexistence of three evolution modes: punctuated, branched and convergent. Punctuated evolution of the trunk was supported by
inheritance of a large set (19 distinct genes) of copy number alterations. Branched evolution was supported by the distribution of site-specific SNVs. Convergent evolution was characterized by a unique asynchronous expansion of three actionable (OncoKB level 3A) mutations at two consecutive ESR1 codons. Low or undetectable in all the sampled tumor tissues, ESR1 mutations expanded rapidly in blood during HER2/hormone double-blockade, and predicted life-threatening local progression at lung and liver metastatic foci. Dramatic clinical response to Fulvestrant (assigned off-label exclusively based on liquid biopsy) was associated with clearance of all 3 subclones and was in stark contrast to the poor therapeutic efficacy reported in large liquid biopsy-informed interventional trials. Altogether, deconvolution of the tumor phylogenetic tree, as shown herein, may help to customize treatment in breast cancers that rapidly develop refractoriness to multiple drugs.
Functional magnetic resonance imaging may provide several quantitative indices strictly related to distinctive tissue signatures with radiobiological relevance, such as tissue cellular density and ...vascular perfusion. The role of Intravoxel Incoherent Motion Diffusion Weighted Imaging (IVIM-DWI) and Dynamic Contrast-Enhanced (DCE) MRI in detecting/predicting radiation-induced volumetric changes of parotids both during and shortly after (chemo)radiotherapy of oropharyngeal squamous cell carcinoma (SCC) was explored.
Patients with locally advanced oropharyngeal SCC were accrued within a prospective study offering both IVIM-DWI and DCE-MRI at baseline; IVIM-DWI was repeated at the 10th fraction of treatment. Apparent diffusion coefficient (ADC), tissue diffusion coefficient D
, perfusion fraction f and perfusion-related diffusion coefficient D
were estimated both at baseline and during RT. Semi-quantitative and quantitative parameters, including the transfer constant K
, were calculated from DCE-MRI. Parotids were contoured on T2-weighted images at baseline, 10th fraction and 8th weeks after treatment end and the percent change of parotid volume between baseline/10th fr (∆Vol
) and baseline/8th wk. (∆Vol
) computed. Correlations among volumetric changes and patient-, treatment- and imaging-related features were investigated at univariate analysis (Spearman's Rho).
Eighty parotids (40 patients) were analyzed. Percent changes were 18.2 ± 10.7% and 31.3 ± 15.8% for ∆Vol
and ∆Vol
, respectively. Among baseline characteristics, ∆Vol
was correlated to body mass index, patient weight as well as the initial parotid volume. A weak correlation was present between parotid shrinkage after the first 2 weeks of treatment and dosimetric variables, while no association was found after radiotherapy. Percent changes of both ADC and D
at the 10th fraction were also correlated to ∆Vol
. Significant relationships were found between ∆Vol
and baseline DCE-MRI parameters.
Both IVIM-DWI and DCE-MRI can help to detect/predict early (during treatment) and shortly after treatment completion the parotid shrinkage. They may contribute to clarify the correlations between volumetric changes of parotid glands and patient-/treatment-related variables by assessing individual microcapillary perfusion and tissue diffusivity.