Machine Learning and Radiomics Analysis for Tumor Budding Prediction in Colorectal Liver Metastases Magnetic Resonance Imaging Assessment DOI Creative Commons
Vincenza Granata, Roberta Fusco,

Maria Chiara Brunese

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(2), P. 152 - 152

Published: Jan. 9, 2024

Purpose: We aimed to assess the efficacy of machine learning and radiomics analysis using magnetic resonance imaging (MRI) with a hepatospecific contrast agent, in pre-surgical setting, predict tumor budding liver metastases. Methods: Patients MRI setting were retrospectively enrolled. Manual segmentation was made by means 3D Slicer image computing, 851 features extracted as median values PyRadiomics Python package. Balancing performed inter- intraclass correlation coefficients calculated between observer within reproducibility all features. A Wilcoxon–Mann–Whitney nonparametric test receiver operating characteristics (ROC) carried out. feature selection procedures performed. Linear non-logistic regression models (LRM NLRM) different learning-based classifiers including decision tree (DT), k-nearest neighbor (KNN) support vector (SVM) considered. Results: The internal training set included 49 patients 119 validation cohort consisted total 28 single lesion patients. best predictor classify original_glcm_Idn obtained T1-W VIBE sequence arterial phase an accuracy 84%; wavelet_LLH_firstorder_10Percentile portal 92%; wavelet_HHL_glcm_MaximumProbability hepatobiliary excretion 88%; wavelet_LLH_glcm_Imc1 T2-W SPACE sequences 88%. Considering linear analysis, statistically significant increase 96% weighted combination 13 radiomic from phase. Moreover, classifier KNN trained sequence, obtaining 95% AUC 0.96. reached 94%, sensitivity 86% specificity 95%. Conclusions: Machine are promising tools predicting budding. there compared feature.

Language: Английский

Combined Hepatocellular-Cholangiocarcinoma: What the Multidisciplinary Team Should Know DOI Creative Commons

Carmen Cutolo,

Federica Dell’Aversana, Roberta Fusco

et al.

Diagnostics, Journal Year: 2022, Volume and Issue: 12(4), P. 890 - 890

Published: April 2, 2022

Combined hepatocellular-cholangiocarcinoma (cHCC-CCA) is a rare type of primary liver malignancy. Among the risk factors, hepatitis B and C virus infections, cirrhosis, male gender are widely reported. The clinical appearance cHCC-CCA similar to that HCC iCCA it usually silent until advanced states, causing delay diagnosis. Diagnosis mainly based on histology from biopsies or surgical specimens. Correct pre-surgical diagnosis during imaging studies very problematic due heterogeneous characteristics lesion in imaging, with overlapping features CCA. predominant histological subtype within establishes findings. Therefore, this scenario, radiological findings characteristic show an overlap those Since cHCC-CCAs prevalent patients at high there these may mimic HCC, currently difficult see non-invasive HCC. Surgery only curative treatment HCC-CCA. role transplantation (LT) remains controversial, as ablative systemic therapies tumour. These lesions still remain challenging, both phase. pre-treatment essential, well identification prognostic factors could stratify recurrence most adequate therapy according patient characteristics.

Language: Английский

Citations

25
Machine Learning Approaches with Textural Features to Calculate Breast Density on Mammography DOI Creative Commons
Mario Sansone, Roberta Fusco, Francesca Grassi

et al.

Current Oncology, Journal Year: 2023, Volume and Issue: 30(1), P. 839 - 853

Published: Jan. 7, 2023

breast cancer (BC) is the world's most prevalent in female population, with 2.3 million new cases diagnosed worldwide 2020. The great efforts made to set screening campaigns, early detection programs, and increasingly targeted treatments led significant improvement patients' survival. Full-Field Digital Mammograph (FFDM) considered gold standard method for diagnosis of BC. From several previous studies, it has emerged that density (BD) a risk factor development BC, affecting periodicity plans present today at an international level.in this study, focus mammographic image processing techniques allow extraction indicators derived from textural patterns mammary parenchyma indicative BD factors.a total 168 patients were enrolled internal training test while 51 compose external validation cohort. Different Machine Learning (ML) have been employed classify breasts based on values tissue density. Textural features extracted only which train classifiers, thanks aid ML algorithms.the accuracy different tested classifiers varied between 74.15% 93.55%. best results reached by Support Vector (accuracy 93.55% percentage true positives negatives equal TPP = 94.44% TNP 92.31%). was not influenced choice selection approach. Considering cohort, SVM, as classifier 7 selected wrapper method, showed 0.95, sensitivity 0.96, specificity 0.90.our preliminary Radiomics analysis approach us objectively identify BD.

Language: Английский

Citations

16
Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence DOI Open Access
Vincenza Granata, Roberta Fusco, Sergio Venanzio Setola

et al.

Cancers, Journal Year: 2023, Volume and Issue: 15(2), P. 351 - 351

Published: Jan. 5, 2023

Pancreatic cancer (PC) is one of the deadliest cancers, and it responsible for a number deaths almost equal to its incidence. The high mortality rate correlated with several explanations; main late disease stage at which majority patients are diagnosed. Since surgical resection has been recognised as only curative treatment, PC diagnosis initial believed tool improve survival. Therefore, patient stratification according familial genetic risk creation screening protocol by using minimally invasive diagnostic tools would be appropriate. cystic neoplasms (PCNs) subsets lesions deserve special management avoid overtreatment. current programs based on annual employment magnetic resonance imaging cholangiopancreatography sequences (MR/MRCP) and/or endoscopic ultrasonography (EUS). For unfit MRI, computed tomography (CT) could proposed, although CT results in lower detection rates, compared small lesions. actual major limit incapacity detect characterize pancreatic intraepithelial neoplasia (PanIN) EUS MR/MRCP. possibility utilizing artificial intelligence models evaluate higher-risk favour these entities, more data needed support real utility applications field screening. motives, appropriate realize research settings.

Language: Английский

Citations

13
Machine learning and radiomics analysis by computed tomography in colorectal liver metastases patients for RAS mutational status prediction DOI
Vincenza Granata, Roberta Fusco, Sergio Venanzio Setola

et al.

La radiologia medica, Journal Year: 2024, Volume and Issue: 129(7), P. 957 - 966

Published: May 18, 2024

Language: Английский

Citations

5
Radiomics and machine learning analysis by computed tomography and magnetic resonance imaging in colorectal liver metastases prognostic assessment DOI
Vincenza Granata, Roberta Fusco, Federica De Muzio

et al.

La radiologia medica, Journal Year: 2023, Volume and Issue: 128(11), P. 1310 - 1332

Published: Sept. 11, 2023

Language: Английский

Citations

13
Radiomics in Lung Metastases: A Systematic Review DOI Open Access
Michela Gabelloni, Lorenzo Faggioni, Roberta Fusco

et al.

Journal of Personalized Medicine, Journal Year: 2023, Volume and Issue: 13(2), P. 225 - 225

Published: Jan. 27, 2023

Due to the rich vascularization and lymphatic drainage of pulmonary tissue, lung metastases (LM) are not uncommon in patients with cancer. Radiomics is an active research field aimed at extraction quantitative data from diagnostic images, which can serve as useful imaging biomarkers for a more effective, personalized patient care. Our purpose illustrate current applications, strengths weaknesses radiomics lesion characterization, treatment planning prognostic assessment LM, based on systematic review literature.

Language: Английский

Citations

12
Machine learning-based radiomics analysis in predicting RAS mutational status using magnetic resonance imaging DOI
Vincenza Granata, Roberta Fusco,

Maria Chiara Brunese

et al.

La radiologia medica, Journal Year: 2024, Volume and Issue: 129(3), P. 420 - 428

Published: Feb. 2, 2024

Language: Английский

Citations

4
Exploring tumor heterogeneity in colorectal liver metastases by imaging: Unsupervised machine learning of preoperative CT radiomics features for prognostic stratification DOI
Qiang Wang, Henrik Nilsson, Keyang Xu

et al.

European Journal of Radiology, Journal Year: 2024, Volume and Issue: 175, P. 111459 - 111459

Published: April 10, 2024

Language: Английский

Citations

4
Radiomics in gastrointestinal stromal tumours: an up-to-date review DOI
Antonio Galluzzo,

Sofia Boccioli,

Ginevra Danti

et al.

Japanese Journal of Radiology, Journal Year: 2023, Volume and Issue: 41(10), P. 1051 - 1061

Published: May 12, 2023

Language: Английский

Citations

10
Preoperative prediction of lymph node metastasis in intrahepatic cholangiocarcinoma: an integrative approach combining ultrasound-based radiomics and inflammation-related markers DOI Creative Commons
Yuting Peng, Jin-shu Pang, Peng Lin

et al.

BMC Medical Imaging, Journal Year: 2025, Volume and Issue: 25(1)

Published: Jan. 2, 2025

To develop ultrasound-based radiomics models and a clinical model associated with inflammatory markers for predicting intrahepatic cholangiocarcinoma (ICC) lymph node (LN) metastasis. Both are integrated enhanced preoperative prediction. This study retrospectively enrolled 156 surgically diagnosed ICC patients. A region of interest (ROI) was manually identified on the ultrasound image tumor to extract features. In training cohort, we performed Wilcoxon test screen differentially expressed features, then used 12 machine learning algorithms 107 within cross-validation framework determine optimal through receiver operating characteristic (ROC) curve analysis. Multivariable logistic regression analysis identify independent risk factors construct model. The combined established by combining parameters. Delong decision (DCA) were compare diagnostic efficacy utility different models. total 1239 features extracted from ROIs tumors. Among prediction models, (Stepglm + LASSO) utilizing 10 ultimately yielded highest average area under (AUC) 0.872, an AUC 0.916 in cohort 0.827 validation cohort. model, which incorporates score, N stage, platelet-to-lymphocyte ratio (PLR), achieved 0.882 significantly outperforming 0.687 (P = 0.009). According DCA analysis, also showed better benefits. incorporating PLR marker offers effective, noninvasive intelligence-assisted tool LN metastasis Not applicable.

Language: Английский

Citations

0