Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence

Cancers, Год журнала: 2023, Номер 15(2), С. 351 - 351

Опубликована: Янв. 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.

Язык: Английский

---

Radiomics and machine learning analysis by computed tomography and magnetic resonance imaging in colorectal liver metastases prognostic assessment

La radiologia medica, Год журнала: 2023, Номер 128(11), С. 1310 - 1332

Опубликована: Сен. 11, 2023

Язык: Английский

---

Radiomics in Lung Metastases: A Systematic Review

Journal of Personalized Medicine, Год журнала: 2023, Номер 13(2), С. 225 - 225

Опубликована: Янв. 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.

Язык: Английский

---

Deep Learning‐Based Multiparametric MRI Model for Preoperative T‐Stage in Rectal Cancer

Journal of Magnetic Resonance Imaging, Год журнала: 2023, Номер 59(3), С. 1083 - 1092

Опубликована: Июнь 27, 2023

Background Conventional MRI staging can be challenging in the preoperative assessment of rectal cancer. Deep learning methods based on have shown promise cancer diagnosis and prognostication. However, value deep T‐staging is unclear. Purpose To develop a model multiparametric for evaluation to investigate its potential improve accuracy. Study Type Retrospective. Population After cross‐validation, 260 patients (123 with T‐stage T1‐2 134 T3‐4) histopathologically confirmed were randomly divided training (N = 208) test sets 52). Field Strength/Sequence 3.0 T/Dynamic contrast enhanced ( DCE ), T2 ‐weighted imaging T2W diffusion‐weighted DWI ). Assessment The (DL) (DCE, T2W, DWI) convolutional neural network constructed evaluating diagnosis. pathological findings served as reference standard T‐stage. For comparison, single parameter DL‐model, logistic regression composed clinical features subjective radiologists used. Statistical Tests receiver operating characteristic curve (ROC) was used evaluate models, Fleiss' kappa intercorrelation coefficients, DeLong compare diagnostic performance ROCs. P ‐values less than 0.05 considered statistically significant. Results Area Under Curve (AUC) DL‐model 0.854, which significantly higher radiologist's (AUC 0.678), 0.747), DL‐models including T2W‐model 0.735), DWI‐model 0.759), DCE‐model 0.789). Data Conclusion In patients, proposed outperformed assessment, well models. has assist clinicians by providing more reliable precise T Evidence Level 3 Technical Efficacy Stage 2

Язык: Английский

---

Peritoneal Carcinosis: What the Radiologist Needs to Know

Diagnostics, Год журнала: 2023, Номер 13(11), С. 1974 - 1974

Опубликована: Июнь 5, 2023

Peritoneal carcinosis is a condition characterized by the spread of cancer cells to peritoneum, which thin membrane that lines abdominal cavity. It serious can result from many different types cancer, including ovarian, colon, stomach, pancreatic, and appendix cancer. The diagnosis quantification lesions in peritoneal are critical management patients with condition, imaging plays central role this process. Radiologists play vital multidisciplinary carcinosis. They need have thorough understanding pathophysiology underlying neoplasms, typical findings. In addition, they be aware differential diagnoses advantages disadvantages various methods available. Imaging lesions, radiologists Ultrasound, computed tomography, magnetic resonance, PET/CT scans used diagnose Each procedure has disadvantages, particular techniques recommended based on patient conditions. Our aim provide knowledge regarding appropriate techniques, findings, diagnoses, treatment options. With advent AI oncology, future precision medicine appears promising, interconnection between structured reporting likely improve diagnostic accuracy outcomes for

Язык: Английский

---

Machine learning-based radiomics analysis in predicting RAS mutational status using magnetic resonance imaging

La radiologia medica, Год журнала: 2024, Номер 129(3), С. 420 - 428

Опубликована: Фев. 2, 2024

Язык: Английский

---

Diagnostic Management of Gastroenteropancreatic Neuroendocrine Neoplasms: Technique Optimization and Tips and Tricks for Radiologists

Tomography, Год журнала: 2023, Номер 9(1), С. 217 - 246

Опубликована: Янв. 27, 2023

Gastroenteropancreatic neuroendocrine neoplasms (GEP-NENs) comprise a heterogeneous group of neoplasms, which derive from cells the diffuse system that specializes in producing hormones and neuropeptides arise most cases sporadically and, to lesser extent, context complex genetic syndromes. Furthermore, they are primarily nonfunctioning, while, case insulinomas, gastrinomas, glucagonomas, vipomas, somatostatinomas, produce responsible for clinical The GEP-NEN tumor grade cell differentiation may result different behaviors prognoses, with one (G1) two (G2) tumors showing more favorable outcome than three (G3) NET carcinoma. Two critical issues should be considered NEN diagnostic workup: first, need identify presence tumor, second, define primary site evaluate regional distant metastases. Indeed, site, stage, grade, function prognostic factors radiologist guide prognosis management. correct management patient includes combination morphological functional evaluations. Concerning evaluations, according consensus guidelines European Neuroendocrine Tumor Society (ENETS), computed tomography (CT) contrast medium is recommended. Contrast-enhanced magnetic resonance imaging (MRI), including diffusion-weighted (DWI), usually indicated use liver, pancreas, brain, bones. Ultrasonography (US) often helpful initial diagnosis liver metastases, contrast-enhanced ultrasound (CEUS) can solve problems characterizing as this tool biopsy lesions. In addition, intraoperative an effective during surgical procedures. Positron emission (PET-CT) FDG nonfunctioning lesions somatostatin analogs very useful identifying evaluating metabolic receptors. detection heterogeneity receptor (SSTR) expression also crucial treatment decision making. narrative review, we have described role tools assessment GEP-NENs current major guidelines.

Язык: Английский

---

A Systematic Review of Disappearing Colorectal Liver Metastases: Resection or No Resection?

Journal of Clinical Medicine, Год журнала: 2025, Номер 14(4), С. 1147 - 1147

Опубликована: Фев. 10, 2025

Background: Colorectal cancer is the second most common type of and a leading cause cancer-related deaths worldwide. Approximately 15% patients with colorectal will already have liver metastases (CRLMs) at diagnosis. Luckily, advances in chemotherapy regimens during past few decades led to increased rates disease regression that could even render an originally unresectable resectable. In certain CRLMs, hepatic lesions are missing on preoperative imaging after neoadjuvant chemotherapy. These can undergo surgery or without resection sites disappearing (DLMs). this systematic review, we assess recurrence rate DLMs were left unresected as well complete pathologic response those resected. Methods: A literature search was conducted PubMed for studies including CRLMs who received had imaging. Two independent reviewers completed according PRISMA checklist. Results: Three hundred twenty-six 1134 included our review. total 47 out 480 (72.29%) removed viable tumor cells postoperative histology. One forty-five tumors not be identified intraoperatively based previous imaging, thirty (20.69%) them presenting cells. Four sixty-five place. Of them, 152 (32.69%) developed local within 5 years. note, 34 categorized non-viable tumors. Finally, identifiable higher possibility compared non-identifiable ones (72.29% vs. 20.69%, respectively). Conclusions: Disappearing recurrence. Patients receiving treatment may better survival chances resecting all DLM sites, either not.

Язык: Английский

---

Artificial intelligence and radiation effects on brain tissue in glioblastoma patient: preliminary data using a quantitative tool

La radiologia medica, Год журнала: 2023, Номер 128(7), С. 813 - 827

Опубликована: Июнь 8, 2023

Язык: Английский

---

Machine Learning and Radiomics Analysis for Tumor Budding Prediction in Colorectal Liver Metastases Magnetic Resonance Imaging Assessment

Diagnostics, Год журнала: 2024, Номер 14(2), С. 152 - 152

Опубликована: Янв. 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.

Язык: Английский

---