The role of multiparametric MRI-based VI-RADS in predicting the need for a second TURB

World Journal of Urology, Год журнала: 2025, Номер 43(1)

Опубликована: Май 5, 2025

Язык: Английский

---

Multiparametric MRI‐Based Deep Learning Radiomics Model for Assessing 5‐Year Recurrence Risk in Non‐Muscle Invasive Bladder Cancer

Journal of Magnetic Resonance Imaging, Год журнала: 2024, Номер unknown

Опубликована: Авг. 21, 2024

Background Accurately assessing 5‐year recurrence rates is crucial for managing non‐muscle‐invasive bladder carcinoma (NMIBC). However, the European Organization Research and Treatment of Cancer (EORTC) model exhibits poor performance. Purpose To investigate whether integrating multiparametric MRI (mp‐MRI) with clinical factors improves NMIBC risk assessment. Study Type Retrospective. Population One hundred ninety‐one patients (median age, 65 years; age range, 54–73 27 females) underwent mp‐MRI between 2011 2017, received ≥5‐year follow‐ups. They were divided into a training cohort (N = 115) validation/testing cohorts 38 in each). Recurrence 23.5% (27/115) 23.7% (9/38) both validation testing cohorts. Field Strength/Sequence 3‐T, fast spin echo T2‐weighted imaging (T2WI), single‐shot planar diffusion‐weighted (DWI), volumetric spoiled gradient dynamic contrast‐enhanced (DCE) sequences. Assessment Radiomics deep learning (DL) features extracted from combined region interest (cROI) including intratumoral peritumoral areas on mp‐MRI. Four models developed, clinical, cROI‐based radiomics, DL, clinical‐radiomics‐DL (CRDL) models. Statistical Tests Student's t ‐tests, DeLong's tests Bonferroni correction, receiver operating characteristics area under curves (AUCs), Cox proportional hazard analyses, Kaplan–Meier plots, SHapley Additive ExPlanations (SHAP) values, Akaike information criterion usefulness. A P ‐value <0.05 was considered statistically significant. Results The CRDL showed superior performance (AUC 0.909; 95% CI: 0.792–0.985) compared to other NMIBC. It achieved highest Harrell's concordance index (0.804; 0.749–0.859) estimating recurrence‐free survival. SHAP analysis further highlighted substantial role (22%) radiomics Data Conclusion Integrating DL preoperative could improve assessment Evidence Level 3 Technical Efficacy Stage

Язык: Английский

---

The role of MRI in muscle-invasive bladder cancer: an update from the last two years

Current Opinion in Urology, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 12, 2024

Muscle invasive bladder cancer (MIBC) is aggressive and requires radical cystectomy neoadjuvant therapy, yet over 40% of patients face recurrence. The loss the also significantly reduces quality life. Accurate staging, crucial for treatment decisions, typically done through transurethral resection (TURBT), but inconsistencies in pathology affect diagnosis 25% cases. MRI most precise imaging method evaluating local tumor invasiveness. This review discusses recent advances staging MIBC predicting responses to therapy.

Язык: Английский

---

Letter to the editor: Multiparametric MRI-based VI-RADS: Can it predict 1- to 5-year recurrence of bladder cancer?

European Radiology, Год журнала: 2024, Номер unknown

Опубликована: Авг. 30, 2024

Язык: Английский

---

Reply to the Letter to the Editor: Multiparametric MRI-based VI-RADS: can it predict 1- to 5-year recurrence of bladder cancer?

European Radiology, Год журнала: 2024, Номер unknown

Опубликована: Авг. 23, 2024

Язык: Английский

---

A Non-Invasive Mri-Based Multimodal Fusion Deep Learning Model (MF-DLM) for Predicting Overall Survival in Bladder Cancer: A Multicenter Retrospective Study

Опубликована: Янв. 1, 2024

Язык: Английский

---