Navigating advanced renal cell carcinoma in the era of artificial intelligence

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

Published: Feb. 18, 2025

Abstract Background Research has helped to better understand renal cell carcinoma and enhance management of patients with locally advanced metastatic disease. More recently, artificial intelligence emerged as a powerful tool in cancer research, particularly oncologic imaging. Body Despite promising results most investigations have focused on localized disease, while relatively fewer studies targeted This paper summarizes major advances focusing mostly their potential clinical value from initial staging identification high-risk features predicting response treatment carcinoma, addressing limitations the development some models highlighting new avenues for future research. Conclusion Artificial intelligence-enabled great improving practice diagnosis when developed both clinicopathologic radiologic data.

Language: Английский

---

Artificial Intelligence-based Radiomics in the Era of Immuno-oncology

The Oncologist, Journal Year: 2022, Volume and Issue: 27(6), P. e471 - e483

Published: Feb. 23, 2022

Abstract The recent, rapid advances in immuno-oncology have revolutionized cancer treatment and spurred further research into tumor biology. Yet, patients respond variably to immunotherapy despite mounting evidence support its efficacy. Current methods for predicting response are unreliable, as these tests cannot fully account heterogeneity microenvironment. An improved method is needed. Recent studies proposed radiomics—the process of converting medical images quantitative data (features) that can be processed using machine learning algorithms identify complex patterns trends—for immunotherapy. Because undergo numerous imaging procedures throughout the course disease, there exists a wealth radiological available training radiomics models. And because radiomic features reflect biology, such microenvironment, models enormous potential predict more accurately than current methods. Models trained on preexisting biomarkers and/or clinical outcomes demonstrated improve patient stratification outcomes. In this review, we discuss applications oncology, followed by discussion recent use toxicity.

Language: Английский

---

A CT-based deep learning radiomics nomogram outperforms the existing prognostic models for outcome prediction in clear cell renal cell carcinoma: a multicenter study

European Radiology, Journal Year: 2023, Volume and Issue: 33(12), P. 8858 - 8868

Published: June 30, 2023

Language: Английский

---

Sub-regional Radiomics Analysis for Predicting Metastasis Risk in Clear Cell Renal Cell Carcinoma: A Multicenter Retrospective Study

Academic Radiology, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 1, 2024

Clear cell renal carcinoma (ccRCC) is the most common malignant neoplasm affecting kidney, exhibiting a dismal prognosis in metastatic instances. Elucidating composition of ccRCC holds promise for discovery highly sensitive biomarkers. Our objective was to utilize habitat imaging techniques and integrate multimodal data precisely predict risk metastasis, ultimately enabling early intervention enhancing patient survival rates.

Language: Английский

---

Artificial Intelligence in Kidney Cancer

American Society of Clinical Oncology Educational Book, Journal Year: 2022, Volume and Issue: 42, P. 300 - 310

Published: May 17, 2022

Artificial intelligence is rapidly expanding into nearly all facets of life, particularly within the field medicine. The diagnosis, characterization, management, and treatment kidney cancer ripe with areas for improvement that may be met promises artificial intelligence. Here, we explore impact current research work in clinicians caring patients renal cancer, a focus on perspectives radiologists, pathologists, urologists. Promising preliminary results indicate assist diagnosis risk stratification newly discovered masses help guide clinical cancer. However, much this still its early stages, limited broader applicability, hampered by small datasets, varied appearance presentation cancers, intrinsic limitations rigidly structured tasks algorithms are trained to complete. Nonetheless, continued exploration holds promise toward improving care

Language: Английский

---

Development and external validation of a radiomics model for assessment of HER2 positivity in men and women presenting with gastric cancer

Insights into Imaging, Journal Year: 2023, Volume and Issue: 14(1)

Published: Feb. 1, 2023

To develop and externally validate a conventional CT-based radiomics model for identifying HER2-positive status in gastric cancer (GC).950 GC patients who underwent pretreatment CT were retrospectively enrolled assigned into training cohort (n = 388, CT), an internal validation 325, CT) external 237, dual-energy CT, DECT). Radiomics features extracted from venous phase images to construct the "Radscore". On basis of univariate multivariate analyses, was built cohort, combining significant clinical-laboratory characteristics Radscore. The assessed validated regarding its diagnostic effectiveness clinical practicability using AUC decision curve analysis, respectively.Location, TNM staging, CEA, CA199, Radscore independent predictors HER2 (all p < 0.05). Integrating these five indicators, proposed exerted favorable performance with AUCs 0.732 (95%CI 0.683-0.781), 0.703 0.624-0.783), 0.711 0.625-0.798) observed training, validation, cohorts, respectively. Meanwhile, would offer more net benefits than default simple schemes not affected by age, gender, location, immunohistochemistry results, type tissue confirmation > 0.05).The had good positivity potential generalize DECT, which is beneficial simplify workflow help clinicians initially identify candidates might benefit HER2-targeted therapy.

Language: Английский

---

The predictive value of radiomics and deep learning for synchronous distant metastasis in clear cell renal cell carcinoma

Discover Oncology, Journal Year: 2025, Volume and Issue: 16(1)

Published: Jan. 25, 2025

The objective of this research was to devise and authenticate a predictive model that employs CT radiomics deep learning methodologies for the accurate prediction synchronous distant metastasis (SDM) in clear cell renal carcinoma (ccRCC). A total 143 ccRCC patients were included training cohort, 62 validation cohort. images from all normalized, tumor regions manually segmented via ITK-SNAP software. Radiomic features extracted FAE toolkit. least absolute shrinkage selection operator (LASSO) algorithm employed select build various machine models. Additionally, largest cross-section cropped train model. Multiple models trained predict SDM patients. results best then fused with those create combined Of 944 radiomic identified, 15 closely associated SDM. With these features, support vector (SVM) emerged as most effective, demonstrating areas under curve (AUC) 0.860 0.813 respectively. Among models, ResNet101 performed optimally, achieving AUC 0.815 0.743 yielded an 0.863. Decision analysis suggested offers superior clinical applicability. integrates learning, showing significant potential predicting It holds promise supporting decision-making, reducing missed diagnoses SDM, guiding further enhancing their systemic examinations.

Language: Английский

---

Multimodal data integration using machine learning to predict the risk of clear cell renal cancer metastasis: a retrospective multicentre study

Abdominal Radiology, Journal Year: 2024, Volume and Issue: 49(7), P. 2311 - 2324

Published: June 15, 2024

Language: Английский

---

CT radiomics for differentiating oncocytoma from renal cell carcinomas: Systematic review and meta-analysis

Clinical Imaging, Journal Year: 2022, Volume and Issue: 94, P. 9 - 17

Published: Nov. 17, 2022

Language: Английский

---

Magnetic Resonance Imaging Radiomics‐Based Nomogram From Primary Tumor for Pretreatment Prediction of Peripancreatic Lymph Node Metastasis in Pancreatic Ductal Adenocarcinoma: A Multicenter Study

Journal of Magnetic Resonance Imaging, Journal Year: 2022, Volume and Issue: 55(3), P. 823 - 839

Published: Jan. 8, 2022

Background Determining the absence or presence of peripancreatic lymph nodal metastasis (PLNM) is important to pathologic staging, prognostication, and guidance treatment in pancreatic ductal adenocarcinoma (PDAC) patients. Computed tomography MRI had a poor sensitivity diagnostic accuracy assessment PLNM. Purposes To develop validate 3 T primary tumor radiomics‐based nomogram from multicenter datasets for pretreatment prediction PLNM PDAC Study Type Retrospective. Subjects A total 251 patients (156 men 95 women; mean age, 60.85 ± 8.23 years) with histologically confirmed three hospitals. Field Strength Sequences 3.0 fat‐suppressed T1‐weighted imaging. Assessment Quantitative imaging features were extracted (FS T1WI) images at arterial phase. Statistical Tests Normally distributed data compared by using t ‐tests, while Mann–Whitney U test was used evaluate non‐normally data. The performances preoperative postoperative nomograms assessed external validation cohort area under receiver operating characteristics curve (AUC), calibration curve, decision analysis (DCA). AUCs De Long test. p value below 0.05 considered be statistically significant. Results magnetic resonance (MRI) Rad‐score 0.868 (95% confidence level [CI]: 0.613–0.852) 0.772 CI: 0.659–0.879) training internal cohort, respectively. could accurately predict (AUC = 0.909 0.851) validated both cohorts 0.835 0.805, 0.808 0.733, respectively). DCA indicated that two novel are similar clinical usefulness. Data Conclusion Pre−/postoperative constructed radiomics signature based on FS T1WI phase serve as potential tool PDAC. Evidence Level Technical Efficacy Stage 2

Language: Английский

---