Radiomics and machine learning for renal tumor subtype assessment using multiphase computed tomography in a multicenter setting

European Radiology, Journal Year: 2024, Volume and Issue: 34(10), P. 6254 - 6263

Published: April 18, 2024

To distinguish histological subtypes of renal tumors using radiomic features and machine learning (ML) based on multiphase computed tomography (CT).

Language: Английский

---

A pilot radiometabolomics integration study for the characterization of renal oncocytic neoplasia

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: Aug. 3, 2023

Differentiating benign renal oncocytic tumors and malignant cell carcinoma (RCC) on imaging histopathology is a critical problem that presents an everyday clinical challenge. This manuscript aims to demonstrate novel methodology integrating metabolomics with radiomics features (RF) differentiate between neoplasia tumors. For this purpose, thirty-three (14 19 RCC) were prospectively collected histopathologically characterised. Matrix-assisted laser desorption/ionisation mass spectrometry (MALDI-MSI) was used extract data, while RF extracted from CT scans of the same Statistical integration generate multilevel network communities -omics features. Metabolites for differentiation two groups (delta centrality > 0.1) pathway enrichment analysis machine learning classifier (XGboost) development. Receiver operating characteristics (ROC) curves areas under curve (AUC) assess performance. Radiometabolomics demonstrated differential node configuration Fourteen nodes (6 8 metabolites) crucial in distinguishing groups. The combined radiometabolomics model achieved AUC 86.4%, whereas metabolomics-only radiomics-only classifiers 72.7% 68.2%, respectively. Analysis significant metabolite identified three distinct tumour clusters (malignant, benign, mixed) differentially enriched metabolic pathways. In conclusion, has been presented as approach evaluate disease entities. our case study, method metabolites important differentiating tumors, highlighting pathways expressed Key by can be improve identification neoplasms.

Language: Английский

---

State of the art review of AI in renal imaging

Abdominal Radiology, Journal Year: 2025, Volume and Issue: unknown

Published: April 28, 2025

Abstract Renal cell carcinoma (RCC) as a significant health concern, with incidence rates rising annually due to increased use of cross-sectional imaging, leading higher detection incidental renal lesions. Differentiation between benign and malignant lesions is essential for effective treatment planning prognosis. tumors present numerous histological subtypes different prognoses, making precise subtype differentiation crucial. Artificial intelligence (AI), especially machine learning (ML) deep (DL), shows promise in radiological analysis, providing advanced tools lesion detection, segmentation, classification improve diagnosis personalize treatment. Recent advancements AI have demonstrated effectiveness identifying predicting surveillance outcomes, yet limitations remain, including data variability, interpretability, publication bias. In this review we explored the current role assessing kidney lesions, highlighting its potential preoperative addressing existing challenges clinical implementation.

Language: Английский

---

Imaging Biomarkers in Evaluation of Malignancy and Aggressiveness in Renal Masses

Radiologic Clinics of North America, Journal Year: 2025, Volume and Issue: unknown

Published: May 1, 2025

Language: Английский

---

Qualitative Assessment of Contrast-Enhanced Ultrasound in Differentiating Clear Cell Renal Cell Carcinoma and Oncocytoma

Journal of Clinical Medicine, Journal Year: 2023, Volume and Issue: 12(9), P. 3070 - 3070

Published: April 23, 2023

We aimed to assess whether clear cell renal carcinoma (ccRCC) can be differentiated from oncocytoma (RO) on a contrast-enhanced ultrasound (CEUS). Between January 2021 and October 2022, we retrospectively queried analyzed our prospectively maintained dataset. Renal mass features were scrutinized with conventional imaging (CUS) CEUS. All lesions confirmed by histopathologic diagnoses after nephron-sparing surgery (NSS). A multivariable analysis was performed identify the potential predictors of ccRCC. The area under curve (AUC) depicted in order diagnostic accuracy model. total 126 masses, including 103 (81.7%) ccRCC 23 (18.3%) RO, matched inclusion criteria. Among these two groups, found significant differences terms enhancement (homogeneous vs. heterogeneous) (p < 0.001), wash-in (fast synchronous/slow) = 0.004), wash-out rim-like 0.001). On multivariate logistic regression, heterogeneous (OR: 19.37; p <0.001) 3.73; 0.049) independent Finally, variables had an AUC 82.5% 75.3%, respectively. Diagnostic for presurgical planning is crucial choice either conservative or radical management. CEUS, its unique features, revealed usefulness differentiating RO.

Language: Английский

---

Machine Learning Integrating 99mTc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors

Cancers, Journal Year: 2023, Volume and Issue: 15(14), P. 3553 - 3553

Published: July 9, 2023

The increasing evidence of oncocytic renal tumors positive in 99mTc Sestamibi Single Photon Emission Tomography/Computed Tomography (SPECT/CT) examination calls for the development diagnostic tools to differentiate these from more aggressive forms. This study combined radiomics analysis with uptake on SPECT/CT benign neoplasms cell carcinoma. A total 57 were prospectively collected. Histopathological and data extraction performed. XGBoost classifiers trained using features alone results visual evaluation examination. SPECT/radiomics model achieved higher accuracy (95%) an area under curve (AUC) 98.3% (95% CI 93.7–100%) than radiomics-only (71.67%) AUC 75% 49.7–100%) (90.8%) 90.8% (95%CI 82.5–99.1%). predictive values SPECT/radiomics, radiomics-only, SPECT/CT-only models 100%, 85.71%, 85%, respectively, whereas negative 55.56%, 94.6%, respectively. Feature importance revealed that was most influential attribute model. highlights potential combining improve preoperative characterization neoplasms. proposed classifier outperformed Sestamibii model, demonstrating integration provides improved performance, minimal false results.

Language: Английский

---

CT radiomics for differentiating fat poor angiomyolipoma from clear cell renal cell carcinoma: Systematic review and meta-analysis

PLoS ONE, Journal Year: 2023, Volume and Issue: 18(7), P. e0287299 - e0287299

Published: July 27, 2023

Purpose Differentiation of fat-poor angiomyolipoma (fp-AMLs) from renal cell carcinoma (RCC) is often not possible just visual interpretation conventional cross-sectional imaging, typically requiring biopsy or surgery for diagnostic confirmation. However, radiomics has the potential to characterize masses without need invasive procedures. Here, we conducted a systematic review on accuracy CT in distinguishing fp-AMLs RCCs. Methods We search using PubMed/MEDLINE, Google Scholar, Cochrane Library, Embase, and Web Science studies published January 2011–2022 that utilized discriminate between A random-effects model was applied meta-analysis according heterogeneity level. Furthermore, subgroup analyses (group 1: RCCs vs. fp-AML, group 2: ccRCC fp-AML), quality assessment were also explore effect interstudy differences. To evaluate performance, pooled sensitivity, specificity, odds ratio (DOR) assessed. This study registered with PROSPERO (CRD42022311034). Results Our literature identified 10 1456 lesions 1437 patients. Pooled sensitivity 0.779 [95% CI: 0.562–0.907] 0.817 0.663–0.910] groups 1 2, respectively. specificity 0.933 0.814–0.978]and 0.926 0.854–0.964] Also, our findings showed higher 0.858 0.742–0.927] 0.886 0.819–0.930] detecting fp-AML unenhanced phase scan as compared corticomedullary nephrogenic phases scan. Conclusion suggested radiomic features derived high differentiating particularly ccRCCs fp-AML. an highest contrast phases. Differentiating RCC surgery; obviate these procedures due its accuracy.

Language: Английский

---

Magnetic resonance imaging based on radiomics for differentiating T1-category nasopharyngeal carcinoma from nasopharyngeal lymphoid hyperplasia: a multicenter study

Japanese Journal of Radiology, Journal Year: 2024, Volume and Issue: 42(7), P. 709 - 719

Published: Feb. 27, 2024

Language: Английский

---

CT-derived radiomics predict the growth rate of renal tumours in von Hippel–Lindau syndrome

Clinical Radiology, Journal Year: 2024, Volume and Issue: 79(5), P. e675 - e681

Published: Feb. 8, 2024

Language: Английский

---

Radiomics-based machine learning role in differential diagnosis between small renal oncocytoma and clear cells carcinoma on contrast-enhanced CT: A pilot study

European Journal of Radiology Open, Journal Year: 2024, Volume and Issue: 13, P. 100604 - 100604

Published: Oct. 10, 2024

Language: Английский

---