Deep-learning-based ensemble method for fully automated detection of renal masses on magnetic resonance images DOI

Agarwal Anush,

Rohini Gaikar, Nicola Schieda

et al.

Journal of Medical Imaging, Journal Year: 2023, Volume and Issue: 10(02)

Published: March 20, 2023

PurposeAccurate detection of small renal masses (SRM) is a fundamental step for automated classification benign and malignant or indolent aggressive tumors. Magnetic resonance image (MRI) may outperform computed tomography (CT) SRM subtype differentiation due to improved tissue characterization, but less explored compared CT. The objective this study autonomously detect on contrast-enhanced magnetic images (CE-MRI).ApproachIn paper, we described novel, fully methodology accurate localization CE-MRI. We first determine the kidney boundaries using U-Net convolutional neural network. then search within localized regions mixture-of-experts ensemble model based architecture. Our dataset contained CE-MRI scans 118 patients with different solid tumor subtypes including cell carcinomas, oncocytomas, fat-poor angiomyolipoma. evaluated proposed entire 5-fold cross validation.ResultsThe developed algorithm reported Dice similarity coefficient 91.20 ± 5.41 % (mean standard deviation) segmentation from volumes consisting 25,025 slices. yielded recall precision 86.2% 83.3% dataset, respectively.ConclusionsWe deep-learning-based method CE-MR images, which has not been studied previously. results are clinically important as pre-step diagnosis subtypes.

Language: Английский

Radiogenomics: a key component of precision cancer medicine DOI
Zaoqu Liu,

Tian Duan,

Yuyuan Zhang

et al.

British Journal of Cancer, Journal Year: 2023, Volume and Issue: 129(5), P. 741 - 753

Published: July 6, 2023

Language: Английский

Citations

45
Novel Liquid Biomarkers and Innovative Imaging for Kidney Cancer Diagnosis: What Can Be Implemented in Our Practice Today? A Systematic Review of the Literature DOI
Riccardo Campi, Grant D. Stewart, Michael Staehler

et al.

European Urology Oncology, Journal Year: 2021, Volume and Issue: 4(1), P. 22 - 41

Published: Jan. 3, 2021

Language: Английский

Citations

46
The role of imaging in the management of renal masses DOI Creative Commons
Athina C. Tsili, Efthimios Andriotis,

Myrsini Gkeli

et al.

European Journal of Radiology, Journal Year: 2021, Volume and Issue: 141, P. 109777 - 109777

Published: May 15, 2021

The wide availability of cross-sectional imaging is responsible for the increased detection small, usually asymptomatic renal masses. More than 50 % cell carcinomas (RCCs) represent incidental findings on noninvasive imaging. Multimodality imaging, including conventional US, contrast-enhanced US (CEUS), CT and multiparametric MRI (mpMRI) pivotal in diagnosing characterizing a mass, but also provides information regarding its prognosis, therapeutic management, follow-up. In this review, data masses that urologists need accurate treatment planning will be discussed. role CEUS, mpMRI characterization masses, RCC staging follow-up surgically treated or untreated localized presented. percutaneous image-guided ablation management reviewed.

Language: Английский

Citations

37
Advances in Imaging-Based Biomarkers in Renal Cell Carcinoma: A Critical Analysis of the Current Literature DOI Open Access

Lina Posada Posada Calderon,

Lennert Eismann, Stephen W. Reese

et al.

Cancers, Journal Year: 2023, Volume and Issue: 15(2), P. 354 - 354

Published: Jan. 5, 2023

Cross-sectional imaging is the standard diagnostic tool to determine underlying biology in renal masses, which crucial for subsequent treatment. Currently, CT limited its ability differentiate benign from malignant disease. Therefore, various modalities have been investigated identify imaging-based parameters improve noninvasive diagnosis of masses and cell carcinoma (RCC) subtypes. MRI was reported predict grading RCC subtypes, has shown a small cohort response targeted therapy. Dynamic promising staging RCC. PET/CT radiotracers, such as 18F-fluorodeoxyglucose (FDG), 124I-cG250, radiolabeled prostate-specific membrane antigen (PSMA), 11C-acetate, identification histology, grading, detection metastasis, assessment systemic therapy, oncological outcomes. Moreover, 99Tc-sestamibi SPECT scans results distinguishing low-grade lesions. Radiomics used further characterize based on semantic textural analyses. In preliminary studies, integrated machine learning algorithms using radiomics proved be more accurate compared radiologists’ interpretations. radiogenomics are complement risk classification models Imaging-based biomarkers hold strong potential RCC, but require standardization external validation before integration into clinical routines.

Language: Английский

Citations

15
Management of Renal Cell Carcinoma: Promising Biomarkers and the Challenges to Reach the Clinic DOI Creative Commons
Iben Lyskjær, Laura Iisager, Christian Tang Axelsen

et al.

Clinical Cancer Research, Journal Year: 2023, Volume and Issue: 30(4), P. 663 - 672

Published: Oct. 24, 2023

Abstract The incidence of renal cell carcinoma (RCC) is increasing worldwide, yet research within this field lagging behind other cancers. Despite increased detection early disease as a consequence the widespread use diagnostic CT scans, 25% patients have disseminated at diagnosis. Similarly, around progress to metastatic following curatively intended surgery. Surgery cornerstone in treatment RCC; however, when disseminated, immunotherapy or combination with tyrosine kinase inhibitor patient's best option. Immunotherapy potent treatment, durable responses and potential cure patient, but only half benefit from administered there are currently no methods that can identify which will respond immunotherapy. Moreover, need greatest risk relapsing after surgery for localized direct adjuvant there. Even though several molecular biomarkers been published date, we still lacking routinely used guide optimal clinical management. purpose review highlight some most promising biomarkers, discuss efforts made describe barriers needed be overcome reliable robust predictive prognostic clinic cancer.

Language: Английский

Citations

14
Accurate detection and delineation boundary of renal cell carcinoma based on dual-targeted magnetic-fluorescent carbon dots DOI

Nana Yu,

Tonghui Huang,

Tengfei Duan

et al.

Chemical Engineering Journal, Journal Year: 2022, Volume and Issue: 440, P. 135801 - 135801

Published: March 15, 2022

Language: Английский

Citations

21
Artificial Intelligence in Kidney Cancer DOI
Robert G. Rasmussen,

Thomas Sanford,

Anil V. Parwani

et al.

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

Citations

21
MRI radiomics-based nomogram for individualised prediction of synchronous distant metastasis in patients with clear cell renal cell carcinoma DOI
Xu Bai, Qingbo Huang,

Panli Zuo

et al.

European Radiology, Journal Year: 2020, Volume and Issue: 31(2), P. 1029 - 1042

Published: Aug. 27, 2020

Language: Английский

Citations

32
Volumetric visceral fat machine learning phenotype on CT for differential diagnosis of inflammatory bowel disease DOI
Ziling Zhou, Ziman Xiong, Ran Cheng

et al.

European Radiology, Journal Year: 2022, Volume and Issue: 33(3), P. 1862 - 1872

Published: Oct. 18, 2022

Language: Английский

Citations

17
Prediction of Distant Metastasis of Renal Cell Carcinoma Based on Interpretable Machine Learning: A Multicenter Retrospective Study DOI Creative Commons

Jin-Kai Dong,

Minjie Duan,

Xiaozhu Liu

et al.

Journal of Multidisciplinary Healthcare, Journal Year: 2025, Volume and Issue: Volume 18, P. 195 - 207

Published: Jan. 1, 2025

The traditional tool for predicting distant metastasis in renal cell carcinoma (RCC) is still insufficient. We aimed to establish an interpretable machine learning model RCC patients. involved a population-based cohort of 121433 patients (mean age = 63 years; 63.58% men) diagnosed with between 2004 and 2015 from the Surveillance, Epidemiology, End Results (SEER) database. lightGBM algorithm was used develop prediction assessed by area under receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity. LightGBM then externally validated 36395 enrolled SEER database 2016 2018. Shapley Additive exPlanations (SHAP) method applied provide insights into model's outcome or prediction. Of study cohort, 10730 (8.84%) had metastasis. showed good performance internal validation set (AUC: 0.955, 95% CI: 0.951-0.959) temporal external sets (0.963, 0.959-0.967; 0.961, 0.954-0.966). Performance also well performed different sub-cohort stratified age, gender, ethnicity. calibration indicated that predicted values are highly consistent actual observed values. SHAP plots demonstrated chemotherapy most vital variable developed capable accurately risk presented could help identify high-risk who require additional treatment strategies follow-up regimens.

Language: Английский

Citations

0