Diagnostic value and clinical significance of ultrasound combined with CT in cystic renal cell carcinoma

Sun, Ming‐Hui; Wang, Chao; Jiang, Fei; Fang, Xiuhong; Guo, Bingcheng

doi:10.3892/ol.2019.10422

Cited by 5 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies showed that CT was significantly better than US in screening of wall or septa nodule. 29,30 From our obtained results, there were 13 Bosniak grade IV by CEUS (EFSUMB 2020) and CEUS (V2019) compared to 15 cases of Bosniak grade IV by CECT (V2019). From Figure 11, we can see a nodule on the septation by CEUS, while it cannot be discovered by CECT.…”

Section: Discussionmentioning

confidence: 86%

Clinical Evaluation of Cystic Renal Masses With Bosniak Classification by Contrast‐Enhanced Ultrasound and Contrast‐Enhanced Computer Tomography

Lan,

Yang,

et al. 2023

J of Ultrasound Medicine

View full text Add to dashboard Cite

ObjectivesThe study aims to compare retrospectively three clinically applied methods for the diagnostic performance of cystic renal masses (CRMs) by contrast‐enhanced ultrasound (CEUS) and contrast‐enhanced computer tomography (CECT) with Bosniak classification system.MethodsA total of 52 cases of Bosniak II–IV CRMs in 49 consecutive patients were diagnosed from January 2013 to July 2022 and their data were analyzed. All patients had been subjected to CEUS and CECT simultaneously. Pathological diagnoses and masses stability were used as standard references to determine whether lesions were malignant or benign. Then 49 CRMs only with pathologic results were classified into group 1 and 2.ResultsA total of 52 CRMs in 49 enrolled patients were classified into 8 category II, 16 category IIF, 15 category III, and 13 category IV by CEUS (EFSUMB 2020), 10 category II, 13 category IIF, 16 category III, and 13 category IV by CEUS (V2019), while 15 category II, 9 category IIF, 13 category III, and 15 category IV by CECT (V2019). Pathological results and masses stability longer than 5 years follow‐up performed substantially for CEUS (EFSUMB 2020), CEUS (V2019), and CECT (V2019) (kappa values were 0.696, 0.735, and 0.696, respectively). Among 49 pathologic approving CRMs, wall/septation thickness ≥4 mm, wall/septation thickness, presence of enhancing nodule and the diameter were found to be statistically significant for malignancy. Twenty‐two malignant masses were correctly diagnosed by CEUS (V2019), while 21 malignant masses were both correctly diagnosed by CEUS (EFSUMB 2020) and CECT (V2019), and 1 mass was misdiagnosed.ConclusionsBosniak classification of EFSUMB 2020 version might be as accurate as version 2019 CEUS and version 2019 CECT in diagnosing CRMs, and CEUS is found to have an excellent safety profile in dealing with clinical works.

show abstract

Section: Discussionmentioning

confidence: 86%

Clinical Evaluation of Cystic Renal Masses With Bosniak Classification by Contrast‐Enhanced Ultrasound and Contrast‐Enhanced Computer Tomography

Lan,

Yang,

et al. 2023

J of Ultrasound Medicine

View full text Add to dashboard Cite

show abstract

“…Although CRCC and CCDC have been relatively well described in pathology studies, comparative study of CT appearances are scanty, particularly in combination with histopathologic examination. However, patients with CRCC have a better prognosis after undergoing total nephrectomy or local resection than that CCDC [ 9 , 10 ]. So, an accurate diagnosis is important for guiding clinical treatment.…”

Section: Discussionmentioning

confidence: 99%

CT and MRI findings of cystic renal cell carcinoma: comparison with cystic collecting duct carcinoma

Zhu

Ling

et al. 2021

Cancer Imaging

View full text Add to dashboard Cite

Background Cystic renal cell carcinoma (CRCC) and cystic collecting duct carcinoma (CCDC) share similar oncogeni and some imaging findings. The aim of this study was to characterize the clinical and CT imagings features of CRCC and CCDC. Methods Thirty-three patients with CRCC and thirteen patients with CCDC with pathologically proven were retrospectively studied. Tumor characteristics were assessed. Results On CT imaging, 33 patients(100 %) with CRCC and 13 patients(100 %) with CCDC, tumors calcifications (8 vs. 9, P < 0.0001), had a clear boundary (capsule sign, 30 vs. 2, P < 0.0001), infiltrative appearance (1 vs. 13, P < 0.0001), exogenous appearance (29 vs. 3, P < 0.0001), invaded the renal pelvis or ureter (1 vs. 10, P < 0.0001), hemorrhage (1 vs. 10, P < 0.0001), had retroperitoneal lymph node or distant metastasis (2 vs. 10, P < 0.0001), thickened enhancing internal septations (31 vs. 2, P < 0.0001), and mural soft-tissue nodules (21 vs. 1, P < 0.0001). On MR imaging,13 patients(39 %) with CRCC and 4 patients(31 %) with CCDC, all CRCCs appeared hypointense on T1-weighted images and hyperintense on T2-weighted images, however, all CCDCs appeared hypointense on T1-weighted images and hypointense on T2-weighted images(P < 0.0001). 33 patients with CRCC, they were all alive from3 years to 10 years follow-up, however, 13 patients with CCDC, of which 11 patients were able to be followed up, and 9 patients expired within 5 years of the initial diagnosis and the others are currently still alive. Conclusions Distinguishing features of CRCC and CCDC included calcifications, capsule signs, infiltrative appearance, metastasis, internal septations, mural nodules and signal on CT or MR images. These imaging features may help in differentiating the two renal tumor types.

show abstract

“…Computed tomography (CT) imaging is highly preferred by radiologists in diagnosing kidney abnormality due to its capability to produce highresolution images characterized by clear anatomical details, optimal contrast, and superior spatial resolution [4]. However, radiologists and nephrologists may occasionally encounter challenges in accurately diagnosing certain cases, leading to the possibility of misdiagnosis [9]. Furthermore, the current standard CT screening procedures are frequently associated with exorbitant financial costs [10].…”

Section: Introductionmentioning

confidence: 99%

The investigation of transferability utilizing the ImageNet weight-based pretrained model for medical image classification: A case study on kidney CT images

Hsu

2023

ACE

View full text Add to dashboard Cite

Due to recent growth in technology, machine learning has emerged to be an effective auxiliary tool in medical field. However, the effectiveness of transfer learning architectures trained on non-medical image data remains unclear. In this paper, two VGG-16 models, a type of pre-trained Convolutional Neural Network architecture, were constructed to classify kidney CT images that belong to four categories: normal, stone, cyst, and tumor. Two VGG-16 models have identical parameters except for the pre-trained weights: one has pre-trained weights trained on ImageNet, and the other one trained on a random large-scale dataset. To gather a more detained insight into models performances, saliency maps and Grad-CAM are employed to assess the models' ability to extract relevant features from the CT images. The result demonstrated that VGG-16 model that is trained on ImageNet can achieve 98.96% accuracy, which is about 30% higher than the other VGG-16 model. The saliency maps and Grad-CAM also support the difference in test accuracy: the model with random pre-trained dataset has saliency map that highlights the whole picture and Grad-CAM image that does not highlight any part of the CT image data, showing that it cannot correctly locate the key features. Additionally, the model with ImageNet can correctly highlight the principal features in both maps. In this study, the utilization of ImageNet is proven to be effective in the usage of transfer learning in processing medical image. Future research and exploration should focus on further enhancing the application of transfer learning in the medical field.

show abstract

Diagnostic value and clinical significance of ultrasound combined with CT in cystic renal cell carcinoma

Cited by 5 publications

References 26 publications

Clinical Evaluation of Cystic Renal Masses With Bosniak Classification by Contrast‐Enhanced Ultrasound and Contrast‐Enhanced Computer Tomography

Clinical Evaluation of Cystic Renal Masses With Bosniak Classification by Contrast‐Enhanced Ultrasound and Contrast‐Enhanced Computer Tomography

CT and MRI findings of cystic renal cell carcinoma: comparison with cystic collecting duct carcinoma

The investigation of transferability utilizing the ImageNet weight-based pretrained model for medical image classification: A case study on kidney CT images

Contact Info

Product

Resources

About