OBJECTIVES: Renal cell carcinoma (RCC) is a malignant renal tumor that poses a significant threat to patient health. Accurate preoperative pathological grading plays a crucial role in determining the appropriate treatment for this disease. Currently, deep learning technology has become an important method for pathological grading of RCC. However, existing methods primarily rely on single-phase computed tomography (CT) imaging for analysis and prediction, which has limitations such as missing small lesions, one-sided evaluation, and local focusing issues. Therefore, this study proposes a multi-modal deep learning algorithm that integrates multi-phase enhanced CT images with clinical variable data, aiming to provide a basis for predicting the pathological grading of RCC. METHODS: First, the algorithm took four-phase enhanced CT images from the plain scan, arterial phase, venous phase, and delayed phase, along with clinical variables, as inputs. Then, an embedding encoding module was used to extract heterogeneous information from the clinical variables, and a 3-dimensional (3D) ResNet50 model was employed to capture spatial information from the multi-phase enhanced CT image data. Finally, a Fusion module deeply integrated the feature information from clinical variables and each phase's CT image features, further utilizing a cross-self-attention mechanism to achieve multi-phase feature fusion. This approach comprehensively captures the deep semantic information from the patient data, fully leveraging the complementary advantages of multi-modal and multi-phase data. To validate the effectiveness of the proposed method, a total of 1 229 RCC patients were approved by ethics review were included to train the model. RESULTS: Experimental results demonstrated superior performance compared to traditional radiomics and state-of-the-art deep learning methods, achieving an accuracy of 83.87%, a recall rate of 95.04%, and an F1-score of 82.23%. CONCLUSIONS The proposed algorithm exhibits strong stability and sensitivity, significantly enhancing the predictive performance of RCC pathological grading. It offers a novel approach for accurate RCC diagnosis and personalized treatment planning.
Humans ; Carcinoma, Renal Cell/pathology* ; Deep Learning ; Kidney Neoplasms/diagnostic imaging* ; Tomography, X-Ray Computed/methods* ; Algorithms ; Neoplasm Grading ; Male ; Female ; Middle Aged

Renal angiomyolipoma (AML) with renal vein, inferior vena cava (IVC), and right atrial embolism is a rare solid tumor, whose etiology and pathogenesis are still unclear. Moreover, it is often misdiagnosed. One patient with renal AML complicated with renal vein, IVC, and right atrial embolism was admitted to the Second Xiangya Hospital of Central South University, who was a 35-year-old female, without any previous medical history, presented with right low back pain for more than 3 years. Computed tomography (CT) scan showed irregular lobulated fatty density mass in the right kidney, renal vein, IVC, and right atrium. The contrast-enhanced scan showed no enhancement of fat components at each phase and mild enhancement of solid components. Radical resection of the right kidney and removal of tumor thrombus were performed, and there was no recurrence 1 year after the operation. It is rare for renal AML to grow along the renal vein, IVC, and extend to the right atrium. Imaging examination is extremely important, and the CT findings of this case are characteristic, but the diagnosis eventually depends on pathological and immunohistochemical examinations.
Female ; Humans ; Adult ; Vena Cava, Inferior/pathology* ; Angiomyolipoma/surgery* ; Atrial Fibrillation ; Kidney Neoplasms/surgery* ; Embolism/pathology* ; Heart Atria/diagnostic imaging* ; Leukemia, Myeloid, Acute/pathology*

The background of abdominal computed tomography (CT) images is complex, and kidney tumors have different shapes, sizes and unclear edges. Consequently, the segmentation methods applying to the whole CT images are often unable to effectively segment the kidney tumors. To solve these problems, this paper proposes a multi-scale network based on cascaded 3D U-Net and DeepLabV3+ for kidney tumor segmentation, which uses atrous convolution feature pyramid to adaptively control receptive field. Through the fusion of high-level and low-level features, the segmented edges of large tumors and the segmentation accuracies of small tumors are effectively improved. A total of 210 CT data published by Kits2019 were used for five-fold cross validation, and 30 CT volume data collected from Suzhou Science and Technology Town Hospital were independently tested by trained segmentation models. The results of five-fold cross validation experiments showed that the Dice coefficient, sensitivity and precision were 0.796 2 ± 0.274 1, 0.824 5 ± 0.276 3, and 0.805 1 ± 0.284 0, respectively. On the external test set, the Dice coefficient, sensitivity and precision were 0.817 2 ± 0.110 0, 0.829 6 ± 0.150 7, and 0.831 8 ± 0.116 8, respectively. The results show a great improvement in the segmentation accuracy compared with other semantic segmentation methods.
Humans ; Kidney Neoplasms/diagnostic imaging* ; Neural Networks, Computer ; Specimen Handling ; Tomography, X-Ray Computed

Objective To investigate the clinicopathological features and prognosis of chromophobe renal cell carcinoma(ChRCC). Methods The clinical and pathological data of 126 patients with ChRCC treated in Cancer Hospital of Chinese Academy of Medical Sciences were retrospectively analyzed. Results The patients included 64 males and 62 females,with the age of 22-80 years(median of 52 years).The tumor was located on the right side in 70 cases and on the left side in 56 cases.Ultrasound,CT or magnetic resonance imaging(MRI)were performed.Of the 110 cases receiving ultrasound examination,63,23,13,10,and 1 cases showed hypoecho,hyperecho,isoecho,uneven or mixed echo,and dark hypoecho,respectively.Color Doppler flow imaging showed no blood flow signal in 42 cases and low blood flow signal in 60 cases out of 68 cases with blood flow signal.Among the 54 cases receiving CT,50 cases showed equal density or low density and 4 cases showed high density with clear boundary.The enhanced scanning showed mild to moderate uniform or non-uniform reinforcement,mostly below the renal parenchyma,and still showed reinforcement in the delayed period.Among the 97 cases receiving MRI,96 cases showed hypo-or isointense signals and 1 case showed hyperintense signal in T1 weighted images;71 cases showed hyper-or isointense signals and 26 cases showed hypo-or isointense signals in T2 weighted images;93 cases showed hyperintense signals with obvious limited diffusion and 4 cases showed unobvious limited diffusion in diffusion weighted images.Mild to moderate uniform or non-uniform reinforcement was observed in most of the enhanced scans.All the 126 patients underwent surgical treatment,including 64 cases of nephron sparing surgery and 62 cases of radical surgery.Pathological examinations confirmed ChRCC for all the patients,including 91 cases of T1N0M0,15 cases of T2N0M0,and 20 cases of T3N0M0.The immunohistochemical assay demonstrated the positive expression rate of 48.2%(54/112)for CD10,92.3%(96/104)for CD117,8.0%(9/112)for vimentin,85.6%(95/111)for CK7,and 97.6%(83/85)for colloidal iron.Conclusions ChRCC is less common,with low level of malignancy and good prognosis.Since the clinical symptoms of ChRCC are not typical,MRI is an important means of imaging differential diagnosis,and the disease can be confirmed depending on pathological diagnosis.Surgery is the preferred treatment method,and currently there is no standard treatment regimen for metastatic patients.
Adult ; Aged ; Aged, 80 and over ; Carcinoma, Renal Cell/diagnostic imaging* ; Diagnosis, Differential ; Female ; Humans ; Immunohistochemistry ; Kidney Neoplasms/surgery* ; Male ; Middle Aged ; Retrospective Studies ; Young Adult

OBJECTIVE: To explore the feasibility of rapid and accurate three-dimensional (3D) image reconstruction using Uromedix-3D software for urological surgery. METHODS: The original renal thin-slice enhancement CT data were obtained from patients with kidney lesions treated in our hospital between December, 2015 and October, 2018. The self-developed Uromedix- 3D system was used to reconstruct the normal kidney structures, blood vessels, collecting systems and the lesions. The spatial anatomic relationships of the structures were measured and digitized for surgical planning. RESULTS: 3D reconstruction of the kidneys was performed in a total of 173 cases, and the mean time for reconstruction was 31.24±2.012 min. Of these cases, 147 (84.9%) had renal tumors, and 2 had renal tumors with tumor thrombus. In addition to renal tumors, the Uromedix-3D system was also used for reconstructing other lesions including UPJO, kidney stones and retroperitoneal masses. Renal artery reconstruction was performed in 170 cases, which allowed observation of the precise terminal branches (up to 7th grade arterial branch) of the artery; 109 (64%) cases showed the 5th grade arterial branch or above. Renal artery variations were detected in 37 cases, including accessory renal artery (24 cases) and multiple renal arteries (13 cases). The renal veins were reconstructed in 164 cases, and second grade or above (up to the 4th grade) vein branches were observed in 138 (84%) cases. CONCLUSIONS Uromedix-3D system can accurately and efficiently reconstruct the 3D structure of human kidneys and the renal lesions based on enhanced CT data. The reconstructed 3D model allows objective assessment of the spatial anatomical relationship of the lesions to provide assistance in surgical planning.
Humans ; Imaging, Three-Dimensional ; Kidney ; Kidney Calculi ; diagnostic imaging ; surgery ; Kidney Neoplasms ; diagnostic imaging ; surgery ; Tomography, X-Ray Computed

Acute Kidney Injury ; diagnostic imaging ; etiology ; Aged ; Humans ; Male ; Necrosis ; diagnostic imaging ; etiology ; Paraganglioma ; complications ; Postoperative Complications ; Retroperitoneal Neoplasms ; complications ; Skin ; diagnostic imaging ; pathology ; Tomography, X-Ray Computed

Hepatic perivascular epithelioid cell tumors (PEComas) are very rare. We report a primary hepatic PEComa with a review of the literature. A 56-year-old women presented with a nodular mass detected during the management of chronic renal failure and chronic hepatitis C. Diagnostic imaging studies suggested a nodular hepatocellular carcinoma in segment 5 of the liver. The patient underwent partial hepatectomy. A brown-colored expansile mass measuring 3.2×3.0 cm was relatively demarcated from the surrounding liver parenchyma. The tumor was mainly composed of epithelioid cells that were arranged in a trabecular growth pattern. Adipose tissue and thick-walled blood vessels were minimally identified. A small amount of extramedullary hematopoiesis was observed in the sinusoidal spaces between tumor cells. Tumor cells were diffusely immunoreactive for human melanoma black 45 (HMB45) and Melan A, focally immunoreactive for smooth muscle actin, but not for hepatocyte specific antigen (HSA).
Actins ; Adipose Tissue ; Blood Vessels ; Carcinoma, Hepatocellular ; Diagnostic Imaging ; Epithelioid Cells* ; Female ; Hematopoiesis, Extramedullary ; Hepatectomy ; Hepatitis C, Chronic ; Hepatocytes ; Humans ; Kidney Failure, Chronic ; Liver ; MART-1 Antigen ; Melanoma ; Middle Aged ; Muscle, Smooth ; Perivascular Epithelioid Cell Neoplasms

BACKGROUNDThe difference between renal oncocytomas (RO) and renal clear cell carcinomas (RCCs) presents the greatest diagnostic challenge. The aim of this study was to retrospectively determine if RO and RCCs could be differentiated on computed tomography (CT) images on the basis of their enhancement patterns with a new enhancement correcting method.

METHODSForty-six patients with a solitary renal mass who underwent total or partial nephrectomy were included in this study. Fourteen of those were RO and 32 were RCCs. All patients were examined with contrast-enhanced CT. The pattern and degree of enhancement were evaluated. We selected the area that demonstrated the greatest degree of enhancement of the renal lesion in the corticomedullary nephrographic and excretory phase images. Regions of interest (ROI) were also placed in adjacent normal renal cortex for normalization. We used the values of the normal renal cortex that were measured at the same time as divisors. The ratios of lesion-to-renal cortex enhancement were calculated for all three phases. The Student's t-test and Pearson's Chi-square test were used for statistical analyses.

RESULTSAll RCCs masses showed contrast that appeared to be better enhanced than RO on all contrast-enhanced phases of CT imaging, but there was no significant difference in absolute attenuation values between these two diseases (P > 0.05). The ratio of lesion-to-cortex attenuation in the corticomedullary phase showed significantly different values between RO and RCCs. The degree of contrast enhancement in RCCs was equal to or greater than that of the normal renal cortex, but it was less than that of the normal cortex in RO in the corticomedullary phase. The ratio of lesion-to-cortex attenuation in the corticomedullary phase was higher than the cut off value of 1.0 in most RCCs (84%, 27/32) and lower than 1.0 in most RO (93%, 13/14) (P < 0.05). In the nephrographic phase, the ratio of lesion-to-cortex attenuation was higher than that in the corticomedullary phase in most RO (71%, 10/14), showing a prolonged enhancement pattern; and was lower than that in most RCCs (97%, 31/32), showing an early washout pattern (P < 0.05). In the differentiation of RO from RCCs, the sensitivity was 93%, specificity 84%, positive predictive value 72%, negative predictive value 84%, and accuracy for RO was 87, if the ratio of lesion-to-cortex attenuation in a cortex phase was lower than the cutoff value of 1.0. The sensitivity was 71%, specificity was 97%, positive predictive value was 91%, negative predictive value was 91%, and accuracy for RO was 89%, if the ratio of lesion-to-cortex attenuation in nephrographic phase was higher than that in the corticomedullary phase.

CONCLUSIONSThe ratios of renal lesion-to-cortex attenuation ratios may be helpful in differentiating RO from RCCs.

Adenoma, Oxyphilic ; diagnosis ; diagnostic imaging ; Adult ; Aged ; Carcinoma, Renal Cell ; diagnosis ; diagnostic imaging ; Female ; Humans ; Kidney Neoplasms ; diagnosis ; diagnostic imaging ; Male ; Middle Aged ; Tomography, X-Ray Computed

Angiomyolipoma ; diagnostic imaging ; etiology ; Brain ; diagnostic imaging ; Female ; Humans ; Kidney Neoplasms ; diagnostic imaging ; etiology ; Lung Neoplasms ; diagnostic imaging ; etiology ; Lymphangioleiomyomatosis ; diagnostic imaging ; etiology ; Magnetic Resonance Imaging ; Middle Aged ; Pedigree ; Tomography, X-Ray Computed ; Tuberous Sclerosis ; complications ; diagnostic imaging

Abdominal Neoplasms ; complications ; secondary ; therapy ; Acute Lung Injury ; diagnostic imaging ; etiology ; Anemia ; complications ; therapy ; Antineoplastic Combined Chemotherapy Protocols ; therapeutic use ; Child, Preschool ; Etoposide ; administration & dosage ; Fluoroscopy ; Humans ; Ifosfamide ; administration & dosage ; Kidney Neoplasms ; pathology ; Lung Neoplasms ; complications ; secondary ; therapy ; Male ; Postoperative Complications ; diagnostic imaging ; etiology ; Prosthesis Implantation ; Radiography, Thoracic ; Radiotherapy ; Respiratory Distress Syndrome, Adult ; diagnostic imaging ; etiology ; Transfusion Reaction ; Vascular Access Devices