Acceptability of adding a non-contrast abdominal CT scan to screen for kidney cancer and other abdominal pathology within a community-based CT screening programme for lung cancer: A qualitative study.

OBJECTIVES: The Yorkshire Kidney Screening Trial (YKST) is a feasibility study of adding non-contrast abdominal CT scanning to screen for kidney cancer and other abdominal malignancies to community-based CT screening for lung cancer within the Yorkshire Lung Screening Trial (YLST). This study explored the acceptability of the combined screening approach to participants and healthcare professionals (HCPs) involved in the trial. METHODS: We conducted semi-structured interviews with eight HCPs and 25 participants returning for the second round of scanning within YLST, 20 who had taken up the offer of the additional abdominal CT scan and five who had declined. Transcripts were analysed using thematic analysis, guided by the Theoretical Framework of Acceptability. RESULTS: Overall, combining the offer of a non-contrast abdominal CT scan alongside the low-dose thoracic CT was considered acceptable to participants, including those who had declined the abdominal scan. The offer of the additional scan made sense and fitted well within the process, and participants could see benefits in terms of efficiency, cost and convenience both for themselves as individuals and also more widely for the NHS. Almost all participants made an instant decision at the point of initial invitation based more on trust and emotions than the information provided. Despite this, there was a clear desire for more time to decide whether to accept the scan or not. HCPs also raised concerns about the burden on the study team and wider healthcare system arising from additional workload both within the screening process and downstream following findings on the abdominal CT scan. CONCLUSIONS: Adding a non-contrast abdominal CT scan to community-based CT screening for lung cancer is acceptable to both participants and healthcare professionals. Giving potential participants prior notice and having clear pathways for downstream management of findings will be important if it is to be offered more widely.

Automation of Wilms' tumor segmentation by artificial intelligence.

BACKGROUND: 3D reconstruction of Wilms' tumor provides several advantages but are not systematically performed because manual segmentation is extremely time-consuming. The objective of our study was to develop an artificial intelligence tool to automate the segmentation of tumors and kidneys in children. METHODS: A manual segmentation was carried out by two experts on 14 CT scans. Then, the segmentation of Wilms' tumor and neoplastic kidney was automatically performed using the CNN U-Net and the same CNN U-Net trained according to the OV2ASSION method. The time saving for the expert was estimated depending on the number of sections automatically segmented. RESULTS: When segmentations were performed manually by two experts, the inter-individual variability resulted in a Dice index of 0.95 for tumor and 0.87 for kidney. Fully automatic segmentation with the CNN U-Net yielded a poor Dice index of 0.69 for Wilms' tumor and 0.27 for kidney. With the OV2ASSION method, the Dice index varied depending on the number of manually segmented sections. For the segmentation of the Wilms' tumor and neoplastic kidney, it varied respectively from 0.97 to 0.94 for a gap of 1 (2 out of 3 sections performed manually) to 0.94 and 0.86 for a gap of 10 (1 section out of 6 performed manually). CONCLUSION: Fully automated segmentation remains a challenge in the field of medical image processing. Although it is possible to use already developed neural networks, such as U-Net, we found that the results obtained were not satisfactory for segmentation of neoplastic kidneys or Wilms' tumors in children. We developed an innovative CNN U-Net training method that makes it possible to segment the kidney and its tumor with the same precision as an expert while reducing their intervention time by 80%.

[A Case of Metastatic Renal Cancer Responding to Sunitinib as the Eighth Line Therapy].

A 62-year-old male presenting with gross hematuria and right renal mass was referred to our Urology Department. Computed tomography revealed a right renal mass, with multiple pulmonary lesions. He underwent right nephrectomy for highly suspected renal cell carcinoma with pulmonary metastases (cT3aN0M1). The pathological diagnosis was clear cell renal cell carcinoma, pT1b. Following surgery, he was treated with multiple regimens of chemotherapy, ranging from interferon alpha, multiple tyrosine kinase inhibitors such as sorafenib, axitinib, pazopanib and cabozantinib, everolimus, and nivolumab, all of which were discontinued after its induction, either due to adverse events or progressive disease. He was finally administered Sunitinib as the 8th line "last-ditch" treatment, which resulted in significant tumor shrinkage. No disease progression has been observed 25 months after initiating sunitinib administration.

[A Case of Xanthogranulomatous Pyelonephritis with Multiple Lymphadenopathy that was Difficult to Differentiate from Renal Tumor].

A 74-year-old woman presented to our hospital with the main complaint of anorexia and weight loss for several months. Computed tomography (CT) revealed right urinary stone, hydronephrosis, multiple lymphadenopathy, and a mass in the right kidney. Considering these findings, she was suspected to have renal malignancy (kidney or renal pelvis cancer) with multiple lymph node metastases; therefore, nephrectomy was performed. Her pathological diagnosis was xanthogranulomatous pyelonephritis (XGPN). There was no postoperative renal function decline, and multiple lymphadenopathy also disappeared on CT 3 months after surgery. It was judged to be reactive swelling due to inflammation. XGPN is a pathological condition characterized by accumulation of mast cells and activated macrophages in the renal tissue; and, the renal tissue recognizes yellowish granulation growth because of repeating pyelonephritis due to urinary tract passing impairment. In some cases, it is difficult to differentiate XGPN from renal malignancy. Moreover, lymphadenopathy may be lymph node metastasis but may also present reactive enlargement due to the effect of inflammation, making it even more difficult to differentiate when accompanied by lymphadenopathy. We report this case in which it was difficult to differentiate XGPN from renal malignancy considering the scarcity of reports of XGPN accompanied by multiple lymphadenopathy.

Volumetric imaging of the tumor microvasculature reflects outcomes and genomic states of clear cell renal cell carcinoma.

Tumor structure is heterogeneous and complex, and it is difficult to obtain complete characteristics by two-dimensional analysis. The aim of this study was to visualize and characterize volumetric vascular information of clear cell renal cell carcinoma (ccRCC) tumors using whole tissue phenotyping and three-dimensional light-sheet microscopy. Here, we used the diagnosing immunolabeled paraffin-embedded cleared organs pipeline for tissue clearing, immunolabeling, and three-dimensional imaging. The spatial distributions of CD34, which targets blood vessels, and LYVE-1, which targets lymphatic vessels, were examined by calculating three-dimensional density, vessel length, vessel radius, and density curves, such as skewness, kurtosis, and variance of the expression. We then examined those associations with ccRCC outcomes and genetic alteration state. Formalin-fixed paraffin-embedded tumor samples from 46 ccRCC patients were included in the study. Receiver operating characteristic curve analyses revealed the associations between blood vessel and lymphatic vessel distributions and pathological factors such as a high nuclear grade, large tumor size, and the presence of venous invasion. Furthermore, three-dimensional imaging parameters stratified ccRCC patients regarding survival outcomes. An analysis of genomic alterations based on volumetric vascular information parameters revealed that PI3K-mTOR pathway mutations related to the blood vessel radius were significantly different. Collectively, we have shown that the spatial elucidation of volumetric vasculature information could be prognostic and may serve as a new biomarker for genomic alterations. High-end tissue clearing techniques and volumetric immunohistochemistry enable three-dimensional analysis of tumors, leading to a better understanding of the microvascular structure in the tumor space.

Primary Renal Angiosarcoma: Rare Tumour with Lethal Outcomes.

Introduction: Renal haemangioma is a benign tumour, and due to its characteristics, it must be distinguished from malignant diseases. We present a clinical case of primary renal angiosarcoma initially mistaken for haemangioma due to their similarity. Case report: A 58-year-old man was admitted to the hospital with suspicion of pulmonary embolism. The patient complained of pain on the left side. An ultrasound and CT scan of the abdomen showed a tumour mass ~20.5 × 17.2 × 15.4 cm in size in the projection of the left kidney. On CT images, there were data for clear cell renal clear cell carcinoma (ccRCC). A left nephrectomy was performed. However, histological examination revealed renal haemangioma. Three months later, the patient presented to the hospital with abdominal and lumbar pain. A CT scan showed multiple small hypoechoic foci up to 2 cm in size in the liver, lungs, and intra-abdominally, with the most data for carcinosis. Histological re-verification of the left kidney showed a renal vascular tumour with pronounced signs of infarction and necrosis with the majority of the evidence supporting angiosarcoma. Despite treatment, the patient's outcome was fatal. Conclusions: Based on the clinical presentation, radiological images and histological examination data, the tumour was initially misdiagnosed as kidney haemangioma. Due to the rarity of this tumour, there are no established treatment protocols or clinical guidelines for managing primary kidney angiosarcoma.

First incidence of extrarenal wilms tumor within the spinal canal in the adult population: a novel case report and literature review.

BACKGROUND: Wilms tumor (WT), also known as nephroblastoma, is rare in adults, accounting for merely 3% of all nephroblastomas or 0.2 cases per million individuals. Extrarenal Wilms tumor (ERWT) emerges outside the renal boundaries and comprises 0.5 to 1% of all WT cases, with even rarer incidences in adults. Oncogenic mutations associated with ectopic nephrogenic rests (NR) may contribute to ERWT development. Diagnosis involves surgical resection and pathology examination. Due to scarce cases, adults often rely on pediatric guidelines. We thoroughly searched PubMed, Scopus, and Web of Science databases to establish our case's uniqueness. To the best of our knowledge, this is the first documented incidence of extrarenal Wilms tumor within the spinal canal in the adult population. CASE PRESENTATION: A 22-year-old woman with a history of congenital lipo-myelomeningocele surgery as an infant presented with a 6-month history of back pain. This pain gradually resulted in limb weakness, paraparesis, and loss of bladder and bowel control. An MRI showed a 6 × 5 × 3 cm spinal canal mass at the L4-S1 level. Consequently, a laminectomy was performed at the L4-L5 level to remove the intramedullary tumor. Post-surgery histopathology and immunohistochemistry confirmed the tumor as ERWT with favorable histology without any teratomatous component. CONCLUSION: This report underscores the rarity of extrarenal Wilms tumor (ERWT) in adults, challenging conventional assumptions about its typical age of occurrence. It emphasizes the importance of clinical awareness regarding such uncommon cases. Moreover, the co-occurrence of spinal ERWTs and a history of spinal anomalies warrants further investigation.

Unusual Unique Renal Metastasis of Rectal Carcinoma.

Rectal cancer Is a Common malignant pathology; its usual spread in volves the liver and lungs. The occurrence of renal metastases is exceptional. CT scanning aims to evaluate extension and may incidentally reveal a renal mass, which can be better characterized through MRI and ultrasound. We describe a case of a solitary renal metastasis from rectal cancer and underscore the significant role of imaging in positively diagnosing this uncommon pathology.

Analysis of Imaging and Pathologic Features in Eosinophilic Solid and Cystic Renal Cell Carcinoma.

OBJECTIVE: Eosinophilic solid and cystic renal cell carcinoma (ESC-RCC) is rare and difficult to diagnose. Therefore, we aim to investigate the imaging and pathologic features of ESC-RCC. METHODS: Fifteen cases of ESC-RCC with pathologically confirmed diagnoses were retrospectively collected: CT was performed in 15 cases and MRI in 9 cases. RESULTS: In these patients (6 males and 9 females) (age: mean, 53.3 ± 14.7 years; range, 27-72 years), all tumors were unilateral, renal, and solitary with no clinical symptoms and were classified into-type 1: cystic-solid component, with equal cystic and solid components, was the most common (8/15, 53.3%); type 2: predominantly cystic with a small solid component (4/15, 26.7%); and type 3: predominantly solid (3/15, 20%). The solid component showed equal/slightly higher density on the CT-plain-scan, equal/slightly high signal on the T1-weighted image (T1WI), and low signal on the T2-weighted image (T2WI). Ten cases showed progressive enhancement, while 5 showed a fast-wash-in and fast-wash-out enhancement. One patient experienced hemorrhage, while the others showed no signs of hemorrhage, necrosis, fat, or calcification. Pathologically, the tumor showed cystic solidity, with eosinophilic cytoplasm and granular basophilic-colored spots with focal or diffuse expression of CK20. Ten patients had componential nephrectomy and 5 had radical nephrectomy. No recurrence or metastasis was noted in any case at the follow-up (8-49 months). CONCLUSION: This study describes the imaging and pathologic features of a rare type of renal cancer and proposes 3 imaging types to enhance physicians' diagnosis of this disease and guide clinical diagnosis and treatment.

Qualitative and quantitative assessment of non-clear cell renal cell carcinoma using contrast-enhanced ultrasound.

BACKGROUND: Non-clear cell renal cell carcinoma (nccRCC) represents a rare form of renal cell carcinoma (RCC) in the clinic. It is now understood that contrast-enhanced ultrasound (CEUS) exhibits diverse manifestations and can be prone to misdiagnosis. Therefore, summarizing the distinctive features of contrast-enhanced ultrasonography is essential for differentiation from ccRCC. OBJECTIVE: This study aims to evaluate the diagnostic efficacy of qualitative and quantitative CEUS in diagnosing nccRCC to enhance our understanding of this condition. METHODS: We conducted a retrospective analysis of 21 patients with confirmed nccRCC following surgery and assessed the characteristic conventional ultrasound and CEUS imaging features. The paired Wilcoxon signed-rank sum test was employed to compare differences in CEUS time-intensity curve (TIC) parameters between the lesions and the normal renal cortex. RESULTS: Routine ultrasound revealed the following primary characteristics in the 21 nccRCC cases: hypoechoic appearance (10/21, 47.6%), absence of liquefaction (18/21, 66.7%), regular shape (19/21, 90.5%), clear boundaries (21/21, 100%), and absence of calcification (17/21, 81%). Color Doppler flow imaging (CDFI) indicated a low blood flow signal (only 1 case of grade III). Qualitative CEUS analysis demonstrated that nccRCC predominantly exhibited slow progression (76.1%), fast washout (57%), uniformity (61.9%), low enhancement (71.5%), and ring enhancement (61.9%). Quantitative CEUS analysis revealed that parameters such as PE, WiAUC, mTTI, WiR, WiPI, WoAUC, WiWoAUC, and WOR in the lesions were significantly lower than those in the normal renal cortex (Z=-3.980, -3.563, -2.427, -3.389, -3.980, -3.493, -3.528, -2.763, P < 0.001, < 0.001, = 0.015, = 0.001, < 0.001, < 0.001, < 0.001, = 0.006). However, there were no significant differences in RT, TTP, FT, or QOF (all P > 0.05). CONCLUSION: nccRCC exhibits distinctive CEUS characteristics, including slow progression, fast washout, low homogeneity enhancement, and ring enhancement, which can aid in distinguishing nccRCC from ccRCC.

A CAIX Dual-Targeting Small-Molecule Probe for Noninvasive Imaging of ccRCC.

Carbonic anhydrase IX (CAIX), a zinc metal transmembrane protein, is highly expressed in 95% of clear cell renal cell carcinomas (ccRCCs). A positron emission tomography (PET) probe designed to target CAIX in nuclear medicine imaging technology can achieve precise positioning, is noninvasive, and can be used to monitor CAIX expression in lesions in real time. In this study, we constructed a novel acetazolamide dual-targeted small-molecule probe [68Ga]Ga-LF-4, which targets CAIX by binding to a specific amino acid sequence. After attenuation correction, the radiolabeling yield reached 66.95 ± 0.57% (n = 5) after 15 min of reaction and the radiochemical purity reached 99% (n = 5). [68Ga]Ga-LF-4 has good in vitro and in vivo stability, and in vivo safety and high affinity for CAIX, with a Kd value of 6.62 nM. Moreover, [68Ga]Ga-LF-4 could be quickly cleared from the blood in vivo. The biodistribution study revealed that the [68Ga]Ga-LF-4 signal was concentrated in the heart, lung, and kidney after administration, which was the same as that observed in the micro-PET/CT study. In a ccRCC patient-derived xenograft (PDX) model, the signal significantly accumulated in the tumor after administration, where it was retained for up to 4 h. After competitive blockade with LF-4, uptake at the tumor site was significantly reduced. The SUVmax of the probe [68Ga]Ga-LF-4 at the ccRCC tumor site was three times greater than that in the PC3 group with low CAIX expression at 30 min (ccRCC vs PC3:1.86 ± 0.03 vs 0.62 ± 0.01, t = 48.2, P < 0.0001). These results indicate that [68Ga]Ga-LF-4 is a novel small-molecule probe that targets CAIX and can be used to image localized and metastatic ccRCC lesions.

Robot-assisted Partial Nephrectomy With Selective Artery Clamping for Renal Cell Carcinoma in Horseshoe Kidney.

BACKGROUND: Robot-assisted partial nephrectomy (RAPN) has become the standard treatment for small renal tumors, including highly complex cases. However, applying RAPN to renal tumors in the horseshoe kidney (HSK) is clinically challenging due to malformations and complex blood supply. Herein, we present two cases of RAPN in patients with HSK treated using selective artery clamping methods. CASE REPORTS: A 61-year-old male with a 15 mm renal tumor located on the upper pole of the right HSK was referred to our Department. The patient underwent RAPN via the transperitoneal approach, following a three-dimensional computed tomography (3D-CT) assessment. Additionally, before surgery, we confirmed which renal arteries would be clamped in surgery by examining the kidney regions supplied by each renal artery. The second patient referred to our Department, a 45-year-old male, had a 46 mm renal tumor located on the isthmus of the HSK. His tumor received blood supply from two renal arteries, with the bilateral collecting systems converging and forming a ureter on 3D-CT. The patient underwent RAPN through an intraperitoneal approach in the semi-lateral position, with port placement lower than in standard RAPN. Pathological examinations revealed clear-cell renal cell carcinoma with negative surgical margins in both cases. Both patients had no recurrences or metastases at 53 and 13 months post-surgery, respectively. CONCLUSION: We present cases successfully treated with RAPN with selective artery clamping methods for HSK using 3D-CT without encountering complications, even in isthmus tumors.

Ultrasound contrast-enhanced radiomics model for preoperative prediction of the tumor grade of clear cell renal cell carcinoma: an exploratory study.

BACKGROUND: This study aims to explore machine learning(ML) methods for non-invasive assessment of WHO/ISUP nuclear grading in clear cell renal cell carcinoma(ccRCC) using contrast-enhanced ultrasound(CEUS) radiomics. METHODS: This retrospective study included 122 patients diagnosed as ccRCC after surgical resection. They were divided into a training set (n = 86) and a testing set(n = 36). CEUS radiographic features were extracted from CEUS images, and XGBoost ML models (US, CP, and MP model) with independent features at different phases were established. Multivariate regression analysis was performed on the characteristics of different radiomics phases to determine the indicators used for developing the prediction model of the combined CEUS model and establishing the XGBoost model. The training set was used to train the above four kinds of radiomics models, which were then tested in the testing set. Radiologists evaluated tumor characteristics, established a CEUS reading model, and compared the diagnostic efficacy of CEUS reading model with independent characteristics and combined CEUS model prediction models. RESULTS: The combined CEUS radiomics model demonstrated the best performance in the training set, with an area under the curve (AUC) of 0.84, accuracy of 0.779, sensitivity of 0.717, specificity of 0.879, positive predictive value (PPV) of 0.905, and negative predictive value (NPV) of0.659. In the testing set, the AUC was 0.811, with an accuracy of 0.784, sensitivity of 0.783, specificity of 0.786, PPV of 0.857, and NPV of 0.688. CONCLUSIONS: The radiomics model based on CEUS exhibits high accuracy in non-invasive prediction of ccRCC. This model can be utilized for non-invasive detection of WHO/ISUP nuclear grading of ccRCC and can serve as an effective tool to assist clinical decision-making processes.

Fast and High-Resolution T2 Mapping Based on Echo Merging Plus k-t Undersampling with Reduced Refocusing Flip Angles (TEMPURA) as Methods for Human Renal MRI.

PURPOSE: To develop a highly accelerated multi-echo spin-echo method, TEMPURA, for reducing the acquisition time and/or increasing spatial resolution for kidney T2 mapping. METHODS: TEMPURA merges several adjacent echoes into one k-space by either combining independent echoes or sharing one echo between k-spaces. The combined k-space is reconstructed based on compressed sensing theory. Reduced flip angles are used for the refocusing pulses, and the extended phase graph algorithm is used to correct the effects of indirect echoes. Two sequences were developed: a fast breath-hold sequence; and a high-resolution sequence. The performance was evaluated prospectively on a phantom, 16 healthy subjects, and two patients with different types of renal tumors. RESULTS: The fast TEMPURA method reduced the acquisition time from 3-5 min to one breath-hold (18 s). Phantom measurements showed that fast TEMPURA had a mean absolute percentage error (MAPE) of 8.2%, which was comparable to a standardized respiratory-triggered sequence (7.4%), but much lower than a sequence accelerated by purely k-t undersampling (21.8%). High-resolution TEMPURA reduced the in-plane voxel size from 3 × 3 to 1 × 1 mm2, resulting in improved visualization of the detailed anatomical structure. In vivo T2 measurements demonstrated good agreement (fast: MAPE = 1.3%-2.5%; high-resolution: MAPE = 2.8%-3.3%) and high correlation coefficients (fast: R = 0.85-0.98; high-resolution: 0.82-0.96) with the standardized method, outperforming k-t undersampling alone (MAPE = 3.3-4.5%, R = 0.57-0.59). CONCLUSION: TEMPURA provides fast and high-resolution renal T2 measurements. It has the potential to improve clinical throughput and delineate intratumoral heterogeneity and tissue habitats at unprecedented spatial resolution.

Evaluation of image-pro plus assisted superb microvascular imaging for differential diagnosis of renal masses.

OBJECTIVE: Previous research on diagnostic assessment by superb microvascular imaging (SMI) were based on qualitative or semi-quantitative assessments of vascularity, which may be subjective and unrepeatable by different sonographers. This study aimed to evaluate diagnostic performance of SMI Image-pro Plus (IPP) based vascular index (VI) for malignant renal masses. METHOD: We retrospectively reviewed 222 masses in 214 patients who underwent SMI between August 2019 and August 2022 in our study. We evaluated the diagnostic performance of blood flow via Alder grade, VI based on both IPP and SMI. RESULTS: The kappa consistency of the Adler grade and VI for renal masses was classified among different observers were 0.765 and 0.824. The intra-observers correlation ecoefficiency (ICC) were 0.727 and 0.874. Benign renal masses were mainly Adler grade 0, grade I, and grade II, VI was 4.30 ± 4.27 (Range 0.98-16.42); while malignant masses were mainly Adler grade III, VI was 14.95 ± 10.94 (Range 0.79-56.89). VI was higher in malignant than benign masses (t = 15.638, P < 0.01). Among the malignant masses, the mean VI in clear cell renal cell carcinoma was higher than that in papillary renal cell carcinoma and chromophobe renal cell carcinoma (F = 30.659, P < 0.01). The sensitivity, specificity and accuracy of SMI were 80.00%, 71.15%, and 78.64%, respectively. The sensitivity, specificity, and accuracy were 60.59%, 88.46%, and 80.18% by using a VI of 7.95 as the cutoff value to identify malignant lesions from benign masses yielded. VI had better diagnostic efficiency than ultrasonic characteristics and Adler grade in benign and malignant differential diagnosis (Z = 4.851, P < 0.01; Z = 2.732, P < 0.01). CONCLUSION: VI was higher in malignant than benign in renal masses. In malignant masses, VI in CCRCC was higher than that in papillary renal cell carcinoma and ChRCC. As a noninvasive examination, it had important clinical significance in the differential diagnosis of renal masses. VI from IPP may assist sonographer in distinguish renal malignances as a quantitative tool for vascularity.

Time conditioning for arbitrary contrast phase generation in interventional computed tomography.

Minimally invasive ablation techniques for renal cancer are becoming more popular due to their low complication rate and rapid recovery period. Despite excellent visualisation, one drawback of the use of computed tomography (CT) in these procedures is the requirement for iodine-based contrast agents, which are associated with adverse reactions and require a higher x-ray dose. The purpose of this work is to examine the use of time information to generate synthetic contrast enhanced images at arbitrary points after contrast agent injection from non-contrast CT images acquired during renal cryoablation cases. To achieve this, we propose a new method of conditioning generative adversarial networks with normalised time stamps and demonstrate that the use of a HyperNetwork is feasible for this task, generating images of competitive quality compared to standard generative modelling techniques. We also show that reducing the receptive field can help tackle challenges in interventional CT data, offering significantly better image quality as well as better performance when generating images for a downstream segmentation task. Lastly, we show that all proposed models are robust enough to perform inference on unseen intra-procedural data, while also improving needle artefacts and generalising contrast enhancement to other clinically relevant regions and features.

Deep Learning Assessment of Small Renal Masses at Contrast-enhanced Multiphase CT.

Background Accurate characterization of suspicious small renal masses is crucial for optimized management. Deep learning (DL) algorithms may assist with this effort. Purpose To develop and validate a DL algorithm for identifying benign small renal masses at contrast-enhanced multiphase CT. Materials and Methods Surgically resected renal masses measuring 3 cm or less in diameter at contrast-enhanced CT were included. The DL algorithm was developed by using retrospective data from one hospital between 2009 and 2021, with patients randomly allocated in a training and internal test set ratio of 8:2. Between 2013 and 2021, external testing was performed on data from five independent hospitals. A prospective test set was obtained between 2021 and 2022 from one hospital. Algorithm performance was evaluated by using the area under the receiver operating characteristic curve (AUC) and compared with the results of seven clinicians using the DeLong test. Results A total of 1703 patients (mean age, 56 years ± 12 [SD]; 619 female) with a single renal mass per patient were evaluated. The retrospective data set included 1063 lesions (874 in training set, 189 internal test set); the multicenter external test set included 537 lesions (12.3%, 66 benign) with 89 subcentimeter (≤1 cm) lesions (16.6%); and the prospective test set included 103 lesions (13.6%, 14 benign) with 20 (19.4%) subcentimeter lesions. The DL algorithm performance was comparable with that of urological radiologists: for the external test set, AUC was 0.80 (95% CI: 0.75, 0.85) versus 0.84 (95% CI: 0.78, 0.88) (P = .61); for the prospective test set, AUC was 0.87 (95% CI: 0.79, 0.93) versus 0.92 (95% CI: 0.86, 0.96) (P = .70). For subcentimeter lesions in the external test set, the algorithm and urological radiologists had similar AUC of 0.74 (95% CI: 0.63, 0.83) and 0.81 (95% CI: 0.68, 0.92) (P = .78), respectively. Conclusion The multiphase CT-based DL algorithm showed comparable performance with that of radiologists for identifying benign small renal masses, including lesions of 1 cm or less. Published under a CC BY 4.0 license. Supplemental material is available for this article.