A novel model of artificial intelligence based automated image analysis of CT urography to identify bladder cancer in patients investigated for macroscopic hematuria.

OBJECTIVE: To evaluate whether artificial intelligence (AI) based automatic image analysis utilising convolutional neural networks (CNNs) can be used to evaluate computed tomography urography (CTU) for the presence of urinary bladder cancer (UBC) in patients with macroscopic hematuria. METHODS: Our study included patients who had undergone evaluation for macroscopic hematuria. A CNN-based AI model was trained and validated on the CTUs included in the study on a dedicated research platform (Recomia.org). Sensitivity and specificity were calculated to assess the performance of the AI model. Cystoscopy findings were used as the reference method. RESULTS: The training cohort comprised a total of 530 patients. Following the optimisation process, we developed the last version of our AI model. Subsequently, we utilised the model in the validation cohort which included an additional 400 patients (including 239 patients with UBC). The AI model had a sensitivity of 0.83 (95% confidence intervals [CI], 0.76-0.89), specificity of 0.76 (95% CI 0.67-0.84), and a negative predictive value (NPV) of 0.97 (95% CI 0.95-0.98). The majority of tumours in the false negative group (n = 24) were solitary (67%) and smaller than 1 cm (50%), with the majority of patients having cTaG1-2 (71%). CONCLUSIONS: We developed and tested an AI model for automatic image analysis of CTUs to detect UBC in patients with macroscopic hematuria. This model showed promising results with a high detection rate and excessive NPV. Further developments could lead to a decreased need for invasive investigations and prioritising patients with serious tumours.

Discrepant guidelines in the evaluation of hematuria.

PURPOSE: To assess discrepancies in current imaging recommendations for hematuria among North American societies: American College of Radiology (ACR), American Urological Association (AUA), and Canadian Urological Association (CUA). METHODS: The latest available ACR Appropriateness Recommendations, AUA guidelines, and CUA guidelines were reviewed. AUA and CUA guidelines imaging recommendations by variants and level of appropriateness were converted to match the style of ACR. Imaging recommendations including modality, anatomy, and requirement for contrast were recorded. RESULTS: Clinical variants included microhematuria without risk factors, microhematuria with risk factors, gross hematuria, and microhematuria during pregnancy. CUA recommends ultrasound kidneys as the first-line imaging study in the first 3 variants; pregnancy is not explicitly addressed. For hematuria without risk factors, ACR does not routinely recommend imaging, while AUA recommends shared decision-making to decide repeat urinalysis versus cystoscopy with ultrasound kidneys. For hematuria with risk factors and gross hematuria, ACR recommends CT urography; MR urography can also be considered in gross hematuria. AUA further stratifies intermediate- and high-risk patients, for which ultrasound kidneys and CT urography are recommended, respectively. For pregnancy, ACR and AUA both recommend ultrasound kidneys, though AUA additionally recommends consideration of CT or MR urography after delivery. CONCLUSION: There is no universally agreed upon algorithm for diagnostic evaluation. Discrepancies centered on the role of upper tract imaging with ultrasound versus CT. Prospective studies and/or repeat simulation studies that apply newly updated guidelines are needed to further clarify the role of imaging, particularly for patients with microhematuria with no and intermediate risk factors.

Essentials of Computed Tomography Imaging of Hematuria.

Hematuria is defined usually as the presence of blood in the urine, either on voiding or in a catheterized specimen. Hematuria is broadly divided into microscopic and gross hematuria and may be symptomatic or asymptomatic. The causes of hematuria include a very wide spectrum of conditions. However, here, we have filtered the causes causing gross hematuria, including calculus, trauma, tumors, vascular, and miscellaneous causes. Plain X-rays of the kidney, ureter, and bladder; ultrasound; intravenous urography; computed tomography (CT); magnetic resonance imaging; retrograde ureterography and pyelography (RGP); cystoscopy; and ureteroscopy are techniques that are useful for diagnosis. In the past, one or a combination of several techniques was used to evaluate hematuria but recently, advances in CT urography mean that it can be used alone for this task. This article briefly reviews the common causes of gross hematuria in adults and their evaluation by CT-based urography. Gross hematuria is evaluated well with CT scan urography which includes an unenhanced scan, the nephrographic phase, and the excretory phase. Unenhanced scans are routinely performed to evaluate the basic parameters such as the size, shape, position, and outline of the kidneys and calculus disease, which is the most common cause of hematuria. Renal parenchymal diseases including masses are best visualized in the nephrographic phase along with other abdominal organs. Delayed excretory phases including the kidneys, ureters, and bladder are useful for detecting urothelial diseases. CT urography's protocol permits evaluations of hematuria through a single examination.

Diagnostic Imaging in the Evaluation of Asymptomatic Microhematuria: Systematic Review and Meta-analysis.

PURPOSE: Microhematuria is a highly prevalent condition with a low associated risk of urothelial and upper tract malignancy. The AUA Guidelines recently changed recommendations for imaging favoring renal ultrasound for low- and intermediate-risk patients with microhematuria. We summarize the diagnostic test characteristics of computed tomography urography, renal ultrasound, and magnetic resonance urography in comparison with surgical pathology for the diagnosis of upper urinary tract cancer in microhematuria and gross hematuria patients. MATERIALS AND METHODS: This study is a systematic review and meta-analysis using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines from evidence collected for the 2020 AUA Microhematuria Guidelines report, including studies assessing imaging following diagnosis of hematuria published from January 2010 through December 2019. RESULTS: The search identified 20 studies which reported the prevalence of malignant and benign diagnoses in relation to imaging modality, of which 6 were included in the quantitative analysis. For the detection of renal cell carcinoma and upper urinary tract carcinoma in patients with microhematuria and gross hematuria, computed tomography urography had a sensitivity of 94% (95% CI, 84%-98%) and a specificity of 99% (95%CI, 97%-100%) with a certainty of evidence rating of very low and low, respectively when 4 studies were pooled. In comparison, ultrasound demonstrated a sensitivity ranging from 14%-96% (low certainty of evidence) and a specificity of 99%-100% in 2 studies (moderate certainty of evidence), while magnetic resonance urography demonstrated a sensitivity of 83% and specificity of 86% in 1 study with a low certainty of evidence. CONCLUSIONS: In a limited data set for each individual imaging modality, computed tomography urography appears the most sensitive imaging modality for the diagnostic evaluation of microhematuria. Future studies will be needed to evaluate the clinical and health system financial impacts of the change in guideline recommendations from computed tomography urography to renal ultrasound in evaluating low- and intermediate-risk patients with microhematuria.

The efficacy of ultrasonography for the detection of upper tract urothelial carcinoma.

PURPOSE: Ultrasonography and computed tomography urography are two commonly used modalities to image the upper tracts for the evaluation of hematuria. This study evaluated the efficacy of ultrasonography for the detection of upper tract urothelial carcinoma compared to computed tomography urography as a standard reference. METHODS: This retrospective study included patients with urothelial carcinoma of the renal pelvis and/or ureter who were diagnosed using computed tomography urography and underwent surgical treatment. We calculated the sensitivity of ultrasonography in upper tract urothelial carcinoma diagnosis, further classified the degree of hydronephrosis on ultrasonography, and analyzed the relationship between the sensitivity and the degree of hydronephrosis and tumor location. Additionally, the usefulness of the combination of the screening ultrasonography findings, the presence of gross hematuria, and/or urine cytology was analyzed. RESULTS: This study included 136 patients with upper urothelial carcinoma. Ultrasonography in the diagnosis had 45.6% sensitivity, and ultrasonography findings, including the detection of hydronephrosis, were present in 72.8%. The presence of hydronephrosis and tumor location were associated with detection by ultrasonography. The tumor was identified in a total of 134 (98.5%) patients by combining tumor detection and hydronephrosis using ultrasonography with gross hematuria and positive urine cytology as screening. CONCLUSION: Ultrasonography showed acceptable sensitivity for upper tract urothelial carcinoma diagnosis. Considering the hydronephrosis findings, ultrasonography is a useful screening tool for upper tract urothelial carcinoma. Additionally, excessive computed tomography examinations can be reduced by adding gross hematuria and positive urine cytology.

CT of the urinary tract revisited.

Computed tomography (CT) of the abdomen is usually appropriate for the initial imaging of many urinary tract diseases, due to its wide availability, fast scanning and acquisition of thin slices and isotropic data, that allow the creation of multiplanar reformatted and three-dimensional reconstructed images of excellent anatomic details. Non-enhanced CT remains the standard imaging modality for assessing renal colic. The technique allows the detection of nearly all types of urinary calculi and the estimation of stone burden. CT is the primary diagnostic tool for the characterization of an indeterminate renal mass, including both cystic and solid tumors. It is also the modality of choice for staging a primary renal tumor. Urolithiasis and urinary tract malignancies represent the main urogenic causes of hematuria. CT urography (CTU) improves the visualization of both the upper and lower urinary tract and is recommended for the investigation of gross hematuria and microscopic hematuria, in patients with predisposing factors for urologic malignancies. CTU is highly accurate in the detection and staging of upper tract urothelial malignancies. CT represents the most commonly used technique for the detection and staging of bladder carcinoma and the diagnostic efficacy of CT staging improves with more advanced disease. Nevertheless, it has limited accuracy in differentiating non-muscle invasive bladder carcinoma from muscle-invasive bladder carcinoma. In this review, clinical indications and the optimal imaging technique for CT of the urinary tract is reviewed. The CT features of common urologic diseases, including ureterolithiasis, renal tumors and urothelial carcinomas are discussed.

Evaluation of screening with urine dipsticks and renal ultrasonography for 3-year-olds in Chiba City over 30 years.

BACKGROUND: Urinary screening for 3-year-olds cannot adequately detect congenital anomalies of the kidney and urinary tract (CAKUT). METHODS: Urinary screening for 3-year-olds was investigated over 30 years. Dipsticks for proteinuria, hematuria, glycosuria, leukocyturia, and nitrite at first screening, and dipsticks, urinary sediments, and renal ultrasonography at second screening were performed. Screening results were evaluated. RESULTS: The positive rates of proteinuria, hematuria, leukocyturia, and nitrite relative to 218,831 children at the first screening were 1.0%, 4.6%, 2.3%, and 0.88%, respectively. Thirty-seven glomerular disease, 122 CAKUT, and 5 urological disease cases were found. We detected 6 stage 3-4 chronic kidney disease (CKD) and 3 end-stage kidney disease cases, including 3 CAKUT, comprising 2 bilateral renal hypoplasia and 1 vesicoureteral reflux (VUR), and 6 glomerular diseases, comprising 4 focal segmental glomerulosclerosis and 2 Alport syndrome. The positive rates relative to 218,831 children and CKD detection rates for each tentative diagnosis of mild hematuria, severe hematuria, proteinuria and hematuria, proteinuria, and suspected urinary tract infection were 1.4% and 0.67%, 0.11% and 3.7%, 0.01% and 28.6%, 0.02% and 45.0%, and 0.08% and 9.7%, respectively. Among 14 VUR cases with significant bacteriuria, 13 were found by leukocyturia, 12 had grade ≥ IV VUR, and 10 had severe renal scars. CONCLUSIONS: Nine stage 3-5 CKD cases comprising 3 CAKUT and 6 glomerular disease were found by urinary screening of 3-year-olds among 218,831 children. The combination of urine dipsticks including leukocyturia at the first screening and ultrasonography at the second screening appeared useful.

Ultrasonographic and contrast-enhanced CT imaging diagnosis of idiopathic renal hematuria with bilateral hydronephrosis and hydroureter in a dog.

A 5-year-old spayed female Maltese presented with a 1-week history of severe hematuria. Abdominal ultrasonography and thoracic, and abdominal computed tomography identified bilateral hydronephrosis and hydroureter due to an obstruction at the left ureter and urinary bladder lesion with no evidence of metastasis. After surgical removal of the material and placement of a temporary ureteral stent, the patient was able to urinate normally. Histological examination revealed a massive blood clot. Based on our review of the literature, this is the first published report describing the imaging diagnosis of obstructive hydronephrosis and hydroureter induced by idiopathic renal hematuria in a dog.

The Nutcracker Syndrome.

Nutcracker syndrome (NCS) is a rare condition caused by the compression of the left renal vein between the abdominal aorta and the superior mesenteric artery. NCS may present with unexplained hematuria. This case report presents a 43-year-old healthy female without any complaints who had newly-detected hematuria in urinalysis during her annual examination. Her physical examination and the whole abdominal ultrasonography failed to explain the cause of hematuria. Further investigation with contrast-enhanced upper abdominal computed tomography revealed a NCS. In unexplained cases of asymptomatic hematuria NCS should be taken into account after excluding other preliminary diagnoses.

[A patient with a palpable mass, haematuria and flank pain]. / Een vrouw met een palpabele zwelling, hematurie en flankpijn.

In this case report we present a 54-year-old female with progressive pain in the left flank. Physical examination showed a non-mobile, painless mass in the left upper abdomen. CT revealed an exceptionally large kidney stone. Stone removal (448 g) was performed by hand-assisted laparoscopic nephrectomy.

Comparison of Conventional and Triple Bolus Computerized Tomographic Urography Protocols for Radiation Dose Reduction in Hematuria Evaluation: A Randomized Controlled Trial.

PURPOSE: Computerized tomographic urography is the diagnostic tool of choice for evaluating hematuria. In keeping with the ALARA (As Low As Reasonably Achievable) principle, we evaluated a triple bolus computerized tomography protocol designed to reduce radiation exposure. MATERIALS AND METHODS: Patients with macroscopic or microscopic hematuria were prospectively randomized to conventional computerized tomography (100) or triple bolus computerized tomography (100). The triple bolus computerized tomography protocol entails 2 scans: pre-contrast scan followed by 3 contrast injections at 40 seconds, 60 seconds and 20 minutes prior to the second scan to capture all 3 phases. The conventional computerized tomography protocol requires 4 scans: pre-contrast scan, and 3 post-contrast scans at the corticomedullary, nephrographic and excretory phases. Radiation exposure and the detection of urological pathology were recorded based on radiology reports. RESULTS: There were no differences in patient demographics or body mass index between the 2 groups. Triple bolus computerized tomography exposed patients to 33% less radiation (1,715 vs 1,145 mGy*cm for conventional vs triple bolus computerized tomography; p <0.001). For macroscopic hematuria, the pathology detection rates were 70% for triple bolus and 73% for conventional computerized tomography (p=0.72). For microscopic hematuria, the detection rates were 59% for triple bolus and 50% for conventional computerized tomography (p=0.68). In both groups, the rates of detection of urolithiasis, renal cysts, urological masses, bladder pathology and prostate pathology were no different between triple bolus and conventional computerized tomography. CONCLUSIONS: In both the settings of macroscopic and microscopic hematuria evaluation, triple bolus computerized tomography significantly reduces radiation exposure while providing equivalent detection of genitourinary pathology compared to conventional computerized tomography. The ability to detect upper tract filling defects was not specifically tested.

Prevalence of Urologic Disease Among Patients Investigated for Hematuria With CT Urography.

PURPOSE: The current study evaluated the prevalence of urologic disease among patients with hematuria referred for computerized tomography (CT) urography to determine which patients require investigation with CT urography. METHODS: We retrospectively reviewed radiology reports of 1046 CT urograms performed for the indication of microscopic (43.7%) or gross hematuria (56.3%). Urological findings were categorized as negative, benign, or suspicious (pathologically confirmed) for malignancy. RESULTS: Of 1046 CT urograms performed, 53.5% were negative, 36.4% were benign, and 10% were suspicious for malignancy. The most common benign finding was urolithiasis (22.3%). Overall, urinary tract malignancies were present in 3.6% of patients, and the rate was significantly higher (P < .001) for gross (5.8%) than microscopic hematuria (0.9%). CT urography identified 0.6% patients with upper urinary tract malignancies; the malignancy rate was significantly higher (P = .038) for gross (1%) than microscopic hematuria (0%), and no significant sex (P = 1.00; male = 0.6%, female = 0.6%) or age (P = .600; < 50 years = 0%, ≥ 50 years = 0.7%) differences were observed. Logistic regression revealed that being male was associated with gross hematuria (odds ratio [OR] = 2.92), and that both age and gross hematuria (ORs = 1.06 and 5.13, respectively) were associated with malignancy. CONCLUSIONS: CT urography found no upper urinary tract malignancies in 99.4% of patients presenting with hematuria, including all patients with microscopic hematuria and those with gross hematuria <50 years old. Investigating these subgroups with CT urography may be unnecessary and result in increased patient morbidity and health-care costs.

Urothelial-phase thin-section MDCT of the bladder in patients with hematuria: added value of multiplanar reformatted images.

PURPOSE: To evaluate the diagnostic performance of MDCT with axial images and multiplanar reformatted (MPR) images from the urothelial phase of the bladder in patients with hematuria using cystoscopy as the reference standard. MATERIALS AND METHODS: Our IRB for human investigation approved this study, and informed consent was waived. We included 192 patients (121 men, 71 women; age range 17-90 years; mean age ± SD: 60 ± 14 years) who underwent contrast-enhanced MDCT (scan delay: 70 s; section thickness: 2 mm) and conventional cystoscopy examination for painless gross hematuria or recurrent microscopic hematuria. Two radiologists in consensus interpreted the images for the presence or absence of bladder lesions. Using the kappa statistic, the patient-based agreement was determined between the CT and cystoscopic findings. We compared the diagnostic performance of axial images to those with coronal and sagittal reformations to detect bladder lesions. RESULTS: MDCT showed excellent agreement between cystoscopy-axial scans (κ = 0.896) and axial with reformatted images (κ = 0.948). The sensitivity, specificity, and accuracy of MDCT were 94%, 96%, and 95% in the axial scans and 98%, 97%, and 97% in the axial with reformatted images, respectively. All statistical parameters of diagnostic performance were similar between the axial and the reformatted images (p > .05). CONCLUSION: Axial MDCT imaging demonstrates high diagnostic performance in detecting bladder lesions, but additional reformatted images can improve diagnostic accuracy.

Comparison of quality of urinary bladder filling in CT urography with different doses of furosemide in the work-up of patients with macroscopic hematuria.

INTRODUCTION: The protocol for preparation of computed tomography urography (CTU) examinations at our hospital was changed in 2013 to improve the quality of urinary bladder filling in the excretory phase. The aim of this study was to evaluate the quality of urinary bladder filling on CTU after different doses of furosemide were administered to patients with macroscopic hematuria. METHODS: The cohort was 215 patients who underwent elective CTU due to macroscopic hematuria between 2014 and 2018. 5 mg furosemide were administrated to 100 patients, 2.5 mg to 100 patients and 0 mg to 15 patients. Contrast medium layered bladders were excluded, leaving 193 patients: 92, 89 and 12 in each group. Urinary bladder volume was calculated in corticomedullary (CMP) and excretory phase (EP). Bladder distension was classified as satisfactory or not. Attenuation of bladder content in EP was noted. RESULTS: Average volume in EP was 370 ± 224 ml (28-1052) after 5 mg furosemide, 274 ± 120 ml (43-628) after 2.5 mg and 180 ± 104 ml (53-351) after 0 mg. 85% of the bladders were satisfactory distended after 5 mg, 80% after 2.5 mg and 58% after 0 mg. Average attenuation was 266 ± 89 HU (103-524) after 5 mg, 362 ± 156 HU (118-948) after 2.5 mg and 761 ± 331 HU (347-1206) after 0 mg. The differences in volume and attenuation were significant. CONCLUSION: 5 mg furosemide is preferred rather than 2.5 mg in preparation for CTU examinations of patients with macroscopic hematuria. There was no difference between the doses concerning rate of satisfactory bladder distension, but the higher dose resulted in larger bladder volume and more suitable attenuation of bladder content. IMPLICATIONS FOR PRACTICE: Development of CTU-image quality could improve bladder cancer diagnostics.