Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 8 de 8
Filter
1.
BJU Int ; 133(6): 690-698, 2024 Jun.
Article in English | MEDLINE | ID: mdl-38343198

ABSTRACT

OBJECTIVE: To automate the generation of three validated nephrometry scoring systems on preoperative computerised tomography (CT) scans by developing artificial intelligence (AI)-based image processing methods. Subsequently, we aimed to evaluate the ability of these scores to predict meaningful pathological and perioperative outcomes. PATIENTS AND METHODS: A total of 300 patients with preoperative CT with early arterial contrast phase were identified from a cohort of 544 consecutive patients undergoing surgical extirpation for suspected renal cancer. A deep neural network approach was used to automatically segment kidneys and tumours, and then geometric algorithms were used to measure the components of the concordance index (C-Index), Preoperative Aspects and Dimensions Used for an Anatomical classification of renal tumours (PADUA), and tumour contact surface area (CSA) nephrometry scores. Human scores were independently calculated by medical personnel blinded to the AI scores. AI and human score agreement was assessed using linear regression and predictive abilities for meaningful outcomes were assessed using logistic regression and receiver operating characteristic curve analyses. RESULTS: The median (interquartile range) age was 60 (51-68) years, and 40% were female. The median tumour size was 4.2 cm and 91.3% had malignant tumours. In all, 27% of the tumours were high stage, 37% high grade, and 63% of the patients underwent partial nephrectomy. There was significant agreement between human and AI scores on linear regression analyses (R ranged from 0.574 to 0.828, all P < 0.001). The AI-generated scores were equivalent or superior to human-generated scores for all examined outcomes including high-grade histology, high-stage tumour, indolent tumour, pathological tumour necrosis, and radical nephrectomy (vs partial nephrectomy) surgical approach. CONCLUSIONS: Fully automated AI-generated C-Index, PADUA, and tumour CSA nephrometry scores are similar to human-generated scores and predict a wide variety of meaningful outcomes. Once validated, our results suggest that AI-generated nephrometry scores could be delivered automatically from a preoperative CT scan to a clinician and patient at the point of care to aid in decision making.


Subject(s)
Kidney Neoplasms , Tomography, X-Ray Computed , Humans , Female , Kidney Neoplasms/pathology , Kidney Neoplasms/surgery , Kidney Neoplasms/diagnostic imaging , Male , Middle Aged , Aged , Nephrectomy/methods , Predictive Value of Tests , Artificial Intelligence , Retrospective Studies
2.
Urol Clin North Am ; 50(2): 239-259, 2023 May.
Article in English | MEDLINE | ID: mdl-36948670

ABSTRACT

Knowledge of functional recovery after partial (PN) and radical nephrectomy for renal cancer has advanced considerably, with PN now established as the reference standard for most localized renal masses. However, it is still unclear whether PN provides an overall survival benefit in patients with a normal contralateral kidney. While early studies seemingly demonstrated the importance of minimizing warm-ischemia time during PN, multiple new investigations over the last 10 years have proven that parenchymal mass lost is the most important predictor of new baseline renal function. Minimizing loss of parenchymal mass during resection and reconstruction is the most important controllable aspect of long-term post-operative renal function preservation.


Subject(s)
Carcinoma, Renal Cell , Kidney Neoplasms , Humans , Kidney/surgery , Kidney/physiology , Kidney Neoplasms/surgery , Carcinoma, Renal Cell/surgery , Nephrectomy/adverse effects , Nephrectomy/methods , Warm Ischemia/methods
3.
Urology ; 163: 64-68, 2022 05.
Article in English | MEDLINE | ID: mdl-34181972

ABSTRACT

OBJECTIVE: To investigate whether penile pathologies are presented diversely in urologic textbooks and identify areas where more diverse presentation is warranted. METHODS: Photographic depictions of penile pathologies in 9 urologic textbooks were assigned a Fitzpatrick skin phototype and constitutive skin color. Fitzpatrick skin phototypes ranged from I to VI, and constitutive skin colors were light, fair, medium, and dark. Fitzpatrick skin phototypes I-III were deemed nonskin of color, and IV-VI considered skin of color. Figures were classified based on pathology presented: infectious benign or sexually transmitted infection (STI), noninfectious benign, or malignant. Chi-square and odds ratios were used to compare skin color ranges across pathologic categories and determine where a figure depicting skin color would most likely be encountered. RESULTS: Within 116 figures meeting inclusion criteria, 15 (51.7%) infectious/STI pathologies displayed skin of color, while 10 (27.8%) noninfectious benign and 7 (13.7%) malignant pathologies displayed skin of color. Within 85 diagnostic images, 15 (51.7%) images of infections/STIs, 10 (28.6%) noninfectious benign, and 4 (19.0%) malignant pathologies presented skin of color (P < 0.01). Overall, images of patients with skin of color were more likely depictions of infections/STIs than any other pathology (P < .001, OR = 2.26). CONCLUSION: There is a lack of depictions of malignant and noninfectious benign penile pathology on the skin of color. This may contribute to continued disparities in the diagnosis and treatment of penile pathologies.


Subject(s)
Skin Pigmentation , Skin , Humans
4.
Radiographics ; 41(3): 909-928, 2021.
Article in English | MEDLINE | ID: mdl-33939544

ABSTRACT

The renal arteries (RAs) are important vessels that usually arise from the abdominal aorta and supply the kidneys; thus, these arteries play a vital role in physiologic functions such as hemofiltration and blood pressure regulation. An understanding of the basis for embryologic development and the frequently variable anatomy of the RAs is necessary to fully appreciate the range of diseases and the implications for procedural planning. Hemorrhage from an RA is relatively common and is typically traumatic or spontaneous, with the latter form often seen in association with underlying tumors or arteriopathy. Accurate diagnostic evaluation of RA disease due to conditions such as atherosclerosis, fibromuscular dysplasia, vasculitis, aneurysm, arteriovenous shunt, embolic disease, and dissection is dependent on the use of multimodality imaging and is essential for selecting appropriate clinical management, with endovascular therapy having a key role in treatment. Surgical considerations include extra-anatomic renal bypass, which remains an important treatment option even in this era of endovascular therapy, and RA embolization as an adjunct to tumor surgery. A novel area of research interest is the potential role of RA denervation in the management of refractory hypertension. ©RSNA, 2021.


Subject(s)
Arteriovenous Fistula , Endovascular Procedures , Aorta, Abdominal , Arteriovenous Fistula/diagnostic imaging , Arteriovenous Fistula/therapy , Humans , Kidney/diagnostic imaging , Renal Artery/diagnostic imaging
5.
Urology ; 151: 19-23, 2021 05.
Article in English | MEDLINE | ID: mdl-32653567

ABSTRACT

OBJECTIVE: To apply the American Urogynecological Society (AUGS)/American College of Obstetricians and Gynecologists (ACOG) recommendations of foregoing workup in patients under 50 years of age with less than 25 red cells per high-powered field, to a cohort of asymptomatic microscopic hematuria (AMH) patients, and assess diagnostic accuracy, sensitivity, specificity, positive, and negative predictive value compared to the American Urologic Association (AUA) guidelines. METHODS: Retrospective review of female patients who underwent AMH evaluation from 2012 to 2015. The number of patients who would have avoided workup following the AUGS/ACOG recommendations was determined. Sensitivity, specificity, positive- and negative-predictive value and accuracy of the AUGS/ACOG recommendations compared to AUA guidelines were determined. RESULTS: Six hundred twenty women underwent AMH workup with 265 women undergoing full workup as per the AUA guidelines. Applying the AUGS/ACOG recommendations to this cohort would not have resulted in missed malignant diagnoses. Two tumors were found, both in patients who had undergone complete workup, and for whom AUGS/ACOG recommends workup. Following the AUGS/ACOG recommendations would have avoided workup in 126/620 of all women and 44/265 women who underwent the full AUA workup. In looking at findings of malignancy, the AUGS/ACOG workup had a sensitivity of 100% and a negative predictive value of 100% as compared to the AUA guidelines. CONCLUSION: AUA guidelines may over screen female low risk AMH patients. Extensive workup in a low risk group of female patients does not result in increased cancer diagnoses. Perhaps a more nuanced approach could result in fewer workups without compromising cancer detection.


Subject(s)
Hematuria/diagnosis , Hematuria/epidemiology , Asymptomatic Diseases , Female , Gynecology , Humans , Incidence , Middle Aged , Practice Guidelines as Topic , Retrospective Studies , Sensitivity and Specificity , Societies, Medical , Urology
6.
Urology ; 141: 27.e1-27.e6, 2020 07.
Article in English | MEDLINE | ID: mdl-32305550

ABSTRACT

OBJECTIVE: To determine if use of the hematuria risk index can reduce testing and cost, while maintaining equivalent lesion detection in patients with asymptomatic microscopic hematuria. MATERIALS AND METHODS: Retrospective cohort study of 1049 patients at single institution. Hematuria risk index score was calculated based on clinical factors including age, sex, smoking history, and degree of hematuria for each patient along with evaluation studies performed and total number of tumors discovered. Cost benefit analysis was performed based on published Medicare averages. RESULTS: Tumor detection rate in overall, low-risk, and moderate-risk groups were 1.2%, 0%, and 2.96% at a total cost of $408,376. When low-risk group is not screened cost decreases to $166,252 with no lesions missed. The cost to discover one lesion/cancer in the overall group was $34,031.3, the cost to find one high-grade clinically significant lesion/cancer was $136,125.3 for the overall group. When the low-risk group was removed, the cost to find a high-grade clinically significant lesion/cancer decreased to $55,417.3 without missing any significant lesions. Ultrasound may be utilized instead of computed tomography with minimal loss of lesion detection in select moderate risk patients. CONCLUSION: None of the low-risk hematuria risk patients were diagnosed with any lesions, as such these patients may not need an evaluation. Furthermore, by utilizing a risk-stratified approach to the assessment of asymptomatic microscopic hematuria health care costs can be significantly decreased with limited negative consequences in terms of lesion detection.


Subject(s)
Asymptomatic Diseases , Hematuria/etiology , Urologic Neoplasms/diagnostic imaging , Age Factors , Area Under Curve , Asymptomatic Diseases/economics , Cost-Benefit Analysis , Cystoscopy/economics , Female , Health Care Costs , Hematuria/economics , Humans , Magnetic Resonance Imaging/economics , Male , Middle Aged , Retrospective Studies , Risk Assessment/economics , Risk Assessment/methods , Sex Factors , Smoking , Tomography, X-Ray Computed/economics , Ultrasonography/economics , Urologic Neoplasms/complications , Urologic Neoplasms/economics
7.
Transl Androl Urol ; 8(4): 374-378, 2019 Aug.
Article in English | MEDLINE | ID: mdl-31555561

ABSTRACT

BACKGROUND: Fournier's gangrene (FG) is a rapidly progressing necrotizing fasciitis that carries a significant morbidity and mortality. The present study sought to identify the predisposing factors related to FG and validate the Fournier's Gangrene Severity Index (FGSI) score as a prognostic tool in the care of the Fournier's patient. METHODS: Medstar Washington Hospital Center records were searched from January 2003 to February 2015 for all patients with a diagnosis code of FG, n=42. Epidemiologic data was collected for patients and used to calculate an FGSI score. RESULTS: The average age was 53.45 yrs and M/F ratio was 39:1. Patients presented with an average 2.675 predisposing factors; the most common was diabetes mellitus (n=21) followed by hypertension (n=18). The most common etiology was periscrotal (n=25) next to perirectal (n=9). Streptococcus was the most common source of infection (n=14). Patients on average required three surgical interventions. The average and median hospitalization period was 19.625 and 11.5 days respectively. Eleven patients developed sepsis. Twenty-four (60%) patients experienced a complication. The overall mortality was 5% (n=2). The average FGSI on admission was 5.368. Multivariate analysis showed FGSI score correlates with more surgical intervention, longer hospitalization, sepsis, complication and mortality. CONCLUSIONS: The FGSI score predicts a greater likelihood of more surgical interventions, longer hospitalization period, sepsis, complications and mortality within this patient population. Diabetes mellitus continues to be the most common predisposing factors in FG patients. The mortality rate of 5% is much less than the historically reported 20-30% and may reflect improved understanding and care of this aggressive disease.

SELECTION OF CITATIONS
SEARCH DETAIL
...