1
|
Xing Z, Zhu Z, Jiang Z, Zhao J, Chen Q, Xing W, Pan L, Zeng Y, Liu A, Ding J. Automatic Urinary Stone Detection System for Abdominal Non-Enhanced CT Images Reduces the Burden on Radiologists. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:444-454. [PMID: 38343222 PMCID: PMC11031534 DOI: 10.1007/s10278-023-00946-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/08/2023] [Revised: 10/18/2023] [Accepted: 10/18/2023] [Indexed: 04/20/2024]
Abstract
To develop a fully automatic urinary stone detection system (kidney, ureter, and bladder) and to test it in a real clinical environment. The local institutional review board approved this retrospective single-center study that used non-enhanced abdominopelvic CT scans from patients admitted urology (uPatients) and emergency (ePatients). The uPatients were randomly divided into training and validation sets in a ratio of 3:1. We designed a cascade urinary stone map location-feature pyramid networks (USm-FPNs) and innovatively proposed a ureter distance heatmap method to estimate the ureter position on non-enhanced CT to further reduce the false positives. The performances of the system were compared using the free-response receiver operating characteristic curve and the precision-recall curve. This study included 811 uPatients and 356 ePatients. At stone level, the cascade detector USm-FPNs has the mean of false positives per scan (mFP) 1.88 with the sensitivity 0.977 in validation set, and mFP was further reduced to 1.18 with the sensitivity 0.977 after combining the ureter distance heatmap. At patient level, the sensitivity and precision were as high as 0.995 and 0.990 in validation set, respectively. In a real clinical set of ePatients (27.5% of patients contain stones), the mFP was 1.31 with as high as sensitivity 0.977, and the diagnostic time reduced by > 20% with the system help. A fully automatic detection system for entire urinary stones on non-enhanced CT scans was proposed and reduces obviously the burden on junior radiologists without compromising sensitivity in real emergency data.
Collapse
Affiliation(s)
- Zhaoyu Xing
- Department of Urology, Third Affiliated Hospital of Soochow University, Changzhou, Jiangsu, China
| | - Zuhui Zhu
- Department of Radiology, Nantong Hospital of Traditional Chinese Medicine, Nantong, Jiangsu, China
| | - Zhenxing Jiang
- Department of Radiology, Third Affiliated Hospital of Soochow University, Changzhou, Jiangsu, China
| | - Jingshi Zhao
- Department of Radiology, Fourth Affiliated Hospital of Harbin Medical University, Harbin, China
| | - Qin Chen
- Department of Radiology, People's Hospital of Pengzhou, Chengdu, Sichuan, China
| | - Wei Xing
- Department of Radiology, Third Affiliated Hospital of Soochow University, Changzhou, Jiangsu, China
| | - Liang Pan
- Department of Radiology, Third Affiliated Hospital of Soochow University, Changzhou, Jiangsu, China
| | - Yan Zeng
- Department of Research Center, Shanghai United Imaging Intelligence Co. Ltd, Shanghai, China.
| | - Aie Liu
- Department of Research Center, Shanghai United Imaging Intelligence Co. Ltd, Shanghai, China.
| | - Jiule Ding
- Department of Radiology, Third Affiliated Hospital of Soochow University, Changzhou, Jiangsu, China.
| |
Collapse
|
2
|
Diamond M, Shin D, Wang J, Samuelsen B, LeBedis C. Imaging of Nontraumatic Upper Urinary Tract Emergencies. Semin Roentgenol 2020; 55:180-196. [PMID: 32438979 DOI: 10.1053/j.ro.2019.10.009] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Affiliation(s)
| | - Donghoon Shin
- Department of Radiology, Boston Medical Center, Boston, MA
| | | | | | | |
Collapse
|
3
|
Increased urinary bladder volume improves the detectability of urinary stones at the ureterovesical junction in non-enhanced computed tomography (NECT). Eur Radiol 2019; 29:6953-6964. [PMID: 31209621 DOI: 10.1007/s00330-019-06279-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2019] [Revised: 05/08/2019] [Accepted: 05/17/2019] [Indexed: 10/26/2022]
Abstract
OBJECTIVES To evaluate the influence of the urinary bladder volume on the detectability of urolithiasis at the ureterovesical junction (UVJ) using a low-dose CT (LD-CT) with iterative reconstruction (IR) and a standard-dose CT (SD-CT) without IR in a large cohort. METHODS Four hundred patients (278 males (69.5%), mean 44.6 ± 14.7 years) with urolithiasis at the UVJ were investigated either by an LD-CT with IR (n = 289, 72%) or an SD-CT without IR (n = 111, 28%) protocol. The detectability of distal urolithiasis was assessed by a dichotomous assessment (definite or questionable) by two radiologists in consensus and by a quantitative analysis of the signal density distribution across a line drawn parallel to the distal ureter. Based on the resulting graph, minimum/maximum density values and mean/maximum upslopes and downslopes were derived and calculated automatically. In all patients, the total bladder volume was calculated by a slice-by-slice approach on axial CT images. RESULTS Patients with definite stones showed significantly higher urinary bladder volumes compared to patients with questionable stones in both LD-CT and SD-CT (p < 0.01). These results were independent of stones' length and patients' BMI values. Using cutoffs of 92 ml for LD-CT and 69 ml for SD-CT, high positive predictive values/accuracy rates of 96%/85% (LD-CT) and 98%/86% (SD-CT) were observed to identify definite urinary stones. CONCLUSIONS Urinary bladder volume has a significant impact on the detectability of distal urolithiasis. Moderate bladder filling by pre-CT hydration with subsequent CT scan at the time of high urge to void increases the detectability of urinary stones at the UVJ in clinical routine. KEY POINTS • Urinary bladder volume significantly affects the detectability of distal urolithiasis • Higher bladder volumes are associated with improved detectability of distal urinary stones • Oral pre-CT hydration for urolithiasis is easily applicable and cost-effective.
Collapse
|
4
|
Chi BH, Chang IH, Lee DH, Park SB, Kim KD, Moon YT, Hur T. Low-Dose Unenhanced Computed Tomography with Iterative Reconstruction for Diagnosis of Ureter Stones. Yonsei Med J 2018; 59:389-396. [PMID: 29611401 PMCID: PMC5889991 DOI: 10.3349/ymj.2018.59.3.389] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/20/2017] [Revised: 02/06/2018] [Accepted: 02/08/2018] [Indexed: 12/25/2022] Open
Abstract
PURPOSE To study the clinical application of low-dose unenhanced computed tomography with iterative reconstruction technique (LDCT-IR) on renal colic in the emergency department. MATERIALS AND METHODS We conducted a prospective, single-blinded, randomized, and non-inferiority study. From March 2014 to August 2015, 112 patients with renal colic were included, and were randomized to either LDCT-IR (n=46) or standard-dose unenhanced CT (SDCT) (n=66) groups. The accuracy of urolithiasis diagnosis was the primary endpoint of this study. Radiation dose, size and location of the stone, hydronephrosis, other diseases except urolithiasis, and results of treatment were analyzed between the two groups. RESULTS The average effective dose radiation of SDCT was approximately four times higher than that of LDCT-IR (6.52 mSv vs. 1.63 mSv, p<0.001). There was no significant difference in the accuracy of ureteral stone diagnosis between the two groups (LDCT-IR group: 96.97% vs. SDCT group: 98.96%, p=0.392). No significant difference was observed regarding the size and location of a stone, hydronephrosis, and diagnosis of other diseases, except urolithiasis. False negative results were found in two LDCT-IR patients and in one SDCT patient. In these patients, stones were misread as vascular calcification, and were difficult to diagnose because evidence of hydronephrosis and ureteral dilatation was not found. CONCLUSION LDCT-IR, as a first-line imaging test, was non-inferior to SDCT with respect to diagnosis of ureter stones, and was clinically available for the evaluation of renal colic.
Collapse
Affiliation(s)
- Byung Hoon Chi
- Department of Urology, College of Medicine, Chung-Ang University, Seoul, Korea
| | - In Ho Chang
- Department of Urology, College of Medicine, Chung-Ang University, Seoul, Korea
| | - Dong Hoon Lee
- Department of Emergency Medicine, College of Medicine, Chung-Ang University, Seoul, Korea.
| | - Sung Bin Park
- Department of Radiology, College of Medicine, Chung-Ang University, Seoul, Korea
| | - Kyung Do Kim
- Department of Urology, College of Medicine, Chung-Ang University, Seoul, Korea
| | - Young Tae Moon
- Department of Urology, College of Medicine, Chung-Ang University, Seoul, Korea
| | - Taekyu Hur
- Chung-Ang University School of Medicine, Seoul, Korea
| |
Collapse
|
5
|
Rodger F, Roditi G, Aboumarzouk O. Diagnostic Accuracy of Low and Ultra-Low Dose CT for Identification of Urinary Tract Stones: A Systematic Review. Urol Int 2018; 100:375-385. [DOI: 10.1159/000488062] [Citation(s) in RCA: 42] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2017] [Accepted: 03/01/2018] [Indexed: 12/27/2022]
|
6
|
Chiang BJ, Liao CH, Lin YH. The efficacy of extracorporeal shockwave lithotripsy for symptomatic ureteral stones: Predictors of treatment failure without the assistance of computed tomography. PLoS One 2017; 12:e0184855. [PMID: 28931028 PMCID: PMC5607160 DOI: 10.1371/journal.pone.0184855] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2016] [Accepted: 09/01/2017] [Indexed: 12/23/2022] Open
Abstract
OBJECTIVES Non-contrast computed tomography (NCCT) is not always performed clinically if the diagnosis of ureteral calculi has been confirmed using other radiographic imaging modalities. The aim of this study was to identify predictors of successful extracorporeal shockwave lithotripsy (ESWL) without assistance of NCCT. METHODS We retrospectively reviewed the medical records of patients with symptomatic solitary ureteral stones who underwent ESWL between November 2015 and January 2016. Abdominal plain radiography or intravenous urography were performed before ESWL for localization. The exclusion criteria were repeated sessions of ESWL for the target stone and congenital genitourinary tract anomalies. The demographic characteristics, clinical history, medical charges, or imaging features of the stones were recorded. Successful treatment was defined as no fragments detected on radiography or ultrasonography in 4 weeks. For radiolucent calculi, successful treatment was regarded as cases without hydronephrosis, symptoms, or hematuria. Patients experiencing intractable pain and undergoing subsequent auxiliary surgeries were regarded as having ESWL treatment failure. RESULTS Age (odds ratio [OR], 1.042; 95% confidence interval [CI], 1.007-1.078), history of ipsilateral renal or ureteral calculi episodes (OR, 2.669; 95% CI, 1.281-5.687), stone burden (OR, 3.499; 95% CI, 1.284-9.530), and radiopaque stone (OR, 2.351; 95% CI, 1.049-5.267) were significant predictors of ESWL failure in all patients. CONCLUSIONS For treating symptomatic ureteral stones, those with smaller size, radiolucency, and without a history of ipsilateral renal or ureteral calculi could be considered for first-line therapy with ESWL.
Collapse
Affiliation(s)
- Bing-Juin Chiang
- Department of Life Science, National Taiwan Normal University, Taipei, Taiwan
- Division of Urology, Department of Surgery, Cardinal Tien Hospital, New Taipei City, Taiwan
- Department of Urology, School of Medicine, Fu-Jen Catholic University, New Taipei City, Taiwan
| | - Chun-Hou Liao
- Division of Urology, Department of Surgery, Cardinal Tien Hospital, New Taipei City, Taiwan
- Department of Urology, School of Medicine, Fu-Jen Catholic University, New Taipei City, Taiwan
| | - Yu-Hua Lin
- Division of Urology, Department of Surgery, Cardinal Tien Hospital, New Taipei City, Taiwan
- Department of Urology, National Taiwan University Hospital, Taipei, Taiwan
| |
Collapse
|
7
|
Sade R, Ogul H, Eren S, Levent A, Kantarci M. Comparison of Ultrasonography and Low-Dose Computed Tomography for the Diagnosis of Pediatric Urolithiasis in the Emergency Department. Eurasian J Med 2017. [PMID: 28638256 DOI: 10.5152/eurasianjmed.2017.17083] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022] Open
Abstract
OBJECTIVE This study aimed to compare ultrasonography (US) and low-dose computed tomography (LDCT) for diagnosing pediatric urolithiasis in the emergency department. MATERIALS AND METHODS This retrospective study was approved by our institutional ethics committee, and informed consent was waived. From March 2016 to March 2017, 100 consecutive patients met the selection criteria and were enrolled in the study. Patients were randomly selected in a 1:1 ratio and were allocated to one of the following two imaging groups: US or abdominal LDCT. LDCT examinations were performed using a 320-detector row CT. Radiation dose analysis was performed using Radimetrics. US examinations were performed using the Aplio 500 ultrasound system. The presence of urolithiasis, anatomical location of urolithiasis, and measurements of renal stones were evaluated and recorded. RESULTS There were statistically significant differences between US and standard-dose CT (SDCT) with respect to the diagnosis of urolithiasis, anatomical location of urolithiasis, and measurements of renal stones (p<0.001, p=0.005, and p=0.03, respectively). The mean effective radiation dose of LDCT was 1.44±0.34 mSv and that of SDCT was calculated to be 4.36±1.33 mSv. There was no statistically significant difference between LDCT and SDCT with regard to the diagnosis of urolithiasis, anatomical location of urolithiasis and measurements of renal stones (p=1 for all). The diagnostic accuracy of US and LDCT was 0.68 and 1.0, respectively. CONCLUSION Low-dose computed tomography had 1/3 SDCT radiation dose, and LDCT and SDCT accurately diagnosed pediatric urolithiasis in the emergency department. US had a lower accuracy than SDCT and LDCT for diagnosing pediatric urolithiasis in the emergency department. LDCT can be an alternative for SDCT for diagnosing pediatric urolithiasis.
Collapse
Affiliation(s)
- Recep Sade
- Department of Radiology, Atatürk University School of Medicine, Erzurum, Turkey
| | - Hayri Ogul
- Department of Radiology, Atatürk University School of Medicine, Erzurum, Turkey
| | - Suat Eren
- Department of Radiology, Atatürk University School of Medicine, Erzurum, Turkey
| | - Akin Levent
- Department of Radiology, Atatürk University School of Medicine, Erzurum, Turkey
| | - Mecit Kantarci
- Department of Radiology, Atatürk University School of Medicine, Erzurum, Turkey
| |
Collapse
|
8
|
|
9
|
Cohen A, Hughes K, Fahey N, Caldwell B, Wang CH, Park S. Wide Variation in Radiation Exposure During Computerized Tomography. Urology 2016; 95:47-53. [PMID: 27233928 DOI: 10.1016/j.urology.2016.05.036] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2016] [Revised: 05/17/2016] [Accepted: 05/18/2016] [Indexed: 11/17/2022]
Abstract
OBJECTIVE To determine the variance in computeed tomography (CT) radiation measured via dose-length product (DLP) and effective dose (ED) during stone protocol CT scans. METHODS We retrospectively examined consecutive records of patients receiving stone protocol diagnostic CT scans (n = 1793) in 2010 and 2014 in our health system. Patient age, body mass index (BMI), and gender were recorded, along with the hospital, machine model, year, DLP, and ED of each scan. Multivariate regression was performed to identify predictive factors for increased DLP. We also collected data on head (n = 837) CT scans to serve as a comparison. RESULTS For stone CT scans, mean patient age was 55.1 ± 18.4 years with no significant difference in age (P=.2557) or BMI (P=.1794) between 2010 and 2014. Gender, BMI, and machine model were independent predictors of radiation dosage (P < .0001). Within each BMI class, there was an inexplicable 6-fold variation in the ED for the same imaging test when comparing the lowest and highest CT dose patients. There was no significant change in DLP over time for stone CT scans, but head scan patients in 2014 received lower radiation doses than those in 2010 (P < .0001). Low-dose scans for renal colic (defined as <4 mSv) were underutilized. Substantial variation exists for head scan radiation doses. CONCLUSION Our data demonstrate large variations in diagnostic CT radiation dosage. Such differences within a single institution suggest similar trends elsewhere, warranting more stringent dosage guidelines and regulations for diagnostic CT scans within institutions.
Collapse
Affiliation(s)
- Andrew Cohen
- Section of Urology, University of Chicago, Chicago, IL
| | - Katie Hughes
- Division of Urology, NorthShore University HealthSystem, Evanston, IL
| | - Natalie Fahey
- Division of Urology, NorthShore University HealthSystem, Evanston, IL
| | - Brandon Caldwell
- Division of Urology, NorthShore University HealthSystem, Evanston, IL
| | - Chi Hsiung Wang
- Division of Urology, NorthShore University HealthSystem, Evanston, IL
| | - Sangtae Park
- Division of Urology, NorthShore University HealthSystem, Evanston, IL.
| |
Collapse
|