| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Jendeberg, Johan, 1972-, et al.
(författare)
-
Differentiation of distal ureteral stones and pelvic phleboliths using a convolutional neural network
- 2021
-
Ingår i: Urolithiasis. - : Springer Berlin/Heidelberg. - 2194-7228 .- 2194-7236. ; 49, s. 41-49
-
Tidskriftsartikel (refereegranskat)abstract
- The objectives were to develop and validate a Convolutional Neural Network (CNN) using local features for differentiating distal ureteral stones from pelvic phleboliths, compare the CNN method with a semi-quantitative method and with radiologists' assessments and to evaluate whether the assessment of a calcification and its local surroundings is sufficient for discriminating ureteral stones from pelvic phleboliths in non-contrast-enhanced CT (NECT). We retrospectively included 341 consecutive patients with acute renal colic and a ureteral stone on NECT showing either a distal ureteral stone, a phlebolith or both. A 2.5-dimensional CNN (2.5D-CNN) model was used, where perpendicular axial, coronal and sagittal images through each calcification were used as input data for the CNN. The CNN was trained on 384 calcifications, and evaluated on an unseen dataset of 50 stones and 50 phleboliths. The CNN was compared to the assessment by seven radiologists who reviewed a local 5 × 5 × 5 cm image stack surrounding each calcification, and to a semi-quantitative method using cut-off values based on the attenuation and volume of the calcifications. The CNN differentiated stones and phleboliths with a sensitivity, specificity and accuracy of 94%, 90% and 92% and an AUC of 0.95. This was similar to a majority vote accuracy of 93% and significantly higher (p = 0.03) than the mean radiologist accuracy of 86%. The semi-quantitative method accuracy was 49%. In conclusion, the CNN differentiated ureteral stones from phleboliths with higher accuracy than the mean of seven radiologists' assessments using local features. However, more than local features are needed to reach optimal discrimination.
|
|
| 6. |
- Lidén, Mats, 1976-
(författare)
-
A new method for predicting uric acid composition in urinary stones using routine single-energy CT
- 2018
-
Ingår i: Urolithiasis. - : Springer. - 2194-7228 .- 2194-7236. ; 46:4, s. 325-332
-
Tidskriftsartikel (refereegranskat)abstract
- Urinary stones composed of uric acid can be treated medically. Prediction of uric acid stone type is, therefore, desirable when a urinary stone is diagnosed with unenhanced CT. The purpose of the present study was to describe single-energy thin slice quantitative CT parameters of urinary stones correlated to chemical stone type and to develop a method to distinguish pure uric acid stones (UA) from other stones (non-UA/Mix). Unenhanced thin slice single-energy CT images of 126 urinary stones (117 patients) with known chemical stone type were retrospectively included in the study. Among the included stones, 22 were UA and 104 were non-UA/Mix. The included CT images and Laplacian filtered images of the stones were quantitatively analyzed using operator-independent methods. A post hoc classification method for pure UA stones was created using a combination of cutoff values for the peak attenuation and peak point Laplacian. The stone types differed in most quantitative image characteristics including mean attenuation (p < 0.001), peak attenuation (p < 0.001), and peak point Laplacian (p < 0.001). The sensitivity for the post hoc-developed peak attenuation-peak point Laplacian method for classifying pure UA stones was 95% [21/22, 95% CI (77-100%)] and the specificity was 99% [103/104, 95% CI (95-100%)]. In conclusion, quantitative image analysis of thin slice routine single-energy CT images is promising for predicting pure UA content in urinary stones, with results comparable to double energy methods.
|
|
| 7. |
|
|
| 8. |
- Popiolek, Marcin, 1981-, et al.
(författare)
-
Finding the optimal candidate for shock wave lithotripsy : external validation and comparison of five prediction models
- 2023
-
Ingår i: Urolithiasis. - : Springer. - 2194-7228 .- 2194-7236. ; 51:1
-
Tidskriftsartikel (refereegranskat)abstract
- We aimed to externally validate five previously published predictive models (Ng score, Triple D score, S3HoCKwave score, Kim nomogram, Niwa nomogram) for shock wave lithotripsy (SWL) single-session outcomes in patients with a solitary stone in the upper ureter. The validation cohort included patients treated with SWL from September 2011 to December 2019 at our institution. Patient-related variables were retrospectively collected from the hospital records. Stone-related data including all measurements were retrieved from computed tomography prior to SWL. We estimated discrimination using area under the curve (AUC), calibration, and clinical net benefit based on decision curve analysis (DCA). A total of 384 patients with proximal ureter stones treated with SWL were included in the analysis. Median age was 55.5 years, and 282 (73%) of the sample were men. Median stone length was 8.0 mm. All models significantly predicted the SWL outcomes after one session. S3HoCKwave score, Niwa, and Kim nomograms had the highest accuracy in predicting outcomes, with AUC 0.716, 0.714 and 0.701, respectively. These three models outperformed both the Ng (AUC: 0.670) and Triple D (AUC: 0.667) scoring systems, approaching statistical significance (P = 0.05). Of all the models, the Niwa nomogram showed the strongest calibration and highest net benefit in DCA. To conclude, the models showed small differences in predictive power. The Niwa nomogram, however, demonstrated acceptable discrimination, the most accurate calibration, and the highest net benefit whilst having relatively simple design. Therefore, it could be useful for counselling patients with a solitary stone in the upper ureter.
|
|
| 9. |
- Popiolek, Marcin, 1981-, et al.
(författare)
-
Radiological signs of stone impaction add no value in predicting spontaneous stone passage
- 2024
-
Ingår i: Urolithiasis. - : Springer. - 2194-7228 .- 2194-7236. ; 52:1
-
Tidskriftsartikel (refereegranskat)abstract
- Stone size and location are key factors in predicting spontaneous stone passage (SSP), but little attention has been paid to the influence of radiological signs of stone impaction (RSSI). This research aims to determine whether RSSI, alongside stone size, can predict SSP and to evaluate the consistency of ureteral wall thickness (UWT) measurements among observers. In this retrospective study, 160 patients with a single upper or middle ureteral stone on acute non-enhanced computed tomography (NCCT) were analysed. Patient data were collected from medical records. Measurements of RSSI, including UWT, ureteral diameters, and average attenuation above and below the stone, were taken on NCCT by four independent readers blind to the outcomes. The cohort consisted of 70% males with an average age of 51 +/- 15. SSP occurred in 61% of patients over 20 weeks. The median stone length was 5.7 mm (IQR: 4.5-7.3) and was significantly shorter in patients who passed their stones at short- (4.6 vs. 7.1, p < 0.001) and long-term (4.8 vs. 7.1, p < 0.001) follow-up. For stone length, the area under the receiver operating characteristic curve (AUC) for predicting SSP was 0.90 (CI 0.84-0.96) and only increased to 0.91 (CI 0.85-0.95) when adding ureteral diameters and UWT. Ureteral attenuation did not predict SSP (AUC < 0.5). Interobserver variability for UWT was moderate, with +/- 2.0 mm multi-reader limits of agreement (LOA). The results suggest that RSSI do not enhance the predictive value of stone size for SSP. UWT measurements exhibit moderate reliability with significant interobserver variability.
|
|
| 10. |
|
|
