File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/s00261-021-03201-w
- Scopus: eid_2-s2.0-85109345175
- PMID: 34227014
- WOS: WOS:000669818900001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Evaluation of pediatric hydronephrosis using deep learning quantification of fluid-to-kidney-area ratio by ultrasonography
Title | Evaluation of pediatric hydronephrosis using deep learning quantification of fluid-to-kidney-area ratio by ultrasonography |
---|---|
Authors | |
Keywords | Ultrasound Kidney Hydronephrosis Renal pelvis anterior–posterior diameter APD Deep learning Segmentation |
Issue Date | 2021 |
Publisher | Springer New York LLC. The Journal's web site is located at https://www.springer.com/medicine/radiology/journal/261 |
Citation | Abdominal Radiology, 2021, v. 46 n. 11, p. 5229-5239 How to Cite? |
Abstract | Purpose:
Hydronephrosis is the dilation of the pelvicalyceal system due to the urine flow obstruction in one or both kidneys. Conventionally, renal pelvis anterior–posterior diameter (APD) was used for quantifying hydronephrosis in medical images (e.g., ultrasound, CT, and functional MRI). Our study aimed to automatically detect and quantify the fluid and kidney areas on ultrasonography, using a deep learning approach.
Methods:
An attention-Unet was used to segment the kidney and the dilated pelvicalyceal system with fluid. The gold standard for diagnosing hydronephrosis was the APD > 1.0 cm. For semi-quantification, we proposed a fluid-to-kidney-area ratio measurement, i.e., renal pelvicalyceal area with fluid/kidney area, as a deep learning-derived biomarker. Dice coefficient, confusion matrix, ROC curve, and Z-test were used to evaluate the model performance. Linear regression was applied to obtain the fluid-to-kidney-area ratio cutoff for detecting hydronephrosis.
Results:
For regional kidney segmentation, the Dice coefficients were 0.92 and 0.83 for the kidney and dilated pelvicalyceal system, respectively. The sensitivity and specificity of detecting dilated pelvicalyceal system were 0.99 and 0.83, respectively. The linear equation was fluid-to-kidney-area ratio = (0.213 ± 0.004) × APD (in cm) for 95% confidence interval on the slope with R2 = 0.87. The fluid-to-kidney-area ratio cutoff for detecting hydronephrosis was 0.213. The sensitivity and specificity for detecting hydronephrosis were 0.90 and 0.80, respectively.
Conclusion:
Our study confirmed the feasibility of deep learning characterization of the kidney and fluid, showing an automatic pediatric hydronephrosis detection. |
Persistent Identifier | http://hdl.handle.net/10722/306378 |
ISSN | 2021 Impact Factor: 2.886 2020 SCImago Journal Rankings: 0.824 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lin, Y | - |
dc.contributor.author | Khong, PL | - |
dc.contributor.author | Zou, Z | - |
dc.contributor.author | Cao, P | - |
dc.date.accessioned | 2021-10-20T10:22:45Z | - |
dc.date.available | 2021-10-20T10:22:45Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Abdominal Radiology, 2021, v. 46 n. 11, p. 5229-5239 | - |
dc.identifier.issn | 2366-004X | - |
dc.identifier.uri | http://hdl.handle.net/10722/306378 | - |
dc.description.abstract | Purpose: Hydronephrosis is the dilation of the pelvicalyceal system due to the urine flow obstruction in one or both kidneys. Conventionally, renal pelvis anterior–posterior diameter (APD) was used for quantifying hydronephrosis in medical images (e.g., ultrasound, CT, and functional MRI). Our study aimed to automatically detect and quantify the fluid and kidney areas on ultrasonography, using a deep learning approach. Methods: An attention-Unet was used to segment the kidney and the dilated pelvicalyceal system with fluid. The gold standard for diagnosing hydronephrosis was the APD > 1.0 cm. For semi-quantification, we proposed a fluid-to-kidney-area ratio measurement, i.e., renal pelvicalyceal area with fluid/kidney area, as a deep learning-derived biomarker. Dice coefficient, confusion matrix, ROC curve, and Z-test were used to evaluate the model performance. Linear regression was applied to obtain the fluid-to-kidney-area ratio cutoff for detecting hydronephrosis. Results: For regional kidney segmentation, the Dice coefficients were 0.92 and 0.83 for the kidney and dilated pelvicalyceal system, respectively. The sensitivity and specificity of detecting dilated pelvicalyceal system were 0.99 and 0.83, respectively. The linear equation was fluid-to-kidney-area ratio = (0.213 ± 0.004) × APD (in cm) for 95% confidence interval on the slope with R2 = 0.87. The fluid-to-kidney-area ratio cutoff for detecting hydronephrosis was 0.213. The sensitivity and specificity for detecting hydronephrosis were 0.90 and 0.80, respectively. Conclusion: Our study confirmed the feasibility of deep learning characterization of the kidney and fluid, showing an automatic pediatric hydronephrosis detection. | - |
dc.language | eng | - |
dc.publisher | Springer New York LLC. The Journal's web site is located at https://www.springer.com/medicine/radiology/journal/261 | - |
dc.relation.ispartof | Abdominal Radiology | - |
dc.subject | Ultrasound | - |
dc.subject | Kidney | - |
dc.subject | Hydronephrosis | - |
dc.subject | Renal pelvis anterior–posterior diameter | - |
dc.subject | APD | - |
dc.subject | Deep learning | - |
dc.subject | Segmentation | - |
dc.title | Evaluation of pediatric hydronephrosis using deep learning quantification of fluid-to-kidney-area ratio by ultrasonography | - |
dc.type | Article | - |
dc.identifier.email | Cao, P: caopeng1@hku.hk | - |
dc.identifier.authority | Khong, PL=rp00467 | - |
dc.identifier.authority | Cao, P=rp02474 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/s00261-021-03201-w | - |
dc.identifier.pmid | 34227014 | - |
dc.identifier.scopus | eid_2-s2.0-85109345175 | - |
dc.identifier.hkuros | 326782 | - |
dc.identifier.volume | 46 | - |
dc.identifier.issue | 11 | - |
dc.identifier.spage | 5229 | - |
dc.identifier.epage | 5239 | - |
dc.identifier.isi | WOS:000669818900001 | - |
dc.publisher.place | United States | - |