Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

Autosomal Dominant Polycystic Kidney Disease (ADPKD) is a genetic disorder that causes uncontrolled kidney cyst growth, leading to kidney volume enlargement and renal function loss over time. Total kidney volume (TKV) and cyst burdens have been used as prognostic imaging biomarkers for ADPKD.

Objective

This study aimed to evaluate nnUNet for automatic kidney and cyst segmentation in T2-weighted (T2W) MRI images of ADPKD patients.

Methods

756 kidney images were retrieved from 95 patients in the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) cohort (95 patients × 2 kidneys × 4 follow-up scans). The nnUNet model was trained, validated, and tested on 604, 76, and 76 images, respectively. In contrast, all images of each patient were exclusively assigned to either the training, validation, or test sets to minimize evaluation bias. The kidney and cyst regions defined using a semi-automatic method were employed as ground truth. The model performance was assessed using the Dice Similarity Coefficient (DSC), the intersection over union (IoU) score, and the Hausdorff distance (HD).

Results

The test DSC values were 0.96±0.01 (mean±SD) and 0.90±0.05 for kidney and cysts, respectively. Similarly, the IoU scores were 0.91± 0.09 and 0.81±0.06, and the HD values were 12.49±8.71 mm and 12.04±10.41 mm, respectively, for kidney and cyst segmentation.

Conclusion

The nnUNet model is a reliable tool to automatically determine kidney and cyst volumes in T2W MRI images for ADPKD prognosis and therapy monitoring.

© 2024 Krishnan et al.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056272767231130110017
2024-01-01
2025-06-18

  • From This Site

    /content/journals/cmir/10.2174/0115734056272767231130110017
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. NiemczykM. NiemczykS. PaczekL. Autosomal dominant polycystic kidney disease and transplantation.Ann. Transplant.2009144869020009161
     [Google Scholar]
  2. ChebibF.T. PerroneR.D. ChapmanA.B. DahlN.K. HarrisP.C. MrugM. MustafaR.A. RastogiA. WatnickT. YuA.S.L. TorresV.E. A practical guide for treatment of rapidly progressive ADPKD with tolvaptan.J. Am. Soc. Nephrol.201829102458247010.1681/ASN.201806059030228150
     [Google Scholar]
  3. Federal Register 80 FR 49244-6 (Docket No. FDA-2015-D-2843)2015
     [Google Scholar]
  4. ChapmanA.B. Guay-WoodfordL.M. GranthamJ.J. TorresV.E. BaeK.T. BaumgartenD.A. KenneyP.J. KingB.F.Jr GlocknerJ.F. WetzelL.H. BrummerM.E. Charles O’NeillW. RobbinM.L. BennettW.M. KlahrS. HirschmanG.H. KimmelP.L. ThompsonP.A. Philip MillerJ. Renal structure in early autosomal-dominant polycystic kidney disease (ADPKD): The consortium for radiologic imaging studies of Polycystic Kidney Disease (CRISP) cohort1.Kidney Int.20036431035104510.1046/j.1523‑1755.2003.00185.x12911554
     [Google Scholar]
  5. SimmsR.J. DoshiT. MetherallP. RyanD. WrightP. GruelN. van GastelM.D.A. GansevoortR.T. TindaleW. OngA.C.M. A rapid high-performance semi-automated tool to measure total kidney volume from MRI in autosomal dominant polycystic kidney disease.Eur. Radiol.20192984188419710.1007/s00330‑018‑5918‑930666443
     [Google Scholar]
  6. KistlerA.D. PosterD. KrauerF. WeishauptD. RainaS. SennO. BinetI. SpanausK. WüthrichR.P. SerraA.L. Increases in kidney volume in autosomal dominant polycystic kidney disease can be detected within 6 months.Kidney Int.200975223524110.1038/ki.2008.55818971924
     [Google Scholar]
  7. NensaF. DemirciogluA. RischplerC. Artificial intelligence in nuclear medicine.J. Nucl. Med.201960Suppl. 229S37S10.2967/jnumed.118.22059031481587
     [Google Scholar]
  8. MagistroniR. CorsiC. MartíT. TorraR. A review of the imaging techniques for measuring kidney and cyst volume in establishing autosomal dominant polycystic kidney disease progression.Am. J. Nephrol.2018481677810.1159/00049102230071518
     [Google Scholar]
  9. BhutaniH. SmithV. Rahbari-OskouiF. MittalA. GranthamJ.J. TorresV.E. MrugM. BaeK.T. WuZ. GeY. LandslittelD. GibbsP. Charles O’NeillW. ChapmanA.B. A comparison of ultrasound and magnetic resonance imaging shows that kidney length predicts chronic kidney disease in autosomal dominant polycystic kidney disease.Kidney Int.201588114615110.1038/ki.2015.7125830764
     [Google Scholar]
  10. CardenasC.E. YangJ. AndersonB.M. CourtL.E. BrockK.B. Advances in auto-segmentation.Semin. Radiat. Oncol.201929318519710.1016/j.semradonc.2019.02.00131027636
     [Google Scholar]
  11. KlineT.L. KorfiatisP. EdwardsM.E. BlaisJ.D. CzerwiecF.S. HarrisP.C. KingB.F. TorresV.E. EricksonB.J. Performance of an artificial multi-observer deep neural network for fully automated segmentation of polycystic kidneys.J. Digit. Imaging201730444244810.1007/s10278‑017‑9978‑128550374
     [Google Scholar]
  12. KlineT.L. EdwardsM.E. FetzerJ. GregoryA.V. AnaamD. MetzgerA.J. EricksonB.J. Automatic semantic segmentation of kidney cysts in MR images of patients affected by autosomal-dominant polycystic kidney disease.Abdom. Radiol.20214631053106110.1007/s00261‑020‑02748‑432940759
     [Google Scholar]
  13. LiC. RomanoD. WangS.J. ZhangH. PrinceM.R. WangY. IRIS—intelligent rapid interactive segmentation for measuring liver cyst volumes in autosomal dominant polycystic kidney disease.Tomography20228144745610.3390/tomography801003735202202
     [Google Scholar]
  14. RombolottiM. SangalliF. CerulloD. RemuzziA. LanzaroneE. Automatic cyst and kidney segmentation in autosomal dominant polycystic kidney disease: Comparison of U-Net based methods.Comput. Biol. Med.202214610543110.1016/j.compbiomed.2022.10543135751190
     [Google Scholar]
  15. da CruzL.B. AraújoJ.D.L. FerreiraJ.L. DinizJ.O.B. SilvaA.C. de AlmeidaJ.D.S. de PaivaA.C. GattassM. Kidney segmentation from computed tomography images using deep neural network.Comput. Biol. Med.202012310390610.1016/j.compbiomed.2020.10390632768047
     [Google Scholar]
  16. AapkesS.E. BartenT.R.M. CoudyzerW. DrenthJ.P.H. GeijselaersI.M.A. ter GroteS.A.M. GansevoortR.T. NevensF. van GastelM.D.A. Validation of a semi-automatic method to measure total liver volumes in polycystic liver disease on computed tomography-high speed and accuracy.Eur. Radiol.20233353222323110.1007/s00330‑022‑09346‑636640173
     [Google Scholar]
  17. KimY. GeY. TaoC. ZhuJ. ChapmanA.B. TorresV.E. YuA.S.L. MrugM. BennettW.M. FlessnerM.F. LandsittelD.P. BaeK.T. Automated Segmentation of Kidneys from MR Images in Patients with Autosomal Dominant Polycystic Kidney Disease.Clin. J. Am. Soc. Nephrol.201611457658410.2215/CJN.0830081526797708
     [Google Scholar]
  18. TurcoD. ValinotiM. MartinE.M. TagliaferriC. ScolariF. CorsiC. Fully automated segmentation of polycystic kidneys from noncontrast computed tomography.Acad. Radiol.201825785085510.1016/j.acra.2017.11.01529331360
     [Google Scholar]
  19. SharmaK. RupprechtC. CaroliA. AparicioM.C. RemuzziA. BaustM. NavabN. Automatic segmentation of kidneys using deep learning for total kidney volume quantification in autosomal dominant polycystic kidney disease.Sci. Rep.201771204910.1038/s41598‑017‑01779‑028515418
     [Google Scholar]
  20. van GastelM.D.A. EdwardsM.E. TorresV.E. EricksonB.J. GansevoortR.T. KlineT.L. Automatic measurement of kidney and liver volumes from mr images of patients affected by autosomal dominant polycystic kidney disease.J. Am. Soc. Nephrol.20193081514152210.1681/ASN.201809090231270136
     [Google Scholar]
  21. CaroliA. KlineT.L. Abdominal imaging in ADPKD: Beyond total kidney volume.J. Clin. Med.20231215513310.3390/jcm1215513337568535
     [Google Scholar]
  22. MüllerD. KramerF. MIScnn: A framework for medical image segmentation with convolutional neural networks and deep learning.BMC Med. Imaging20212111210.1186/s12880‑020‑00543‑733461500
     [Google Scholar]
  23. HuangX. ChenJ. ChenM. ChenL. WanY. TDD-UNet: Transformer with double decoder UNet for COVID-19 lesions segmentation.Comput. Biol. Med.2022151Pt A10630610.1016/j.compbiomed.2022.10630636403357
     [Google Scholar]
  24. IsenseeF. JaegerP.F. KohlS.A.A. PetersenJ. Maier-HeinK.H. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation.Nat. Methods202118220321110.1038/s41592‑020‑01008‑z33288961
     [Google Scholar]
  25. PettitRW MarlattBB CorrSJ HavelkaJ RanaA nnU-Net deep learning method for segmenting parenchyma and determining liver volume from computed tomography images.Ann Surg Open 32022
     [Google Scholar]
  26. IrazabalM.V. RangelL.J. BergstralhE.J. OsbornS.L. HarmonA.J. SundsbakJ.L. BaeK.T. ChapmanA.B. GranthamJ.J. MrugM. HoganM.C. El-ZoghbyZ.M. HarrisP.C. EricksonB.J. KingB.F. TorresV.E. Imaging classification of autosomal dominant polycystic kidney disease: a simple model for selecting patients for clinical trials.J. Am. Soc. Nephrol.201526116017210.1681/ASN.201310113824904092
     [Google Scholar]
  27. DoughertyG. Digital image processing for medical applications.New YorkCambridge University Press200910.1017/CBO9780511609657
     [Google Scholar]
  28. JohansenA.R. JinJ. MaszczykT. DauwelsJ. CashS.S. WestoverM.B. Epileptiform spike detection via convolutional neural networks.Proc. IEEE Int. Conf. Acoust. Speech Signal Process.2016201675475810.1109/ICASSP.2016.747177629527131
     [Google Scholar]
  29. TanabeY. IshidaT. EtoH. SeraT. EmotoY. Evaluation of the correlation between prostatic displacement and rectal deformation using the Dice similarity coefficient of the rectum.Med. Dosim.2019444e39e4310.1016/j.meddos.2018.12.00530642696
     [Google Scholar]
  30. RuengchaijatupornN. ChatnuntawechI. TeerapittayanonS. SriswasdiS. ItthipuripatS. HemrungrojnS. BunyabukkanaP. PetchlorlianA. ChunamchaiS. ChotibutT. ChunharasC. An explainable self-attention deep neural network for detecting mild cognitive impairment using multi-input digital drawing tasks.Alzheimers Res. Ther.202214111110.1186/s13195‑022‑01043‑235945568
     [Google Scholar]
  31. KarimiD. SalcudeanS.E. Reducing the hausdorff distance in medical image segmentation with convolutional neural networks.IEEE Trans. Med. Imaging202039249951310.1109/TMI.2019.293006831329113
     [Google Scholar]
  32. KooT.K. LiM.Y. A guideline of selecting and reporting intraclass correlation coefficients for reliability research.J. Chiropr. Med.201615215516310.1016/j.jcm.2016.02.01227330520
     [Google Scholar]
  33. RodgersJ.L. NicewanderW.A. Thirteen ways to look at the correlation coefficient.Am. Stat.1988421596610.2307/2685263
     [Google Scholar]
  34. MishraP. SinghU. PandeyC. MishraP. PandeyG. Application of student’s t-test, analysis of variance, and covariance.Ann. Card. Anaesth.201922440741110.4103/aca.ACA_94_1931621677
     [Google Scholar]
  35. BartlettJ.W. FrostC. Reliability, repeatability and reproducibility: analysis of measurement errors in continuous variables.Ultrasound Obstet. Gynecol.200831446647510.1002/uog.525618306169
     [Google Scholar]
  36. ZhangG. YangZ. HuoB. ChaiS. JiangS. Multiorgan segmentation from partially labeled datasets with conditional nnU-Net.Comput. Biol. Med.202113610465810.1016/j.compbiomed.2021.10465834311262
     [Google Scholar]
  37. RajA. TollensF. HansenL. GollaA.K. SchadL.R. NörenbergD. ZöllnerF.G. Deep learning-based total kidney volume segmentation in autosomal dominant polycystic kidney disease using attention, cosine loss, and sharpness aware minimization.Diagnostics2022125115910.3390/diagnostics1205115935626314
     [Google Scholar]
  38. KociołekM. StrzeleckiM. ObuchowiczR. Does image normalization and intensity resolution impact texture classification?Comput. Med. Imaging Graph.20208110171610.1016/j.compmedimag.2020.10171632222685
     [Google Scholar]
  39. BelliniD. CarboneI. RengoM. ViciniS. PanviniN. CarusoD. IannicelliE. TomboliniV. LaghiA. Performance of machine learning and texture analysis for predicting response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer with 3T MRI.Tomography2022842059207210.3390/tomography804017336006071
     [Google Scholar]
  40. LeuenrothS.J. BencivengaN. IgarashiP. SomloS. CrewsC.M. Triptolide reduces cystogenesis in a model of ADPKD.J. Am. Soc. Nephrol.20081991659166210.1681/ASN.200803025918650476
     [Google Scholar]
  41. GuoQ. WuX.J. KittlerJ. FengZ. Weak sub-network pruning for strong and efficient neural networks.Neural Netw.202114461462610.1016/j.neunet.2021.09.01534653719
     [Google Scholar]
/content/journals/cmir/10.2174/0115734056272767231130110017
Loading
nnUNet for Automatic Kidney and Cyst Segmentation in Autosomal Dominant Polycystic Kidney Disease
Curr. Med. Imaging 20, e15734056272767 (2024); https://doi.org/10.2174/0115734056272767231130110017
/content/journals/cmir/10.2174/0115734056272767231130110017
/content/journals/cmir/10.2174/0115734056272767231130110017
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): ADPKD; Deep learning; Kidney image segmentation; nnUNet; Renal cyst image segmentation; Total kidney volume

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test