Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Feb 9;8(1):447-456.
doi: 10.3390/tomography8010037.

IRIS-Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease

Collin Li  1 , Dominick Romano  1 , Sophie J Wang  1 , Hang Zhang  1 , Martin R Prince  1 , Yi Wang  1
Affiliations

IRIS-Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease

Collin Li et al. Tomography. .

Abstract

Purpose: To develop and integrate interactive features with automatic methods for accurate liver cyst segmentation in patients with autosomal dominant polycystic kidney and liver disease (ADPKD).

Methods: SmartClick and antiSmartClick were developed using iterative region growth guided by spatial and intensity connections and were integrated with automated level set (LS) segmentation and graphical user interface, forming an intelligent rapid interactive segmentation (IRIS) tool. IRIS and LS segmentations of liver cysts on T2 weighted images of patients with ADPKD (n = 17) were compared with manual segmentation as ground truth (GT).

Results: Compared to manual GT, IRIS reduced the segmentation time by more than 10-fold. Compared to automated LS, IRIS reduced the mean liver cyst volume error from 42.22% to 13.44% (p < 0.001). IRIS segmentation agreed well with manual GT (79% dice score and 99% intraclass correlation coefficient).

Conclusion: IRIS is feasible for fast, accurate liver cyst segmentation in patients with ADPKD.

Keywords: intelligent rapid interactive segmentation; lesion segmentation; liver cyst.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Liver cyst segmentation by (a) manual as ground truth (GT), (b) automated level set (LS), and (c) IRIS. LS included substantial vasculature (b), which was cleaned up rapidly using antiSmartClick (c). Small cysts missed on manual GT were captured on IRIS (arrows in (c)).
Figure 2
Figure 2
Scatter plots of liver cyst volume measurements by (a) LS and (b) IRIS against GT. IRIS improved regression slope and regression coefficient. GT = ground truth segmentation, LS = automatic level set segmentation, and IRIS = intelligent rapid interactive segmentation.
Figure 3
Figure 3
Bland–Altman plots for (a) LS and (b) IRIS for cyst volume measurements. LS had a bias of 8.53%, STD of 61.61%, lower limit of agreement (LLA) of −112%, and upper limit of agreement (ULA) of 129%. (a). IRIS had a bias of −5.49%, STD of 15.94%, LLA of −37%, and ULA of 26%. GT = ground truth segmentation, LS = automatic level set segmentation, IRIS = intelligent rapid interactive segmentation, and STD = standard deviation.
Figure 4
Figure 4
Liver cyst segmentation by manual GT (a), automated LS (b), and IRIS (c). The voxels in the space between neighboring cysts (arrows in (c)) were easily included in the manual GT, contributing to the observed segmentation errors. GT = ground truth segmentation, LS = automatic level set segmentation, and IRIS = intelligent rapid interactive segmentation.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Cnossen W.R., Drenth J.P.H. Polycystic liver disease: An overview of pathogenesis, clinical manifestations and management. Orphanet J. Rare Dis. 2014;9:69. doi: 10.1186/1750-1172-9-69. - DOI - PMC - PubMed
    1. Van Keimpema L., De Koning D.B., Van Hoek B., Van Den Berg A.P., Van Oijen M.G., De Man R.A., Nevens F., Drenth J.P. Patients with isolated polycystic liver disease referred to liver centres: Clinical characterization of 137 cases. Liver Int. 2011;31:92–98. doi: 10.1111/j.1478-3231.2010.02247.x. - DOI - PubMed
    1. Muto S., Ando M., Nishio S., Hanaoka K., Ubara Y., Narita I., Kamura K., Mochizuki T., Tsuchiya K., Tsuruya K., et al. The relationship between liver cyst volume and QOL in Japanese ADPKD patients. Clin. Exp. Nephrol. 2020;24:314–322. doi: 10.1007/s10157-019-01830-6. - DOI - PubMed
    1. Malmberg F., Nordenskjold R., Strand R., Kullberg J. SmartPaint: A tool for interactive segmentation of medical volume images. Comput. Methods Biomech. Biomed. Eng.-Imaging Vis. 2017;5:36–44. doi: 10.1080/21681163.2014.960535. - DOI
    1. Kim Y., Bae S.K., Cheng T., Tao C., Ge Y., Chapman A.B., Torres V.E., Yu A.S.L., Mrug M., Bennett W.M., et al. Automated segmentation of liver and liver cysts from bounded abdominal MR images in patients with autosomal dominant polycystic kidney disease. Phys. Med. Biol. 2016;61:7864–7880. doi: 10.1088/0031-9155/61/22/7864. - DOI - PMC - PubMed

Publication types

MeSH terms