Top

Published in:

01-03-2019 | Technical Note

Can the spherical gold standards be used as an alternative to painted gold standards for the computerized detection of lesions using voxel-based classification?

Authors: Yukihiro Nomura, Naoto Hayashi, Shouhei Hanaoka, Tomomi Takenaga, Mitsutaka Nemoto, Soichiro Miki, Takeharu Yoshikawa, Osamu Abe

Published in: Japanese Journal of Radiology | Issue 3/2019

Abstract

Purpose

For the development of computer-assisted detection (CAD) software using voxel-based classification, gold standards defined by pixel-by-pixel painting, called painted gold standards, are desirable. However, for radiologists who define gold standards, a simplified method of definition is desirable. One of the simplest methods of defining gold standards is a spherical region, called a spherical gold standard. In this study, we investigated whether spherical gold standards can be used as an alternative to painted gold standards for computerized detection using voxel-based classification.

Materials and methods

The spherical gold standards were determined by the center of gravity and the maximum diameter. We compared two types of gold standard, painted gold standards and spherical gold standards, by two types of CAD software using voxel-based classification.

Results

The time required to paint the area of one lesion was 4.7–6.5 times longer than the time required to define a spherical gold standard. For the same performance of the CAD software, the number of training cases required for the spherical gold standard was 1.6–7.6 times that for the painted gold standards.

Conclusion

Spherical gold standards can be used as an alternative to painted gold standards for the computerized detection of lesions with simple shapes.

Available only for authorised users

The parameters of the DoG, shape index, dot enhancement filter, line enhancement filter, and vessel enhancement filter are the same as those in the voxel-based classification.

Masutani Y, Nemoto M, Nomura Y, Hayashi N. Clinical machine learning in action: CAD system design, development, tuning, and long-term experience. In: Suzuki K, editor. Machine learning in computer-aided diagnosis: medical imaging intelligence and analysis. Hershey: IGI Global; 2012. p. 159–76.CrossRef

Suzuki K. A supervised ‘lesion-enhancement’ filter by use of a massive-training artificial neural network (MTANN) in computer-aided diagnosis (CAD). Phys Med Biol. 2009;54:S31–45.CrossRefPubMedPubMedCentral

Nomura Y, Masutani Y, Miki S, et al. Performance improvement in computerized detection of cerebral aneurysms by retraining classifier using feedback data collected in routine reading environment. J Biomed Graph Comput. 2014;4(4):12–21.

Dou Q, Chen H, Yu L, et al. Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks. IEEE Trans Med Imaging. 2016;35:1182–95.CrossRef

Debats OA, Meijs M, Litjens GJ, Huisman HJ. Automated multistructure atlas-assisted detection of lymph nodes using pelvic MR lymphography in prostate cancer patients. Med Phys. 2016;43:3132–42.CrossRefPubMed

Hamidian S, Sahiner B, Petrick N, Pezeshk A. 3D convolutional neural network for automatic detection of lung nodules in chest CT. Proc SPIE (Med Imaging). 2017;10134:1013409.CrossRef

Nemoto M, Hayashi N, Hanaoka S, Nomura Y, Miki S, Yoshikawa T. Feasibility study of a generalized framework for developing computer-aided detection systems-a new paradigm. J Digit Imaging. 2017;30:629–39.CrossRefPubMedPubMedCentral

Armato SG 3rd, McLennan G, Bidaut L, et al. The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med Phys. 2011;38:915–31.CrossRefPubMedPubMedCentral

van Ginneken B, Armato SG 3rd, de Hoop B, et al. Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: the ANODE09 study. Med Image Anal. 2010;14:707–22.CrossRefPubMed

10.

Kuhnigk JM, Dicken V, Bornemann L, et al. Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic CT scans. IEEE Trans Med Imaging. 2006;25(4):417–34.CrossRefPubMed

11.

Diciotti S, Picozzi G, Falchini M, Mascalchi M, Villari N, Valli G. 3-D segmentation algorithm of small lung nodules in spiral CT images. IEEE Trans Inf Technol Biomed. 2008;12(1):7–19.CrossRefPubMed

12.

Lassen BC, Jacobs C, Kuhnigk JM, van Ginneken B, van Rikxoort EM. Robust semi-automatic segmentation of pulmonary subsolid nodules in chest computed tomography scans. Phys Med Biol. 2015;60(3):1307–23.CrossRefPubMed

13.

Schapire RE, Freund Y, Bartlett P, Lee WS. Boosting the margin: a new explanation for the effectiveness of voting methods. Ann Stat. 1998;26:1651–86.CrossRef

14.

Iba W, Langley P. Induction of one-level decision trees. In: Proceedings of international conference on machine learning (ICML 1992). 1992. pp. 233–240.

15.

Dorai C, Jain AK. COSMOS-a representation scheme for 3D free-form objects. IEEE Trans Pattern Anal Mach Intell. 1997;19:1115–30.CrossRef

16.

Li Q, Sone S, Doi K. Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans. Med Phys. 2003;30:2040–51.CrossRefPubMed

17.

Frangi AF, Niessen WJ, Vincken KL, Viergever MA. Multiscale vessel enhancement filtering. MICCAI’98 LNCS. 1998;1496:130–137.

18.

Nomura Y, Nemoto M, Masutani Y, et al. Reduction of false positives at vessel bifurcations in computerized detection of lung nodules. J Biomed Graph Comput. 2014;4(3):36–46.

19.

te Brake GM, Karssemeijer N, Hendriks JHCL. An automatic method to discriminate malignant masses from normal tissue in digital mammograms. Phys Med Biol. 2000;45:2843–57.CrossRef

20.

Hanaoka S, Nomura Y, Nemoto M, et al. HoTPiG: a novel geometrical feature for vessel morphometry and its application to cerebral aneurysm detection. MICCAI Part II LNCS. 2015;2015(9350):103–10.

21.

Wan SY, Higgins WE. Symmetric region growing. IEEE Trans Image Process. 2003;12:1007–15.CrossRefPubMed

22.

Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern. 1979;9:62–6.CrossRef

23.

Canny J. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell. 1986;PAMI-8:679–98.CrossRef

24.

Gu L, Peters T. 3D segmentation of medical images using a fast multistage hybrid algorithm. Int J Comput Assist Radiol Surg. 2006;1:23–31.CrossRef

Title: Can the spherical gold standards be used as an alternative to painted gold standards for the computerized detection of lesions using voxel-based classification?
Authors: Yukihiro Nomura
Naoto Hayashi
Shouhei Hanaoka
Tomomi Takenaga
Mitsutaka Nemoto
Soichiro Miki
Takeharu Yoshikawa
Osamu Abe
Publication date: 01-03-2019
Publisher: Springer Japan
Published in: Japanese Journal of Radiology / Issue 3/2019
Print ISSN: 1867-1071
Electronic ISSN: 1867-108X
DOI: https://doi.org/10.1007/s11604-018-0784-6

Keynote webinar | Spotlight on sleep in brain health

Springer Medicine

Can the spherical gold standards be used as an alternative to painted gold standards for the computerized detection of lesions using voxel-based classification?

Abstract

Purpose

Materials and methods

Results

Conclusion

Keynote webinar | Spotlight on sleep in brain health

Springer Medicine

Abstract

Purpose

Materials and methods

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 3/2019

Efficacy and prognostic factors of transarterial embolization as initial treatment for spontaneously ruptured hepatocellular carcinoma: a single-center retrospective analysis in 57 patients

Pleuroparenchymal fibroelastosis-like lesions on chest computed tomography in routine clinical practice

Postmortem computed tomographic features in the diagnosis of drowning: a comparison of fresh water and salt water drowning cases

Imaging findings of complications after thoracic surgery

Computed tomographic colonography with a reduced dose of laxative using a novel barium sulfate contrast agent in Japan

A diagnostic strategy for breast calcifications based on a long-term follow-up of 615 lesions