Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress
Clinical Collections
Advances in Alzheimer’s

At a glance: The STEP trials

A round-up of the STEP phase 3 clinical trials evaluating semaglutide for weight loss in people with overweight or obesity.
ADVANCED SEARCH
Log in
Top
Skeletal Radiology
Published in: Skeletal Radiology 4/2008

01-04-2008 | Scientific Article

Automated bony region identification using artificial neural networks: reliability and validation measurements

Authors: Esther E. Gassman, Stephanie M. Powell, Nicole A. Kallemeyn, Nicole A. DeVries, Kiran H. Shivanna, Vincent A. Magnotta, Austin J. Ramme, Brian D. Adams, Nicole M. Grosland

Published in: Skeletal Radiology | Issue 4/2008

Login to get access

Abstract

Objective

The objective was to develop tools for automating the identification of bony structures, to assess the reliability of this technique against manual raters, and to validate the resulting regions of interest against physical surface scans obtained from the same specimen.

Materials and methods

Artificial intelligence-based algorithms have been used for image segmentation, specifically artificial neural networks (ANNs). For this study, an ANN was created and trained to identify the phalanges of the human hand.

Results

The relative overlap between the ANN and a manual tracer was 0.87, 0.82, and 0.76, for the proximal, middle, and distal index phalanx bones respectively. Compared with the physical surface scans, the ANN-generated surface representations differed on average by 0.35 mm, 0.29 mm, and 0.40 mm for the proximal, middle, and distal phalanges respectively. Furthermore, the ANN proved to segment the structures in less than one-tenth of the time required by a manual rater.

Conclusions

The ANN has proven to be a reliable and valid means of segmenting the phalanx bones from CT images. Employing automated methods such as the ANN for segmentation, eliminates the likelihood of rater drift and inter-rater variability. Automated methods also decrease the amount of time and manual effort required to extract the data of interest, thereby making the feasibility of patient-specific modeling a reality.
Literature
1.
Westin C-F, Warfield S, Bhalerao A, Mui L, Richolt J, Kikinis R. Tensor controlled local structure enhancement of CT images for bone segmentation. In: Wells WM, Colchester A, Delp S, editors. Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI’98) 1998; 1998. p. 1205–1212.
2.
Choi SM, Lee JE, Kim J, Kim MH. Volumetric object reconstruction using the 3D-MRF model-based segmentation. IEEE Trans Med Imaging 1997; 16(6): 887–892.PubMedCrossRef
3.
Lorigo LM, Faugeras O, Grimson WEL, Keriven R, Kikinis R. Segmentation of bone in clinical knee MRI using texture-based geodesic active contours. Lect Notes Comput Sci 1998;1496: 1195.CrossRef
4.
Warfield SK, Kaus M, Jolesz FA, Kikinis R. Adaptive, template moderated, spatially varying statistical classification. Med Image Anal 2000; 4(1): 43–55.PubMedCrossRef
5.
Grau V, Mewes AU, Alcaniz M, Kikinis R, Warfield SK. Improved watershed transform for medical image segmentation using prior information. IEEE Trans Med Imaging 2004; 23(4): 447–458.PubMedCrossRef
6.
Hajder L, Kardos I, Chetverikov D, Renner G. Active contours and fast marching methods in medical image processing [in Hungarian]. In: Fourth Hungarian Conference on Image Processing and Pattern Recognition (KÉPAF); 2004; Miskolc-Tapolca; 2004. p. 90–96.
7.
Ehrhardt J, Handels H, Malina T, Strathmann B, Plotz W, Poppl SJ. Atlas-based segmentation of bone structures to support the virtual planning of hip operations. Int J Med Inform 2001; 64(2–3): 439–447.PubMedCrossRef
8.
Azhari H, Oliker S, Rogers WJ, Weiss JL, Shapiro EP. Three-dimensional mapping of acute ischemic regions using artificial neural networks and tagged MRI.. IEEE Trans Biomed Eng 1996; 43(6): 619–626; erratum appears in IEEE Trans Biomed Eng 1996; 43(9): 972.PubMedCrossRef
9.
Binder T, Sussner M, Moertl D, et al. Artificial neural networks and spatial temporal contour linking for automated endocardial contour detection on echocardiograms: a novel approach to determine left ventricular contractile function. Ultrasound Med Biol 1999; 25(7): 1069–1076.PubMedCrossRef
10.
Chen DR, Chang RF, Kuo WJ, Chen MC, Huang YL. Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks. Ultrasound Med Biol 2002; 28(10): 1301–1310.PubMedCrossRef
11.
Itchhaporia D, Snow PB, Almassy RJ, Oetgen WJ. Artificial neural networks: current status in cardiovascular medicine. J Am Coll Cardiol 1996; 28(2): 515–521.PubMed
12.
Joo S, Yang YS, Moon WK, Kim HC. Computer-aided diagnosis of solid breast nodules: use of an artificial neural network based on multiple sonographic features. IEEE Trans Med Imaging 2004; 23(10): 1292–1300.PubMedCrossRef
13.
Kallergi M. Computer-aided diagnosis of mammographic microcalcification clusters. Med Phys 2004; 31(2): 314–326.PubMedCrossRef
14.
Lin KC, Yang MS, Liu HC, Lirng JF, Wang PN. Generalized Kohonen’s competitive learning algorithms for ophthalmological MR image segmentation. Magn Reson Imaging 2003; 21(8): 863–870.PubMedCrossRef
15.
Lindahl D, Palmer J, Edenbrandt L. Myocardial SPET: artificial neural networks describe extent and severity of perfusion defects. Clin Physiol 1999; 19(6): 497–503.PubMedCrossRef
16.
Lindahl D, Toft J, Hesse B, et al. Scandinavian test of artificial neural network for classification of myocardial perfusion images. Clin Physiol 2000; 20(4): 253–261.PubMedCrossRef
17.
Magnotta VA, Heckel D, Andreasen NC, et al. Measurements of brain structures with artificial neural networks: Two- and three-dimensional applications. Radiology 1999; 211(3): 781–790.PubMed
18.
Middleton I, Damper RI. Segmentation of magnetic resonance images using a combination of neural networks and active contour models. Med Eng Phys 2004; 26(1): 71–86.PubMedCrossRef
19.
Ohlsson M. WeAidU—a decision support system for myocardial perfusion images using artificial neural networks. Artif Intell Med 2004; 30(1): 49–60.PubMedCrossRef
20.
Raff U, Scherzinger AL, Vargas PF, Simon JH. Quantitation of grey matter, white matter, and cerebrospinal fluid from spin-echo magnetic resonance images using an artificial neural network technique. Med Phys 1994; 21(12): 1933–1942.PubMedCrossRef
21.
Rajab MI, Woolfson MS, Morgan SP. Application of region-based segmentation and neural network edge detection to skin lesions. Comput Med Imaging Graph 2004; 28(1–2): 61–68.PubMedCrossRef
22.
Reddick WE, Glass JO, Cook EN, Elkin TD, Deaton RJ. Automated segmentation and classification of multispectral magnetic resonance images of brain using artificial neural networks. IEEE Trans Med Imaging 1997; 16(6): 911–918.PubMedCrossRef
23.
Santos-Garcia G, Varela G, Novoa N, Jimenez MF. Prediction of postoperative morbidity after lung resection using an artificial neural network ensemble. Artif Intell Med 2004; 30(1): 61–69.PubMedCrossRef
24.
Shen S, Sandham W, Granat M, Sterr A. MRI fuzzy segmentation of brain tissue using neighborhood attraction with neural-network optimization. IEEE Trans Inf Technol Biomed 2005; 9(3): 459–467.PubMedCrossRef
25.
Spinks R, Magnotta VA, Andreasen NC, et al. Manual and automated measurement of the whole thalamus and mediodorsal nucleus using magnetic resonance imaging. Neuroimage 2002; 17(2): 631–642.PubMedCrossRef
26.
Szabo BK, Aspelin P, Wiberg MK. Neural network approach to the segmentation and classification of dynamic magnetic resonance images of the breast: comparison with empiric and quantitative kinetic parameters. Acad Radiol 2004; 11(12): 1344–1354.PubMedCrossRef
27.
Simon I, Pound CR, Partin AW, Clemens JQ, Christens-Barry WA. Automated image analysis system for detecting boundaries of live prostate cancer cells. Cytometry 1998; 31(4): 287–294.PubMedCrossRef
28.
Pham DL, Xu C, Prince JL. Current methods in medical image segmentation. Annu Rev Biomed Eng 2000; 2: 315–337.PubMedCrossRef
29.
Neu CP, Crisco JJ, Wolfe SW. In vivo kinematic behavior of the radio-capitate joint during wrist flexion-extension and radio-ulnar deviation. J Biomech 2001; 34(11): 1429–1438.PubMedCrossRef
30.
Andreasen NC, Cohen G, Harris G, et al. Image processing for the study of brain structure and function: problems and programs. J Neuropsychiatry Clin Neurosci 1992; 4(2): 125–133.PubMed
31.
Magnotta VA, Harris G, Andreasen NC, O’Leary DS, Yuh WTC, Heckel D. Structural MR image processing using the BRAINS2 toolbox. Comput Med Imaging Graph 2002; 26(4): 251–264.PubMedCrossRef
32.
Powell S, Magnotta VA, Johnson HJ, Andreasen NC. Automated brain segmentation using neural networks. University of Iowa; 2006.
33.
Davis MH, Khotanzad A, Flamig DP, Harms SE. A physics-based coordinate transformation for 3-D image matching. IEEE Trans Med Imaging 1997; 16(3): 317–328.PubMedCrossRef
34.
Thirion JP. Image matching as a diffusion process: an analogy with Maxwell’s demons. Med Image Anal 1998; 2(3): 243–260.PubMedCrossRef
35.
Donahue TLH, Hull ML, Rashid MM, Jacobs CR. A finite element model of the human knee joint for the study of tibio-femoral contact. J Biomech Eng 2002; 124: 273–280.PubMedCrossRef
36.
Sharp GC, Lee SW, Wehe DK. Invariant features and the registration of rigid bodies. In: Proceedings of the IEEE International Conference on Robotics and Automation; 1999: 932–937.
37.
Danielsson PE. Euclidean distance mapping. Comput Graph Image Process 1980; 14: 227–248.CrossRef
38.
DeVries NA, Gassman EE, Kallemeyn NA, Shivanna KH, Magnotta VA, Grosland NM. Validation of phalanx bone three-dimensional surface segmentation from computed tomography images using laser scanning. Skeletal Radiol 2008; 37(1): 35–42.PubMedCrossRef
39.
Powell S, Magnotta VA, Johnson HJ, Jammalamadaka VK, Peierson R, Andreasen NC. Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures. Neuroimage 2008; 39(1): 238–247.PubMedCrossRef
Metadata
Title
Automated bony region identification using artificial neural networks: reliability and validation measurements
Authors
Esther E. Gassman
Stephanie M. Powell
Nicole A. Kallemeyn
Nicole A. DeVries
Kiran H. Shivanna
Vincent A. Magnotta
Austin J. Ramme
Brian D. Adams
Nicole M. Grosland
Publication date
01-04-2008
Publisher
Springer-Verlag
Published in
Skeletal Radiology / Issue 4/2008
Print ISSN: 0364-2348
Electronic ISSN: 1432-2161
DOI
https://doi.org/10.1007/s00256-007-0434-z

Other articles of this Issue 4/2008

Skeletal Radiology 4/2008 Go to the issue

Abstracts

Society of Skeletal Radiology 2008 Annual Meeting, Scientific Presentation Sessions, 9–12 March 2008, La Quinta Resort and Club, La Quinta, CA, USA

Scientific Article

Optimal 3-T MRI for depiction of the finger A2 pulley: comparison between T1-weighted, fat-saturated T2-weighted and gadolinium-enhanced fat-saturated T1-weighted sequences

Scientific Article

Frequency of USP6 rearrangements in myositis ossificans, brown tumor, and cherubism: molecular cytogenetic evidence that a subset of “myositis ossificans-like lesions” are the early phases in the formation of soft-tissue aneurysmal bone cyst

Case Report

Cartilaginous avulsion fracture of the tibial spine in a 5-year-old girl

Perspective

Growing cartilage for human replacement—where are we?

Case Report

Dedifferentiated parosteal osteosarcoma with giant cell tumor component