Unsupervised connectivity-based thresholding segmentation of midsagittal brain MR images

Chulhee Lee, Shin Huh, Terence A. Ketter, Michael Unser

Research output: Contribution to journalArticlepeer-review

56 Citations (Scopus)


In this paper, we propose an algorithm for automated segmentation of midsagittal brain MR images. First, we apply thresholding to obtain binary images. From the binary images, we locate some landmarks. Based on the landmarks and anatomical information, we preprocess the binary images, which substantially simplifies the subsequent operations. To separate regions what are incorrectly merged after this initial segmentation, a new connectivity- based threshold algorithm is proposed. Assuming that some prior information about the general shape and location of objects is available, the algorithm finds a boundary between two regions using the path connection algorithm and changing the threshold adaptively. In order to test the robustness of the proposed algorithm. We applied the algorithm to 120 midsagittal brain images and obtained satisfactory results.

Original languageEnglish
Pages (from-to)309-338
Number of pages30
JournalComputers in Biology and Medicine
Issue number3
Publication statusPublished - 1998 May

Bibliographical note

Funding Information:
[7–20] Appendix A For additional results using the proposed algorithm see . Figs. 20–31 Chulhee Lee received the B.Sc. and M.Sc. degrees in electronics engineering from Seoul National University in 1984 and 1986, respectively, and the Ph.D. degree in electrical engineering from Purdue University, West Lafayette, IN, in 1992. From 1986 to 1987, he was a researcher in the Acoustic Laboratory at Technical University of Denmark (DTH). From 1993 to 1996, he worked with National Institutes of Health, Bethesda, MD. In 1996, he joined the faculty of the Department of Electronic Engineering, Yonsei University, Seoul. His research interests include image/signal processing, pattern recognition, and neural networks. Dr. Lee is a member of Tau Beta Pi, Eta Kappa Nu and KSEA. Shin Huh was born in Seoul on February 22, 1976. He received the B.Sc. degree in electronics engineering from Yonsei University in 1998. He is currently working towards the M.Sc. degree in electronics engineering at Yonsei University. His current research interests include image segmentation and image/signal processing. Dr. Terence Ketter obtained his medical degree from the University of Toronto and had internship and residency training in psychiatry at the University of California at San Francisco. He had subsequent fellowship training in psychopharmacology and brain imaging research methods in the Biological Psychiatry Branch of the National Institute of Mental Health in Bethesda, MD. He is currently Associate Professor of Psychiatry and Behavioral Sciences and Chief of the Bipolar Disorders Clinic at the Stanford University School of Medicine in Stanford, California. Dr. Ketter's research interests include the use of brain imaging methods such as positron emission tomography (PET) and magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) to better understand the neurobiology of mood (and especially bipolar) disorders. Dr. Ketter has also investigated the use of novel therapies such as new anticonvulsant drugs and combinations of medications in the treatment of mood disorders. His current work includes exploring the possibility of using brain imaging techniques to more effectively target treatments in mood disorders. Michael Unser was born in Zug, Switzerland, on April 9, 1958. He received the M.Sc. (summa cum laude) and Ph.D. degrees in Electrical Engineering in 1981 and 1984, respectively, from the Swiss Federal Institute of Technology in Lausanne. From 1985 to 1997, he was with the Biomedical Engineering and Instrumentation Program, National Institutes of Health, Bethesda, where he had been heading the Image Processing Group. He is now Professor of Biomedical Image Processing at the Swiss Federal Institute of Technology in Lausanne, Switzerland. His research is centered around the numerical aspects of biomedical imaging. He has a strong interest in sampling theories, multiresolution algorithms, wavelets, and the use of splines for image processing. He is the author of over 70 published journal papers in these areas. Dr. Unser serves as an Associate Editor for the IEEE Signal Processing Letters, and is a member of the Image and Multidimensional Signal Processing Committee of the IEEE Signal Processing Society. He is also on the editorial boards of Signal Processing, the Journal of Visual Communication and Image Representation, Pattern Recognition, and was a former Associate Editor (1992–1995) for the IEEE Transactions on Image Processing. He coorganized the 1994 IEEE–EMBS workshop on wavelets in medicine and biology, and serves as conference chair for SPIE's Wavelet applications in signal and image processing, which has been held annually since 1993. He received the Dommer prize for excellence from the Swiss Federal Institute of Technology in 1981, the research prize of the Brown–Boveri Corporation, Switzerland, for his thesis in 1984 and the IEEE Signal Processing Society's 1995 Best Paper Award (IMDSP technical area) for a Transactions paper with A. Aldroubi and M. Eden on B-spline signal processing.

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Health Informatics


Dive into the research topics of 'Unsupervised connectivity-based thresholding segmentation of midsagittal brain MR images'. Together they form a unique fingerprint.

Cite this