Fetal brain extraction from magnetic resonance image (MRI) of human fetus

ABSTRACT

Study of a fetus is a rapidly growing field of research and it requires fetal brain segmentation. Automatic segmentation of the fetal brain from magnetic resonance imaging (MRI) is challenging, due to the highly variable size and shape of the developing brain, possible brain structure abnormalities, movement of the fetus and a poor resolution of fetal MRI scans. This is in contrast to adult brain segmentation, where the brain structure is stable and several established methods exist. This paper presents a fully automatic segmentation method to segment the fetal brain portion from MRI. The segmentation pipeline developed in this study includes contrast enhancement, region growing and hole filling. Twenty-five volumes of retrospective fetal MRI are used in this work. Experimental results show that this method can successfully segment the fetal brain from magnetic resonance images which are comparable to that of a semi-automatic method.

KEYWORDS:

• Fetal MRI
• fetal brain
• contrast enhancement
• region growing
• hole filling

Acknowledgements

The authors wish to thank Dr Sudha Ramakrishnan MD MRCOG (UK), Fell.Fetal Medicine, Consultant in Fetal Medicine, MediScan Ashvita, Fetal Medicine & Research Centre, Trichy, for her help in qualitative validation. The authors extend their gratitude to Dr K. G. Srinivasan MD, RD, Consultant Radiologist, KGS Advanced MR & CT Scan, Madurai, for providing fetal MRI datasets. The authors would also wish to thank Dr N. Karunakaran MBBS, DMRD, DNB(RD), Consultant Radiologist, Meenakshi Mission Hospital and Research Centre, Madurai, Dr S. P. Balachandran MD, DM, (Neuro), Neurologist, Dindigul Neuro Centre, Dindigul, for their help in validating our results. This is a collaborative work between Gandhigram Rural Institute – Deemed University, India and Sree Ramachandra Medical University, Chennai, India, under the MoU dated 20.02.2014. Ethical approval was granted by the Ethical Committee (ethics no. IEC-NI/14/OCT/43/65) of the same University.

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

K. Somasundaram http://orcid.org/0000-0003-0932-3538

Notes on contributors

K. Somasundaram received his MSc degree in Physics from the University of Madras, Chennai, India, in 1976, a PhD degree in Theoretical Physics from Indian Institute of Science, Bangalore, India, in 1984, and a Post Graduate Diploma in Computer Methods from Madurai Kamaraj University, Madurai, India, in 1989 . He is presently a Professor at the Department of Computer Science and Applications, Gandhigram Rural Institute, Gandhigram, India. From 1976 to 1989, he was a Professor with the Department of Physics at the same institute. He was previously a Researcher at an International Centre for Theoretical Physics, Trieste, Italy, and a Development Fellow of Commonwealth Universities at the School of Multimedia, Edith Cowan University, Australia. His research interests are in image processing, image compression, medical image processing, magnetohydrodyanmic surface waves and astrophysical plasmas. He is a Life member of the Indian Society for Technical Education and Telemedicine Society of India. He is also an annual member in ACM, USA and IEEE Computer Society, USA.

S.P. Gayathri received her Master of Computer Science from Seethalakshmi Ramasamy College of Arts and Science, Trichy, India. From 2004 to 2007, she was a Lecturer in the Department of Computer Science, Ramaprabha College of Arts and Science, Dindigul, TN, India. From 2007 to 2011 December, she was an assistant professor in the Department of Computer Science and Applications in Gandhigram Rural Institute (DU), Dindigul, TN, India. She finished her Ph.D in Segmentation and Volume Estimation of Fetal Brain from T2-W Magnetic Resonance Images (MRI) of Human Fetus in the Department of Computer Science and Applications, Gandhigram Rural Institute - Deemed University, Dindigul, India. Her research interest is Digital and Medical Image Processing. She is presently working as Associate professor in Sakthi College of Arts and Science for Women, Oddanchatram, TN, India.

R. Rajeswaran obtained his MBBS from Kilpauk Medical College, Chennai in 1993 and his MD (Radio diagnosis) from SCB Medical College, Cuttack, India, in 1997. He was conferred a PhD for his research work on Fetal MRI in 2011. He has been working as faculty in the Dept. of Radiology, Sri Ramachandra Medical College, Chennai, since 1997 and is currently holding the post of Professor. His interests are Fetal, Paediatric imaging, Neuro and musculoskeletal imaging.

Dr Dighe Manjiri is section chief of body imaging at the University of Washington and a UW associate professor of radiology. In addition to body imaging, she is an expert in obstetric and thyroid imaging. She also conducts research on thyroid nodules using non-invasive ways to diagnose malignancy which includes ultrasound elastography. For long she has had interest and expertise in obstetric imaging and works closely with the Maternal Fetal Medicine group in UW to diagnose complex cases. She completed her residency in radiology in 2002. After completing her residency training, she underwent a year of abdominal imaging fellowship at the University of Washington Medical Center. She joined the staff in August of 2004 as an acting assistant professor, becoming an assistant professor in 2005 and associate professor in 2011. She is also the director of ultrasound at the UW Medical Center. She is a fellow of the Society of Abdominal Radiology and Society of Radiologists in Ultrasound. She is board certified in radiology.