Automatic segmentation of facial soft tissue in MRI data based on non-rigid normalization in application to soft tissue thickness measurement
Authors:
- Iryna Gorbenko,
- Krzysztof Mikołajczyk,
- Magdalena Jasionowska-Skop,
- Jerzy Narloch,
- Krzysztof Kałużyński
Abstract
For measuring the thickness of soft tissue in magnetic resonance (MRI) images, precise borders between skull and face surfaces should be known. We present an algorithm for segmentation of the human head in T1-weighted MRI images that generates smooth, complete segments of head tissues for further landmarks definition and measurements of the soft tissue thickness of the human head. As a segmentation tool we use an algorithm based on nonlinear normalization of the MRI template to MRI data and application of transform matrix to the head model. The algorithm uses preprocessed subject MRI data and a head model with separate tissue segments. The head model is obtained using a hybrid algorithm and consists of four segments: soft tissue, skull, brain and air. To assess the precision of segmentation, specificity, sensitivity, Dice and Jaccard Similarity Coefficients were computed. The algorithm was tested on MRI images from 10 Caucasian adults from free public database IXI. Specificity of 93% and 98% and sensitivity of 87% and 93% was achieved for soft tissue and brain segment, respectively. Specificity of 67% and 72% and sensitivity of 83% and 62% was achieved for the skull and air segments, respectively.
- Record ID
- WUT5eb3c3257daa43c0ac2b8c644d648277
- Author
- Journal series
- Biomedical Signal Processing and Control, ISSN 1746-8094, e-ISSN 1746-8108
- Issue year
- 2020
- Vol
- 56
- Pages
- 1-8
- Publication size in sheets
- 0.50
- Article number
- 101698
- Keywords in Polish
- segmentacja tkanek miękkich,mózgu, kości czaszki i powietrza, rezonans magnetyczny, model głowy, elastyczne dopasowanie
- Keywords in English
- head segmentation, skull segmentation, soft tissue segmentation, soft tissue measurement, head model, non-rigid normalization, MRI imaging
- ASJC Classification
- ;
- Abstract in Polish
- Do pomiaru grubości tkanek miękkich w obrazach rezonansu magnetycznego (MRI) potrzebna jest dokładna segmentacja powierzchni twarzy i kości czaszki. W tym celu zaproponowano algorytm segmentacji ludzkiej głowy w obrazach MRI T1-zależnych. Zastosowano do tego algorytm elastycznego dopasowania do wzorcowego badania MRI (wzorca). Algorytm wykorzystuje wstępnie przetworzone dane MRI pacjenta oraz zaproponowany model głowy z odseparowanymi segmentami tkanki miękkiej, kości czaszki, mózgu i powietrza. Algorytm testowano na 10 obrazach MRI dorosłych osób rasy kaukaskiej. Dla segmentacji tkanek miękkich i mózgu uzyskano odpowiednio swoistość 93% i 98% oraz czułość 87% i 93%, natomiast dla kości czaszki i powietrza - swoistość 67% i 72% oraz czułość 83% i 62%.
- DOI
- DOI:10.1016/j.bspc.2019.101698 Opening in a new tab
- URL
- https://www.sciencedirect.com/science/article/pii/S1746809419302794 Opening in a new tab
- Language
- (en) English
- Score (nominal)
- 140
- Score source
- journalList
- Score
- = 140.0, 09-05-2022, ArticleFromJournal
- Publication indicators
- = 1; = 1; : 2018 = 1.841; : 2020 (2 years) = 3.880 - 2020 (5 years) =3.992
- Uniform Resource Identifier
- https://repo.pw.edu.pl/info/article/WUT5eb3c3257daa43c0ac2b8c644d648277/
- URN
urn:pw-repo:WUT5eb3c3257daa43c0ac2b8c644d648277
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or PerishOpening in a new tab system.