Segmentation Based on Propagation of Dynamically Changing Superpixels; Programming and Computer Software; Vol. 46, iss. 3

Bibliographische Detailangaben
Parent link:Programming and Computer Software
Vol. 46, iss. 3.— 2020.— [P. 195-206]
Körperschaften: Национальный исследовательский Томский политехнический университет Инженерная школа информационных технологий и робототехники Научно-образовательная лаборатория обработки и анализа больших данных, Национальный исследовательский Томский политехнический университет Инженерная школа информационных технологий и робототехники Отделение информационных технологий
Weitere Verfasser: Danilov V. V. Vyacheslav Vladimirovich, Gerget O. M. Olga Mikhailovna, Skirnevsky I. P. Igor Petrovich, Manakov R. Roman, Kolpashchikov D. Yu. Dmitry Yurjevich
Zusammenfassung:Title screen
This paper describes a new method for medical data segmentation based on superpixel propagation. The proposed method is a modification of the classical region growing algorithm and partly inherits the concept of octrees. The key difference of the proposed approach is the transition to the superpixel domain, as well as more flexible conditions for adding neighbor superpixels to the region. The region formation algorithm checks superpixels for compliance with some homogeneity criteria. First, the average intensity of superpixels is compared with the intensity of a resulting region. Second, each pixel on the edges and diagonals of a superpixel is compared with a threshold value. An important feature of the proposed method is the dynamically changing (floating) size of superpixels. The resulting region is formed by constructing a spline based on the points of intersection among the superpixels external to the region. To test the accuracy of the method, we use the MRI images of the left ventricle obtained at the University of York and MRI images of brain tumors obtained at the Southern Medical University. To demonstrate the performance of our method, a set of high-resolution synthetic images was additionally created. As an accuracy estimation metric, we use the Dice similarity coefficient (DSC). For the proposed method, it corresponds to 0.93 ± 0.03 and 0.89 ± 0.07 for the left ventricle and tumor segmentation, respectively. It is demonstrated that a step-by-step reduction in the size of a superpixel can significantly speed up the method without loss of accuracy.
Режим доступа: по договору с организацией-держателем ресурса
Sprache:Englisch
Veröffentlicht: 2020
Schlagworte:
Online-Zugang:https://doi.org/10.1134/S0361768820030044
Format: MixedMaterials Elektronisch Buchkapitel
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=662244

MARC

LEADER 00000naa0a2200000 4500
001 662244
005 20251127113121.0
035 |a (RuTPU)RU\TPU\network\33381 
090 |a 662244 
100 |a 20200618d2020 k||y0rusy50 ba 
101 0 |a eng 
102 |a DE 
135 |a drcn ---uucaa 
181 0 |a i  
182 0 |a b 
200 1 |a Segmentation Based on Propagation of Dynamically Changing Superpixels  |f V. V. Danilov, O. M. Gerget, I. P. Skirnevsky [et al.] 
203 |a Text  |c electronic 
300 |a Title screen 
320 |a [References: 29 tit.] 
330 |a This paper describes a new method for medical data segmentation based on superpixel propagation. The proposed method is a modification of the classical region growing algorithm and partly inherits the concept of octrees. The key difference of the proposed approach is the transition to the superpixel domain, as well as more flexible conditions for adding neighbor superpixels to the region. The region formation algorithm checks superpixels for compliance with some homogeneity criteria. First, the average intensity of superpixels is compared with the intensity of a resulting region. Second, each pixel on the edges and diagonals of a superpixel is compared with a threshold value. An important feature of the proposed method is the dynamically changing (floating) size of superpixels. The resulting region is formed by constructing a spline based on the points of intersection among the superpixels external to the region. To test the accuracy of the method, we use the MRI images of the left ventricle obtained at the University of York and MRI images of brain tumors obtained at the Southern Medical University. To demonstrate the performance of our method, a set of high-resolution synthetic images was additionally created. As an accuracy estimation metric, we use the Dice similarity coefficient (DSC). For the proposed method, it corresponds to 0.93 ± 0.03 and 0.89 ± 0.07 for the left ventricle and tumor segmentation, respectively. It is demonstrated that a step-by-step reduction in the size of a superpixel can significantly speed up the method without loss of accuracy. 
333 |a Режим доступа: по договору с организацией-держателем ресурса 
461 |t Programming and Computer Software 
463 |t Vol. 46, iss. 3  |v [P. 195-206]  |d 2020 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
610 1 |a пиксели 
610 1 |a сегментация 
610 1 |a опухоли 
701 1 |a Danilov  |b V. V.  |c specialist in the field of informatics and computer technology  |c engineer of Tomsk Polytechnic University  |f 1989-  |g Vyacheslav Vladimirovich  |3 (RuTPU)RU\TPU\pers\37831 
701 1 |a Gerget  |b O. M.  |c Specialist in the field of informatics and computer technology  |c Professor of Tomsk Polytechnic University, Doctor of Sciences  |f 1974-  |g Olga Mikhailovna  |3 (RuTPU)RU\TPU\pers\31430  |9 15593 
701 1 |a Skirnevsky  |b I. P.  |c specialist in the field of automation and computer systems  |c educational master Tomsk Polytechnic University  |f 1989-  |g Igor Petrovich  |3 (RuTPU)RU\TPU\pers\35105 
701 1 |a Manakov  |b R.  |g Roman 
701 1 |a Kolpashchikov  |b D. Yu.  |g Dmitry Yurjevich 
712 0 2 |a Национальный исследовательский Томский политехнический университет  |b Инженерная школа информационных технологий и робототехники  |b Научно-образовательная лаборатория обработки и анализа больших данных  |3 (RuTPU)RU\TPU\col\23599 
712 0 2 |a Национальный исследовательский Томский политехнический университет  |b Инженерная школа информационных технологий и робототехники  |b Отделение информационных технологий  |3 (RuTPU)RU\TPU\col\23515 
801 2 |a RU  |b 63413507  |c 20200618  |g RCR 
856 4 |u https://doi.org/10.1134/S0361768820030044 
942 |c CF