Adaptation of multifractal analysis to segmentation of microcalcifications in digital mammograms
Само за регистроване кориснике
2006
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
A method for detecting microcalcifications in digital mammograms is proposed. After recognizing basic features of microcalcifications we introduced several modifications in multifractal analysis, obtaining an efficient method adapted to enhance only small light parts not belonging to surrounding tissue, possibly microcalcifications. Started with a mammogram image, a method creates corresponding multifractal image from which a radiologist has the freedom to change the level of segmentation in an interactive manner and to find suspicious regions, which may contain microcalcifications. Additional postprocessing, based on mathematical morphology, refines the procedure by selecting and outlining regions that contain clusters with microcalcifications. The proposed method was tested through referent mammograms from MiniMIAS database, which is available at public domain. The proposed method successfully extracted microcalcifications in all (clinically approved) cases belonging to this database....
Кључне речи:
multifractal analysis / microcalcifications / mammography / image segmentation / image processingИзвор:
Physica A-Statistical Mechanics and Its Applications, 2006, 367, 494-508Издавач:
- Elsevier, Amsterdam
DOI: 10.1016/j.physa.2005.11.030
ISSN: 0378-4371
WoS: 000238236700043
Scopus: 2-s2.0-33646485663
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Stojić, Tomislav AU - Rejin, Inni AU - Rejin, Branimir PY - 2006 UR - https://machinery.mas.bg.ac.rs/handle/123456789/628 AB - A method for detecting microcalcifications in digital mammograms is proposed. After recognizing basic features of microcalcifications we introduced several modifications in multifractal analysis, obtaining an efficient method adapted to enhance only small light parts not belonging to surrounding tissue, possibly microcalcifications. Started with a mammogram image, a method creates corresponding multifractal image from which a radiologist has the freedom to change the level of segmentation in an interactive manner and to find suspicious regions, which may contain microcalcifications. Additional postprocessing, based on mathematical morphology, refines the procedure by selecting and outlining regions that contain clusters with microcalcifications. The proposed method was tested through referent mammograms from MiniMIAS database, which is available at public domain. The proposed method successfully extracted microcalcifications in all (clinically approved) cases belonging to this database. PB - Elsevier, Amsterdam T2 - Physica A-Statistical Mechanics and Its Applications T1 - Adaptation of multifractal analysis to segmentation of microcalcifications in digital mammograms EP - 508 SP - 494 VL - 367 DO - 10.1016/j.physa.2005.11.030 ER -
@article{ author = "Stojić, Tomislav and Rejin, Inni and Rejin, Branimir", year = "2006", abstract = "A method for detecting microcalcifications in digital mammograms is proposed. After recognizing basic features of microcalcifications we introduced several modifications in multifractal analysis, obtaining an efficient method adapted to enhance only small light parts not belonging to surrounding tissue, possibly microcalcifications. Started with a mammogram image, a method creates corresponding multifractal image from which a radiologist has the freedom to change the level of segmentation in an interactive manner and to find suspicious regions, which may contain microcalcifications. Additional postprocessing, based on mathematical morphology, refines the procedure by selecting and outlining regions that contain clusters with microcalcifications. The proposed method was tested through referent mammograms from MiniMIAS database, which is available at public domain. The proposed method successfully extracted microcalcifications in all (clinically approved) cases belonging to this database.", publisher = "Elsevier, Amsterdam", journal = "Physica A-Statistical Mechanics and Its Applications", title = "Adaptation of multifractal analysis to segmentation of microcalcifications in digital mammograms", pages = "508-494", volume = "367", doi = "10.1016/j.physa.2005.11.030" }
Stojić, T., Rejin, I.,& Rejin, B.. (2006). Adaptation of multifractal analysis to segmentation of microcalcifications in digital mammograms. in Physica A-Statistical Mechanics and Its Applications Elsevier, Amsterdam., 367, 494-508. https://doi.org/10.1016/j.physa.2005.11.030
Stojić T, Rejin I, Rejin B. Adaptation of multifractal analysis to segmentation of microcalcifications in digital mammograms. in Physica A-Statistical Mechanics and Its Applications. 2006;367:494-508. doi:10.1016/j.physa.2005.11.030 .
Stojić, Tomislav, Rejin, Inni, Rejin, Branimir, "Adaptation of multifractal analysis to segmentation of microcalcifications in digital mammograms" in Physica A-Statistical Mechanics and Its Applications, 367 (2006):494-508, https://doi.org/10.1016/j.physa.2005.11.030 . .