A cross-cutting approach for tracking architectural distortion locii on digital breast tomosynthesis slices
Carregando...
Citações na Scopus
7
Tipo de produção
article
Data de publicação
2019
Título da Revista
ISSN da Revista
Título do Volume
Editora
ELSEVIER SCI LTD
Autores
OLIVEIRA, Helder C. R. de
MENCATTINI, Arianna
CASTI, Paola
GONZAGA, Adilson
MARTINELLI, Eugenio
VIEIRA, Marcelo A. da Costa
Citação
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, v.50, p.92-102, 2019
Resumo
Background and objective: Full-field digital mammography (FFDM) is the predominant breast cancer screening exam used. However, with the emergence of digital breast tomosynthesis (DBT) the radiologists could improve early recognition of breast cancer signs. In this scenario, the detection of architectural distortion (AD) is still a challenging task. ADs are very subtle contraction of the breast parenchyma that could represent the earliest manifestation of cancer, assessing at present 50% of missed cases. Methods: This paper proposes a new paradigm to detect AD in DBT exams by a cross-cutting approach exploiting the 3-dimensionality of the imaging modality. After locating AD candidates in each DBT slice, the suspicious spots are tracked in cross-slice direction and then characterized in terms of neighboring texture. In this approach, which mimics radiologist's scrolling down over zoomed slices, we reduce the amount of uninformative signs collected in DBT exams by preserving the large variability of AD appearance. Results: Using 37 sets of DBT slices containing at least one AD locus indicated by a radiologist, the proposed methodology reaches an AUC of 0.84, with only one false negative exam at sensitivity of 0.9. Conclusions: The results show that the proposed algorithm can be a promising tool for the automatic detection of AD locii. Future work will address the extension of the dataset of DBT slices as well the improvement of algorithm performance toward the application in the clinical practice. (C) 2019 Published by Elsevier Ltd.
Palavras-chave
Architectural distortion, Digital breast tomosynthesis, Breast cancer, Computer aided detection, Gabor filter, Cell tracking
Referências
- Abbena E, 2006, MODERN DIFFERENTIAL
- Alshafeiy TI, 2018, RADIOLOGY, V288, P38, DOI 10.1148/radiol.2018171159
- Ayres FJ, 2007, J ELECTRON IMAGING, V16, DOI 10.1117/1.2728751
- Bahl M, 2017, AM J ROENTGENOL, V209, P1162, DOI 10.2214/AJR.17.17979
- Bahl M, 2015, AM J ROENTGENOL, V205, P1339, DOI 10.2214/AJR.15.14628
- Baker JA, 2011, ACAD RADIOL, V18, P1298, DOI 10.1016/j.acra.2011.06.011
- Benedikt RA, 2018, AM J ROENTGENOL, V210, P685, DOI 10.2214/AJR.17.18185
- Biselli E, 2017, SCI REP-UK, V7, DOI 10.1038/s41598-017-13070-3
- Casti P, 2016, BIOMED SIGNAL PROCES, V25, P165, DOI 10.1016/j.bspc.2015.11.010
- Casti P, 2013, COMPUT BIOL MED, V43, P1870, DOI 10.1016/j.compbiomed.2013.09.001
- Casti P, 2015, IEEE T MED IMAGING, V34, P662, DOI 10.1109/TMI.2014.2365436
- Chan H.-P., 2018, MED IMAGE ANAL INFOR, P241
- Chan HP, 2017, ACAD RADIOL, V24, P1372, DOI 10.1016/j.acra.2017.04.016
- Chen W, 2007, MAGN RESON MED, V58, P562, DOI 10.1002/mrm.21347
- D'Orsi CJ, 2013, ACR BI RADS ATLAS BR
- Dean JC, 2006, AM J ROENTGENOL, V187, P20, DOI 10.2214/AJR.05.0111
- Durand MA, 2015, RADIOLOGY, V274, P85, DOI 10.1148/radiol.14131319
- Elmore JG, 2003, JNCI-J NATL CANCER I, V95, P1384, DOI 10.1093/jnci/djg048
- Gaur S, 2013, AM J ROENTGENOL, V201, pW662, DOI 10.2214/AJR.12.10153
- Gilbert FJ, 2016, CLIN RADIOL, V71, P141, DOI 10.1016/j.crad.2015.11.008
- Glynn CG, 2011, RADIOLOGY, V260, P664, DOI 10.1148/radiol.11110159
- Hamidinekoo A, 2018, MED IMAGE ANAL, V47, P45, DOI 10.1016/j.media.2018.03.006
- Jaqaman K, 2008, NAT METHODS, V5, P695, DOI 10.1038/nmeth.1237
- Jasionowska M, 2010, ADV INTEL SOFT COMPU, V69, P73
- Kamra A, 2016, J DIGIT IMAGING, V29, P104, DOI 10.1007/s10278-015-9807-3
- Karellas A, 2008, MED PHYS, V35, P4878, DOI 10.1118/1.2986144
- Kim DH, 2017, PHYS MED BIOL, V62, P1009, DOI 10.1088/1361-6560/aa504e
- Kovalev VA, 1999, IEEE T IMAGE PROCESS, V8, P346, DOI 10.1109/83.748890
- Krizhevsky A., 2012, ADV NEURAL INFORM PR, V1, P1097, DOI 10.1145/3065386
- Liu XM, 2016, 2016 9TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2016), P422, DOI 10.1109/CISP-BMEI.2016.7852748
- Maidment ADA, 2003, SEMIN ROENTGENOL, V38, P216, DOI 10.1016/S0037-198X(03)00048-8
- Minavathi, 2011, INT J COMPUT SCI ENG, V3, P3534
- Morra L, 2015, RADIOLOGY, V277, P56, DOI 10.1148/radiol.2015141959
- Nemoto M, 2009, INT J COMPUT ASS RAD, V4, P27, DOI 10.1007/s11548-008-0267-9
- Ojala T, 2002, IEEE T PATTERN ANAL, V24, P971, DOI 10.1109/TPAMI.2002.1017623
- Oliveira H. C. R., 2017, P SPIE MED IM 2017 C
- Palma G, 2014, PATTERN RECOGN, V47, P2467, DOI 10.1016/j.patcog.2014.01.009
- Pan SJ, 2010, IEEE T KNOWL DATA EN, V22, P1345, DOI 10.1109/TKDE.2009.191
- Parlato S, 2017, SCI REP-UK, V7, DOI 10.1038/s41598-017-01013-x
- Rafferty EA, 2013, RADIOLOGY, V266, P104, DOI 10.1148/radiol.12120674
- Rangayyan RM, 2013, INT J COMPUT ASS RAD, V8, P527, DOI 10.1007/s11548-012-0793-3
- Rangayyan RM, 2010, J DIGIT IMAGING, V23, P611, DOI 10.1007/s10278-009-9257-x
- Rangayyan RM, 2010, J DIGIT IMAGING, V23, P547, DOI 10.1007/s10278-009-9238-0
- Ray KM, 2015, BREAST J, V21, P538, DOI 10.1111/tbj.12446
- Samala RK, 2016, MED PHYS, V43, P6654, DOI 10.1118/1.4967345
- Schindelin J, 2012, NAT METHODS, V9, P676, DOI [10.1038/NMETH.2019, 10.1038/nmeth.2019]
- Sechopoulos I, 2013, MED PHYS, V40, DOI 10.1118/1.4770279
- Suleiman WI, 2016, CLIN RADIOL, V71, pE35, DOI 10.1016/j.crad.2015.10.009
- Tinevez JY, 2017, METHODS, V115, P80, DOI 10.1016/j.ymeth.2016.09.016
- Vedantham S, 2015, RADIOLOGY, V277, P663, DOI 10.1148/radiol.2015141303
- Veronesi U, 2005, LANCET, V365, P1727, DOI 10.1016/S0140-6736(05)66546-4
- Yang SK, 2007, RADIOLOGY, V244, P104, DOI 10.1148/radiol.2441060756
- Yousefi M, 2018, COMPUT BIOL MED, V96, P283, DOI 10.1016/j.compbiomed.2018.04.004