TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Micro-parenchymal patterns for breast cancer risk assessment

Tutkimustuotosvertaisarvioitu

Standard

Micro-parenchymal patterns for breast cancer risk assessment. / Pertuz, Said; Sassi, Antti; Karivaara-Makela, Mirva; Holli-Helenius, Kirsi; Laaperi, Anna-Leena; Rinta-Kiikka, Irina; Arponen, Otso; Kämäräinen, Joni-Kristian.

julkaisussa: Biomedical Physics & Engineering Express, Vuosikerta 5, Nro 6, 065008, 10.2019.

Tutkimustuotosvertaisarvioitu

Harvard

Pertuz, S, Sassi, A, Karivaara-Makela, M, Holli-Helenius, K, Laaperi, A-L, Rinta-Kiikka, I, Arponen, O & Kämäräinen, J-K 2019, 'Micro-parenchymal patterns for breast cancer risk assessment', Biomedical Physics & Engineering Express, Vuosikerta. 5, Nro 6, 065008. https://doi.org/10.1088/2057-1976/ab42f4

APA

Pertuz, S., Sassi, A., Karivaara-Makela, M., Holli-Helenius, K., Laaperi, A-L., Rinta-Kiikka, I., ... Kämäräinen, J-K. (2019). Micro-parenchymal patterns for breast cancer risk assessment. Biomedical Physics & Engineering Express, 5(6), [065008]. https://doi.org/10.1088/2057-1976/ab42f4

Vancouver

Pertuz S, Sassi A, Karivaara-Makela M, Holli-Helenius K, Laaperi A-L, Rinta-Kiikka I et al. Micro-parenchymal patterns for breast cancer risk assessment. Biomedical Physics & Engineering Express. 2019 loka;5(6). 065008. https://doi.org/10.1088/2057-1976/ab42f4

Author

Pertuz, Said ; Sassi, Antti ; Karivaara-Makela, Mirva ; Holli-Helenius, Kirsi ; Laaperi, Anna-Leena ; Rinta-Kiikka, Irina ; Arponen, Otso ; Kämäräinen, Joni-Kristian. / Micro-parenchymal patterns for breast cancer risk assessment. Julkaisussa: Biomedical Physics & Engineering Express. 2019 ; Vuosikerta 5, Nro 6.

Bibtex - Lataa

@article{8e7dcab0ecdf4288bd579f65b4cfd46e,
title = "Micro-parenchymal patterns for breast cancer risk assessment",
abstract = "We evaluated small radiological regions of the parenchymal tissue in mammograms-micro-parenchymal (MP) patterns-for breast cancer risk assessment. We adapted path based analysis, a computer vision technique, in order to build a model of the distribution of MP patterns in mammograms from a training population sample. Subsequently, the model was utilized to infer the level of risk of individual women based on the distribution of MP patterns in test mammograms. We validated our method using a pilot case/control study with 114 women diagnosed with cancer and 114 healthy controls matched by age, screening year and mammographic system. Experiments with 5-fold cross validation showed a statistically significant positive association between the MP-based risk scores and breast cancer risk with an OPERA (odds per standard deviation of the risk score) value of 1.66 (p-value <0.001) and an area under the receiver operating characteristic curve (AUC) of 0.653. Results retain their statistical significance after adjusting for visual and quantitative breast densities, widely known imaging biomarkers for breast cancer risk. This work provides experimental evidence that there are specific MP patterns identifiable as cues of breast cancer and prompt the validation of these results in larger datasets.",
keywords = "breast cancer, mammography, risk assessment, texture analysis, parenchymal patterns, MAMMOGRAPHIC DENSITY, TEXTURE ANALYSIS, CLASSIFICATION",
author = "Said Pertuz and Antti Sassi and Mirva Karivaara-Makela and Kirsi Holli-Helenius and Anna-Leena Laaperi and Irina Rinta-Kiikka and Otso Arponen and Joni-Kristian K{\"a}m{\"a}r{\"a}inen",
note = "EXT={"}Pertuz, Said{"}",
year = "2019",
month = "10",
doi = "10.1088/2057-1976/ab42f4",
language = "English",
volume = "5",
journal = "Biomedical Physics & Engineering Express",
issn = "2057-1976",
publisher = "IOP Publishing",
number = "6",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Micro-parenchymal patterns for breast cancer risk assessment

AU - Pertuz, Said

AU - Sassi, Antti

AU - Karivaara-Makela, Mirva

AU - Holli-Helenius, Kirsi

AU - Laaperi, Anna-Leena

AU - Rinta-Kiikka, Irina

AU - Arponen, Otso

AU - Kämäräinen, Joni-Kristian

N1 - EXT="Pertuz, Said"

PY - 2019/10

Y1 - 2019/10

N2 - We evaluated small radiological regions of the parenchymal tissue in mammograms-micro-parenchymal (MP) patterns-for breast cancer risk assessment. We adapted path based analysis, a computer vision technique, in order to build a model of the distribution of MP patterns in mammograms from a training population sample. Subsequently, the model was utilized to infer the level of risk of individual women based on the distribution of MP patterns in test mammograms. We validated our method using a pilot case/control study with 114 women diagnosed with cancer and 114 healthy controls matched by age, screening year and mammographic system. Experiments with 5-fold cross validation showed a statistically significant positive association between the MP-based risk scores and breast cancer risk with an OPERA (odds per standard deviation of the risk score) value of 1.66 (p-value <0.001) and an area under the receiver operating characteristic curve (AUC) of 0.653. Results retain their statistical significance after adjusting for visual and quantitative breast densities, widely known imaging biomarkers for breast cancer risk. This work provides experimental evidence that there are specific MP patterns identifiable as cues of breast cancer and prompt the validation of these results in larger datasets.

AB - We evaluated small radiological regions of the parenchymal tissue in mammograms-micro-parenchymal (MP) patterns-for breast cancer risk assessment. We adapted path based analysis, a computer vision technique, in order to build a model of the distribution of MP patterns in mammograms from a training population sample. Subsequently, the model was utilized to infer the level of risk of individual women based on the distribution of MP patterns in test mammograms. We validated our method using a pilot case/control study with 114 women diagnosed with cancer and 114 healthy controls matched by age, screening year and mammographic system. Experiments with 5-fold cross validation showed a statistically significant positive association between the MP-based risk scores and breast cancer risk with an OPERA (odds per standard deviation of the risk score) value of 1.66 (p-value <0.001) and an area under the receiver operating characteristic curve (AUC) of 0.653. Results retain their statistical significance after adjusting for visual and quantitative breast densities, widely known imaging biomarkers for breast cancer risk. This work provides experimental evidence that there are specific MP patterns identifiable as cues of breast cancer and prompt the validation of these results in larger datasets.

KW - breast cancer

KW - mammography

KW - risk assessment

KW - texture analysis

KW - parenchymal patterns

KW - MAMMOGRAPHIC DENSITY

KW - TEXTURE ANALYSIS

KW - CLASSIFICATION

U2 - 10.1088/2057-1976/ab42f4

DO - 10.1088/2057-1976/ab42f4

M3 - Article

VL - 5

JO - Biomedical Physics & Engineering Express

JF - Biomedical Physics & Engineering Express

SN - 2057-1976

IS - 6

M1 - 065008

ER -