Fully Integrated Decision-Support System for Detection and
Segmentation of Breast Lesions in Digital Mammogram

D 2022

Fully Integrated Decision-Support System for Detection and Segmentation of Breast Lesions in Digital Mammogram

HRUBÝ, Robert; Daniel KVAK; Anna CHROMCOVÁ a Marek BIROŠ

Základní údaje

Originální název

Fully Integrated Decision-Support System for Detection and Segmentation of Breast Lesions in Digital Mammogram

Název anglicky

Fully Integrated Decision-Support System for Detection and Segmentation of Breast Lesions in Digital Mammogram

Autoři

HRUBÝ, Robert; Daniel KVAK; Anna CHROMCOVÁ a Marek BIROŠ

Vydání

34. vyd. Praha, Medsoft 2022, od s. 28-32, 5 s. 2022

Nakladatel

Creative Connections, a.s.

Další údaje

Typ výsledku

Stať ve sborníku

Stát vydavatele

Česká republika

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Odkazy

URL

Označené pro přenos do RIV

ISSN

DOI

https://doi.org/10.35191/medsoft_2022_1_34_50_54

Klíčová slova anglicky

Breast Cancer, Breast Lesion Detection, Computer-Aided Detection, Deep Learning, Image Segmentation, Mammogram, Picture Archiving and Communicating System.

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 12. 12. 2023 11:00, Mgr. Daniel Kvak

Anotace

V originále

Breast cancer is one of the most prevalent forms of cancer affecting women. Detection of suspicious lesions on mammographic images is considered a challenging task due to the variability of lesion sizes and shapes, the problematic margins of the findings, and some extremely small lesions that are difficult to localize. With the increasing availability of digitized clinical archives and the development of complex deep learning (DL) methods, we are witnessing a trend towards the integration of robust computer-aided detection (CAD) systems to assist in the automatic segmentation of lesions on mammograms to aid in the diagnosis of breast cancer. This study presents deep learning–based automatic detection algorithm (DLAD), directly implemented in picture archiving and communication system (PACS) to aid in improving the radiologist's workflow. The proposed DLAD is evaluated on INbreast dataset with a sample size of n=138 (71 [51.45\%] BI-RADS 4/5/6 images, 67 [48.55\%] BI-RADS 1 images). Preliminary results show a sensitivity of 0.9296 [95\% CI 0.8701-0.9891], specificity of 0.7273 [0.6207-0.8339] and IoU of 0.5661, indicating a low false negative rate while maintaining a reasonable false positive rate.

Citovat

HRUBÝ, Robert; Daniel KVAK; Anna CHROMCOVÁ a Marek BIROŠ. Fully Integrated Decision-Support System for Detection and Segmentation of Breast Lesions in Digital Mammogram. In Jiří Kofránek a kol. Medsoft 2022. 34. vyd. Praha: Creative Connections, a.s., 2022, s. 28-32. ISSN 1803-8115. Dostupné z: https://doi.org/10.35191/medsoft_2022_1_34_50_54.

@inproceedings{2238163,
   author = {Hrubý, Robert and Kvak, Daniel and Chromcová, Anna and Biroš, Marek},
   address = {Praha},
   booktitle = {Medsoft 2022},
   doi = {https://doi.org/10.35191/medsoft_2022_1_34_50_54},
   edition = {34},
   editor = {Jiří Kofránek a kol.},
   keywords = {Breast Cancer, Breast Lesion Detection, Computer-Aided Detection, Deep Learning, Image Segmentation, Mammogram, Picture Archiving and Communicating System.},
   howpublished = {tištěná verze "print"},
   location = {Praha},
   pages = {28-32},
   publisher = {Creative Connections, a.s.},
   title = {Fully Integrated Decision-Support System for Detection and Segmentation of Breast Lesions in Digital Mammogram},
   url = {https://www.creativeconnections.cz/medsoft/2022/Medsoft_Sbornik_2022_Kvak.pdf},
   year = {2022}
}

TY  - CONF
ID  - 2238163
AU  - Hrubý, Robert - Kvak, Daniel - Chromcová, Anna - Biroš, Marek
PY  - 2022
TI  - Fully Integrated Decision-Support System for Detection and Segmentation of Breast Lesions in Digital Mammogram
PB  - Creative Connections, a.s.
CY  - Praha
KW  - Breast Cancer, Breast Lesion Detection, Computer-Aided Detection, Deep Learning, Image Segmentation, Mammogram, Picture Archiving and Communicating System.
UR  - https://www.creativeconnections.cz/medsoft/2022/Medsoft_Sbornik_2022_Kvak.pdf
N2  - Breast cancer is one of the most prevalent forms of cancer affecting women. Detection of suspicious lesions on mammographic images is considered a challenging task due to the variability of lesion sizes and shapes, the problematic margins of the findings, and some extremely small lesions that are difficult to localize. With the increasing availability of digitized clinical archives and the development of complex deep learning (DL) methods, we are witnessing a trend towards the integration of robust computer-aided detection (CAD) systems to assist in the automatic segmentation of lesions on mammograms to aid in the diagnosis of breast cancer. This study presents deep learning–based automatic detection algorithm (DLAD), directly implemented in picture archiving and communication system (PACS) to aid in improving the radiologist's workflow. The proposed DLAD is evaluated on INbreast dataset with a sample size of n=138 (71 [51.45\%] BI-RADS 4/5/6 images, 67 [48.55\%] BI-RADS 1 images). Preliminary results show a sensitivity of 0.9296 [95\% CI 0.8701-0.9891], specificity of 0.7273 [0.6207-0.8339] and IoU of 0.5661, indicating a low false negative rate while maintaining a reasonable false positive rate.
ER  -

HRUBÝ, Robert; Daniel KVAK; Anna CHROMCOVÁ a Marek BIROŠ. Fully Integrated Decision-Support System for Detection and Segmentation of Breast Lesions in Digital Mammogram. In Jiří Kofránek a kol. \textit{Medsoft 2022}. 34. vyd. Praha: Creative Connections, a.s., 2022, s.~28-32. ISSN~1803-8115. Dostupné z: https://doi.org/10.35191/medsoft\_{}2022\_{}1\_{}34\_{}50\_{}54.

Přehled o publikaci