Back to the list
Congress: ECR24
Poster Number: C-23452
Type: EPOS Radiographer (scientific)
Authorblock: M. Koshizuka1, H. Watanabe1, Y. Takeda1, Y. Ezawa1, K. Saito2, N. Hayashi1, M. Sato1, T. Ogura1, M. Shimosegawa1; 1Maebashi/JP, 2Saitama/JP
Disclosures:
Momoko Koshizuka: Nothing to disclose
Haruyuki Watanabe: Nothing to disclose
Yuto Takeda: Nothing to disclose
Yuina Ezawa: Nothing to disclose
Kazuho Saito: Nothing to disclose
Norio Hayashi: Nothing to disclose
Mitsuru Sato: Nothing to disclose
Toshihiro Ogura: Nothing to disclose
Masayuki Shimosegawa: Nothing to disclose
Keywords: Breast, Mammography, Technology assessment, Image verification
Purpose Breast cancer is the most common cancer worldwide. Early detection is crucial for reducing its mortality rate. Mammography is beneficial for early breast cancer diagnosis and reduces cancer mortality. Mammography is a useful tool for detecting breast cancer at an early stage, which can help reduce cancer-related deaths [1, 2]. Mammography guidelines define the necessary equipment, quality control, and techniques for proper imaging [3, 4]. Mammographic positioning is an essential factor that influences the extraction of lesions in imaging techniques,...
Read more Methods and materials A 1631 mediolateral oblique (MLO) mammogram dataset was obtained from an open database [6]. Mammography positioning is evaluated using guideline criteria in the pectoral major muscle, retromammary space, bilateral breast symmetry, IMF, and nipple area. The retromammary space was targeted in our study.The labeled mammograph's region of interest (ROI) was automatically extracted from the retromammary space. After the grayscale mammogram images were converted to binary images, morphological filters were applied to the images to eliminate radiopaque artifacts and labels. To...
Read more Results The VGG16 model achieved the highest accuracy in the retromammary space for both ROI sizes. There was not much difference when comparing ROI size. The probability from softmax was confirmed as a value corresponding to the mammographic positioning accuracy. [fig 6] [fig 7] [fig 1]
Read more Conclusion In this study, we proposed that retromammary space of a mammogram can be automatically detected, and breast positioning was classified based on quality control and validation using DCNNs. For the automatic classification, the accuracy was approx. 58%, the highest value obtained using VGG16. Although the initial results were low, the study demonstrated that evaluating positioning techniques in mammography using automation is feasible. Improving accuracy requires adjusting the learning image localization. Further improvement in accuracy is expected by performing other various...
Read more References [1] Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2021. CA Cancer J. Clin. 2021;71:7–33.[2] Independent UK Panel on Breast Cancer Screening The benefits and harms of breast cancer screening: An independent review. Lancet. 2012;380:1778–1786.[3] Programme, NBS Guidance for Breast Screening Mammographers 3rd ed. Public Health England, UK, 2017.[4] EUREF. European Guidelines for Quality Assurance in Breast Cancer Screening and Diagnosis 4th ed. European Reference Organisation for Quality Assured Breast Screening and Diagnostic Services, 2006.[5] Watanabe, H., Hayashi, S., Kondo, Y. et...
Read more
GALLERY