Back to the list
Congress: ECR25
Poster Number: C-24405
Type: Poster: EPOS Radiologist (scientific)
Authorblock: M. Wodrich, F. Sahlin, J. Karlsson, I. Arvidsson, K. Lang; Lund/SE
Disclosures:
Marisa Wodrich: Nothing to disclose
Freja Sahlin: Nothing to disclose
Jennie Karlsson: Nothing to disclose
Ida Arvidsson: Nothing to disclose
Kristina Lang: Nothing to disclose
Keywords: Artificial Intelligence, Breast, Oncology, Ultrasound, Comparative studies, Computer Applications-Detection, diagnosis, Screening, Cancer
Purpose Breast cancer diagnosis using high-end ultrasound is costly in terms of time and machines, and requires highly trained breast radiologists. The use of point-of-care ultrasound (POCUS) combined with artificial intelligence (AI) could be a cost-effective solution for limited-resource settings. The following learning objectives have been identified:   To test for non-inferiority of POCUS compared to standard breast ultrasound (BUS)  To compare the performance of AI to expert radiologists in breast cancer detection on POCUS and standard breast ultrasound (BUS)  To develop a proof of concept...
Read more Methods and materials Background Breast cancer is the number one leading cause for cancer-related death in women worldwide, with morbidity and mortality rates varying largely between different countries. Late-stage diagnosis and limited access to diagnostics have been directly linked to low survival rates in low- and middle-income countries [1].  While mammography and BUS are the standard diagnostic tools for breast cancer detection in many high-income countries, POCUS could be a cost-effective alternative. POCUS is a simplified ultrasound approach which consists of a stand-alone portable ultrasound...
Read more Results Results for AUC, sensitivity and specificity, as well as corresponding 95% CIs can be seen in Table 1, and corresponding ROC plots for POCUS and BUS are shown in Figure 2 and 3.  Findings for POCUS vs. BUS  For radiologists reading POCUS/BUS, the sensitivity was 100.0%/100.0%, and the specificity was 76.7%/78.0% respectively. The AUC for POCUS/BUS was 98.5%/97.1%. No significant difference was found between the two imaging modalities.  AI performance on POCUS/BUS achieved a sensitivity of 90.9%/100.0% and specificity 88.1%/86.4%. The AI missed...
Read more Conclusion Radiologists' performance on POCUS and BUS was similar, with no significant difference.   AI performed slightly better on BUS than on POCUS, with higher specificity than average breast radiologists on both data sets.   AI outperformed the radiologists on BUS, with higher specificity for the same sensitivity.  On POCUS, radiologists performed better than AI, which missed one malignant case.   Our results serve as a proof of concept and indicate the potential of using AI to automatically analyze POCUS breast images in limited-resource settings. Further studies with...
Read more References [1] Sung, H., Ferlay, J., Siegel, R. L., Laversanne, M., Soerjomataram, I., Jemal, A., & Bray, F. (2021). Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA: a cancer journal for clinicians, 71(3), 209–249. https://doi.org/10.3322/caac.21660  [2] Lee, L., & DeCara, J. M. (2020). Point-of-care ultrasound. Current cardiology reports, 22, 1-10. [3] Dietrich, C. F., Goudie, A., Chiorean, L., Cui, X. W., Gilja, O. H., Dong, Y., ... & Blaivas, M. (2017). Point of...
Read more
GALLERY