Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Sep:101:77-85.
doi: 10.1016/j.clinimag.2023.05.005. Epub 2023 May 18.

A role for breast ultrasound Artificial Intelligence decision support in the evaluation of small invasive lobular carcinomas

Tali Amir  1 , Kristen Coffey  2 , Varadan Sevilimedu  3 , Reza Fardanesh  4 , Victoria L Mango  5
Affiliations

A role for breast ultrasound Artificial Intelligence decision support in the evaluation of small invasive lobular carcinomas

Tali Amir et al. Clin Imaging. 2023 Sep.

Abstract

Objective: To evaluate the diagnostic performance of an Artificial Intelligence (AI) decision support (DS) system in the ultrasound (US) assessment of invasive lobular carcinoma (ILC) of the breast, a cancer that can demonstrate variable appearance and present insidiously.

Methods: Retrospective review was performed of 75 patients with 83 ILC diagnosed by core biopsy or surgery between November 2017 and November 2019. ILC characteristics (size, shape, echogenicity) were recorded. AI DS output (lesion characteristics, likelihood of malignancy) was compared to radiologist assessment.

Results: The AI DS system interpreted 100% of ILCs as suspicious or probably malignant (100% sensitivity, and 0% false negative rate). 99% (82/83) of detected ILCs were initially recommended for biopsy by the interpreting breast radiologist, and 100% (83/83) were recommended for biopsy after one additional ILC was identified on same-day repeat diagnostic ultrasound. For lesions in which the AI DS output was probably malignant, but assigned a BI-RADS 4 assessment by the radiologist, the median lesion size was 1 cm, compared with a median lesion size of 1.4 cm for those given a BI-RADS 5 assessment (p = 0.006). These results suggest that AI may offer more useful DS in smaller sub-centimeter lesions in which shape, margin status, or vascularity is more difficult to discern. Only 20% of patients with ILC were assigned a BI-RADS 5 assessment by the radiologist.

Conclusion: The AI DS accurately characterized 100% of detected ILC lesions as suspicious or probably malignant. AI DS may be helpful in increasing radiologist confidence when assessing ILC on ultrasound.

Keywords: Artificial Intelligence; Breast cancer; Breast ultrasound; Decision support; Invasive lobular carcinoma.

PubMed Disclaimer

Conflict of interest statement

Declaration of competing interest The authors declare no conflict of interest.

Figures

Figure 1:
Figure 1:
59-year-old female with a negative screening mammogram. Screening ultrasound detected a 0.8 cm irregular, taller-than-wide hypoechoic mass. The radiologist gave a BI-RADS 4 assessment. AI DS output assigned a probably malignant assessment.
Figure 2:
Figure 2:
Patients included and excluded from analysis.
Figure 3:
Figure 3:
66-year-old female presented with a palpable lump. Ultrasound demonstrated a 1.5 cm irregular, hypoechoic mass. The finding was given a BI-RADS 4 assessment. AI DS output assigned a suspicious assessment.
Figure 4
Figure 4
a–c: 67-year-old female with history of breast cancer presented for her annual mammogram. The radiologist noted an asymmetry on mammogram, which was felt to efface on spot compression imaging. Diagnostic ultrasound of the left breast showed no suspicious findings. The patient was given a BI-RADS 2 assessment. The patient had a same-day appointment in breast clinic, in which the physician palpated a lump in the lower outer left breast. Subsequent ultrasound to the marked lump revealed a 1.8 cm heterogenous, ill-defined area (Figure 4a), corresponding to the original mammographic finding (Figure 4b), confirmed on post-procedure imaging (Figure 4c).
Figure 5:
Figure 5:
75-year-old female with history of breast cancer presenting with a palpable lump. Ultrasound demonstrated a 1.2 cm oval, circumscribed mass. The radiologist interpreted the finding as probably clustered microcysts but assigned a BI-RADS 4 assessment given palpable nature. AI DS output assigned a suspicious assessment.
Figure 6:
Figure 6:
95-year-old female with history of breast cancer. Ultrasound demonstrated a 1.5cm irregular, heterogeneous mass with internal vascularity. The radiologist assigned a BI-RADS 4 assessment and AI DS output assigned a suspicious assessment.
Figure 7:
Figure 7:
68-year-old female with 0.6 cm irregular, hypoechoic mass detected on diagnostic ultrasound. The radiologist assigned a BI-RADS 4 assessment and AI DS output assigned a probably malignant assessment.
Figure 8:
Figure 8:
76-year-old female with history of breast cancer. Screening ultrasound detected a 1.6 cm irregular hypoechoic. The radiologist assigned a BI-RADS 4 assessment and AI DS output assigned a probably malignant assessment.
Figure 9:
Figure 9:
72-year-old female with history of breast cancer. Diagnostic ultrasound detected a 0.5 cm irregular hypoechoic mass. The radiologist assigned a BI-RADS 4 assessment and AI DS output assigned a probably malignant assessment.
See this image and copyright information in PMC

References

    1. Ries L, et al., SEER cancer statistics review, 1975–2005. Bethesda, MD: National Cancer Institute, 2008. 2999.
    1. Oliveira TM, et al., Evolving concepts in breast lobular neoplasia and invasive lobular carcinoma, and their impact on imaging methods. Insights Imaging, 2014. 5(2): p. 183–94. - PMC - PubMed
    1. Yeatman TJ, et al., Tumor biology of infiltrating lobular carcinoma. Implications for management. Ann Surg, 1995. 222(4): p. 549–59; discussion 559–61. - PMC - PubMed
    1. Arpino G, et al., Infiltrating lobular carcinoma of the breast: tumor characteristics and clinical outcome. Breast Cancer Res, 2004. 6(3): p. R149–56. - PMC - PubMed
    1. Brouckaert O, et al., Prognostic implications of lobular breast cancer histology: new insights from a single hospital cross-sectional study and SEER data. Breast, 2014. 23(4): p. 371–7. - PubMed