Utilization of artificial intelligence to triage patients with delayed follow-up of probably benign breast ultrasound findings

Abstract

Purpose: This study aimed to evaluate our institution's experience in using artificial intelligence (AI) decision support (DS) as part of the clinical workflow to triage patients with Breast Imaging Reporting and Data System (BI-RADS) 3 sonographic lesions whose follow-up was delayed during the coronavirus disease 2019 (COVID-19) pandemic, against subsequent imaging and/or pathologic follow-up results.

Methods: This retrospective study included patients with a BI-RADS category 3 (i.e., probably benign) breast ultrasound assessment from August 2019-December 2019 whose follow-up was delayed during the COVID-19 pandemic and whose breast ultrasounds were re-reviewed using Koios DS Breast AI as part of the clinical workflow for triaging these patients. The output of Koios DS was compared with the true outcome of a presence or absence of breast cancer defined by resolution/stability on imaging follow-up for at least 2 years or pathology results.

Results: The study included 161 women (mean age, 52 years) with 221 BI-RADS category 3 sonographic lesions. Of the 221 lesions, there were two confirmed cancers (0.9% malignancy rate). Koios DS assessed 112/221 lesions (50.7%) as benign, 42/221 lesions (19.0%) as probably benign, 64/221 lesions (29.0%) as suspicious, and 3/221 lesions (1.4%) as probably malignant. Koios DS had a sensitivity of 100% (2/2; 95% confidence interval [CI], 16% to 100%), specificity of 70% (154/219; 95% CI, 64% to 76%), negative predictive value of 100% (154/154; 95% CI, 98% to 100%), and false-positive rate of 30% (65/219; 95% CI, 24% to 36%).

Conclusion: When many follow-up appointments are delayed, e.g., natural disaster, or scenarios where resources are limited, breast ultrasound AI DS can help triage patients with probably benign breast ultrasounds.

Keywords: Artificial intelligence; Breast ultrasonography; COVID-19; Decision support systems, clinical; Triage.

Fig. 1.. Patients included and excluded from analysis.

BI-RADS, Breast Imaging Reporting and Data System.

Fig. 2.. Artificial intelligence decision support (AI DS) output and ground truth for 221 Breast Imaging Reporting and Data System category 3 ultrasound lesions with delayed follow-up.

The center circle shows the different output categories of the AI DS system. The outer boxes show the ground truth for each of the AI DS system’s output categories based on 2-year imaging follow-up results or pathology results.

Fig. 3.. A 76-year-old female patient who presented with a palpable left breast lump.

Ultrasonorgaphy demonstrated a 1.2-cm isoechoic mass assessed as probably benign fat necrosis secondary to post-surgical reduction changes. Surgical biopsy yielded adenoid cystic carcinoma. The artificial intelligence decision support system assessed the finding as suspicious.

Fig. 4.. An 82-year-old female patient with a 0.8-cm left axillary tail mass initially assessed as a probably benign lymph node.

Ultrasound-guided core biopsy was recommended at 6-month follow-up due to an increase in size. Pathology revealed invasive ductal carcinoma. The artificial intelligence decision support system assessed the finding as suspicious on the initial ultrasound.

Fig. 5.. A 40-year-old female patient with prior mastectomy for breast cancer and flap reconstruction presented with a palpable lump.

Ultrasonography shows a 0.8-cm mass, which the interpreting radiologist assessed as probably benign, likely fat necrosis. Ultrasound followup showed a decrease in the size of the mass, consistent with benign etiology. The artificial intelligence decision support system accurately assessed the finding as benign based on the initial ultrasound.