AI Applications to Breast MRI: Today and Tomorrow.

In breast imaging, there is an unrelenting increase in the demand for breast imaging services, partly explained by continuous expanding imaging indications in breast diagnosis and treatment. As the human workforce providing these services is not growing at the same rate, the implementation of artificial intelligence (AI) in breast imaging has gained significant momentum to maximize workflow efficiency and increase productivity while concurrently improving diagnostic accuracy and patient outcomes. Thus far, the implementation of AI in breast imaging is at the most advanced stage with mammography and digital breast tomosynthesis techniques, followed by ultrasound, whereas the implementation of AI in breast magnetic resonance imaging (MRI) is not moving along as rapidly due to the complexity of MRI examinations and fewer available dataset. Nevertheless, there is persisting interest in AI-enhanced breast MRI applications, even as the use of and indications of breast MRI continue to expand. This review presents an overview of the basic concepts of AI imaging analysis and subsequently reviews the use cases for AI-enhanced MRI interpretation, that is, breast MRI triaging and lesion detection, lesion classification, prediction of treatment response, risk assessment, and image quality. Finally, it provides an outlook on the barriers and facilitators for the adoption of AI in breast MRI. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 6.

Outcomes of atypical lobular hyperplasia managed by active surveillance or immediate surgery.

BACKGROUND: Atypical lobular hyperplasia (ALH) is typically diagnosed via needle core biopsy (NCB) and is commonly removed surgically in light of upgrade to malignancy rates of 1%-5%. As studies on radiographic outcomes of ALH managed by active surveillance (AS) are limited, we investigated the upgrade rates of surgically excised ALH as well as radiographic progression during AS. METHODS: In this retrospective study, 125 patients with 127 ALH lesions diagnosed via NCB at Weill Cornell Medicine from 2015 to 2021 were included. The upgrade rate to cancer was determined for patients who had surgical management ≤6 months after biopsy. Among patients with ALH managed by AS, we investigated radiographic progression on 6-month interval imaging. RESULTS: Of 127 ALH lesions, 75% (n = 95) were immediately excised and 25% (n = 32) were observed under AS. The upgrade rate of immediately excised ALH was 2.1% (n = 2; invasive ductal carcinoma [IDC], T1N0 and IDC, and T1Nx). In the AS cohort, no ALH lesions progressed radiographically during the follow-up period of 22.5 months (median), with all remaining stable (50%, n = 16), resolving (47%, n = 15), or decreasing in size (3%, n = 1). CONCLUSIONS: In this study, NCB-diagnosed ALH had a low upgrade to malignancy rate (2.1%), and no ALH lesions managed by AS progressed radiographically during the follow-up period of 22.5 months. These results support AS as the favorable option for patients with pure ALH on biopsy, with surgical excision for lesions that progress on surveillance.

Active Surveillance of Atypical Ductal Hyperplasia of the Breast.

BACKGROUND: When needle core biopsy (NCB) of the breast yields atypical ductal hyperplasia (ADH), excision is typically recommended. The natural history of ADH undergoing active surveillance (AS) is not well described. We investigate the rates of upgrade to malignancy of excised ADH and the rates of radiographic progression under AS. MATERIALS AND METHODS: We retrospectively reviewed records of 220 cases of ADH on NCB. Of patients who had surgery within 6 months of NCB, we examined the malignancy upgrade rate. In the AS cohort, we examined rates of radiographic progression on interval imaging. RESULTS: The malignancy upgrade rate among patients who underwent immediate excision (n = 185) was 15.7%: 14.1% (n = 26) ductal carcinoma in situ (DCIS) and 1.6% (n = 3) invasive ductal carcinoma (IDC). Upgrade to malignancy was less common in lesions <4 mm in size (0%) or with focal ADH (5%), and more common among lesions presenting with a radiographic mass (26%). Among the 35 patients who underwent AS, median follow-up was 20 months. Two lesions progressed on imaging (incidence 3.8% at 2 years). One patient without radiographic progression was found to have IDC at delayed surgery. The remaining lesions remained stable (46%), decreased in size (11%), or resolved (37%). CONCLUSIONS: Our findings suggest that AS is a safe approach to managing ADH on NCB for most patients. This could spare many patients with ADH from unnecessary surgery. Given that AS is being investigated for low-risk DCIS in multiple international prospective trials, these results suggest that AS should also be investigated for ADH.