Effect of Benign Biopsy Findings on an Artificial Intelligence-Based Cancer Detector in Screening Mammography: Retrospective Case-Control Study.

BACKGROUND: Artificial intelligence (AI)-based cancer detectors (CAD) for mammography are starting to be used for breast cancer screening in radiology departments. It is important to understand how AI CAD systems react to benign lesions, especially those that have been subjected to biopsy. OBJECTIVE: Our goal was to corroborate the hypothesis that women with previous benign biopsy and cytology assessments would subsequently present increased AI CAD abnormality scores even though they remained healthy. METHODS: This is a retrospective study applying a commercial AI CAD system (Insight MMG, version 1.1.4.3; Lunit Inc) to a cancer-enriched mammography screening data set of 10,889 women (median age 56, range 40-74 years). The AI CAD generated a continuous prediction score for tumor suspicion between 0.00 and 1.00, where 1.00 represented the highest level of suspicion. A binary read (flagged or not flagged) was defined on the basis of a predetermined cutoff threshold (0.40). The flagged median and proportion of AI scores were calculated for women who were healthy, those who had a benign biopsy finding, and those who were diagnosed with breast cancer. For women with a benign biopsy finding, the interval between mammography and the biopsy was used for stratification of AI scores. The effect of increasing age was examined using subgroup analysis and regression modeling. RESULTS: Of a total of 10,889 women, 234 had a benign biopsy finding before or after screening. The proportions of flagged healthy women were 3.5%, 11%, and 84% for healthy women without a benign biopsy finding, those with a benign biopsy finding, and women with breast cancer, respectively (P<.001). For the 8307 women with complete information, radiologist 1, radiologist 2, and the AI CAD system flagged 8.5%, 6.8%, and 8.5% of examinations of women who had a prior benign biopsy finding. The AI score correlated only with increasing age of the women in the cancer group (P=.01). CONCLUSIONS: Compared to healthy women without a biopsy, the examined AI CAD system flagged a much larger proportion of women who had or would have a benign biopsy finding based on a radiologist's decision. However, the flagging rate was not higher than that for radiologists. Further research should be focused on training the AI CAD system taking prior biopsy information into account.

False-negative rate in the extended prospective TATTOO trial evaluating targeted axillary dissection by carbon tattooing in clinically node-positive breast cancer patients receiving neoadjuvant systemic therapy.

PURPOSE: In clinically node-positive breast cancer patients receiving neoadjuvant systemic therapy (NST), nodal metastases can be initially marked and then removed during surgical axillary staging. Marking methods vary significantly in terms of feasibility and cost. The purpose of the extended TATTOO trial was to report on the false-negative rate (FNR) of the low-cost method carbon tattooing. METHODS: The international prospective single-arm TATTOO trial included clinically node-positive breast cancer patients planned for NST from November 2017 to January 2021. For the present analysis, patients who received both the targeted procedure with or without an additional sentinel lymph node (SLN) biopsy and a completion axillary lymph node dissection (ALND) were selected. Primary endpoint was the FNR. RESULTS: Out of 172 included patients, 149 had undergone a completion ALND. The detection rate for the tattooed node was 94.6% (141 out of 149). SLN biopsy was attempted in 132 out of 149 patients with a detection rate of 91.7% (121 out of 132). SLN and tattooed node were identical in 58 out of 121 individuals (47.9%). The combined procedure, i.e. targeted axillary dissection (TAD) was successful in 147 of 149 cases (98.7%). Four out of 65 patients with a clinically node-negative status after NST had a negative TAD but metastases on ALND, corresponding to a FNR of 6.2%. All false-negative TAD procedures were performed in the first 2 years of the trial (2018-2019, p = 0.022). CONCLUSION: Carbon tattooing is a feasible marking method for TAD with a high detection rate and an acceptably low FNR. The TATTOO trial was preregistered as prospective trial before initiation at the University of Rostock, Germany (DRKS00013169).

Swedish prospective multicenter trial evaluating sentinel lymph node biopsy after neoadjuvant systemic therapy in clinically node-positive breast cancer.

PURPOSE: Patients with clinically node-positive breast cancer planned for neoadjuvant systemic therapy (NAST) may draw advantages from the nodal downstaging effect and reduce the extent of axillary surgery with sentinel lymph node biopsy (SLNB) performed after NAST. Since there are concerns about lower sentinel lymph node (SLN) detection and higher false-negative rates (FNR) in this setting, our aim was to define the accuracy of SLNB after NAST. METHODS: This Swedish national multicenter trial prospectively recruited 195 breast cancer patients from ten hospitals with T1-T4d biopsy-proven node-positive disease planned for NAST between October 1, 2010 and December 31, 2015. Clinically node-negative axillary status after NAST was not mandatory. SLNB was always attempted and followed by a completion axillary lymph node dissection (ALND). RESULTS: The SLN identification rate was 77.9% (152/195) but improved to 80.7% (138/171) with dual mapping. The median number of SLNs was two (range 1-5). A positive SLNB was found in 52% (79/152), almost 66% (52/79) of whom had additional positive non-sentinel lymph nodes. The overall pathologic nodal response rate was 33.3% (66/195). The overall FNR was 14.1% (13/92) but decreased to 4% (2/50) when only patients with two or more sentinel nodes were analyzed. CONCLUSIONS: In biopsy-proven node-positive breast cancer, SLNB after NAST is feasible even though the identification rate is lower than in clinically node-negative patients. Since the overall FNR is unacceptably high, the omission of ALND should only be considered if two or more SLNs are identified.