No abstract

Background: The phase Ib KEYNOTE-173 study was conducted to assess the safety and preliminary antitumor activity of neoadjuvant chemotherapy plus pembrolizumab in high-risk, early-stage, non-metastatic triple-negative breast cancer (TNBC). Patients and methods: Six pembrolizumab plus chemotherapy regimens were evaluated (cohorts AeF). All cohorts received a pembrolizumab 200-mg run-in dose (cycle 1), then eight cycles of pembrolizumab in combination with a taxane with or without carboplatin for 12 weeks, and then doxorubicin and cyclophosphamide for an additional 12 weeks before surgery. Primary end points were safety and recommended phase II dose (RP2D); secondary end points were pathological complete response (pCR) rate, objective response rate, and event-free and overall survival. Exploratory end points were the relationship between outcome and potential biomarkers, such as tumor programmed death ligand 1 (PD-L1) expression (combined positive score) and stromal tumor-infiltrating lymphocyte levels (sTILs). Results: Sixty patients were enrolled between 18 February 2016, and 28 February 2017. Dose-limiting toxicities occurred in 22 patients, most commonly febrile neutropenia (n ¼ 10 across cohorts). Four cohorts (B, C, D, F) did not meet the RP2D threshold; two cohorts did (A, E). The most common grade !3 treatment-related adverse event was neutropenia (73%). Immune-mediated adverse events and infusion reactions occurred in 18 patients (30%) and were grade !3 in six patients (10%). The pCR rate (ypT0/Tis ypN0) across all cohorts was 60% (range 49%e71%). Twelve-month event-free and overall survival rates ranged from 80% to 100% across cohorts (100% for four cohorts). Higher pre-treatment PD-L1 combined positive score, and pre-and on-treatment sTILs were significantly associated with higher pCR rates (P ¼ 0.0127, 0.0059, and 0.0085, respectively). Conclusion: Combination neoadjuvant chemotherapy and pembrolizumab for high-risk, early-stage TNBC showed manageable toxicity and promising antitumor activity. In an exploratory analysis, the pCR rate showed a positive correlation with tumor PD-L1 expression and sTIL levels. Trial registration: ClinicalTrials.gov identifier: NCT02622074.

IMPORTANCE A computer algorithm that performs at or above the level of radiologists in mammography screening assessment could improve the effectiveness of breast cancer screening.OBJECTIVE To perform an external evaluation of 3 commercially available artificial intelligence (AI) computer-aided detection algorithms as independent mammography readers and to assess the screening performance when combined with radiologists. DESIGN, SETTING, AND PARTICIPANTSThis retrospective case-control study was based on a double-reader population-based mammography screening cohort of women screened at an academic hospital in Stockholm, Sweden, from 2008 to 2015. The study included 8805 women aged 40 to 74 years who underwent mammography screening and who did not have implants or prior breast cancer. The study sample included 739 women who were diagnosed as having breast cancer (positive) and a random sample of 8066 healthy controls (negative for breast cancer). MAIN OUTCOMES AND MEASURESPositive follow-up findings were determined by pathology-verified diagnosis at screening or within 12 months thereafter. Negative follow-up findings were determined by a 2-year cancer-free follow-up. Three AI computer-aided detection algorithms (AI-1, AI-2, and AI-3), sourced from different vendors, yielded a continuous score for the suspicion of cancer in each mammography examination. For a decision of normal or abnormal, the cut point was defined by the mean specificity of the first-reader radiologists (96.6%). RESULTSThe median age of study participants was 60 years (interquartile range, 50-66 years) for 739 women who received a diagnosis of breast cancer and 54 years (interquartile range, 47-63 years) for 8066 healthy controls. The cases positive for cancer comprised 618 (84%) screen detected and 121 (16%) clinically detected within 12 months of the screening examination. The area under the receiver operating curve for cancer detection was 0.956 (95% CI, 0.948-0.965) for AI-1, 0.922 (95% CI, 0.910-0.934) for AI-2, and 0.920 (95% CI, 0.909-0.931) for AI-3. At the specificity of the radiologists, the sensitivities were 81.9% for AI-1, 67.0% for AI-2, 67.4% for AI-3, 77.4% for first-reader radiologist, and 80.1% for second-reader radiologist. Combining AI-1 with first-reader radiologists achieved 88.6% sensitivity at 93.0% specificity (abnormal defined by either of the 2 making an abnormal assessment). No other examined combination of AI algorithms and radiologists surpassed this sensitivity level. CONCLUSIONS AND RELEVANCETo our knowledge, this study is the first independent evaluation of several AI computer-aided detection algorithms for screening mammography. The results of this study indicated that a commercially available AI computer-aided detection algorithm can assess screening mammograms with a sufficient diagnostic performance to be further evaluated as an independent reader in prospective clinical trials. Combining the first readers with the best algorithm identified more cases positive for cancer than combining the first readers with se...