Improving Ki67 assessment concordance by the use of an artificial intelligence-empowered microscope: a multi-institutional ring study Aims: The nuclear proliferation biomarker Ki67 plays potential prognostic and predictive roles in breast cancer treatment. However, the lack of interpathologist consistency in Ki67 assessment limits the clinical use of Ki67. The aim of this article was to report a solution utilising an artificial intelligence (AI)-empowered microscope to improve Ki67 scoring concordance. Methods and results: We developed an AI-empowered microscope in which the conventional microscope was equipped with AI algorithms, and AI results were provided to pathologists in real time through augmented reality. We recruited 30 pathologists with various experience levels from five institutes to assess the Ki67 labelling index on 100 Ki67-stained slides from invasive breast cancer patients. In the first round, pathologists conducted visual assessment on a conventional microscope; in the second round, they were assisted with reference cards; and in the third round, they were assisted with an AI-empowered microscope. Experienced pathologists had better reproducibility and accuracy [intraclass correlation coefficient (ICC) = 0.864, mean error = 8.25%] than inexperienced pathologists (ICC = 0.807, mean error = 11.0%) in visual assessment. Moreover, with reference cards, inexperienced pathologists (ICC = 0.836, mean error = 10.7%) and experienced pathologists (ICC = 0.875, mean error = 7.56%) improved their reproducibility and accuracy. Finally, both experienced pathologists (ICC = 0.937, mean error = 4.36%) and inexperienced pathologists (ICC = 0.923, mean error = 4.71%) improved the reproducibility and accuracy significantly with the AI-empowered microscope. Conclusion:The AI-empowered microscope allows seamless integration of the AI solution into the clinical workflow, and helps pathologists to obtain higher consistency and accuracy for Ki67 assessment.

No abstract

Background: Acute kidney injury (AKI) is a major complication of cardiac surgery, with high rates of morbidity and mortality. The aim of this study was to identify risk factors for the incidence and prognosis of AKI in high-risk patients before and after surgery for acute type A aortic dissection (TAAD) in the intensive care unit (ICU). Methods: We performed a retrospective cohort study from April 2018 to April 2019. The primary end points of this study were morbidity due to AKI and risk factors for incidence, and the secondary end points were mortality at 28 days and risk factors for death. Results: We enrolled 60 patients, 52 (86.67%) patients developed postoperative AKI, 28 (53.84%) patients died. Preoperative lactic acid level (P=0.022) and cardiopulmonary bypass (CPB) duration (P=0.009) were identified as independent risk factors for postoperative AKI. The 28-day mortality for postoperative patients with TAAD was 46.67%, 53.84% for those with TAAD and AKI, 67.5% for those who required continue renal replacement therapy (CRRT). The risk factors for 28-day mortality due to postoperative AKI for patients requiring CRRT were CPB duration (P=0.019) and norepinephrine dose upon diagnosis of AKI (P=0.037).Conclusions: Morbidity due to AKI in postoperative patients with TAAD was 86.67%, and preoperative lactic acid level and CPB duration were independent risk factors. The 28-day mortality of postoperative patients with TAAD was 46.67%, 53.84% for those with TAAD and AKI, and 67.5% for those requiring CRRT. CPB duration and norepinephrine dose upon diagnosis of AKI may influence patients' short-term prognosis.

BackgroundThe emergence of HER2 antibody-drug conjugates provides new treatment decisions for breast cancer patients, especially those with HER2-low expression. In order to explore the biological characteristics of breast cancer with HER2-low expression, the HER2-low category in primary breast cancer and residual tumor after neoadjuvant therapy was investigated to reflect the evolution of HER2 expression.MethodsHER2 was assessed according to the latest ASCO/CAP guidelines. The cut-off value for staining of HER2-positive cells was >10%. HER2-negative cases were divided into HER2-low (IHC=1+/2+ and no ISH amplification) and HER2-zero (IHC-0), and the clinicopathological characteristics of the cases were collected.ResultsThis study included 1140 patients with invasive breast cancer who received preoperative neoadjuvant therapy from 2018 to 2021, of which 365 patients achieved pCR and 775 were non-pCR. In the non-pCR cohort, HER2-low cases accounted for 59.61% of primary tumors and 55.36% of residual tumors. Among HER2-negative cases, HR-positive tumors had a higher incidence of low HER2 expression compared with triple-negative tumors (80.27% vs 60.00% in primary tumors and 72.68% vs 50.77% in residual tumors). The inconsistency rate of HER2 expression was 21.42%, mainly manifested as the conversion of HER2-low cases to HER2-zero (10.19%) and the conversion of HER2-zero to HER2-low (6.45%). Among the HER2-negative cases in the primary tumor, the HER2 discordance rate of HR-positive cases was lower than that of triple-negative cases (23.34% VS 36.92%). This difference was mainly caused by the case switching from HER2-low to HER2-zero. Compared with HER2-zero cases, there were statistically significant differences in RCB grade, MP grade and the number of metastatic lymph nodes in HER2-low cases. Patients with low HER2 expression had a lower pathological response rate and a higher number of metastatic lymph nodes.ConclusionHER2-low breast cancer is highly unstable during disease evolution and has certain biological characteristics. HER2-low breast cancer is not only correlated with positive HR, but also has a certain correlation with positive AR. Re-detection of HER2 in breast cancer after neoadjuvant therapy may lead to new treatment opportunities for a certain proportion of patients.

The new HER2-targeting antibody drug conjugate offers the opportunity to treat patients with HER2-low breast cancer. Distinguishing HER2 immunohistochemistry (IHC) scores of 0 and 1+, is critical but also challenging due to HER2 heterogeneity and variability of observers. In this study, we aimed to increase interpretation accuracy and consistency of HER2 IHC 0 and 1 + evaluations through assistance from artificial intelligence (AI) algorithm. In addition, we examined the value of AI algorithm in evaluating HER2 IHC scores in tumors with heterogeneity. The AI-assisted interpretation consisted of AI algorithms and an augmenting reality module with microscope. Fifteen pathologists (5 junior, 5 mid-level and 5 senior) participated this multi-institutional two-round ring study that included 246 infiltrating duct carcinoma not otherwise specified (NOS) cases. In round 1, pathologists analyzed 246 HER2 IHC slides by microscope without AI assistance. After 2 weeks of washout period, the pathologists read the same slides with AI algorithm assistance and rendered the final results by adjusting to the AI algorithm. The interpretation accuracy was significantly increased with AI assistance (Accuracy 0.93 vs 0.80), as well as the evaluation precision of HER2 0 and the recall of HER2 1+. The AI algorithm also improved the total consistency (ICC = 0.542 to 0.812), especially in HER2 1 + cases. In cases with heterogeneity, the accuracy was improved significantly (Accuracy 0.68 to 0.89) and to similar level as cases without heterogeneity (Accuracy 0.95). Both accuracy and the consistency of junior pathologists were better improved than the mid-level and senior pathologists. To the best of our knowledge, it is the first study to show that the accuracy and consistency of HER2 IHC 0 and 1 + evaluations and the accuracy of HER2 IHC evaluation in breast cancers with heterogeneity can be significantly improved using AI-assisted interpretation.