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.

An interobserver reproducibility analysis of size-set semiautomatic counting for Ki67 assessment in breast cancer.

PURPOSE: The proliferation marker Ki67 has prognostic and predictive values in breast cancer, and the cutoff of the Ki67 label index (LI) is a key index for chemotherapy. However, poor interobserver consistency in Ki67 assessment has limited the clinical use of Ki67, especially in luminal cancers. Here, we reported a modified Ki67 assessment method, size-set semiautomatic counting (SSSAC) and investigated its interobserver reproducibility. METHODS: One hundred invasive breast cancer tissues were set immunostained for Ki67 in one laboratory, scanned as digital slides, and sent to 41 pathologists at the laboratories of 16 hospitals for Ki67 LI assessment using size-set semiautomatic counting (SSSAC), size-set visual assessment (SSVA) and size-set digital image analysis (SSDIA) with a specific image viewing software (Aperio Image Scope, Leica, Germany). The intraclass correlation coefficient (ICC) and Bland-Altman plot were used to evaluate interobserver reproducibility. The Wilcoxon signed-rank test was used to analyze the difference in the Ki67 values assessed by SSSAC and SSDIA. RESULTS: SSSAC demonstrated better interobserver reproducibility (ICC = 0.942) than SSVA (ICC = 0.802). The interobserver reproducibility was better in Ki67 homogeneously stained slides and centralized hot-spot slides than in scattered hot-spot slides. The Ki67 value assessed with SSSAC was obviously higher than that assessed with SSDIA (negative ranks (SSDIA < SSSAC): N = 80, sum of ranks = 4274.50; positive ranks (SSDIA > SSSAC): N = 17, sum of ranks = 478.50; Z = -6.837; P < 0.001). CONCLUSION: SSSAC shows satisfactory interobserver reproducibility in the Ki67 assessment of breast cancer and may be a candidate standard method for Ki67 LI assessment in breast cancer and other malignancies.

External quality assessment (EQA) program for the immunohistochemical detection of ER, PR and Ki-67 in breast cancer: results of an interlaboratory reproducibility ring study in China.

BACKGROUND: An External Quality Assessment (EQA) program was developed to investigate the status of estrogen receptor (ER), progesterone receptor (PR), and Ki-67 immunohistochemical (IHC) detection in breast cancer and to evaluate the reproducibility of staining and interpretation in 44 pathology laboratories in China. METHODS: This program was implemented through three specific steps. In study I, three revising centres defined the reference value for 11 sections. In study II, 41 participating centres (PC) stained and interpreted 11 sections by their own daily practice IHC protocols. In study III, all cases received second interpretation opinions. RESULTS: The stained slides of 44 laboratories were up to the interpretation standard. The overall interpretation concordance rate of this study was over 90%. A perfect agreement was reached among the PCs for the cases with ER+ and PR+ > 50% and Ki-67 > 30%, whereas a moderate agreement was observed for intermediate categories. After second interpretations, the misclassification rates for ER were reduced by 12.20%, for PR were reduced by 17.07%, and for Ki-67 were reduced by 4.88%. Up to 31 PCs observed a benefit from the second opinion strategy. CONCLUSIONS: This project is the first EQA study performed on a national scale for assessment of ER, PR and Ki-67 status by IHC in China. In the whole IHC evaluation process, the intermediate categories were less reproducible than those with high expression rates. Second opinions can significantly improve the diagnostic agreement of pathologists' interpretations.

A decision tree-based prediction model for fluorescence in situ hybridization HER2 gene status in HER2 immunohistochemistry-2+ breast cancers: a 2538-case multicenter study on consecutive surgical specimens.

Objective: To investigate the proportion of HER2 gene amplifications and the association between the HER2-IHC-staining pattern and gene status in IHC-2+ breast cancers according to 2013 American Society of Clinical Oncology (ASCO)/College of American Pathologists (CAP) guidelines. Methods: We retrospectively analyzed and re-evaluated the IHC-staining pattern of 2538 IHC-2+ surgical specimens of breast cancer from November 2014 to October 2015 in 12 institutions. All cases used for building a prediction model of HER2 gene amplification according to the IHC-staining pattern and were randomly divided into a training set (n = 1914) or validation set (n = 624). Results: The overall HER2 fluorescence in situ hybridization (FISH) amplification, non-amplification and equivocation rates in HER2 IHC-2+ cases were 17.8%, 76.2% and 6.0%, respectively. In the training set, cases that had ≤ 10% of cells with intense, complete and circumferential membrane staining or had > 85% of cells with complete membrane staining of any staining intensity tended to be HER2 gene amplified (77.0% and 60.5%, respectively). And cases with weak and incomplete membrane staining had the lowest amplification rate of 6.1%. The prediction model was constructed based on IHC-staining pattern in the training set and validated using a validation set. The positive and negative prediction values were 51.6% and 79.2%, respectively, in the validation set. Moreover, the HER2 copy number per cell was much higher in cases with amplification-associated staining patterns (7.84 and 8.75) than in cases with non-amplification-associated staining patterns (2.97 to 4.41, P < 0.05). Conclusions: In HER2 IHC-2+ breast cancers, the staining pattern is associated with the HER2 gene status. This finding is compatible with recommendations of 2013 ASCO/CAP guidelines.