AI improves accuracy, agreement and efficiency of pathologists for Ki67 assessments in breast cancer.

The Ki-67 proliferation index (PI) guides treatment decisions in breast cancer but suffers from poor inter-rater reproducibility. Although AI tools have been designed for Ki-67 assessment, their impact on pathologists' work remains understudied. 90 international pathologists were recruited to assess the Ki-67 PI of ten breast cancer tissue microarrays with and without AI. Accuracy, agreement, and turnaround time with and without AI were compared. Pathologists' perspectives on AI were collected. Using AI led to a significant decrease in PI error (2.1% with AI vs. 5.9% without AI, p < 0.001), better inter-rater agreement (ICC: 0.70 vs. 0.92; Krippendorff's α: 0.63 vs. 0.89; Fleiss' Kappa: 0.40 vs. 0.86), and an 11.9% overall median reduction in turnaround time. Most pathologists (84%) found the AI reliable. For Ki-67 assessments, 76% of respondents believed AI enhances accuracy, 82% said it improves consistency, and 83% trust it will improve efficiency. This study highlights AI's potential to standardize Ki-67 scoring, especially between 5 and 30% PI-a range with low PI agreement. This could pave the way for a universally accepted PI score to guide treatment decisions, emphasizing the promising role of AI integration into pathologist workflows.

Reliability and Variability of Ki-67 Digital Image Analysis Methods for Clinical Diagnostics in Breast Cancer.

Ki-67 is a nuclear protein associated with proliferation, and a strong potential biomarker in breast cancer, but is not routinely measured in current clinical management owing to a lack of standardization. Digital image analysis (DIA) is a promising technology that could allow high-throughput analysis and standardization. There is a dearth of data on the clinical reliability as well as intra- and interalgorithmic variability of different DIA methods. In this study, we scored and compared a set of breast cancer cases in which manually counted Ki-67 has already been demonstrated to have prognostic value (n = 278) to 5 DIA methods, namely Aperio ePathology (Lieca Biosystems), Definiens Tissue Studio (Definiens AG), Qupath, an unsupervised immunohistochemical color histogram algorithm, and a deep-learning pipeline piNET. The piNET system achieved high agreement (interclass correlation coefficient: 0.850) and correlation (R = 0.85) with the reference score. The Qupath algorithm exhibited a high degree of reproducibility among all rater instances (interclass correlation coefficient: 0.889). Although piNET performed well against absolute manual counts, none of the tested DIA methods classified common Ki-67 cutoffs with high agreement or reached the clinically relevant Cohen's κ of at least 0.8. The highest agreement achieved was a Cohen's κ statistic of 0.73 for cutoffs 20% and 25% by the piNET system. The main contributors to interalgorithmic variation and poor cutoff characterization included heterogeneous tumor biology, varying algorithm implementation, and setting assignments. It appears that image segmentation is the primary explanation for semiautomated intra-algorithmic variation, which involves significant manual intervention to correct. Automated pipelines, such as piNET, may be crucial in developing robust and reproducible unbiased DIA approaches to accurately quantify Ki-67 for clinical diagnosis in the future.

Heterogeneity of Circulating Tumor Cell-Associated Genomic Gains in Breast Cancer and Its Association with the Host Immune Response.

Tumor cells that preferentially enter circulation include the precursors of metastatic cancer. Previously, we characterized circulating tumor cells (CTC) from patients with breast cancer and identified a signature of genomic regions with recurrent copy-number gains. Through FISH, we now show that these CTC-associated regions are detected within the matched untreated primary tumors of these patients (21% to 69%, median 55.5%, n = 19). Furthermore, they are more prevalent in the metastases of patients who died from breast cancer after multiple rounds of treatment (70% to 100%, median 93%, samples n = 41). Diversity indices revealed that higher spatial heterogeneity for these regions within primary tumors is associated with increased dissemination and metastasis. An identified subclone with multiple regions gained (MRG clone) was enriched in a posttreatment primary breast carcinoma as well as multiple metastatic tumors and local breast recurrences obtained at autopsy, indicative of a distinct early subclone with the capability to resist multiple lines of treatment and eventually cause death. In addition, multiplex immunofluorescence revealed that tumor heterogeneity is significantly associated with the degree of infiltration of B lymphocytes in triple-negative breast cancer, a subtype with a large immune component. Collectively, these data reveal the functional potential of genetic subclones that comprise heterogeneous primary breast carcinomas and are selected for in CTCs and posttreatment breast cancer metastases. In addition, they uncover a relationship between tumor heterogeneity and host immune response in the tumor microenvironment. SIGNIFICANCE: As breast cancers progress, they become more heterogeneous for multiple regions amplified in circulating tumor cells, and intratumoral spatial heterogeneity is associated with the immune landscape.