Abstract
BackgroundKi-67 standard reference card (SRC) and artificial intelligence (AI) software were used to evaluate breast cancer Ki-67LI. We established training and validation sets and studied the repeatability inter-observers.MethodsA total of 300 invasive breast cancer specimens were randomly divided into training and validation sets, with each set including 150 cases. Breast cancer Ki-67 standard reference card ranging from 5 to 90% were created. The training set was interpreted by nine pathologists of different ages through microscopic visual assessment (VA), SRC, microscopic manual counting (MC), and AI. The validation set was interpreted by three randomly selected pathologists using SRC and AI. The intra-group correlation coefficient (ICC) were used for consistency analysis.ResultsIn the homogeneous and heterogeneous groups of validation sets, the consistency among the pathologists that used SRC and AI was very good, with an ICC of>0.905. In the validation set, using SRC and AI, three pathologists obtained results that were very consistent with the gold standard, having an ICC above 0.95, and the inter-observer agreement was also very good, with an ICC of>0.9.ConclusionsAI has satisfactory inter-observer repeatability, and the true value was closer to the gold standard, which is the preferred method for Ki-67LI reproducibility; While AI software has not been popularized, SRC may be interpreted as breast cancer Ki-67LI’s standard candidate method.
Highlights
Marked Ki-67 (Ki-67) standard reference card (SRC) and artificial intelligence (AI) software were used to evaluate breast cancer Ki-67 Label Index (Ki-67LI)
Ki-67LI interpretation time The results show that the SRC method requires the least time to interpret Ki67 and can improve the work efficiency of pathologists (Table 1)
Ki-67LI interpretation results The Kolmogorov-Smirnov (KS) test was used to assess the normality of Ki-67LI in breast cancer using visual assessment (VA), manual counting (MC), SRC, and AI
Summary
Ki-67 standard reference card (SRC) and artificial intelligence (AI) software were used to evaluate breast cancer Ki-67LI. Ki-67 is an indispensable nuclear antigen for cell proliferation. It can be rapidly detected using immunohistochemistry [1]. Pathologists generally use visual assessment or manual cell counting under a microscope to evaluate Ki-67LI. Visual assessment lacks repeatability among observers [2,3,4]. Digital pathology has made great progress in image acquisition and digital analysis, which makes artificial intelligence comparable to visual evaluation under the microscope regarding Ki-67 interpretation [12]. By comparing the difference between AIassisted and manual interpretation, the clinical applicability of AI-assisted interpretation was analyzed to provide a scientific theoretical basis for an accurate and individualized treatment of breast cancer patients
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
