Noninferiority of Artificial Intelligence-Assisted Analysis of Ki-67 and Estrogen/Progesterone Receptor in Breast Cancer Routine Diagnostics.

Image analysis assistance with artificial intelligence (AI) has become one of the great promises over recent years in pathology, with many scientific studies being published each year. Nonetheless, and perhaps surprisingly, only few image AI systems are already in routine clinical use. A major reason for this is the missing validation of the robustness of many AI systems: beyond a narrow context, the large variability in digital images due to differences in preanalytical laboratory procedures, staining procedures, and scanners can be challenging for the subsequent image analysis. Resulting faulty AI analysis may bias the pathologist and contribute to incorrect diagnoses and, therefore, may lead to inappropriate therapy or prognosis. In this study, a pretrained AI assistance tool for the quantification of Ki-67, estrogen receptor (ER), and progesterone receptor (PR) in breast cancer was evaluated within a realistic study set representative of clinical routine on a total of 204 slides (72 Ki-67, 66 ER, and 66 PR slides). This represents the cohort with the largest image variance for AI tool evaluation to date, including 3 staining systems, 5 whole-slide scanners, and 1 microscope camera. These routine cases were collected without manual preselection and analyzed by 10 participant pathologists from 8 sites. Agreement rates for individual pathologists were found to be 87.6% for Ki-67 and 89.4% for ER/PR, respectively, between scoring with and without the assistance of the AI tool regarding clinical categories. Individual AI analysis results were confirmed by the majority of pathologists in 95.8% of Ki-67 cases and 93.2% of ER/PR cases. The statistical analysis provides evidence for high interobserver variance between pathologists (Krippendorff's α, 0.69) in conventional immunohistochemical quantification. Pathologist agreement increased slightly when using AI support (Krippendorff α, 0.72). Agreement rates of pathologist scores with and without AI assistance provide evidence for the reliability of immunohistochemical scoring with the support of the investigated AI tool under a large number of environmental variables that influence the quality of the diagnosed tissue images.

P53 Codon 72 Polymorphism and Risk for Squamous Cell Carcinoma of the Penis: A Caucasian Case-Control Study.

Squamous cell carcinoma of the penis is a rare but often aggressive disease. A large proportion of penile cancers are associated with HPV infection, mainly with HPV high-risk subtypes 16 and 18. From other HPV-related malignancies a link between a functional SNP in the p53 gene (rs1042522, p.Arg72Pro) and a higher disease risk in the presence of HPV is documented. The p53 p.Arg72 variant was described as a risk factor for developing a malignancy in combination with the presence of HPV as the p.72Arg variant is more prone to HPV E6 protein-mediated degradation than the p.72Pro variant. For penile carcinoma there are only sparse data available on this topic. We therefore analyzed the distribution of this p53 codon 72 SNP in a cohort of 107 penile cancer patients and a healthy control group (n=194) using Restriction Fragment Length Polymorphism (RFLP) analysis. After DNA isolation a PCR amplicon including the variant nucleotide was generated. Based on the variant nucleotide this amplicon can be cleaved into two parts or remain unaffected by a restriction enzyme. Subsequent electrophoresis allowed the discrimination of SNP alleles in the investigated sample. Comparison of the allelic variants revealed no significant differences in the distribution of this SNP between cases and controls (p=0,622). There was also no difference in SNP distribution between cases with/without HPV infection (p=0,558) or histologic variants (p=0.339). In order to strengthen the impact of our data we performed a combined analysis of all published data on this topic with our results. This ended up in SNP distribution data from 177 cases and 1149 controls. Overall, there were also no significant differences in the allelic distribution of the p53 codon 72 SNP between either cases and controls (p=0,914) or HPV-positive and HPV-negative cases (p=0,486). From this most comprehensive data available to date we conclude that there is no influence of the p53 codon 72 SNP on the risk of development of penile carcinoma in Caucasians even in the presence of HPV.