Agreement and error rates using blinded review to evaluate surgical pathology of biopsy material

Artificial intelligence-assisted cancer diagnosis improves the efficiency of pathologists in prostatic biopsies

Paige Prostate is a clinical-grade artificial intelligence tool designed to assist the pathologist in detecting, grading, and quantifying prostate cancer. In this work, a cohort of 105 prostate core needle biopsies (CNBs) was evaluated through digital pathology. Then, we compared the diagnostic performance of four pathologists diagnosing prostatic CNB unaided and, in a second phase, assisted by Paige Prostate. In phase 1, pathologists had a diagnostic accuracy for prostate cancer of 95.00%, maintaining their performance in phase 2 (93.81%), with an intraobserver concordance rate between phases of 98.81%. In phase 2, pathologists reported atypical small acinar proliferation (ASAP) less often (about 30% less). Additionally, they requested significantly fewer immunohistochemistry (IHC) studies (about 20% less) and second opinions (about 40% less). The median time required for reading and reporting each slide was about 20% lower in phase 2, in both negative and cancer cases. Lastly, the average total agreement with the software performance was observed in about 70% of the cases, being significantly higher in negative cases (about 90%) than in cancer cases (about 30%). Most of the diagnostic discordances occurred in distinguishing negative cases with ASAP from small foci of well-differentiated (less than 1.5 mm) acinar adenocarcinoma. In conclusion, the synergic usage of Paige Prostate contributes to a significant decrease in IHC studies, second opinion requests, and time for reporting while maintaining highly accurate diagnostic standards.

An independent assessment of an artificial intelligence system for prostate cancer detection shows strong diagnostic accuracy

Prostate cancer is a leading cause of morbidity and mortality for adult males in the US. The diagnosis of prostate carcinoma is usually made on prostate core needle biopsies obtained through a transrectal approach. These biopsies may account for a significant portion of the pathologists' workload, yet variability in the experience and expertise, as well as fatigue of the pathologist may adversely affect the reliability of cancer detection. Machine-learning algorithms are increasingly being developed as tools to aid and improve diagnostic accuracy in anatomic pathology. The Paige Prostate AI-based digital diagnostic is one such tool trained on the digital slide archive of New York's Memorial Sloan Kettering Cancer Center (MSKCC) that categorizes a prostate biopsy whole-slide image as either "Suspicious" or "Not Suspicious" for prostatic adenocarcinoma. To evaluate the performance of this program on prostate biopsies secured, processed, and independently diagnosed at an unrelated institution, we used Paige Prostate to review 1876 prostate core biopsy whole-slide images (WSIs) from our practice at Yale Medicine. Paige Prostate categorizations were compared to the pathology diagnosis originally rendered on the glass slides for each core biopsy. Discrepancies between the rendered diagnosis and categorization by Paige Prostate were each manually reviewed by pathologists with specialized genitourinary pathology expertise. Paige Prostate showed a sensitivity of 97.7% and positive predictive value of 97.9%, and a specificity of 99.3% and negative predictive value of 99.2% in identifying core biopsies with cancer in a data set derived from an independent institution. Areas for improvement were identified in Paige Prostate's handling of poor quality scans. Overall, these results demonstrate the feasibility of porting a machine-learning algorithm to an institution remote from its training set, and highlight the potential of such algorithms as a powerful workflow tool for the evaluation of prostate core biopsies in surgical pathology practices.

Multireader multicase reader studies with binary agreement data: simulation, analysis, validation, and sizing

We treat multireader multicase (MRMC) reader studies for which a reader's diagnostic assessment is converted to binary agreement (1: agree with the truth state, 0: disagree with the truth state). We present a mathematical model for simulating binary MRMC data with a desired correlation structure across readers, cases, and two modalities, assuming the expected probability of agreement is equal for the two modalities ([Formula: see text]). This model can be used to validate the coverage probabilities of 95% confidence intervals (of [Formula: see text], [Formula: see text], or [Formula: see text] when [Formula: see text]), validate the type I error of a superiority hypothesis test, and size a noninferiority hypothesis test (which assumes [Formula: see text]). To illustrate the utility of our simulation model, we adapt the Obuchowski-Rockette-Hillis (ORH) method for the analysis of MRMC binary agreement data. Moreover, we use our simulation model to validate the ORH method for binary data and to illustrate sizing in a noninferiority setting. Our software package is publicly available on the Google code project hosting site for use in simulation, analysis, validation, and sizing of MRMC reader studies with binary agreement data.

Merkel cell carcinoma frequently shows histologic features of basal cell carcinoma: a study of 30 cases

BACKGROUND

Merkel cell carcinoma (MCC) is a basaloid cutaneous neoplasm that may be mistaken for basal cell carcinoma (BCC).

METHODS

Thirty MCCs were examined for areas that histologically resembled BCC.

RESULTS

One of the histologic features of BCC (either a mucinous stroma or stromal artifactual retraction) was identified in all MCCs. A mucinous stroma was found in 28 MCCs (93%), stromal artifactual retraction in 27 (90%), mucin-containing gland-like spaces within tumor nests in 8 (27%), focal peripheral palisading in 8 (27%), epidermal involvement in 3 (10%) and dystrophic calcification in 1 MCC (3%). The cytologic features and absence of widespread peripheral palisading were the most reliable discriminators between MCC and BCC on routine sections. Squamous cell carcinoma was identified in four cases (13%). Two cases (7%) contained pagetoid intraepidermal spread (IES) of MCC. In one case, there was IES over the entire epidermal surface associated with intranuclear clearing, resembling the intranuclear cytoplasmic inclusions (INI) common in melanocytic tumors. INI were identified in six MCCs (20%).

CONCLUSIONS

MCCs frequently contain areas that histologically resemble BCC and other more common cutaneous malignancies. This can lead to diagnostic errors, particularly in small fragmented curettage specimens or frozen sections.

Single nucleotide polymorphism profiling assay to confirm the identity of human tissues

To identify issues of sample mix-ups, various molecular techniques are currently used. These techniques, however, are time consuming and require experience and/or DNA sequencing equipment or have a relatively high risk of errors because of contamination. Therefore, a quick and straightforward single nucleotide polymorphism (SNP) profiling assay was developed to link human tissues to a source. SNPs are common sequence variations in the human genome, and each individual has a unique combination of these nucleotide variations. Using potentially mislabeled paraffin-embedded tissues, DNA was extracted and SNP profiles were determined by real-time polymerase chain reaction analysis of the purified DNA using a selection of 10 commercially available SNP amplification assays. These profiles were compared with profiles of the supposed owners. All issues (34 in total) of potential sample mix-ups during the last 3 years were adequately solved, with six cases described here. The SNP profiling assay provides a quick (within 24 hours), easy, and reliable way to link human samples to a source, without polymerase chain reaction postprocessing. The chance for two randomly chosen individuals to have an identical profile is 1 in 18,000. Solving potential sample mix-ups will secure downstream evaluations and critical decisions concerning the patients involved.