ABSTRACT
Pathology is practiced by visual inspection of histochemically stained tissue slides. While the hematoxylin and eosin (H&E) stain is most commonly used, special stains can provide additional contrast to different tissue components. Here, we demonstrate the utility of supervised learning-based computational stain transformation from H&E to special stains (Masson's Trichrome, periodic acid-Schiff and Jones silver stain) using kidney needle core biopsy tissue sections. Based on the evaluation by three renal pathologists, followed by adjudication by a fourth pathologist, we show that the generation of virtual special stains from existing H&E images improves the diagnosis of several non-neoplastic kidney diseases, sampled from 58 unique subjects (P = 0.0095). A second study found that the quality of the computationally generated special stains was statistically equivalent to those which were histochemically stained. This stain-to-stain transformation framework can improve preliminary diagnoses when additional special stains are needed, also providing significant savings in time and cost.
Subject(s)
Biopsy, Large-Core Needle/methods , Deep Learning , Diagnosis, Computer-Assisted/methods , Kidney Diseases/pathology , Kidney/pathology , Staining and Labeling/methods , Algorithms , Coloring Agents/chemistry , Coloring Agents/classification , Coloring Agents/standards , Diagnosis, Differential , Humans , Kidney Diseases/diagnosis , Pathology, Clinical/methods , Pathology, Clinical/standards , Reference Standards , Reproducibility of Results , Sensitivity and Specificity , Staining and Labeling/standardsABSTRACT
OBJECTIVES/HYPOTHESIS: Merkel cell carcinoma (MCC) is a rare and aggressive neuroendocrine neoplasm of the skin. Growing evidence supports the benefit of postoperative adjuvant radiation therapy (RT) for locoregional control, but whether it improves overall survival (OS) has been debated. Our objective was to compare the OS of MCC patients who received postoperative RT with those who received surgery alone. STUDY DESIGN: Retrospective case series. METHODS: Cases of MCC between 2001 and 2016 at the University of California, Los Angeles Health System were reviewed. We identified 87 unique cases of MCC. Among the patients, 74% were identified as male and 26% as female. The average age at diagnosis was 71.2 years. The median survival was 48.0 months. The OS of all the patients at 2 years, 5 years, and 10 years was 54%, 46%, and 26%, respectively. Univariate analysis showed that stage, T stage, N stage, and M stage were significant determinants of OS. The inclusion of RT was not found to be a determinant; however, when restricting the analysis to early-stage MCC (stages I and II), postoperative adjuvant RT was associated with significantly improved OS. A Cox regression model confirmed that inclusion of RT was an independent prognosticator of OS even when controlled for overall stage and negative margin status. The small sample size and retrospective nature of this study limit its statistical power. CONCLUSIONS: MCC is an aggressive tumor with a poor prognosis for survival especially in elderly patients. In this study, we found that RT during early-stage MCC improves OS. Prospective randomized control trials are necessary to validate the observed benefit for MCC patients. LEVEL OF EVIDENCE: 4 Laryngoscope, 1862-1866, 2018.