Histopathological diagnosis of pancreatic ductal adenocarcinoma (PDAC) on endoscopic ultrasonography-guided fine-needle biopsy (EUS-FNB) specimens has become the mainstay of preoperative pathological diagnosis. However, on EUS-FNB specimens, accurate histopathological evaluation is difficult due to low specimen volume with isolated cancer cells and high contamination of blood, inflammatory and digestive tract cells. In this study, we performed annotations for training sets by expert pancreatic pathologists and trained a deep learning model to assess PDAC on EUS-FNB of the pancreas in histopathological whole-slide images. We obtained a high receiver operator curve area under the curve of 0.984, accuracy of 0.9417, sensitivity of 0.9302 and specificity of 0.9706. Our model was able to accurately detect difficult cases of isolated and low volume cancer cells. If adopted as a supportive system in routine diagnosis of pancreatic EUS-FNB specimens, our model has the potential to aid pathologists diagnose difficult cases.
Introduction: The aim of this study was to examine whether a combined test using both cell sediment and supernatant cytology cell‐free DNA (ccfDNA) is more useful in detecting EGFR mutation than using cell sediment DNA or supernatant ccfDNA alone in pleural effusion of lung cancer patients.Methods: A total of 74 lung adenocarcinoma patients with paired samples between primary tumour and corresponding metastatic tumour with both cell sediment and supernatant ccfDNA of pleural effusion cytology were enrolled in this study. Cell sediment and supernatant ccfDNA were analysed separately for EGFR mutations by polymerase chain reaction.Results: Out of 45 patients with mutant EGFR in primary tumours, EGFR mutations were detected in 23 cell sediments of corresponding metastases (sensitivity; 51.1%) and 20 supernatant ccfDNA corresponding metastases (sensitivity; 44.4%). By contrast, the combined test detected EGFR mutations in 27 corresponding metastases (sensitivity; 60.0%), and had a higher sensitivity than the cell sediment or the supernatant ccfDNA alone (P < .05). Out of 45 patients with mutant EGFR, 24, three and 18 were cytologically diagnosed as positive, atypical or negative, respectively. The detection rate in the combined test was highest (95.8%) in the positive group, and mutant EGFR was also detected in four of 18 samples (22.2%) in the negative group.Conclusions: A combined test using both cell sediment DNA and supernatant ccfDNA samples increases the concordance rate of EGFR mutations between primary tumour and corresponding metastases. Our findings indicate that supernatant ccfDNA is useful even in cases where the cytological diagnosis is negative.
1 December 2018 in Pathology - Research and Practice