Search

Background and Aim: An early and accurate diagnosis of ampullary neoplasia is crucial; however, sampling bias is still a major concern. New‐generation endocytoscopy enables real‐time visualization of cellular structures and enables an accurate pathological prediction; however, its feasibility for small ampullary lesions has never been investigated. Methods: We developed a novel endocytoscopic (EC) classification system for ampullary lesions after an expert review and agreement from five experienced endoscopists and one pathologist. We then consecutively enrolled a total of 43 patients with an enlarged ampulla (< 3 cm), all of whom received an endocytoscopic examination. The feasibility of endocytoscopy was evaluated, and the performance of the EC classification system was then correlated with the final histopathology. Results: In five cases (11.6%), the endocytoscope could not approach the ampulla, and these cases were defined as technical failure. Among the remaining 38 patients, 8 had histopathology‐confirmed adenocarcinoma, 15 had adenoma, and 15 had non‐neoplastic lesions. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the EC classification system to diagnose ampullary neoplasias were 95.7%, 86.7%, 91.7%, 92.9%, and 92.1%, respectively. Moreover, the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the EC classification to diagnose ampullary cancer were 62.5%, 100%, 100%, 90.9%, and 92.1%, respectively. One case with intra‐ampullary papillary–tubular carcinoma was classified as having a non‐neoplastic lesion by endocytoscopy. Conclusions: Endocytoscopy and the novel EC classification system demonstrated good feasibility to discriminate ampullary neoplasias from non‐neoplastic lesions and may be useful for optical biopsies of clinically suspicious ampullary lesions. [ABSTRACT FROM AUTHOR]

Simple Summary: This study included 227 patients, among whom 27.7% (63/227) were diagnosed with tumors spread through air spaces (STASs), which have been shown to be associated with shorter recurrence-free survival and poor prognosis. A prediction model was developed to forecast tumor STAS in early-stage lung adenocarcinoma pathology images. The radiomics prediction model demonstrated good performance, with an AUC value of 0.83. This prediction model can assist pathologists in the diagnostic processes of clinical practice. The presence of spread through air spaces (STASs) in early-stage lung adenocarcinoma is a significant prognostic factor associated with disease recurrence and poor outcomes. Although current STAS detection methods rely on pathological examinations, the advent of artificial intelligence (AI) offers opportunities for automated histopathological image analysis. This study developed a deep learning (DL) model for STAS prediction and investigated the correlation between the prediction results and patient outcomes. To develop the DL-based STAS prediction model, 1053 digital pathology whole-slide images (WSIs) from the competition dataset were enrolled in the training set, and 227 WSIs from the National Taiwan University Hospital were enrolled for external validation. A YOLOv5-based framework comprising preprocessing, candidate detection, false-positive reduction, and patient-based prediction was proposed for STAS prediction. The model achieved an area under the curve (AUC) of 0.83 in predicting STAS presence, with 72% accuracy, 81% sensitivity, and 63% specificity. Additionally, the DL model demonstrated a prognostic value in disease-free survival compared to that of pathological evaluation. These findings suggest that DL-based STAS prediction could serve as an adjunctive screening tool and facilitate clinical decision-making in patients with early-stage lung adenocarcinoma. [ABSTRACT FROM AUTHOR]

Determining the exact type of epidermal growth factor receptor (EGFR) exon 20 insertion (ex20ins) mutation in lung cancer has become important. We found that not all ex20ins mutations reported by cobas EGFR test v2 could be validated by Sanger sequencing even using surgical specimens with high tumor contents. This study aimed to validate the ex20ins results reported by the cobas test and to determine whether there were clinicopathological factors associated with aberrant cobas ex20ins report. In total, 123 cobas-reported cases with ex20ins were retrospectively collected and validated by Sanger sequencing and Idylla assay. Clinicopathological features between ex20ins cobas+/Sanger+ group (n = 71) and cobas+/Sanger− group (n = 52) were compared. The Idylla assay detected ex20ins in 82.6% of cobas+/Sanger+ cases but only in 4.9% of cobas+/Sanger− cases. The cobas+/Sanger− group was significantly associated with higher tumor contents, poorly differentiated patterns, tumor necrosis, and a lower internal control cycle threshold value reported by the Idylla which suggesting the presence of increased EGFR gene copy numbers. EGFR fluorescence in situ hybridization (FISH) revealed the majority of cobas+/Sanger− group had EGFR high copy number gain (16%) or amplification (76%) according to the Colorado criteria. Among cases reported to have concomitant classic EGFR and ex20ins mutations by the cobas, the classic EGFR mutations were all detected by Sanger sequencing and Idylla, while the ex20ins mutations were undetected by Sanger sequencing (0%) or rarely reported by Idylla assay (3%). FISH revealed high EGFR copy number gain (17.9%) and amplification (79.5%) in cases reported having concomitant classic EGFR and ex20ins mutations by the cobas. This study demonstrated an unusually high frequency of EGFR amplification in cases with aberrant cobas ex20ins report which could not be validated by Sanger sequencing or Idylla assay. Ex20ins reported by the cobas test should be validated using other methods especially those reported having concomitant ex20ins and classic EGFR mutations. [ABSTRACT FROM AUTHOR]