Search

Objectives: The landmark ADAURA study recently demonstrated a significant disease-free survival benefit of adjuvant osimertinib in patients with resected EGFR-mutated lung adenocarcinoma. However, data on prevalence rates and stage distribution of EGFR mutations in non-small cell lung cancer in Western populations are limited since upfront EGFR testing in early stage lung adenocarcinoma is not common practice. Here, we present a unique, real-world, unselected cohort of lung adenocarcinoma to aid in providing a rationale for routine testing of early stage lung cancers for EGFR mutations in the West-European population. Material and methods: We performed routine unbiased testing of all cases, regardless of TNM stage, with targeted next-generation sequencing on 486 lung adenocarcinoma cases between 01- January 2014 and 01 February 2020. Clinical and pathological data, including co-mutations and morphology, were collected. EGFR-mutated cases were compared to KRAS-mutated cases to investigate EGFR-specific characteristics. Results: In total, 53 of 486 lung adenocarcinomas (11%) harboured an EGFR mutation. In early stages (stage 0-IIIA), the prevalence was 13%, versus 9% in stage IIIB-IV. Nine out of 130 (7%) stage IB-IIIA patients fit the ADAURA criteria. Early stage cases harboured more L858R mutations (p = 0.02), fewer exon 20 insertions (p = 0.048), fewer TP53 co-mutations (p = 0.007), and were more frequently never smokers (p = 0.04) compared to late stage cases with EGFR mutations. The KRAS-mutated cases were distributed more evenly across TNM stages compared to the EGFR-mutated cases. Conclusion: As (neo-)adjuvant targeted therapy regimes enter the field of lung cancer treatment, molecular analysis of early stage non-small cell lung cancer becomes relevant. Testing for EGFR mutations in early stage lung adenocarcinoma holds a substantial yield in our population, as our number needed to test ratio for adjuvant osimertinib was 14.4. The observed differences betwee

In digital pathology, whole slide images (WSIs) are widely used for applications such as cancer diagnosis and prognosis prediction. Visual transformer models have recently emerged as a promising method for encoding large regions of WSIs while preserving spatial relationships among patches. However, due to the large number of model parameters and limited labeled data, applying transformer models to WSIs remains challenging. Inspired by masked language models, we propose a pretext task for training the transformer model without labeled data to address this problem. Our model, MaskHIT, uses the transformer output to reconstruct masked patches and learn representative histological features based on their positions and visual features. The experimental results demonstrate that MaskHIT surpasses various multiple instance learning approaches by 3% and 2% on survival prediction and cancer subtype classification tasks, respectively. Furthermore, MaskHIT also outperforms two of the most recent state-of-the-art transformer-based methods. Finally, a comparison between the attention maps generated by the MaskHIT model with pathologist's annotations indicates that the model can accurately identify clinically relevant histological structures in each task.

Endometrial cancer, the fourth most common cancer in females in the United States, with the lifetime risk for developing this disease is approximately 2.8% in women. Precise histologic evaluation and molecular classification of endometrial cancer is important for effective patient management and determining the best treatment modalities. This study introduces EndoNet, which uses convolutional neural networks for extracting histologic features and a vision transformer for aggregating these features and classifying slides based on their visual characteristics into high- and low- grade. The model was trained on 929 digitized hematoxylin and eosin-stained whole-slide images of endometrial cancer from hysterectomy cases at Dartmouth-Health. It classifies these slides into low-grade (Endometroid Grades 1 and 2) and high-grade (endometroid carcinoma FIGO grade 3, uterine serous carcinoma, carcinosarcoma) categories. EndoNet was evaluated on an internal test set of 110 patients and an external test set of 100 patients from the public TCGA database. The model achieved a weighted average F1-score of 0.91 (95% CI: 0.86-0.95) and an AUC of 0.95 (95% CI: 0.89-0.99) on the internal test, and 0.86 (95% CI: 0.80-0.94) for F1-score and 0.86 (95% CI: 0.75-0.93) for AUC on the external test. Pending further validation, EndoNet has the potential to support pathologists without the need of manual annotations in classifying the grades of gynecologic pathology tumors., Comment: 4 Tables and 3 Figures

Objectives: Programmed death-ligand 1 (PD-L1) is the only approved predictive biomarker for immunotherapy in non-small cell lung cancer (NSCLC). However, predictive PD-L1 immunohistochemistry is subject to interobserver variability. We hypothesized that a pathologist's personality influences the interobserver variability and diagnostic accuracy of PD-L1 immunoscoring.& nbsp;Materials and Methods: Seventeen pathologists performed PD-L1 immunoscoring on 50 resected NSCLC tumors in three categories (< 1%;1-49%;>= 50%). Also, the pathologists completed a certified personality test (NEO-PI-r), assessing five personality traits: neuroticism, extraversion, openness, altruism and conscientiousness.& nbsp;Results: The overall agreement among pathologists for a series of 47 tumors was substantial (kappa = 0.63). Of these, 23/47 (49%) tumors were entirely negative or largely positive, resulting in a kappa value of 0.93. The remaining 24/47 (51%) tumors had a PD-L1 score around the cutoff value, generating a kappa value of 0.32. Pathologists with high scores for conscientiousness (careful, diligent) had the least interobserver variability (r = 0.6, p = 0.009). Also, they showed a trend towards higher sensitivity (74% vs. 68%, p = 0.4), specificity (86% vs. 82%, p = 0.3) and percent agreement (83% vs. 79%, p = 0.3), although not significant. In contrast, pathologists with high scores for neuroticism (sensitive, anxious) had significantly lower specificity (80% vs. 87%, p = 0.03) and percent agreement (78% vs. 85%, p = 0.03). Also, a trend towards high interobserver variability (r =-0.3, p = 0.2) and lower sensitivity (68% vs. 74%, p = 0.3) was observed, although not significant. Pathologists with relatively high scores for conscientiousness scored fewer tumors PD-L1 positive at the >= 1% cut-off (r =-0.5, p = 0.03). In contrast, pathologists with relatively high scores for neuroticism score more tumors PD-L1 positive at > 1% (r = 0.6, p = 0.017) and >= 50% cut-offs (r = 0.6, p =

Objectives: Programmed death-ligand 1 (PD-L1) is the only approved predictive biomarker for immunotherapy in non-small cell lung cancer (NSCLC). However, predictive PD-L1 immunohistochemistry is subject to interobserver variability. We hypothesized that a pathologist's personality influences the interobserver variability and diagnostic accuracy of PD-L1 immunoscoring. Materials and Methods: Seventeen pathologists performed PD-L1 immunoscoring on 50 resected NSCLC tumors in three categories (<1%;1–49%;≥50%). Also, the pathologists completed a certified personality test (NEO-PI-r), assessing five personality traits: neuroticism, extraversion, openness, altruism and conscientiousness. Results: The overall agreement among pathologists for a series of 47 tumors was substantial (kappa = 0.63). Of these, 23/47 (49%) tumors were entirely negative or largely positive, resulting in a kappa value of 0.93. The remaining 24/47 (51%) tumors had a PD-L1 score around the cutoff value, generating a kappa value of 0.32. Pathologists with high scores for conscientiousness (careful, diligent) had the least interobserver variability (r = 0.6, p = 0.009). Also, they showed a trend towards higher sensitivity (74% vs. 68%, p = 0.4), specificity (86% vs. 82%, p = 0.3) and percent agreement (83% vs. 79%, p = 0.3), although not significant. In contrast, pathologists with high scores for neuroticism (sensitive, anxious) had significantly lower specificity (80% vs. 87%, p = 0.03) and percent agreement (78% vs. 85%, p = 0.03). Also, a trend towards high interobserver variability (r = -0.3, p = 0.2) and lower sensitivity (68% vs. 74%, p = 0.3) was observed, although not significant. Pathologists with relatively high scores for conscientiousness scored fewer tumors PD-L1 positive at the ≥ 1% cut-off (r = −0.5, p = 0.03). In contrast, pathologists with relatively high scores for neuroticism score more tumors PD-L1 positive at ≥ 1% (r = 0.6, p = 0.017) and ≥ 50% cut-offs (r = 0.6, p = 0.009).

Introduction: With the approval of first-line osimertinib treatment in stage IV EGFR-mutated NSCLC, detection of resistance mechanisms will become increasingly important—and complex. Clear guidelines for analyses of these resistance mechanisms are currently lacking. Here, we provide our recommendations for optimal molecular diagnostics in the post-EGFR tyrosine kinase inhibitor (TKI) resistance setting. Methods: We compared molecular workup strategies from three hospitals of 161 first- or second-generation EGFR TKI–treated cases and 159 osimertinib-treated cases. Laboratories used combinations of DNA next-generation sequencing (NGS), RNA NGS, in situ hybridization (ISH), and immunohistochemistry (IHC). Results: Resistance mechanisms were identified in 72 first-generation TKI cases (51%) and 85 osimertinib cases (57%). RNA NGS, when performed, revealed fusions or exon-skipping events in 4% of early TKI cases and 10% of osimertinib cases. Of the 30 MET and HER2 amplifications, 10 were exclusively detected by ISH or IHC, and not detected by DNA NGS, mostly owing to low tumor cell percentage (<30%) and possibly tumor heterogeneity. Conclusions: Our real-world data support a method for molecular diagnostics, consisting of a parallel combination of DNA NGS, RNA NGS, MET ISH, and either HER2 ISH or IHC. Combining RNA and DNA isolation into one step limits dropout rates. In case of financial or tissue limitations, a sequential approach is justifiable, in which RNA NGS is only performed in case no resistance mechanisms are identified. Yet, this is suboptimal as—although rare—multiple acquired resistance mechanisms may occur.