Conventional and semi-automatic histopathological analysis of tumor cell content for multigene sequencing of lung adenocarcinoma

Concordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathology

The incorporation of digital pathology in clinical practice will require the training of pathologists in digital skills. Our study aimed to assess the reliability among pathologists in determining tumor percentage in whole slide images (WSI) of non-small cell lung cancer (NSCLC) using digital image analysis, and study how the results correlate with the molecular findings. Pathologists from nine centers were trained to quantify epithelial tumor cells, tumor-associated stromal cells, and non-neoplastic cells from NSCLC WSI using QuPath. Then, we conducted two consecutive ring trials. In the first trial, analyzing four WSI, reliability between pathologists in the assessment of tumor cell percentage was poor (intraclass correlation coefficient (ICC) 0.09). After performing the first ring trial pathologists received feedback. The second trial, comprising 10 WSI with paired next-generation sequencing results, also showed poor reliability (ICC 0.24). Cases near the recommended 20% visual threshold for molecular techniques exhibited higher values with digital analysis. In the second ring trial reliability slightly improved and human errors were reduced from 5.6% to 1.25%. Most discrepancies arose from subjective tasks, such as the annotation process, suggesting potential improvement with future artificial intelligence solutions.

Digital counting of tissue cells for molecular analysis: the QuANTUM pipeline

The estimation of tumor cellular fraction (TCF) is a crucial step in predictive molecular pathology, representing an entry adequacy criterion also in the next-generation sequencing (NGS) era. However, heterogeneity of quantification practices and inter-pathologist variability hamper the robustness of its evaluation, stressing the need for more reliable results. Here, 121 routine histological samples from non-small cell lung cancer (NSCLC) cases with complete NGS profiling were used to evaluate TCF interobserver variability among three different pathologists (pTCF), developing a computational tool (cTCF) and assessing its reliability vs ground truth (GT) tumor cellularity and potential impact on the final molecular results. Inter-pathologist reproducibility was fair to good, with overall Wk ranging between 0.46 and 0.83 (avg. 0.59). The obtained cTCF was comparable to the GT (p = 0.129, 0.502, and 0.130 for surgical, biopsies, and cell block, respectively) and demonstrated good reliability if elaborated by different pathologists (Wk = 0.9). Overall cTCF was lower as compared to pTCF (30 ± 10 vs 52 ± 19, p < 0.001), with more cases < 20% (17, 14%, p = 0.690), but none containing < 100 cells for the algorithm. Similarities were noted between tumor area estimation and pTCF (36 ± 29, p < 0.001), partly explaining variability in the human assessment of tumor cellularity. Finally, the cTCF allowed a reduction of the copy number variations (CNVs) called (27 vs 29, - 6.9%) with an increase of effective CNVs detection (13 vs 7, + 85.7%), some with potential clinical impact previously undetected with pTCF. An automated computational pipeline (Qupath Analysis of Nuclei from Tumor to Uniform Molecular tests, QuANTUM) has been created and is freely available as a QuPath extension. The computational method used in this study has the potential to improve efficacy and reliability of TCF estimation in NSCLC, with demonstrated impact on the final molecular results.

Current challenges and practical aspects of molecular pathology for non-small cell lung cancers

The continuing evolution of treatment options in thoracic oncology requires the pathologist to regularly update diagnostic algorithms for management of tumor samples. It is essential to decide on the best way to use tissue biopsies, cytological samples, as well as liquid biopsies to identify the different mandatory predictive biomarkers of lung cancers in a short turnaround time. However, biological resources and laboratory member workforce are limited and may be not sufficient for the increased complexity of molecular pathological analyses and for complementary translational research development. In this context, the surgical pathologist is the only one who makes the decisions whether or not to send specimens to immunohistochemical and molecular pathology platforms. Moreover, the pathologist can rapidly contact the oncologist to obtain a new tissue biopsy and/or a liquid biopsy if he/she considers that the biological material is not sufficient in quantity or quality for assessment of predictive biomarkers. Inadequate control of algorithms and sampling workflow may lead to false negative, inconclusive, and incomplete findings, resulting in inappropriate choice of therapeutic strategy and potentially poor outcome for patients. International guidelines for lung cancer treatment are based on the results of the expression of different proteins and on genomic alterations. These guidelines have been established taking into consideration the best practices to be set up in clinical and molecular pathology laboratories. This review addresses the current predictive biomarkers and algorithms for use in thoracic oncology molecular pathology as well as the central role of the pathologist, notably in the molecular tumor board and her/his participation in the treatment decision-making. The perspectives in this setting will be discussed.

Pathologist Computer-Aided Diagnostic Scoring of Tumor Cell Fraction: A Swiss National Study

Tumor cell fraction (TCF) estimation is a common clinical task with well-established large interobserver variability. It thus provides an ideal test bed to evaluate potential impacts of employing a tumor cell fraction computer-aided diagnostic (TCFCAD) tool to support pathologists' evaluation. During a National Slide Seminar event, pathologists (n = 69) were asked to visually estimate TCF in 10 regions of interest (ROIs) from hematoxylin and eosin colorectal cancer images intentionally curated for diverse tissue compositions, cellularity, and stain intensities. Next, they re-evaluated the same ROIs while being provided a TCFCAD-created overlay highlighting predicted tumor vs nontumor cells, together with the corresponding TCF percentage. Participants also reported confidence levels in their assessments using a 5-tier scale, indicating no confidence to high confidence, respectively. The TCF ground truth (GT) was defined by manual cell-counting by experts. When assisted, interobserver variability significantly decreased, showing estimates converging to the GT. This improvement remained even when TCFCAD predictions deviated slightly from the GT. The standard deviation (SD) of the estimated TCF to the GT across ROIs was 9.9% vs 5.8% with TCFCAD (P < .0001). The intraclass correlation coefficient increased from 0.8 to 0.93 (95% CI, 0.65-0.93 vs 0.86-0.98), and pathologists stated feeling more confident when aided (3.67 ± 0.81 vs 4.17 ± 0.82 with the computer-aided diagnostic [CAD] tool). TCFCAD estimation support demonstrated improved scoring accuracy, interpathologist agreement, and scoring confidence. Interestingly, pathologists also expressed more willingness to use such a CAD tool at the end of the survey, highlighting the importance of training/education to increase adoption of CAD systems.

Accurate tumor purity determination is critical for the analysis of homologous recombination deficiency (HRD)

Homologous recombination deficiency (HRD) is a predictive marker for response to poly (ADP-ribose) polymerase inhibitors (PARPi) in ovarian carcinoma. HRD scores have entered routine diagnostics, but the influence of algorithms, parameters and confounders has not been analyzed comprehensively. A series of 100 poorly differentiated ovarian carcinoma samples was analyzed using whole exome sequencing (WES) and genotyping. Tumor purity was determined using conventional pathology, digital pathology, and two bioinformatic methods. HRD scores were calculated from copy number profiles determined by Sequenza and by Sclust either with or without fixed tumor purity. Tumor purity determination by digital pathology combined with a tumory purity informed variant of Sequenza served as reference method for HRD scoring. Seven tumors had deleterious mutations in BRCA1/2, 12 tumors had deleterious mutations in other homologous recombination repair (HRR) genes, 18 tumors had variants of unknown significance (VUS) in BRCA1/2 or other HRR genes, while the remaining 63 tumors had no relevant alterations. Using the reference method for HRD scoring, 68 tumors were HRD-positive. HRDsum determined by WES correlated strongly with HRDsum determined by single nucleotide polymorphism (SNP) arrays (R = 0.85). Conventional pathology systematically overestimated tumor purity by 8% compared to digital pathology. All investigated methods agreed on classifying the deleterious BRCA1/2-mutated tumors as HRD-positive, but discrepancies were observed for some of the remaining tumors. Discordant HRD classification of 11% of the tumors was observed comparing the tumor purity uninformed default of Sequenza and the reference method. In conclusion, tumor purity is a critical factor for the determination of HRD scores. Assistance by digital pathology helps to improve accuracy and imprecision of its estimation.

The Swin-Transformer network based on focal loss is used to identify images of pathological subtypes of lung adenocarcinoma with high similarity and class imbalance

PURPOSE

The classification of primary lung adenocarcinoma is complex and varied. Different subtypes of lung adenocarcinoma have different treatment methods and different prognosis. In this study, we collected 11 datasets comprising subtypes of lung cancer and proposed FL-STNet model to provide the assistance for improving clinical problems of pathologic classification in primary adenocarcinoma of lung.

METHODS

Samples were collected from 360 patients diagnosed with lung adenocarcinoma and other subtypes of lung diseases. In addition, an auxiliary diagnosis algorithm based on Swin-Transformer, which used Focal Loss for function in training, was developed. Meanwhile, the diagnostic accuracy of the Swin-Transformer was compared to pathologists.

RESULTS

The Swin-Transformer captures not only information in the overall tissue structure but also the local tissue details in the images of lung cancer pathology. Furthermore, training FL-STNet with the Focal Loss function can further balance the difference in the amount of data between different subtypes, improving recognition accuracy. The average classification accuracy, F1, and AUC of the proposed FL-STNet reached 85.71%, 86.57%, and 0.9903. The average accuracy of the FL-STNet was higher by 17% and 34%, respectively, than in the senior pathologist and junior pathologist group.

CONCLUSION

The first deep learning based on an 11-category classifier was developed for classifying lung adenocarcinoma subtypes based on WSI histopathology. Aiming at the deficiencies of the current CNN and Vit, FL-STNet model is proposed in this study by introducing Focal Loss and combining the advantages of Swin-Transformer model.

Quantitative Evaluation of Inflammatory Markers in Peri-Implantitis and Periodontitis Tissues: Digital vs. Manual Analysis—A Proof of Concept Study

Background and Objectives: In dentistry, the assessment of the histomorphometric features of periodontal (PD) and peri-implant (PI) lesions is important to evaluate their underlying pathogenic mechanism. The present study aimed to compare manual and digital methods of analysis in the evaluation of the inflammatory biomarkers in PI and PD lesions. Materials and Methods: PD and PI inflamed soft tissues were excised and processed for histological and immunohistochemical analyses for CD3+, CD4+, CD8+, CD15+, CD20+, CD68+, and CD138+. The obtained slides were acquired using a digital scanner. For each marker, 4 pictures per sample were extracted and the area fraction of the stained tissue was computed both manually using a 594-point counting grid (MC) and digitally using a dedicated image analysis software (DC). To assess the concordance between MC and DC, two blinded observers analysed a total of 200 pictures either with good quality of staining or with non-specific background noise. The inter and intraobserver concordance was evaluated using the intraclass coefficient and the agreement between MC and DC was assessed using the Bland–Altman plot. The time spent analysing each picture using the two methodologies by both observers was recorded. Further, the amount of each marker was compared between PI and PD with both methodologies. Results: The inter- and intraobserver concordance was excellent, except for images with background noise analysed using DC. MC and DC showed a satisfying concordance. DC was performed in half the time compared to MC. The morphological analysis showed a larger inflammatory infiltrate in PI than PD lesions. The comparison between PI and PD showed differences for CD68+ and CD138+ expression. Conclusions: DC could be used as a reliable and time-saving procedure for the immunohistochemical analysis of PD and PI soft tissues. When non-specific background noise is present, the experience of the pathologist may be still required.

Biomarkers of response to checkpoint inhibitors beyond PD-L1 in lung cancer

Immunotherapy, including use of checkpoint inhibitors against PD-1, PD-L1, and CTLA-4, forms the backbone of oncologic management for the majority of non-small cell lung carcinoma patients. However, response to these therapies varies widely, from patients who have complete resolution of metastatic disease and long-term remission, to those who rapidly progress and succumb to their cancer despite use of the newest checkpoint inhibitors. While PD-L1 protein expression by immunohistochemistry serves as the principle predictive biomarker for immunotherapy response, neither the sensitivity nor the specificity of this approach is optimal, and clinical PD-L1 testing is plagued by concerns around result reproducibility and confusion born from the proliferation of different companion diagnostic assays. At the same time, insights into tumor and host immune-specific factors that inform both prognosis and response prediction are beginning to define better immunotherapy biomarkers. Beyond immune checkpoint expression status, common themes in analyses of immunotherapy response prediction include cancer neoantigen production, the state of the antigen presentation pathway in both tumor and antigen presenting cells, the admixture of effector and suppressor immune cells in the tumor microenvironment, and the genomic drivers and comutations that can influence the all of these variables. This review will address the state of PD-L1 testing in lung cancer, the role for tumor mutation burden as a predictive biomarker, the evolving status of human leukocyte antigen/major histocompatibility complex expression as a marker of antigen presentation, approaches to tumor immune cell quantitation including by multiplex immunofluorescence, and the importance of tumor genomic profiling to ascertain oncogenic driver (EGFR, ALK, KRAS, MET, etc.) and co-mutation (STK11, KEAP1, SMARCA4) status.