Fast-Track Development and Multi-Institutional Clinical Validation of an Artificial Intelligence Algorithm for Detection of Lymph Node Metastasis in Colorectal Cancer.

Lymph node metastasis (LNM) detection can be automated using artificial intelligence (AI)-based diagnostic tools. Only limited studies have addressed this task for colorectal cancer (CRC). This study aimed to develop of a clinical-grade digital pathology tool for LNM detection in CRC using the original fast-track framework. The training cohort included 432 slides from one department. A segmentation algorithm detecting 8 relevant tissue classes was trained. The test cohorts consisted of materials from 5 pathology departments digitized by 4 different scanning systems. A high-quality, large training data set was generated within 7 days and a minimal amount of annotation work using fast-track principles. The AI tool showed very high accuracy for LNM detection in all cohorts, with sensitivity, negative predictive value, and specificity ranges of 0.980 to 1.000, 0.997 to 1.000, and 0.913 to 0.990, correspondingly. Only 5 of 14,460 analyzed test slides with tumor cells over all cohorts were classified as false negative (3/5 representing clusters of tumor cells in lymphatic vessels). A clinical-grade tool was trained in a short time using fast-track development principles and validated using the largest international, multi-institutional, multiscanner cohort of cases to date, showing very high precision for LNM detection in CRC. We are releasing a part of the test data sets to facilitate academic research.

Standardized Classification of Lung Adenocarcinoma Subtypes and Improvement of Grading Assessment Through Deep Learning.

The histopathologic distinction of lung adenocarcinoma (LADC) subtypes is subject to high interobserver variability, which can compromise the optimal assessment of patient prognosis. Therefore, this study developed convolutional neural networks capable of distinguishing LADC subtypes and predicting disease-specific survival, according to the recently established LADC tumor grades. Consensus LADC histopathologic images were obtained from 17 expert pulmonary pathologists and one pathologist in training. Two deep learning models (AI-1 and AI-2) were trained to predict eight different LADC classes. Furthermore, the trained models were tested on an independent cohort of 133 patients. The models achieved high precision, recall, and F1 scores exceeding 0.90 for most of the LADC classes. Clear stratification of the three LADC grades was reached in predicting the disease-specific survival by the two models, with both Kaplan-Meier curves showing significance (P = 0.0017 and 0.0003). Moreover, both trained models showed high stability in the segmentation of each pair of predicted grades with low variation in the hazard ratio across 200 bootstrapped samples. These findings indicate that the trained convolutional neural networks improve the diagnostic accuracy of the pathologist and refine LADC grade assessment. Thus, the trained models are promising tools that may assist in the routine evaluation of LADC subtypes and grades in clinical practice.

Presence of focal usual interstitial pneumonia is a key prognostic factor in progressive pulmonary fibrosis.

AIMS: Progressive pulmonary fibrosis (PPF) is a newly recognised clinical phenotype of interstitial lung diseases in the 2022 interstitial pulmonary fibrosis (IPF) guidelines. This category is based entirely on clinical and radiological factors, and the background histopathology is unknown. Our objective was to investigate the histopathological characteristics of PPF and to examine the correlation between usual interstitial pneumonia (UIP) and prognosis in this new disease type. We hypothesised that the presence of UIP-like fibrosis predicts patients' survival in PPF cases. METHODS AND RESULTS: We selected 201 cases fulfilling the clinical criteria of PPF from case archives. Cases diagnosed as IPF by a multidisciplinary team were excluded. Whole slide images were evaluated by three pathologists who were blinded to clinical and radiological data. We measured areas of UIP-like fibrosis and calculated what percentage of the total lesion area they occupied. The presence of focal UIP-like fibrosis amounting to 10% or more of the lesion area was seen in 148 (73.6%), 168 (83.6%) and 165 (82.1%) cases for each pathologist, respectively. Agreement of the recognition of UIP-like fibrosis in PPF cases was above κ = 0.6 between all pairs. Survival analysis showed that the presence of focal UIP-like fibrosis correlated with worsened survival under all parameters tested (P < 0.001). CONCLUSIONS: The presence of UIP-like fibrosis is a core pathological feature of clinical PPF, and its presence within diseased areas is associated with poorer prognosis. This study highlights the importance of considering the presence of focal UIP-like fibrosis in the evaluation and management of PPF.

Artificial Intelligence and Lung Pathology.

This manuscript provides a comprehensive overview of the application of artificial intelligence (AI) in lung pathology, particularly in the diagnosis of lung cancer. It discusses various AI models designed to support pathologists and clinicians. AI models supporting pathologists are to standardize diagnosis, score PD-L1 status, supporting tumor cellularity count, and indicating explainability for pathologic judgements. Several models predict outcomes beyond pathologic diagnosis and predict clinical outcomes like patients' survival and molecular alterations. The manuscript emphasizes the potential of AI to enhance accuracy and efficiency in pathology, while also addressing the challenges and future directions for integrating AI into clinical practice.

Real-World Implementation of Digital Pathology: Results From an Intercontinental Survey.

The past 70 years have been characterized by rapid advancements in computer technology, and the health care system has not been immune to this trend. However, anatomical pathology has remained largely an analog discipline. In recent years, this has been changing with the growing adoption of digital pathology, partly driven by the potential of computer-aided diagnosis. As part of an international collaboration, we conducted a comprehensive survey to gain a deeper understanding of the status of digital pathology implementation in Europe and Asia. A total of 127 anatomical pathology laboratories participated in the survey, including 75 from Europe and 52 from Asia, with 72 laboratories having established digital pathology workflow and 55 without digital pathology. Laboratories using digital pathology for diagnostic (n = 29) and nondiagnostic (n = 43) purposes were thoroughly questioned about their implementation strategies and institutional experiences, including details on equipment, storage, integration with laboratory information system, computer-aided diagnosis, and the costs of going digital. The impact of the digital pathology workflow was also evaluated, focusing on turnaround time, specimen traceability, quality control, and overall satisfaction. Laboratories without access to digital pathology were asked to provide insights into their perceptions of the technology, expectations, barriers to adoption, and potential facilitators. Our findings indicate that although digital pathology is still the future for many, it is already the present for some. This decade may be a time when anatomical pathology finally embraces digital revolution on a larger scale.

Artificial Intelligence-Based Tool for Tumor Detection and Quantitative Tissue Analysis in Colorectal Specimens.

Digital pathology adoption allows for applying computational algorithms to routine pathology tasks. Our study aimed to develop a clinical-grade artificial intelligence (AI) tool for precise multiclass tissue segmentation in colorectal specimens (resections and biopsies) and clinically validate the tool for tumor detection in biopsy specimens. The training data set included 241 precisely manually annotated whole-slide images (WSIs) from multiple institutions. The algorithm was trained for semantic segmentation of 11 tissue classes with an additional module for biopsy WSI classification. Six case cohorts from 5 pathology departments (4 countries) were used for formal and clinical validation, digitized by 4 different scanning systems. The developed algorithm showed high precision of segmentation of different tissue classes in colorectal specimens with composite multiclass Dice score of up to 0.895 and pixel-wise tumor detection specificity and sensitivity of up to 0.958 and 0.987, respectively. In the clinical validation study on multiple external cohorts, the AI tool reached sensitivity of 1.0 and specificity of up to 0.969 for tumor detection in biopsy WSI. The AI tool analyzes most biopsy cases in less than 1 minute, allowing effective integration into clinical routine. We developed and extensively validated a highly accurate, clinical-grade tool for assistive diagnostic processing of colorectal specimens. This tool allows for quantitative deciphering of colorectal cancer tissue for development of prognostic and predictive biomarkers and personalization of oncologic care. This study is a foundation for a SemiCOL computational challenge. We open-source multiple manually annotated and weakly labeled test data sets, representing a significant contribution to the colorectal cancer computational pathology field.

Pathomic Features Reveal Immune and Molecular Evolution From Lung Preneoplasia to Invasive Adenocarcinoma.

Recent statistics on lung cancer, including the steady decline of advanced diseases and the dramatically increasing detection of early-stage diseases and indeterminate pulmonary nodules, mark the significance of a comprehensive understanding of early lung carcinogenesis. Lung adenocarcinoma (ADC) is the most common histologic subtype of lung cancer, and atypical adenomatous hyperplasia is the only recognized preneoplasia to ADC, which may progress to adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) and eventually to invasive ADC. Although molecular evolution during early lung carcinogenesis has been explored in recent years, the progress has been significantly hindered, largely due to insufficient materials from ADC precursors. Here, we employed state-of-the-art deep learning and artificial intelligence techniques to robustly segment and recognize cells on routinely used hematoxylin and eosin histopathology images and extracted 9 biology-relevant pathomic features to decode lung preneoplasia evolution. We analyzed 3 distinct cohorts (Japan, China, and United States) covering 98 patients, 162 slides, and 669 regions of interest, including 143 normal, 129 atypical adenomatous hyperplasia, 94 AIS, 98 MIA, and 205 ADC. Extracted pathomic features revealed progressive increase of atypical epithelial cells and progressive decrease of lymphocytic cells from normal to AAH, AIS, MIA, and ADC, consistent with the results from tissue-consuming and expensive molecular/immune profiling. Furthermore, pathomics analysis manifested progressively increasing cellular intratumor heterogeneity along with the evolution from normal lung to invasive ADC. These findings demonstrated the feasibility and substantial potential of pathomics in studying lung cancer carcinogenesis directly from the low-cost routine hematoxylin and eosin staining.

Analysis of Immune Intratumor Heterogeneity Highlights Immunoregulatory and Coinhibitory Lymphocytes as Hallmarks of Recurrence in Stage I Non-Small Cell Lung Cancer.

Our understanding of the molecular mechanisms underlying postsurgical recurrence of non-small cell lung cancer (NSCLC) is rudimentary. Molecular and T cell repertoire intratumor heterogeneity (ITH) have been reported to be associated with postsurgical relapse; however, how ITH at the cellular level impacts survival is largely unknown. Here we report the analysis of 2880 multispectral images representing 14.2% to 27% of tumor areas from 33 patients with stage I NSCLC, including 17 cases (relapsed within 3 years after surgery) and 16 controls (without recurrence ≥5 years after surgery) using multiplex immunofluorescence. Spatial analysis was conducted to quantify the minimum distance between different cell types and immune cell infiltration around malignant cells. Immune ITH was defined as the variance of immune cells from 3 intratumor regions. We found that tumors from patients having relapsed display different immune biology compared with nonrecurrent tumors, with a higher percentage of tumor cells and macrophages expressing PD-L1 (P =.031 and P =.024, respectively), along with an increase in regulatory T cells (Treg) (P =.018), antigen-experienced T cells (P =.025), and effector-memory T cells (P =.041). Spatial analysis revealed that a higher level of infiltration of PD-L1+ macrophages (CD68+PD-L1+) or antigen-experienced cytotoxic T cells (CD3+CD8+PD-1+) in the tumor was associated with poor overall survival (P =.021 and P =.006, respectively). A higher degree of Treg ITH was associated with inferior recurrence-free survival regardless of tumor mutational burden (P =.022), neoantigen burden (P =.021), genomic ITH (P =.012) and T cell repertoire ITH (P =.001). Using multiregion multiplex immunofluorescence, we characterized ITH at the immune cell level along with whole exome and T cell repertoire sequencing from the same tumor regions. This approach highlights the role of immunoregulatory and coinhibitory signals as well as their spatial distribution and ITH that define the hallmarks of tumor relapse of stage I NSCLC.

Enhanced immune complex formation in the lungs of patients with dermatomyositis.

BACKGROUND: Interstitial lung disease is frequently comorbid with dermatomyositis and has a poor prognosis, especially in patients with the anti-melanoma differentiation-associated gene 5 (MDA5) autoantibody. However, the pathogenesis of dermatomyositis-related interstitial lung disease remains unclear. METHODS: We examined 18 and 19 patients with dermatomyositis-related interstitial lung disease and idiopathic pulmonary fibrosis (control), respectively. Lung tissues obtained from these patients were semi-quantitatively evaluated by immunohistochemical staining with in-house anti-human MDA5 monoclonal antibodies, as well as anti-human immunoglobulin (Ig) G, IgM, IgA, and complement component 3(C3) antibodies. We established human MDA5 transgenic mice and treated them with rabbit anti-human MDA5 polyclonal antibodies, and evaluated lung injury and Ig and C3 expression. RESULTS: MDA5 was moderately or strongly expressed in the lungs of patients in both groups, with no significant differences between the groups. However, patients with dermatomyositis-related interstitial lung disease showed significantly stronger expression of C3 (p < 0.001), IgG (p < 0.001), and IgM (p = 0.001) in the lungs than control. Moreover, lung C3, but IgG, IgA, nor IgM expression was significantly stronger in MDA5 autoantibody-positive dermatomyositis-related interstitial lung disease (n = 9) than in MDA5 autoantibody-negative dermatomyositis-related interstitial lung disease (n = 9; p = 0.022). Treatment with anti-MDA5 antibodies induced lung injury in MDA5 transgenic mice, and strong immunoglobulin and C3 expression was observed in the lungs of the mice. CONCLUSION: Strong immunoglobulin and C3 expression in the lungs involve lung injury related to dermatomyositis-related interstitial lung disease. Enhanced immune complex formation in the lungs may contribute to the poor prognosis of MDA5 autoantibody-positive dermatomyositis-related interstitial lung disease.

Frequency of subclinical interstitial lung disease in COVID-19 autopsy cases: potential risk factors of severe pneumonia.

Risk factors of severe coronavirus disease 2019 (COVID-19) have been previously reported; however, histological risk factors have not been defined thus far. The aim of this study was to clarify subclinical hidden interstitial lung disease (ILD) as a risk factor of severe pneumonia associated with COVID-19. We carefully examined autopsied lungs and chest computed tomography scanning (CT) images from patients with COVID-19 for interstitial lesions and then analyzed their relationship with disease severity. Among the autopsy series, subclinical ILD was found in 13/27 cases (48%) in the COVID-19 group, and in contrast, 8/65 (12%) in the control autopsy group (p = 0.0006; Fisher's exact test). We reviewed CT images from the COVID-19 autopsy cases and verified that subclinical ILD was histologically detectable in the CT images. Then, we retrospectively examined CT images from another series of COVID-19 cases in the Yokohama, Japan area between February-August 2020 for interstitial lesions and analyzed the relationship to the severity of COVID-19 pneumonia. Interstitial lesion was more frequently found in the group with the moderate II/severe disease than in the moderate I/mild disease (severity was evaluated according to the COVID-19 severity classification system of the Ministry of Health, Labor, and Welfare [Japan]) (moderate II/severe, 11/15, 73.3% versus moderate I/mild, 108/245, 44.1%; Fisher exact test, p = 0.0333). In conclusion, it was suggested that subclinical ILD could be an important risk factor for severe COVID-19 pneumonia. A benefit of these findings could be the development of a risk assessment system using high resolution CT images for fatal COVID-19 pneumonia.

MIXTURE of human expertise and deep learning-developing an explainable model for predicting pathological diagnosis and survival in patients with interstitial lung disease.

Interstitial pneumonia is a heterogeneous disease with a progressive course and poor prognosis, at times even worse than those in the main cancer types. Histopathological examination is crucial for its diagnosis and estimation of prognosis. However, the evaluation strongly depends on the experience of pathologists, and the reproducibility of diagnosis is low. Herein, we propose MIXTURE (huMan-In-the-loop eXplainable artificial intelligence Through the Use of REcurrent training), an original method to develop deep learning models for extracting pathologically significant findings based on an expert pathologist's perspective with a small annotation effort. The procedure of MIXTURE consists of three steps as follows. First, we created feature extractors for tiles from whole slide images using self-supervised learning. The similar looking tiles were clustered based on the output features and then pathologists integrated the pathologically synonymous clusters. Using the integrated clusters as labeled data, deep learning models to classify the tiles into pathological findings were created by transfer-learning the feature extractors. We developed three models for different magnifications. Using these extracted findings, our model was able to predict the diagnosis of usual interstitial pneumonia, a finding suggestive of progressive disease, with high accuracy (AUC 0.90 in validation set and AUC 0.86 in test set). This high accuracy could not be achieved without the integration of findings by pathologists. The patients predicted as UIP had poorer prognosis (5-year overall survival [OS]: 55.4%) than those predicted as non-UIP (OS: 95.2%). The Cox proportional hazards model for each microscopic finding and prognosis pointed out dense fibrosis, fibroblastic foci, elastosis, and lymphocyte aggregation as independent risk factors. We suggest that MIXTURE may serve as a model approach to different diseases evaluated by medical imaging, including pathology and radiology, and be the prototype for explainable artificial intelligence that can collaborate with humans.

A collaborative workflow between pathologists and deep learning for the evaluation of tumour cellularity in lung adenocarcinoma.

AIMS: The reporting of tumour cellularity in cancer samples has become a mandatory task for pathologists. However, the estimation of tumour cellularity is often inaccurate. Therefore, we propose a collaborative workflow between pathologists and artificial intelligence (AI) models to evaluate tumour cellularity in lung cancer samples and propose a protocol to apply it to routine practice. METHODS AND RESULTS: We developed a quantitative model of lung adenocarcinoma that was validated and tested on 50 cases, and a collaborative workflow where pathologists could access the AI results and adjust their original tumour cellularity scores (adjusted-score) that we tested on 151 cases. The adjusted-score was validated by comparing them with a ground truth established by manual annotation of haematoxylin and eosin slides with reference to immunostains with thyroid transcription factor-1 and napsin A. For training, validation, testing the AI and testing the collaborative workflow, we used 40, 10, 50 and 151 whole slide images of lung adenocarcinoma, respectively. The sensitivity and specificity of tumour segmentation were 97 and 87%, respectively, and the accuracy of nuclei recognition was 99%. One pathologist's visually estimated scores were compared to the adjusted-score, and the pathologist's scores were altered in 87% of cases. Comparison with the ground truth revealed that the adjusted-score was more precise than the pathologists' scores (P < 0.05). CONCLUSION: We proposed a collaborative workflow between AI and pathologists as a model to improve daily practice and enhance the prediction of tumour cellularity for genetic tests.

Cicatricial organising pneumonia associated with fibrosing interstitial pneumonia - a clinicopathological study.

AIMS: The recent recognition of cicatricial organising pneumonia (ciOP) indicates that the ciOP may resemble or simulate fibrotic interstitial pneumonia; however, there has been great uncertainty regarding the affected populations, pathogenesis, clinical relevance and characteristics. In this study, we compared the characteristics of fibrotic interstitial pneumonia with and without ciOP. METHODS AND RESULTS: We enrolled 121 patients from the consultation archive whose pathological findings were fibrotic interstitial pneumonia and for whom follow-up clinical data were available. We reviewed these cases histopathologically and classified them according to whether or not they showed ciOP. We compared the clinicopathological features between the two groups. CiOP, histopathologically characterised by deposition of dense collagenous fibres within the alveolar space without destruction of the lung structure, was found in 48 patients (39.7%). None of the cases with ciOP experienced acute exacerbation during 12 months' follow-up. The group with ciOP had more severe diffusion impairment but this, together with restrictive ventilatory impairment, improved significantly compared to the group without ciOP. CONCLUSION: CiOP is a histopathological finding commonly found in fibrotic interstitial pneumonia. It does not relate to acute exacerbation or decrease in pulmonary function.

A comprehensible machine learning tool to differentially diagnose idiopathic pulmonary fibrosis from other chronic interstitial lung diseases.

BACKGROUND AND OBJECTIVE: Idiopathic pulmonary fibrosis (IPF) has poor prognosis, and the multidisciplinary diagnostic agreement is low. Moreover, surgical lung biopsies pose comorbidity risks. Therefore, using data from non-invasive tests usually employed to assess interstitial lung diseases (ILDs), we aimed to develop an automated algorithm combining deep learning and machine learning that would be capable of detecting and differentiating IPF from other ILDs. METHODS: We retrospectively analysed consecutive patients presenting with ILD between April 2007 and July 2017. Deep learning was used for semantic image segmentation of HRCT based on the corresponding labelled images. A diagnostic algorithm was then trained using the semantic results and non-invasive findings. Diagnostic accuracy was assessed using five-fold cross-validation. RESULTS: In total, 646,800 HRCT images and the corresponding labelled images were acquired from 1068 patients with ILD, of whom 42.7% had IPF. The average segmentation accuracy was 96.1%. The machine learning algorithm had an average diagnostic accuracy of 83.6%, with high sensitivity, specificity and kappa coefficient values (80.7%, 85.8% and 0.665, respectively). Using Cox hazard analysis, IPF diagnosed using this algorithm was a significant prognostic factor (hazard ratio, 2.593; 95% CI, 2.069-3.250; p < 0.001). Diagnostic accuracy was good even in patients with usual interstitial pneumonia patterns on HRCT and those with surgical lung biopsies. CONCLUSION: Using data from non-invasive examinations, the combined deep learning and machine learning algorithm accurately, easily and quickly diagnosed IPF in a population with various ILDs.

Prevalence and prognosis of chronic fibrosing interstitial lung diseases with a progressive phenotype.

BACKGROUND AND OBJECTIVE: The development of clinically progressive fibrosis complicates a wide array of interstitial lung diseases (ILDs). However, there are limited data regarding its prevalence and prognosis. METHODS: We analysed consecutive patients seen for initial evaluation of a fibrosing form of ILD (FILD). Patients were evaluated for evidence of progressive fibrosis over the first 24 months of follow-up. We defined a progressive phenotype as the presence of at least one of the following: a relative decline in forced vital capacity (FVC) of ≥10%; a relative decline in FVC of ≥5%-<10% with a relative decline in diffusing capacity of the lung for carbon monoxide of ≥15%, increased fibrosis on HRCT or progressive symptoms. RESULTS: Eight hundred and forty-four patients (397 with idiopathic pulmonary fibrosis [IPF] and 447 non-IPF FILD) made up the final analysis cohort. Three hundred and fifty-five patients (42.1%) met the progressive phenotype criteria (59.4% of IPF patients and 26.6% of non-IPF FILD patients, p <0.01). In both IPF and non-IPF FILD, transplantation-free survival differed between patients with a progressive phenotype and those without (p <0.01). Multivariable analysis showed that a progressive phenotype was an independent predictor of transplantation-free survival (hazard ratio [HR]: 3.36, 95% CI: 2.68-4.23, p <0.01). Transplantation-free survival did not differ between non-IPF FILD with a progressive phenotype and IPF (HR: 1.12, 95% CI: 0.85-1.48, p = 0.42). CONCLUSION: Over one-fourth of non-IPF FILD patients develop a progressive phenotype compared to approximately 60% of IPF patients. The survival of non-IPF FILD patients with a progressive phenotype is similar to IPF.

Augmented Lipocalin-2 Is Associated with Chronic Obstructive Pulmonary Disease and Counteracts Lung Adenocarcinoma Development.

Rationale: Early pathogenesis of lung adenocarcinoma (LUAD) remains largely unknown. We found that, relative to wild-type littermates, the innate immunomodulator Lcn2 (lipocalin-2) was increased in normal airways from mice with knockout of the airway lineage gene Gprc5a (Gprc5a-/-) and that are prone to developing inflammation and LUAD. Yet, the role of LCN2 in lung inflammation and LUAD is poorly understood.Objectives: Delineate the role of Lcn2 induction in LUAD pathogenesis.Methods: Normal airway brushings, uninvolved lung tissues, and tumors from Gprc5a-/- mice before and after tobacco carcinogen exposure were analyzed by RNA sequencing. LCN2 mRNA was analyzed in public and in-house data sets of LUAD, lung squamous cancer (LUSC), chronic obstructive pulmonary disease (COPD), and LUAD/LUSC with COPD. LCN2 protein was immunohistochemically analyzed in a tissue microarray of 510 tumors. Temporal lung tumor development, gene expression programs, and host immune responses were compared between Gprc5a-/- and Gprc5a-/-/Lcn2-/- littermates.Measurements and Main Results:Lcn2 was progressively elevated during LUAD development and positively correlated with proinflammatory cytokines and inflammation gene sets. LCN2 was distinctively elevated in human LUADs, but not in LUSCs, relative to normal lungs and was associated with COPD among smokers and patients with LUAD. Relative to Gprc5a-/- mice, Gprc5a-/-/Lcn2-/- littermates exhibited significantly increased lung tumor development concomitant with reduced T-cell abundance (CD4+) and richness, attenuated antitumor immune gene programs, and increased immune cell expression of protumor inflammatory cytokines.Conclusions: Augmented LCN2 expression is a molecular feature of COPD-associated LUAD and counteracts LUAD development in vivo by maintaining antitumor immunity.

CD24, not CD47, negatively impacts upon response to PD-1/L1 inhibitors in non-small-cell lung cancer with PD-L1 tumor proportion score < 50.

CD24, a heavily glycosylated glycosylphosphatidylinositol-anchored surface protein, inhibits phagocytosis as potently as CD47. The relationship between such anti-phagocytic factors and the immune response with immune-checkpoint inhibitors (ICI) remains unexplored. We evaluated CD24 and CD47 tumor proportion scores (TPS) in 68 of the 106 patients with advanced non-small-cell lung cancer who participated in a prospective observational study of ICI treatment. We also explored the impact of CD24 TPS and CD47 TPS on ICI efficacy and serum cytokine changes. CD24 positivity (TPS ≥ 1) was negatively associated with progression-free survival (PFS) of ICI when PD-L1 TPS was < 50 (median PFS; 37 vs 127 d, P = .033), but there was no association when PD-L1 TPS was ≥ 50 (median PFS; 494 vs 144 d, P = .168). CD24 positivity was also related to significantly higher increase of CCL2 from baseline to 4-6 wk later, and such increase was notably observed only when PD-L1 TPS < 50 (P = .0004). CCL2 increase after ICI initiation was negatively predictive for survival after initiation of ICI (median survival time; not reached vs 233 d; P = .028). CD47 TPS high (≥60) significantly suppressed the increase in vascular endothelial growth factor (VEGF)-A, D and PDGF-AB/BB after ICI initiation. There was no association, however, between CD47 tumor expression and the efficacy of ICI. In conclusion, CD24, not CD47, is a candidate negative predictive marker of ICI in advanced, non-small-cell lung cancer with PD-L1 TPS < 50. Tumor expression of both CD24 and CD47 was associated with changes in factors related to monocytes and angiogenesis after ICI initiation (UMIN000024414).

Quality control stress test for deep learning-based diagnostic model in digital pathology.

Digital pathology provides a possibility for computational analysis of histological slides and automatization of routine pathological tasks. Histological slides are very heterogeneous concerning staining, sections' thickness, and artifacts arising during tissue processing, cutting, staining, and digitization. In this study, we digitally reproduce major types of artifacts. Using six datasets from four different institutions digitized by different scanner systems, we systematically explore artifacts' influence on the accuracy of the pre-trained, validated, deep learning-based model for prostate cancer detection in histological slides. We provide evidence that any histological artifact dependent on severity can lead to a substantial loss in model performance. Strategies for the prevention of diagnostic model accuracy losses in the context of artifacts are warranted. Stress-testing of diagnostic models using synthetically generated artifacts might be an essential step during clinical validation of deep learning-based algorithms.

Clinicopathological significance of the expression of PD-L1 in non-small cell lung cancer.

INTRODUCTION: PD1/PD-L1 pathway targeting therapies are nowadays an established treatment option for patients with NSCLC. We assessed whether PD-L1 expression in NSCLC tumor cells was associated with specific clinical features or overall survival using four different clones. METHODS AND RESULTS: A retrospective study included formalin-fixed paraffin embedded (FFPE) surgical tumors from 482 patients. PD-L1 status was assessed with immunohistochemistry in tumor cells on tissue microarrays using clones 28-8, 22C3, SP263 and SP142. Associations with OS were assessed by Kaplan-Meier and multivariate Cox's regression analysis. Patients' median age: 68 years (39-86); histology: adenocarcinoma (AdCa) 61%, squamous-cell carcinoma (SqCC) 33%, and large cell carcinoma (LCC) 6%; p-stage: IA (46%), IB (30%), IIA (10%), IIB (11,4%), IIIA (1,2%), IIIB - IV (0,4%). PD-L1 positivity (≥1%) in NSCLC for clones 28-8, 22C3, SP263, SP142 was 41.5%, 34.2%, 42.7%, 10.4%, respectively (Pearson Chi-square p < 0.0001). PD-L1 expression was correlated with histology, tumor size and grading. Statistically significant association between PD-L1 expression and OS in NSCLC and Non-AdCa was observed with clone SP142 (log-rank p = 0.045 and p = 0.05, respectively). Statistically significant association between PD-L1 expression and OS in LCC was observed with clones 22C3 (log-rank p = 0.009) and SP263 (log-rank p = 0.050). CONCLUSIONS: Overexpression of the PD-L1 clone SP142 was associated with poor overall survival in NSCLC and Non-AdCa. Clones 22C3 and SP263 were associated with poor prognosis in LCC. PD-L1 status might serve as a prognostic marker in NSCLC.

Determining Response to Treatment for Drug-Induced Bronchocentric Granulomatosis by the Forced Oscillation Technique.

Anti-tumor necrosis factor alpha (TNFα) therapy is widely used to treat various inflammatory conditions. Paradoxically, there are several case reports describing the development of bronchocentric granulomatosis treated with TNFα inhibitors, and it is difficult to determine the effect of treatment using conventional spirometry because the lesions are located in small airways. However, it has been reported that the forced oscillation technique (FOT) is useful in the evaluation of small airway disease in bronchial asthma or chronic obstructive pulmonary disease. We performed the FOT to determine the effect of treatment on bronchocentric granulomatosis and found it to be useful. We report the case of a 55-year-old female with ulcerative colitis who was treated with golimumab and who developed bronchocentric granulomatosis as a sarcoid-like reaction to golimumab. She was successfully treated with prednisone, and the treatment efficacy was confirmed by the FOT. The FOT may be useful in the evaluation of small airway disease in bronchocentric granulomatosis. This case may help inform clinicians of the usefulness of the FOT to assess small airway disease in various diseases.