Explore the vast range of titles available.

The tumor microenvironment (TME) is associated with tumor prognosis, immunotherapy response, and prognosis in patients. Here, we hypothesized that the entire TME in pathology image is associated with the survival time prediction. To address this hypothesis, we utilize the entire TME on pathology image of early-stage lung adenocarcinoma (esLUAD), which is the most common histological subtype of lung cancer. Notably, we investigated whether machine learning models can predict individual survival time from pathology images without region-level annotation and solely based on patient-level survival data. In particular, we proposed a pathology image-based predictive model in a cascaded learning system to predict the individual survival time of esLUAD patients in two independent cohorts (National Lung Screening Trial (NLST) and Cancer Genome Atlas Program (TCGA)). Besides that, we estimate a mean absolute error (MAE) score and a C-index score that are strongly associated with the survival time prediction. Our method achieved (361.90 MAE - 0.70 C-index) and (365.67 MAE - 0.58 C-index) in early-stage NLST and early-stage TCGA cohorts, respectively. Together, the presented results highlight the importance of computation pathology algorithms in predicting survival time using the entire TME information in pathology images and support the use of computational methods to improve the efficiency of clinical trial studies.

Background Accurate classification of breast cancer molecular subtypes is crucial in determining treatment strategies and predicting clinical outcomes. This classification largely depends on the assessment of human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER), and progesterone receptor (PR) status. However, variability in interpretation among pathologists pose challenges to the accuracy of this classification. This study evaluates the role of artificial intelligence (AI) in enhancing the consistency of these evaluations. Methods AI-powered HER2 and ER/PR analyzers, consisting of cell and tissue models, were developed using 1,259 HER2, 744 ER, and 466 PR-stained immunohistochemistry (IHC) whole-slide images of breast cancer. External validation cohort comprising HER2, ER, and PR IHCs of 201 breast cancer cases were analyzed with these AI-powered analyzers. Three board-certified pathologists independently assessed these cases without AI annotation. Then, cases with differing interpretations between pathologists and the AI analyzer were revisited with AI assistance, focusing on evaluating the influence of AI assistance on the concordance among pathologists during the revised evaluation compared to the initial assessment. Results Reevaluation was required in 61 (30.3%), 42 (20.9%), and 80 (39.8%) of HER2, in 15 (7.5%), 17 (8.5%), and 11 (5.5%) of ER, and in 26 (12.9%), 24 (11.9%), and 28 (13.9%) of PR evaluations by the pathologists, respectively. Compared to initial interpretations, the assistance of AI led to a notable increase in the agreement among three pathologists on the status of HER2 (from 49.3 to 74.1%, p  < 0.001), ER (from 93.0 to 96.5%, p  = 0.096), and PR (from 84.6 to 91.5%, p  = 0.006). This improvement was especially evident in cases of HER2 2+ and 1+, where the concordance significantly increased from 46.2 to 68.4% and from 26.5 to 70.7%, respectively. Consequently, a refinement in the classification of breast cancer molecular subtypes (from 58.2 to 78.6%, p  < 0.001) was achieved with AI assistance. Conclusions This study underscores the significant role of AI analyzers in improving pathologists' concordance in the classification of breast cancer molecular subtypes.

Tumor-infiltrating lymphocytes (TILs) have been recognized as key players in the tumor microenvironment of breast cancer, but substantial interobserver variability among pathologists has impeded its utility as a biomarker. We developed a deep learning (DL)-based TIL analyzer to evaluate stromal TILs (sTILs) in breast cancer. Three pathologists evaluated 402 whole slide images of breast cancer and interpreted the sTIL scores. A standalone performance of the DL model was evaluated in the 210 cases (52.2%) exhibiting sTIL score differences of less than 10 percentage points, yielding a concordance correlation coefficient of 0.755 (95% confidence interval [CI], 0.693–0.805) in comparison to the pathologists’ scores. For the 226 slides (56.2%) showing a 10 percentage points or greater variance between pathologists and the DL model, revisions were made. The number of discordant cases was reduced to 116 (28.9%) with the DL assistance (p < 0.001). The DL assistance also increased the concordance correlation coefficient of the sTIL score among every two pathologists. In triple-negative and human epidermal growth factor receptor 2 (HER2)-positive breast cancer patients who underwent the neoadjuvant chemotherapy, the DL-assisted revision notably accentuated higher sTIL scores in responders (26.8 ± 19.6 vs. 19.0 ± 16.4, p = 0.003). Furthermore, the DL-assistant revision disclosed the correlation of sTIL-high tumors (sTIL ≥ 50) with the chemotherapeutic response (odd ratio 1.28 [95% confidence interval, 1.01–1.63], p = 0.039). Through enhancing inter-pathologist concordance in sTIL interpretation and predicting neoadjuvant chemotherapy response, here we report the utility of the DL-based tool as a reference for sTIL scoring in breast cancer assessment.

BackgroundThe inflamed immune phenotype (IIP), defined by enrichment of tumor-infiltrating lymphocytes (TILs) within intratumoral areas, is a promising tumor-agnostic biomarker of response to immune checkpoint inhibitor (ICI) therapy. However, it is challenging to define the IIP in an objective and reproducible manner during manual histopathologic examination. Here, we investigate artificial intelligence (AI)-based immune phenotypes capable of predicting ICI clinical outcomes in multiple solid tumor types.MethodsLunit SCOPE IO is a deep learning model which determines the immune phenotype of the tumor microenvironment based on TIL analysis. We evaluated the correlation between the IIP and ICI treatment outcomes in terms of objective response rates (ORR), progression-free survival (PFS), and overall survival (OS) in a cohort of 1,806 ICI-treated patients representing over 27 solid tumor types retrospectively collected from multiple institutions.ResultsWe observed an overall IIP prevalence of 35.2% and significantly more favorable ORRs (26.3% vs 15.8%), PFS (median 5.3 vs 3.1 months, HR 0.68, 95% CI 0.61 to 0.76), and OS (median 25.3 vs 13.6 months, HR 0.66, 95% CI 0.57 to 0.75) after ICI therapy in IIP compared with non-IIP patients, respectively (p<0.001 for all comparisons). On subgroup analysis, the IIP was generally prognostic of favorable PFS across major patient subgroups, with the exception of the microsatellite unstable/mismatch repair deficient subgroup.ConclusionThe AI-based IIP may represent a practical, affordable, clinically actionable, and tumor-agnostic biomarker prognostic of ICI therapy response across diverse tumor types.

Background Gynecologic malignancy is one of the leading causes of mortality in female adults worldwide. Comprehensive genomic analysis has revealed a list of molecular aberrations that are essential to tumorigenesis, progression, and metastasis of gynecologic tumors. However, targeting such alterations has frequently led to treatment failures due to underlying genomic complexity and simultaneous activation of various tumor cell survival pathway molecules. A compilation of molecular characterization of tumors with pharmacological drug response is the next step toward clinical application of patient-tailored treatment regimens. Results Toward this goal, we establish a library of 139 gynecologic tumors including epithelial ovarian cancers (EOCs), cervical, endometrial tumors, and uterine sarcomas that are genomically and/or pharmacologically annotated and explore dynamic pharmacogenomic associations against 37 molecularly targeted drugs. We discover lineage-specific drug sensitivities based on subcategorization of gynecologic tumors and identify TP53 mutation as a molecular determinant that elicits therapeutic response to poly (ADP-Ribose) polymerase (PARP) inhibitor. We further identify transcriptome expression of inhibitor of DNA biding 2 (ID2) as a potential predictive biomarker for treatment response to olaparib. Conclusions Together, our results demonstrate the potential utility of rapid drug screening combined with genomic profiling for precision treatment of gynecologic cancers.

Immunohistochemistry (IHC) is the common companion diagnostics in targeted therapies. However, quantifying protein expressions in IHC images present a significant challenge, due to variability in manual scoring and inherent subjective interpretation. Deep learning (DL) offers a promising approach to address these issues, though current models require extensive training for each cancer and IHC type, limiting the practical application. We developed a Universal IHC (UIHC) analyzer, a DL-based tool that quantifies protein expression across different cancers and IHC types. This multi-cohort trained model outperformed conventional single-cohort models in analyzing unseen IHC images (Kappa score 0.578 vs. up to 0.509) and demonstrated consistent performance across varying positive staining cutoff values. In a discovery application, the UIHC model assigned higher tumor proportion scores to MET amplification cases, but not MET exon 14 splicing or other non-small cell lung cancer cases. This UIHC model represents a novel role for DL that further advances quantitative analysis of IHC.

Although epidermal growth factor receptor (EGFR), v-Ki-ras2 Kirsten rat sarcoma viral oncogene (KRAS), and anaplastic lymphoma kinase (ALK) mutations in non-small cell lung cancer (NSCLC) were thought to be mutually exclusive, some tumors harbor concomitant mutations. Discovering a driver mutation on the basis of morphologic features and therapeutic responses with mutation analysis can be used to understand pathogenesis and predict resistance in targeted therapy. In 6,637 patients with NSCLC, 12 patients who had concomitant mutations were selected and clinicopathologic features were reviewed. Clinical characteristics included sex, age, smoking history, previous treatment, and targeted therapy with response and disease-free survival. Histologic features included dominant patterns, nuclear and cytoplasmic features. All patients were diagnosed with adenocarcinoma and had an EGFR mutation. Six patients had concomitant KRAS mutations and the other six had KRAS mutations. Five of six EGFR-KRAS mutation patients showed papillary and acinar histologic patterns with hobnail cells. Three of six received EGFR tyrosine kinase inhibitor (TKI) and showed partial response for 7-29 months. All six EGFR-ALK mutation patients showed solid or cribriform patterns and three had signet ring cells. Five of six EGFR-ALK mutation patients received EGFR TKI and/or ALK inhibitor and four showed partial response or stable disease, except for one patient who had acquired an EGFR mutation. EGFR and ALK mutations play an important role as driver mutations in double mutated NSCLC, and morphologic analysis can be used to predict treatment response.

Abstract Diaschisis has been described as functional depression distant to the lesion. A variety of neuroscientific approaches have been used to investigate the mechanisms underlying diaschisis. However, few studies have examined the pathological changes in diaschisis at ultrastructural level. Here, we used a rat model of capsular infarct that consistently produces diaschisis in ipsilesional and contralesional motor and sensory cortices. To verify the occurrence of diaschisis and monitor time-dependent changes in diaschisis, we performed longitudinal 2-deoxy-2-[18F]-fluoro-d-glucose microPET (FDG-microPET) study. We also used light and electron microscopy to identify the microscopic and ultrastructural changes at the diaschisis site at 7, 14, and 21 days after capsular infarct modeling (CIM). FDG-microPET showed the occurrence of diaschisis after CIM. Light microscopic examinations revealed no significant histopathological changes at the diaschisis site except a mild degree of reactive astrogliosis. However, electron microscopy revealed swollen, hydropic degeneration of axial dendrites and axodendritic synapses, although the neuronal soma (including nuclear chromatin and cytoplasmic organelles) and myelinated axons were relatively well preserved up to 21 days after injury. Furthermore, number of axodendritic synapses was significantly decreased after CIM. These data indicate that a circumscribed subcortical white-matter lesion produces ultrastructural pathological changes related to the pathogenesis of diaschisis.

Cytologic diagnosis of nuclear protein in testis (NUT) midline carcinoma (NMC) is important due to its aggressive behavior and miserable prognosis. Early diagnosis of NMC can facilitate proper management, and here we report two rare cases of thoracic NMC with cytohistologic correlation. In aspiration cytology, the tumor presented with mixed cohesive clusters and dispersed single cells, diffuse background necrosis and many neutrophils. Most of the tumor cells had scanty cytoplasm and medium-sized irregular nuclei, which had fine to granular nuclear chromatin. Interestingly, a few dyskeratotic cells or squamoid cell clusters were present in each case. Biopsy specimen histology revealed more frequent squamous differentiation, and additional immunohistochemistry tests showed nuclear expression of NUT. Because this tumor has a notorious progression and has been previously underestimated in terms of its prevalence, awareness of characteristic findings and proper ancillary tests should be considered in all suspicious cases.

BackgroundThe tumor microenvironment has recently become important in cancer and immune phenotype (IP) has been proposed as a way to assess it. A variety of methods to assess IP in tumor tissue were proposed, mostly from histology slides of IHC including CD3 and CD8 or hematoxylin and eosin (H&E). However, methodology based on spatial tumor-infiltrating lymphocyte (TIL) analysis in PD-L1 IHC has been rarely investigated. Here, we performed AI-based IP classification in TNBC using PD-L1 22C3 IHC whole slide images (WSIs) as well as PD-L1 combined positive score (CPS) and its positivity.MethodsWe employed Lunit SCOPE IO, an AI-powered H&E analyzer for spatial TIL analysis, identifying and quantifying TIL within cancer or stromal areas in H&E slides. For PD-L1 IHC analysis, Lunit SCOPE PD-L1 CPS, an AI-powered PD-L1 CPS analyzer was used. This model detects and quantifies PD-L1 status in tumor and immune cells and was developed with 3.35x105 tumor cells and 3.45x105 immune cells from PD-L1 IHC-stained WSI of breast cancer. To validate, 180 pairs of PD-L1 IHC and H&E WSIs from a cohort of TNBC were analyzed. The IPs were classified as inflamed (high TIL density in the cancer area, IIP) or non-inflamed (non-IIP) in H&E and PD-L1 IHC WSIs, using a standardized 0.5x0.5mm2 grid for both and a lymphocyte cutoff of 130/mm2 for AI-based PD-L1 IHC analysis.ResultsIPs were classified as inflamed in 69 cases (38.3%) in PD-L1 and 40 cases (22.2%) in H&E. The agreement in IPs between two models was 73.9% (table 1). The median PD-L1 CPS was 10 (interquartile range 2 - 25). AI-based PD-L1 IHC analysis revealed significant differences in median CPS levels between IIP and non-IIP, with values of 32.5 (15.6 - 77.2) and 2.9 (0.6 - 8.6), respectively (p<0.001). Moreover, median values of PD-L1 positivity in IIP were significantly higher than in the non-IIP across cell types: tumor cells (14.9% vs. 1.4%, p<0.001), lymphocytes (36.2% vs. 14.1%, p<0.001), and macrophages (14.9% vs. 9.7%, p=0.001).ConclusionsThe IP determined by the AI-powered PD-L1 IHC analyzer showed a high concordance rate with the IP determined by the AI-powered H&E analyzer. Moreover, high PD-L1 expression of each respective cell type of tumor, lymphocyte, and macrophage was observed in the IIP. Consistent with previous knowledge of the IP, our PD-L1 results support use of immune-oncology approaches in this phenotype.Abstract 1308 Table 1Analysis of IPs by two AI-powered analyzers