Dissecting AI-based mutation prediction in lung adenocarcinoma: A comprehensive real-world study.

INTRODUCTION: Molecular profiling of lung cancer is essential to identify genetic alterations that predict response to targeted therapy. While deep learning shows promise for predicting oncogenic mutations from whole tissue images, existing studies often face challenges such as limited sample sizes, a focus on earlier stage patients, and insufficient analysis of robustness and generalizability. METHODS: This retrospective study evaluates factors influencing mutation prediction accuracy using the large Heidelberg Lung Adenocarcinoma Cohort (HLCC), a cohort of 2356 late-stage FFPE samples. Validation is performed in the publicly available TCGA-LUAD cohort. RESULTS: Models trained on the larger HLCC cohort generalized well to the TCGA dataset for mutations in EGFR (AUC 0.76), STK11 (AUC 0.71) and TP53 (AUC 0.75), in line with the hypothesis that larger cohort sizes improve model robustness. Variation in performance due to pre-processing and modeling choices, such as mutation variant calling, affected EGFR prediction accuracy by up to 7 %. DISCUSSION: Model explanations suggest that acinar and papillary growth patterns are critical for the detection of EGFR mutations, whereas solid growth patterns and large nuclei are indicative of TP53 mutations. These findings highlight the importance of specific morphological features in mutation detection and the potential of deep learning models to improve mutation prediction accuracy. CONCLUSION: Although deep learning models trained on larger cohorts show improved robustness and generalizability in predicting oncogenic mutations, they cannot replace comprehensive molecular profiling. However, they may support patient pre-selection for clinical trials and deepen the insight in genotype-phenotype relationships.

Peripheral Inflammation Featuring Eosinophilia or Neutrophilia Is Associated with the Survival and Infiltration of Eosinophils within the Tumor among Various Histological Subgroups of Patients with NSCLC.

Immune activation status determines non-small cell lung cancer (NSCLC) prognosis, with reported positive/negative associations for T helper type 2 (TH2) responses, including allergen-specific IgE and eosinophils. Our study seeks to explore the potential impact of these comorbid immune responses on the survival rates of patients with NSCLC. Our retrospective study used data from the Data Warehouse of the German Center for Lung Research (DZL) and Lung Biobank at Thoraxklinik Heidelberg. We estimated the association of blood eosinophilia and neutrophilia on survival rates in an inflammatory cohort of 3143 patients with NSCLC. We also tested sensitization to food and inhalants and high-sensitivity C-reactive protein (hs-CRP) in a comorbidity cohort of 212 patients with NSCLC. Finally, we estimated the infiltration of immune-relevant cells including eosinophils, T-cells, and mast cells in a tissue inflammatory sub-cohort of 60 patients with NSCLC. Sensitization to at least one food or inhalant (sIgE) was higher in patients with adenocarcinoma (adeno-LC) than the non-adenocarcinoma (non-adeno-LC). Furthermore, hs-CRP was higher in non-adeno-LC compared with adeno-LC. Peripheral inflammation, particularly eosinophilia and neutrophilia, was associated with poor survival outcomes in NSCLC with a clear difference between histological subgroups. Finally, blood eosinophilia was paralleled by significant eosinophil infiltration into the peritumoral tissue in the lung. This study provides novel perspectives on the crucial role of peripheral inflammation, featuring eosinophilia and neutrophilia, with overall survival, underscoring distinctions between NSCLC subgroups (adeno-LC vs. non-adeno-LC). Peripheral eosinophilia enhances eosinophil infiltration into tumors. This sheds light on the complex interplay between inflammation, eosinophil infiltration, and NSCLC prognosis among various histological subtypes. Further studies are required to underscore the role of eosinophils in NSCLC among different histological subgroups and their role in shaping the tumor microenvironment.

SIAH3 is frequently epigenetically silenced in cancer and regulates mitochondrial metabolism.

Of the seven in absentia homologue (SIAH) family, three members have been identified in the human genome. In contrast to the E3 ubiquitin ligase encoding SIAH1 and SIAH2, little is known on the regulation and function of SIAH3 in tumorigenesis. In this study, we reveal that SIAH3 is frequently epigenetically silenced in different cancer entities, including cutaneous melanoma, lung adenocarcinoma and head and neck cancer. Low SIAH3 levels correlate with an impaired survival of cancer patients. Additionally, induced expression of SIAH3 reduces cell proliferation and induces cell death. Functionally, SIAH3 negatively affects cellular metabolism by shifting cells form aerobic oxidative phosphorylation to glycolysis. SIAH3 is localized in the mitochondrion and interacts with proteins involved in mitochondrial ribosome biogenesis and translation. We also report that SIAH3 interacts with ubiquitin ligases, including SIAH1 or SIAH2, and is degraded by them. These results suggest that SIAH3 acts as an epigenetically controlled tumor suppressor by regulating cellular metabolism through the inhibition of oxidative phosphorylation.

Peri- and postoperative morbidity and mortality in older patients with non-small cell lung cancer: a matched-pair study.

BACKGROUND: Reports from case series suggest that operative outcomes are comparable amongst different age groups following surgery with curative intent for non-small cell lung cancer (NSCLC). The purpose of this study was to compare morbidity and mortality after NSCLC surgery in older patients (≥ 75 years) versus younger patients (< 75 years) and identify independent predictive risk factors. METHODS: We identified 2015 patients with postoperative stages IA to IIIA according to AJCC/UICC 7th edition who had undergone NSCLC surgery with curative intent at a single specialized lung cancer center from January 2010 to December 2015. A matched-pair analysis was performed on 227 older patients and corresponding 227 younger patients. Short-term surgical outcomes were postoperative morbidity, length of hospital stay, 30-day and 90-day mortality. Long-term operative outcomes were disease-free and overall survival. RESULTS: 454 patients were included in the matched-pair analysis. 36% of younger patients developed postoperative complications versus 42% in older patients (p = 0.163). Age was not significantly associated with the occurrence of postoperative complications. Median length of hospital stay was 14 days in older patients and 13 days in younger patients (p = 0.185). 90-day mortality was 2.2% in younger patients compared to 4% in older patients (p = 0.424). In patients aged 75 and older impaired performance status (ECOG ≥ 1) was associated with decreased overall survival (HR = 2.15, CI 1.34-3.46), as were preoperative serum C-reactive protein / albumin ratio ≥ 0.3 (HR = 1.95, CI 1.23-3.11) and elevated preoperative serum creatinine levels ≥ 1.1 mg/dl (HR = 1.84, CI 1.15-2.95). In the younger cohort male sex (HR = 2.26, CI 1.17-4.36), postoperative stage III disease (HR 4.61, CI 2.23-9.54) and preoperative anemia (hemoglobin < 12 g/dl) (HR 2.09, CI 1.10-3.96) were associated with decreased overall survival. CONCLUSIONS: Lung resection for NSCLC in older patients is associated with postoperative morbidity and mortality comparable to those of younger patients. In older patients, physical activity, comorbidities and nutritional status are related to survival and should influence the indication for surgery rather than age alone.

CT-guided needle biopsy is not associated with increased ipsilateral pleural metastasis.

INTRODUCTION: Histological confirmation of a lung tumor is the prerequisite for treatment planning. It has been suspected that CT-guided needle biopsy (CTGNB) exposes the patient to a higher risk of pleural recurrence. However, the distance between tumor and pleura has largely been neglected as a possible confounder when comparing CTGNB to bronchoscopy. METHODS: All patients with lung cancer histologically confirmed by bronchoscopy or CTGNB between 2010 and 2020 were enrolled and studied. Patients' medical histories, radiologic and pathologic findings and surgical records were reviewed. Pleural recurrence was diagnosed by pleural biopsy, fluid cytology, or by CT chest imaging showing progressive pleural nodules. RESULTS: In this retrospective unicenter analysis, 844 patients underwent curative resection for early-stage lung cancer between 2010 and 2020. Median follow-up was 47.5 months (3-137). 27 patients (3.2 %) with ipsilateral pleural recurrence (IPR) were identified. The distance of the tumor to the pleura was significantly smaller in patients who underwent CTGNB. A tendency of increased risk of IPR was observed in tumors located in the lower lobe (HR: 2.18 [±0.43], p = 0.068), but only microscopic pleural invasion was a significant independent predictive factor for increased risk of IPR (HR: 5.33 [± 0.51], p = 0.001) by multivariate cox analysis. Biopsy by CTGNB did not affect IPR (HR: 1.298 [± 0.39], p = 0.504). CONCLUSION: CTGNB is safe and not associated with an increased incidence of IPR in our cohort of patients. This observation remains to be validated in a larger multicenter patient cohort.

Combination of calretinin, MALAT1, and GAS5 as a potential prognostic biomarker to predict disease progression in surgically treated mesothelioma patients.

BACKGROUND: The role of cytoreductive surgery for epithelioid pleural mesothelioma within a multimodal treatment approach remains controversial. Carefully selected patients benefit from cytoreductive surgery and adjuvant chemotherapy, but there is no established biomarker to predict tumor recurrence or progression during the course of the disease. The aim of this study was to identify potential biomarkers to predict therapeutic response in terms of progression-free survival. METHODS: Between 03/2014 and 08/2022, preoperative blood samples were collected from 76 patients with epithelioid pleural mesothelioma who underwent cytoreductive surgery as part of a multimodal treatment approach. Identification of potential biomarkers was performed by determination of mesothelin and calretinin, as well as specific long non-coding RNAs and microRNAs. Receiver operating characteristic analysis, Kaplan-Meier survival analysis, and Cox regression were used to assess the association between biomarker concentrations and patient recurrence status and survival. RESULTS: MALAT1, GAS5, and calretinin showed statistically significant increased biomarker levels in patients with recurrence in contrast to recurrence-free patients after surgical treatment (p < 0.0001, p = 0.0190, and p = 0.0068, respectively). The combination of the three biomarkers resulted in a sensitivity of 68 % and a specificity of 89 %. CONCLUSION: MALAT1, GAS5, and calretinin could be potential biomarkers for the prediction of tumor recurrence, improving the benefit from multimodal treatment including cytoreductive surgery.

Robotic thoracic surgery for neurogenic tumors.

OBJECTIVE: Thoracic neurogenic tumors usually present as benign nerve sheath tumors that can be resected via transthoracic or posterior approaches, depending on the anatomical location. Robot-assisted thoracic surgery (RATS) is increasingly being used for the transthoracic approach, but evidence is very limited. The authors initiated the current study to evaluate the efficacy and safety of RATS for thoracic neurogenic tumors. METHODS: This retrospective study is based on a prospectively created database that includes all RATS surgeries between 2018 and 2023. All patients with histologically confirmed neurogenic tumors were included in the study. The patients' medical and surgical records as well as radiological and pathological findings were analyzed. RESULTS: During a 5-year period, 27 patients underwent robotic resection of neurogenic tumors at a high-volume thoracic surgery center. Two patients had previously undergone posterior laminectomy for resection of the intraspinal components. The pathologies included schwannomas (18, 64%), ganglioneuromas (8, 29%), 1 paraganglioma, and 1 neurofibroma occurring close to a schwannoma unilaterally in the same patient. The median tumor size was 4.7 cm (range 0.9-11.4 cm). The median operating time was 69 minutes (range 27-169 minutes), and the median postoperative stay was 3 days (range 1-19 days). There was one conversion due to adhesions after a previous surgery. No major bleeding occurred. There was no perioperative mortality. Morbidity included a lymphatic fistula (n = 1), pneumonia (n = 1), prolonged air leak (n = 1), and 4 cases of postoperative pain persisting for more than 4 weeks. Neurological complications were mostly observed in patients with tumors located at the thoracic apex: 2 cases of Horner's syndrome, 2 cases with compensatory hyperhidrosis, 1 patient with paresis of the recurrent laryngeal nerve, and a T1 lesion resulting in a minor motor deficit of the small hand muscles (Medical Research Council grade 4) and hypoesthesia of the respective dermatome. CONCLUSIONS: RATS for thoracic neurogenic tumors is feasible and safe. Tumors at the thoracic apex are at high risk of neurological deficit and should be approached with care. Close interdisciplinary collaboration between neurosurgeons and thoracic surgeons is necessary for optimal patient selection and a good postoperative outcome.

The pregnancy-associated protein glycodelin as a potential sex-specific target for resistance to immunotherapy in non-small cell lung cancer.

Lung cancer has been shown to be targetable by novel immunotherapies which reactivate the immune system and enable tumor cell killing. However, treatment failure and resistance to these therapies is common. Consideration of sex as a factor influencing therapy resistance is still rare. We hypothesize that the success of the treatment is impaired by the presence of the immunosuppressive pregnancy-associated glycoprotein glycodelin that is expressed in patients with non-small-cell lung cancer (NSCLC). We demonstrate that the glycan pattern of NSCLC-derived glycodelin detected by a lectin-based enrichment assay highly resembles amniotic fluid-derived glycodelin A, which is known to have immunosuppressive properties. NSCLC-derived glycodelin interacts with immune cells in vitro and regulates the expression of genes associated with inflammatory and tumor microenvironment pathways. In tumor microarray samples of patients, high glycodelin staining in tumor areas results in an impaired overall survival of female patients. Moreover, glycodelin colocalizes to tumor infiltrating CD8+ T cells and pro-tumorigenic M2 macrophages. High serum concentrations of glycodelin prior to immunotherapy are associated with a poor progression-free survival (p < 0.001) of female patients receiving PD-(L)1 inhibitors. In summary, our findings suggest that glycodelin not only is a promising immunological biomarker for early identification of female patients that do not benefit from the costly immunotherapy, but also represents a promising immunotherapeutic target in NSCLC to improve therapeutic options in lung cancer.

PITX2 as a Sensitive and Specific Marker of Midgut Neuroendocrine Tumors: Results from a Cohort of 1157 Primary Neuroendocrine Neoplasms.

As neuroendocrine tumors (NETs) often present as metastatic lesions, immunohistochemical assignment to a site of origin is one of the most important tasks in their pathologic assessment. Because a fraction of NETs eludes the typical expression profiles of their primary localization, additional sensitive and specific markers are required to improve diagnostic certainty. We investigated the expression of the transcription factor Pituitary Homeobox 2 (PITX2) in a large-scale cohort of 909 NET and 248 neuroendocrine carcinomas (NEC) according to the immunoreactive score (IRS) and correlated PITX2 expression groups with general tumor groups and primary localization. PITX2 expression (all expression groups) was highly sensitive (98.1%) for midgut-derived NET, but not perfectly specific, as non-midgut NET (especially pulmonary/duodenal) were quite frequently weak or moderately positive. The specificity rose to 99.5% for a midgut origin of NET if only a strong PITX2 expression was considered, which was found in only 0.5% (one pancreatic/one pulmonary) of non-midgut NET. In metastases of midgut-derived NET, PITX2 was expressed in all cases (87.5% strong, 12.5% moderate), whereas CDX2 was negative or only weakly expressed in 31.3% of the metastases. In NEC, a fraction of cases (14%) showed a weak or moderate PITX2 expression, which was not associated with a specific tumor localization. Our study independently validates PITX2 as a very sensitive and specific immunohistochemical marker of midgut-derived NET in a very large collective of neuroendocrine neoplasms. Therefore, our data argue toward implementation into diagnostic panels applied for NET as a firstline midgut marker.

CYFRA 21-1, CA 125 and CEA provide additional prognostic value in NSCLC patients with stable disease at first CT scan.

BACKGROUND: Serum tumor markers (STM) may complement imaging and provide additional clinical information for patients with non-small cell lung cancer (NSCLC). OBJECTIVE: To determine whether STMs can predict outcomes in patients with stable disease (SD) after initial treatment. METHODS: This single-center, prospective, observational trial enrolled 395 patients with stage III/IV treatment-naïve NSCLC; of which 263 patients were included in this analysis. Computed Tomography (CT) scans were performed and STMs measured before and after initial treatment (two cycles of chemotherapy and/or an immune checkpoint inhibitor or tyrosine kinase inhibitor); analyses were based on CT and STM measurements obtained at first CT performed after cycle 2 only PFS and OS were analyzed by Kaplan-Meier curves and Cox-proportional hazard models. RESULTS: When patients with SD (n = 100) were split into high- and low-risk groups based on CYFRA 21-1, CEA and CA 125 measurements using an optimized cut-off, a 4-fold increase risk of progression or death was estimated for high- vs low-risk SD patients (PFS, HR 4.17; OS, 3.99; both p < 0.0001). Outcomes were similar between patients with high-risk SD or progressive disease (n = 35) (OS, HR 1.17) and between patients with low-risk SD or partial response (n = 128) (PFS, HR 0.98; OS, 1.14). CONCLUSIONS: STMs can provide further guidance in patients with indeterminate CT responses by separating them into high- and low-risk groups for future PFS and OS events.

Prognostic value of tumor markers ProGRP, NSE and CYFRA 21-1 in patients with small cell lung cancer and chemotherapy-induced remission.

BACKGROUND: Despite successful response to first line therapy, patients with small-cell lung cancer (SCLC) often suffer from early relapses and disease progression. OBJECTIVE: To investigate the relevance of serum tumor markers for estimation of prognosis at several time points during the course of disease. METHODS: In a prospective, single-center study, serial assessments of progastrin-releasing peptide (ProGRP), neuron-specific enolase (NSE), cytokeratin-19 fragments (CYFRA 21-1) and carcino-embryogenic antigen (CEA) were performed during and after chemotherapy in 232 SCLC patients, and correlated with therapy response and overall survival (OS). RESULTS: ProGRP, NSE and CYFRA 21-1 levels decreased quickly after the first chemotherapy cycle and correlated well with the radiological response. Either as single markers or in combination they provided valuable prognostic information regarding OS at all timepoints investigated: prior to first-line therapy, after two treatment cycles in patients with successful response to first-line therapy, and prior to the start of second-line therapy. Furthermore, they were useful for continuous monitoring during and after therapy and often indicated progressive disease several months ahead of radiological changes. CONCLUSIONS: The results indicate the great potential of ProGRP, NSE and CYFRA 21-1 for estimating prognosis and monitoring of SCLC patients throughout the course of the disease.

Preliminary results from the EMoLung clinical study showing early lung cancer detection by the LC score.

BACKGROUND: Lung cancer (LC) causes more deaths worldwide than any other cancer type. Despite advances in therapeutic strategies, the fatality rate of LC cases remains high (95%) since the majority of patients are diagnosed at late stages when patient prognosis is poor. Analysis of the International Association for the Study of Lung Cancer (IASLC) database indicates that early diagnosis is significantly associated with favorable outcome. However, since symptoms of LC at early stages are unspecific and resemble those of benign pathologies, current diagnostic approaches are mostly initiated at advanced LC stages. METHODS: We developed a LC diagnosis test based on the analysis of distinct RNA isoforms expressed from the GATA6 and NKX2-1 gene loci, which are detected in exhaled breath condensates (EBCs). Levels of these transcript isoforms in EBCs were combined to calculate a diagnostic score (the LC score). In the present study, we aimed to confirm the applicability of the LC score for the diagnosis of early stage LC under clinical settings. Thus, we evaluated EBCs from patients with early stage, resectable non-small cell lung cancer (NSCLC), who were prospectively enrolled in the EMoLung study at three sites in Germany. RESULTS: LC score-based classification of EBCs confirmed its performance under clinical conditions, achieving a sensitivity of 95.7%, 91.3% and 84.6% for LC detection at stages I, II and III, respectively. CONCLUSIONS: The LC score is an accurate and non-invasive option for early LC diagnosis and a valuable complement to LC screening procedures based on computed tomography.

Prognostic Impact of the Immune-Cell Infiltrate in N1-Positive Non-Small-Cell Lung Cancer.

INTRODUCTION: The tumoral immune milieu plays a crucial role for the development of non-small-cell lung cancer (NSCLC) and may influence individual prognosis. We analyzed the predictive role of immune cell infiltrates after curative lung cancer surgery. MATERIALS AND METHODS: The tumoral immune-cell infiltrate from 174 patients with pN1 NSCLC and adjuvant chemotherapy was characterized using immunofluorescence staining. The density and distribution of specific immune cells in tumor center (TU), invasive front (IF) and normal tissue (NORM) were correlated with clinical parameters and survival data. RESULTS: Tumor specific survival (TSS) of all patients was 69.9% at 5 years. The density of tumor infiltrating lymphocytes (TIL) was higher in TU and IF than in NORM. High TIL density in TU (low vs. high: 62.0% vs. 86.7%; p = .011) and the presence of cytotoxic T-Lymphocytes (CTLs) in TU and IF were associated with improved TSS (positive vs. negative: 90.6% vs. 64.7% p = .024). High TIL-density correlated with programmed death-ligand 1 expression levels ≥50% (p < .001). Multivariate analysis identified accumulation of TIL (p = .016) and low Treg density (p = .003) in TU as negative prognostic predictors in squamous cell carcinoma (p = .025), whereas M1-like tumor- associated macrophages (p = .019) and high programmed death-ligand 1 status (p = .038) were associated with better survival in adenocarcinoma. CONCLUSION: The assessment of specific intratumoral immune cells may serve as a prognostic predictor in pN1 NSCLC. However differences were observed related to adenocarcinoma or squamous cell carcinoma histology. Prospective assessment of the immune-cell infiltrate and further clarification of its prognostic relevance could assist patient selection for upcoming perioperative immunotherapies.

Early Detection of Lung Cancer Using Small RNAs.

INTRODUCTION: Lung cancer remains the deadliest cancer in the world, and lung cancer survival is heavily dependent on tumor stage at the time of detection. Low-dose computed tomography screening can reduce mortality; however, annual screening is limited by low adherence in the United States of America and still not broadly implemented in Europe. As a result, less than 10% of lung cancers are detected through existing programs. Thus, there is a great need for additional screening tests, such as a blood test, that could be deployed in the primary care setting. METHODS: We prospectively recruited 1384 individuals meeting the National Lung Screening Trial demographic eligibility criteria for lung cancer and collected stabilized whole blood to enable the pipetting-free collection of material, thus minimizing preanalytical noise. Ultra-deep small RNA sequencing (20 million reads per sample) was performed with the addition of a method to remove highly abundant erythroid RNAs, and thus open bandwidth for the detection of less abundant species originating from the plasma or the immune cellular compartment. We used 100 random data splits to train and evaluate an ensemble of logistic regression classifiers using small RNA expression of 943 individuals, discovered an 18-small RNA feature consensus signature (miLung), and validated this signature in an independent cohort (441 individuals). Blood cell sorting and tumor tissue sequencing were performed to deconvolve small RNAs into their source of origin. RESULTS: We generated diagnostic models and report a median receiver-operating characteristic area under the curve of 0.86 (95% confidence interval [CI]: 0.84-0.86) in the discovery cohort and generalized performance of 0.83 in the validation cohort. Diagnostic performance increased in a stage-dependent manner ranging from 0.73 (95% CI: 0.71-0.76) for stage I to 0.90 (95% CI: 0.89-0.90) for stage IV in the discovery cohort and from 0.76 to 0.86 in the validation cohort. We identified a tumor-shed, plasma-bound ribosomal RNA fragment of the L1 stalk as a dominant predictor of lung cancer. The fragment is decreased after surgery with curative intent. In additional experiments, results of dried blood spot collection and sequencing revealed that small RNA analysis could potentially be conducted through home sampling. CONCLUSIONS: These data suggest the potential of a small RNA-based blood test as a viable alternative to low-dose computed tomography screening for early detection of smoking-associated lung cancer.

Corrigendum: Deep learning for the detection of anatomical tissue structures and neoplasms of the skin on scanned histopathological tissue sections.

[This corrects the article DOI: 10.3389/fonc.2022.1022967.].

High-resolution transcriptomic and epigenetic profiling identifies novel regulators of COPD.

Patients with chronic obstructive pulmonary disease (COPD) are still waiting for curative treatments. Considering its environmental cause, we hypothesized that COPD will be associated with altered epigenetic signaling in lung cells. We generated genome-wide DNA methylation maps at single CpG resolution of primary human lung fibroblasts (HLFs) across COPD stages. We show that the epigenetic landscape is changed early in COPD, with DNA methylation changes occurring predominantly in regulatory regions. RNA sequencing of matched fibroblasts demonstrated dysregulation of genes involved in proliferation, DNA repair, and extracellular matrix organization. Data integration identified 110 candidate regulators of disease phenotypes that were linked to fibroblast repair processes using phenotypic screens. Our study provides high-resolution multi-omic maps of HLFs across COPD stages. We reveal novel transcriptomic and epigenetic signatures associated with COPD onset and progression and identify new candidate regulators involved in the pathogenesis of chronic lung diseases. The presence of various epigenetic factors among the candidates demonstrates that epigenetic regulation in COPD is an exciting research field that holds promise for novel therapeutic avenues for patients.

Lung Adenocarcinoma Diagnosed at a Younger Age Is Associated with Advanced Stage, Female Sex, and Ever-Smoker Status, in Patients Treated with Lung Resection.

To date, the factors which affect the age at diagnosis of lung adenocarcinoma are not fully understood. In our study, we examined the relationships of age at diagnosis with smoking, pathological stage, sex, and year of diagnosis in a discovery (n = 1694) and validation (n = 1384) series of lung adenocarcinoma patients who had undergone pulmonary resection at hospitals in the Milan area and at Thoraxklinik (Heidelberg), respectively. In the discovery series, younger age at diagnosis was associated with ever-smoker status (OR = 1.5, p = 0.0035) and advanced stage (taking stage I as reference: stage III OR = 1.4, p = 0.0067; stage IV OR = 1.7, p = 0.0080), whereas older age at diagnosis was associated with male sex (OR = 0.57, p < 0.001). Analysis in the validation series confirmed the ever versus never smokers' association (OR = 2.9, p < 0.001), the association with highest stages (stage III versus stage I OR = 1.4, p = 0.0066; stage IV versus stage I OR = 2.0, p = 0.0022), and the male versus female sex association (OR = 0.78, p = 0.032). These data suggest the role of smoking in affecting the natural history of the disease. Moreover, aggressive tumours seem to have shorter latency from initiation to clinical detection. Finally, younger age at diagnosis is associated with the female sex, suggesting that hormonal status of young women confers risk to develop lung adenocarcinoma. Overall, this study provided novel findings on the mechanisms underlying age at diagnosis of lung adenocarcinoma.

Comparison of the sensitivity of different criteria to select lung cancer patients for screening in a cohort of German patients.

INTRODUCTION: Trials of CT-based screening for lung cancer have shown a mortality advantage for screening in North America and Europe. Before introducing a nationwide lung cancer screening program in Germany, it is important to assess the criteria used in international trials in the German population. METHODS: We used data from 3623 lung cancer patients from the data warehouse of the German Center for Lung Research (DZL). We compared the sensitivity of the following lung cancer screening criteria overall and stratified by age and histology: the National Lung Screening Trial (NLST), the Danish Lung Cancer Screening Trial (DLCST), the 2013 and 2021 US Preventive Services Task Force (USPSTF), and an adapted version of the Prostate, Lung, Colorectal, and Ovarian no race model (adapted PLCOm2012) with 6-year risk thresholds of 1.0%/6 year and 1.7%/6 year. RESULTS: Overall, the adapted PLCOm2012 model (1%/6 years), selected the highest proportion of lung cancer patients for screening (72.4%), followed by the 2021 USPSTF (70.0%), the adapted PLCOm2012 (1.7%/6 year) (57.4%), the 2013 USPTF (57.0%), DLCST criteria (48.7%), and the NLST (48.5%). The adapted PLCOm2012 risk model (1.0%/6 year) had the highest sensitivity for all histological types except for small-cell and large-cell carcinomas (non-significant), whereas the 2021 USPTF selected a higher proportion of patients. The sensitivity levels were higher in males than in females. CONCLUSION: Using a risk-based selection score resulted in higher sensitivities compared to criteria using dichotomized age and smoking history. However, gender disparities were apparent in all studied eligibility criteria. In light of increasing lung cancer incidences in women, all selection criteria should be reviewed for ways to close this gender gap, especially when implementing a large-scale lung cancer screening program.

Deep learning for the detection of anatomical tissue structures and neoplasms of the skin on scanned histopathological tissue sections.

Basal cell carcinoma (BCC), squamous cell carcinoma (SqCC) and melanoma are among the most common cancer types. Correct diagnosis based on histological evaluation after biopsy or excision is paramount for adequate therapy stratification. Deep learning on histological slides has been suggested to complement and improve routine diagnostics, but publicly available curated and annotated data and usable models trained to distinguish common skin tumors are rare and often lack heterogeneous non-tumor categories. A total of 16 classes from 386 cases were manually annotated on scanned histological slides, 129,364 100 x 100 µm (~395 x 395 px) image tiles were extracted and split into a training, validation and test set. An EfficientV2 neuronal network was trained and optimized to classify image categories. Cross entropy loss, balanced accuracy and Matthews correlation coefficient were used for model evaluation. Image and patient data were assessed with confusion matrices. Application of the model to an external set of whole slides facilitated localization of melanoma and non-tumor tissue. Automated differentiation of BCC, SqCC, melanoma, naevi and non-tumor tissue structures was possible, and a high diagnostic accuracy was achieved in the validation (98%) and test (97%) set. In summary, we provide a curated dataset including the most common neoplasms of the skin and various anatomical compartments to enable researchers to train, validate and improve deep learning models. Automated classification of skin tumors by deep learning techniques is possible with high accuracy, facilitates tumor localization and has the potential to support and improve routine diagnostics.

Multimodal therapy of epithelioid pleural mesothelioma: improved survival by changing the surgical treatment approach.

Background: The exact role and type of surgery for malignant pleural mesothelioma (MPM) remains controversial. This study aimed at analyzing a 20-year single center perioperative experience in MPM surgery at our high-volume thoracic surgery center and comparing the overall survival after trimodal extrapleural pneumonectomy (EPP) and extended pleurectomy and decortication combined with hyperthermic intrathoracic chemoperfusion (EPD/HITOC) and adjuvant chemotherapy with that after chemotherapy (CTx) alone. Methods: Patients with epithelioid MPM treated with neoadjuvant chemotherapy, EPP and adjuvant radiotherapy within a trimodal concept or EPD/HITOC in combination with adjuvant chemotherapy between 2001 and 2018 were included in this retrospective analysis. Surgical cohorts were compared to patients treated with standard chemotherapy. Results: Overall, 182 patients (69 EPP, 57 EPD/HITOC, 56 CTx) were analyzed. Due to occupational exposure to asbestos for most of the patients, 154 patients (84.6%) were male. The patients in the surgical cohorts were significantly younger than those in the CTx cohort. There was no significant difference between the proportion of patient age and side. The median overall survival of the EPD/HITOC cohort with 38.1 months was significantly longer than that of the EPP and CTx cohorts (24.0 and 15.8 months). Better survival was significantly associated with an ECOG 0 performance status, age below 70 years, and negative lymph node status. In the multivariate analysis, EPD/HITOC was significantly associated with improved overall survival. Perioperative morbidity was lower in the EPD/HITOC group than in the EPP cohort. Conclusions: EPD/HITOC is feasible and safe for localized epithelioid pleural mesothelioma. Changing the surgical approach to a less radical lung-sparing technique may improve overall survival compared to trimodal EPP.