Independent External Dataset Research Articles

Predicting the distribution of Ixodes ricinus and Dermacentor reticulatus in Europe: a comparison of climate niche modelling approaches

BackgroundThe ticks Ixodes ricinus and Dermacentor reticulatus are two of the most important vectors in Europe. Climate niche modelling has been used in many studies to attempt to explain their distribution and to predict changes under a range of climate change scenarios. The aim of this study was to assess the ability of different climate niche modelling approaches to explain the known distribution of I. ricinus and D. reticulatus in Europe.MethodsA series of climate niche models, using different combinations of input data, were constructed and assessed. Species occurrence records obtained from systematic literature searches and Global Biodiversity Information Facility data were thinned to different degrees to remove sampling spatial bias. Four sources of climate data were used: bioclimatic variables, WorldClim, TerraClimate and MODIS satellite-derived data. Eight different model training extents were examined and three modelling frameworks were used: maximum entropy, generalised additive models and random forest models. The results were validated through internal cross-validation, comparison with an external independent dataset and expert opinion.ResultsThe performance metrics and predictive ability of the different modelling approaches varied significantly within and between each species. Different combinations were better able to define the distribution of each of the two species. However, no single approach was considered fully able to capture the known distribution of the species. When considering the mean of the performance metrics of internal and external validation, 24 models for I. ricinus and 11 models for D. reticulatus of the 96 constructed were considered adequate according to the following criteria: area under the receiver-operating characteristic curve > 0.7; true skill statistic > 0.4; Miller’s calibration slope 0.25 above or below 1; Boyce index > 0.9; omission rate < 0.15.ConclusionsThis comprehensive analysis suggests that there is no single ‘best practice’ climate modelling approach to account for the distribution of these tick species. This has important implications for attempts to predict climate-mediated impacts on future tick distribution. It is suggested here that climate variables alone are not sufficient; habitat type, host availability and anthropogenic impacts, not included in current modelling approaches, could contribute to determining tick presence or absence at the local or regional scale.Graphical abstract

Multi-modal fusion network with channel information guided module for prognosis prediction in patients with anti-N-methyl-D-aspartate receptor encephalitis

As the most common type of autoimmune encephalitis, the pathological mechanism of anti-N-methyl-D-aspartate receptor (anti-NMDAR) encephalitis has been gradually clarified, but the optimal treatment has not yet been clarified. Accurate early prognostic assessment is of great significance for reversing the symptoms of anti-NMDAR encephalitis. Compared with the expensive costs of human evaluation, the prognostic evaluation method based on the deep learning diagnosis model has obvious advantages. In addition, full consideration of multi-modal information, such as multi-sequence magnetic resonance imaging (MRI) features and clinical variables, has a positive impact on the accurate prediction of patient prognosis. In this paper, a multimodal fusion network is proposed to predict the prognosis of patients with anti-NMDAR encephalitis. The proposed network contains three key substructures. First of all, the channel information guided module is designed to constrain the heterogeneity between the features of different modes through the attention mechanism to achieve more effective feature fusion. Second, we design a backbone network for feature extraction of brain MRI, which is based on a dual-branch residual structure and utilizes the channel information guided module to ensure that the information of features on different scales is complementary. Finally, a feature fusion network is proposed, which uses channel information guided module and dynamic normalization weighting to control the fusion of clinical variables and MRI features. Different from the existing multi-modal methods, our method avoids the huge model structure and uses an end-to-end structure to predict the prognosis of patients with multi-modal features. The above method was applied to the dataset proposed by a dual-center study on anti-NMDAR encephalitis in Southwest China, achieving excellent performance in terms of AUC (0.9799) and accuracy (0.9512). We further validate the model on an independent external validation dataset, and the results show that the model has good generalization.

Delta-radiomics features for predicting the major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer.

To investigate if delta-radiomics features have the potential to predict the major pathological response (MPR) to neoadjuvant chemoimmunotherapy in non-small cell lung cancer (NSCLC) patients. Two hundred six stage IIA-IIIB NSCLC patients from three institutions (Database1 = 164; Database2 = 21; Database3 = 21) who received neoadjuvant chemoimmunotherapy and surgery were included. Patients in Database1 were randomly assigned to the training dataset and test dataset, with a ratio of 0.7:0.3. Patients in Database2 and Database3 were used as two independent external validation datasets. Contrast-enhanced CT scans were obtained at baseline and before surgery. The delta-radiomics features were defined as the relative net change of radiomics features between baseline and preoperative. The delta-radiomics model and pre-treatment radiomics model were established. The performance of Immune-Related Response Evaluation Criteria in Solid Tumors (iRECIST) for predicting MPR was also evaluated. Half of the patients (106/206, 51.5%) showed MPR after neoadjuvant chemoimmunotherapy. For predicting MPR, the delta-radiomics model achieved a satisfying area under the curves (AUCs) values of 0.768, 0.732, 0.833, and 0.716 in the training, test, and two external validation databases, respectively, which showed a superior predictive performance than the pre-treatment radiomics model (0.644, 0.616, 0.475, and 0.608). Compared with iRECIST criteria (0.624, 0.572, 0.650, and 0.466), a mixed model that combines delta-radiomics features and iRECIST had higher AUC values for MPR prediction of 0.777, 0.761, 0.850, and 0.670 in four sets. The delta-radiomics model demonstrated superior diagnostic performance compared to pre-treatment radiomics model and iRECIST criteria in predicting MPR preoperatively in neoadjuvant chemoimmunotherapy for stage II-III NSCLC. Delta-radiomics features based on the relative net change of radiomics features between baseline and preoperative CT scans serve a vital support tool in accurately identifying responses to neoadjuvant chemoimmunotherapy, which can help physicians make more appropriate treatment decisions. •The performances of pre-treatment radiomics model and iRECIST model in predicting major pathological response of neoadjuvant chemoimmunotherapy were unsatisfactory. •The delta-radiomics features based on relative net change of radiomics features between baseline and preoperative CT scans may be used as a noninvasive biomarker for predicting major pathological response of neoadjuvant chemoimmunotherapy. •Combining delta-radiomics features and iRECIST can further improve the predictive performance of responses to neoadjuvant chemoimmunotherapy.

Towards reproducible radiomics research: introduction of a database for radiomics studies

ObjectivesTo investigate the model-, code-, and data-sharing practices in the current radiomics research landscape and to introduce a radiomics research database.MethodsA total of 1254 articles published between January 1, 2021, and December 31, 2022, in leading radiology journals (European Radiology, European Journal of Radiology, Radiology, Radiology: Artificial Intelligence, Radiology: Cardiothoracic Imaging, Radiology: Imaging Cancer) were retrospectively screened, and 257 original research articles were included in this study. The categorical variables were compared using Fisher’s exact tests or chi-square test and numerical variables using Student’s t test with relation to the year of publication.ResultsHalf of the articles (128 of 257) shared the model by either including the final model formula or reporting the coefficients of selected radiomics features. A total of 73 (28%) models were validated on an external independent dataset. Only 16 (6%) articles shared the data or used publicly available open datasets. Similarly, only 20 (7%) of the articles shared the code. A total of 7 (3%) articles both shared code and data. All collected data in this study is presented in a radiomics research database (RadBase) and could be accessed at https://github.com/EuSoMII/RadBase.ConclusionAccording to the results of this study, the majority of published radiomics models were not technically reproducible since they shared neither model nor code and data. There is still room for improvement in carrying out reproducible and open research in the field of radiomics.Clinical relevance statementTo date, the reproducibility of radiomics research and open science practices within the radiomics research community are still very low. Ensuring reproducible radiomics research with model-, code-, and data-sharing practices will facilitate faster clinical translation.Key Points• There is a discrepancy between the number of published radiomics papers and the clinical implementation of these published radiomics models.• The main obstacle to clinical implementation is the lack of model-, code-, and data-sharing practices.• In order to translate radiomics research into clinical practice, the radiomics research community should adopt open science practices.

Application of a validated prostate MRI deep learning system to independent same-vendor multi-institutional data: demonstration of transferability

ObjectivesTo evaluate a fully automatic deep learning system to detect and segment clinically significant prostate cancer (csPCa) on same-vendor prostate MRI from two different institutions not contributing to training of the system.Materials and methodsIn this retrospective study, a previously bi-institutionally validated deep learning system (UNETM) was applied to bi-parametric prostate MRI data from one external institution (A), a PI-RADS distribution-matched internal cohort (B), and a csPCa stratified subset of single-institution external public challenge data (C). csPCa was defined as ISUP Grade Group ≥ 2 determined from combined targeted and extended systematic MRI/transrectal US-fusion biopsy. Performance of UNETM was evaluated by comparing ROC AUC and specificity at typical PI-RADS sensitivity levels. Lesion-level analysis between UNETM segmentations and radiologist-delineated segmentations was performed using Dice coefficient, free-response operating characteristic (FROC), and weighted alternative (waFROC). The influence of using different diffusion sequences was analyzed in cohort A.ResultsIn 250/250/140 exams in cohorts A/B/C, differences in ROC AUC were insignificant with 0.80 (95% CI: 0.74–0.85)/0.87 (95% CI: 0.83–0.92)/0.82 (95% CI: 0.75–0.89). At sensitivities of 95% and 90%, UNETM achieved specificity of 30%/50% in A, 44%/71% in B, and 43%/49% in C, respectively. Dice coefficient of UNETM and radiologist-delineated lesions was 0.36 in A and 0.49 in B. The waFROC AUC was 0.67 (95% CI: 0.60–0.83) in A and 0.7 (95% CI: 0.64–0.78) in B. UNETM performed marginally better on readout-segmented than on single-shot echo-planar-imaging.ConclusionFor same-vendor examinations, deep learning provided comparable discrimination of csPCa and non-csPCa lesions and examinations between local and two independent external data sets, demonstrating the applicability of the system to institutions not participating in model training.Clinical relevance statementA previously bi-institutionally validated fully automatic deep learning system maintained acceptable exam-level diagnostic performance in two independent external data sets, indicating the potential of deploying AI models without retraining or fine-tuning, and corroborating evidence that AI models extract a substantial amount of transferable domain knowledge about MRI-based prostate cancer assessment.Key Points• A previously bi-institutionally validated fully automatic deep learning system maintained acceptable exam-level diagnostic performance in two independent external data sets.• Lesion detection performance and segmentation congruence was similar on the institutional and an external data set, as measured by the weighted alternative FROC AUC and Dice coefficient.• Although the system generalized to two external institutions without re-training, achieving expected sensitivity and specificity levels using the deep learning system requires probability thresholds to be adjusted, underlining the importance of institution-specific calibration and quality control.

Efficient plasma metabolic fingerprinting as a novel tool for diagnosis and prognosis of gastric cancer: a large-scale, multicentre study

ObjectiveMetabolic biomarkers are expected to decode the phenotype of gastric cancer (GC) and lead to high-performance blood tests towards GC diagnosis and prognosis. We attempted to develop diagnostic and prognostic...

Integrative bioinformatics and artificial intelligence analyses of transcriptomics data identified genes associated with major depressive disorders including NRG1

Major depressive disorder (MDD) is a common mental disorder and is amongst the most prevalent psychiatric disorders. MDD remains challenging to diagnose and predict its onset due to its heterogeneous phenotype and complex etiology. Hence, early detection using diagnostic biomarkers is critical for rapid intervention. In this study, a mixture of AI and bioinformatics were used to mine transcriptomic data from publicly available datasets including 170 MDD patients and 121 healthy controls. Bioinformatics analysis using gene set enrichment analysis (GSEA) and machine learning (ML) algorithms were applied. The GSEA revealed that differentially expressed genes in MDD patients are mainly enriched in pathways related to immune response, inflammatory response, neurodegeneration pathways and cerebellar atrophy pathways. Feature selection methods and ML provided predicted models based on MDD-altered genes with ≥75% of accuracy. The integrative analysis between the bioinformatics and ML approaches identified ten key MDD-related biomarkers including NRG1, CEACAM8, CLEC12B, DEFA4, HP, LCN2, OLFM4, SERPING1, TCN1 and THBS1. Among them, NRG1, active in synaptic plasticity and neurotransmission, was the most robust and reliable to distinguish between MDD patients and healthy controls amongst independent external datasets consisting of a mixture of populations. Further evaluation using saliva samples from an independent cohort of MDD and healthy individuals confirmed the upregulation of NRG1 in patients with MDD compared to healthy controls. Functional mapping to the human brain regions showed NRG1 to have high expression in the main subcortical limbic brain regions implicated in depression. In conclusion, integrative bioinformatics and ML approaches identified putative non-invasive diagnostic MDD-related biomarkers panel for the onset of depression.

A deep learning-based framework for predicting survival-associated groups in colon cancer by integrating multi-omics and clinical data

Precise prognostic classification of patients and identifying survival subgroups and their associated genes can be important clinical references when designing treatment strategies for cancer patients. Multi-omics and data integration techniques are powerful tools to achieve this goal. This study aimed to introduce a machine learning method to integrate three types of biological data, and investigate the performance of two other methods, in identifying the survival dependency of patients. The data included TCGA RNA-seq gene expression, DNA methylation, and clinical data from 368 patients with colon cancer also we use an independent external validation data set, containing 232 samples. Three methods including, hyper-parameter optimized autoencoders (HPOAE), normal autoencoder, and penalized principal component analysis (PPCA) were used for simultaneous data integration and estimation under a COX hazards model. The HPOAE was thought to outperform other methods. The HPOAE had the Log Rank Mantel-Cox value of 14.27 ± 2, and a Breslow-Generalized Wilcoxon value of 13.13 ± 1. Ten miRNA, 11 methylated genes, and 28 mRNA all by (importance of marginal cutoff > 0.95) were identified. The study demonstrated that hsa-miR-485-5p targets both ZMYM1 and tp53, the latter of which has been previously associated with cancer in numerous studies. Furthermore, compared to other methods, the HPOAE exhibited a greater capacity for identifying survival subgroups and the genes associated with them in patients with colon cancer. However, all of the results were obtained by computational methods, and clinical and experimental studies are needed to validate these results.

Integrated analysis of single-cell and bulk RNA-sequencing reveals tumor heterogeneity and a signature based on NK cell marker genes for predicting prognosis in hepatocellular carcinoma.

Background: Natural killer (NK) cells are a type of innate immune cell that recognize and eliminate tumor cells and infected cells, without prior sensitization or activation. Herein, we aimed to construct a predictive model based on NK cell-related genes for hepatocellular carcinoma (HCC) patients and assess the feasibility of utilizing this model for prognosis prediction. Methods: Single-cell RNA-seq data were obtained from the Gene Expression Omnibus (GEO) database to identify marker genes of NK cells. Univariate Cox and lasso regression were performed to further establish a signature in the TCGA dataset. Subsequently, qPCR and immunohistochemistry (IHC) staining were employed to validate the expression levels of prognosis signature genes in HCC. The effectiveness of the model was further validated using two external cohorts from the GEO and ICGC datasets. Clinical characteristics, prognosis, tumor mutation burden, immune microenvironments, and biological function were compared for different genetic subtypes and risk groups. Finally, molecular docking was performed to evaluate the binding affinity between the hub gene and chemotherapeutic drugs. Results: A total of 161 HCC-related NK cell marker genes (NKMGs) were identified, 28 of which were significantly associated with overall survival in HCC patients. Based on differences in gene expression characteristics, HCC patients were classified into three subtypes. Ten prognosis genes (KLRB1, CD7, LDB2, FCER1G, PFN1, FYN, ACTG1, PABPC1, CALM1, and RPS8) were screened to develop a prognosis model. The model not only demonstrated excellent predictive performance on the training dataset, but also were successfully validated on two independent external datasets. The risk scores derived from the model were shown to be an independent prognosis factor for HCC and were correlated with pathological severity. Moreover, qPCR and IHC staining confirmed that the expression of the prognosis genes was generally consistent with the results of the bioinformatic analysis. Finally, molecular docking revealed favorable binding energies between the hub gene ACTG1 and chemotherapeutic drugs. Conclusion: In this study, we developed a model for predicting the prognosis of HCC based on NK cells. The utilization of NKMGs as innovative biomarkers showed promise in the prognosis assessment of HCC.

Identification of a novel MSI-related ceRNA network for predicting the prognosis and immunotherapy response of gastric cancer

Mounting evidence has underscored the pivotal role of the competitive endogenous RNA (ceRNA) regulatory networks among various cancers. However, the behavior characteristics and complexity of the ceRNA network in Gastric cancer (GC) remains unclear. In this study, we aimed to clarify a Microsatellite instability (MSI)-related ceRNA regulatory network and identify potential prognostic markers associated with GC.We extracted transcriptome data of GC patients from The Cancer Genome Atlas (TCGA) and identified differentially expressed lncRNAs, miRNAs and mRNAs based on MSI status. A hub ceRNA network including 1 lncRNAs (MIR99AHG), 2 miRNAs and 26 mRNAs specific to MSI was established in GC. We further constructed a prognostic model with seven target mRNAs by Lasso Cox regression, which yielded AUC values of 0.76. The prognostic model was further validated in an external independent dataset that integrated three GEO datasets. The characterization of immune cell infiltration and immunotherapy effects between high-risk and low-risk groups were then analyzed. Immune cell infiltration was significantly different between high- and low-risk groups based on risk scores. GC patients with lower risk scores correlated with better immune checkpoint inhibitor therapy (ICI) response. We further validated the expression and regulatory relationship of the ceRNA network in vitro experiments, and also confirmed the relationship between MIR99AHG and PD-L1.Our research provides in-depth insights on the role of MSI-related ceRNA in GC and the prognosis and ICIs therapy response of GC patients can be assessed by the risk model based on MSI-related ceRNA network.

Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study

ObjectiveTo develop an interpretable artificial intelligence algorithm to rule out normal large bowel endoscopic biopsies, saving pathologist resources and helping with early diagnosis.DesignA graph neural network was developed incorporating pathologist...

Insulin-like growth factor 2 hypermethylation in peripheral blood leukocytes and colorectal cancer risk and prognosis: a propensity score analysis.

To comprehensively assess and validate the associations between insulin-like growth factor 2 (IGF2) gene methylation in peripheral blood leukocytes (PBLs) and colorectal cancer (CRC) risk and prognosis. The association between IGF2 methylation in PBLs and CRC risk was initially evaluated in a case-control study and then validated in a nested case-control study and a twins' case-control study, respectively. Meanwhile, an initial CRC patient cohort was used to assess the effect of IGF2 methylation on CRC prognosis and then the finding was validated in the EPIC-Italy CRC cohort and TCGA datasets. A propensity score (PS) analysis was performed to control for confounders, and extensive sensitivity analyses were performed to assess the robustness of our findings. PBL IGF2 hypermethylation was associated with an increased risk of CRC in the initial study (ORPS-adjusted, 2.57, 95% CI: 1.65 to 4.03, P<0.0001), and this association was validated using two independent external datasets (ORPS-adjusted, 2.21, 95% CI: 1.28 to 3.81, P=0.0042 and ORPS-adjusted, 10.65, 95% CI: 1.26 to 89.71, P=0.0295, respectively). CRC patients with IGF2 hypermethylation in PBLs had significantly improved overall survival compared to those patients with IGF2 hypomethylation (HRPS-adjusted, 0.47, 95% CI: 0.29 to 0.76, P=0.0019). The prognostic signature was also observed in the EPIC-Italy CRC cohort, although the HR did not reach statistical significance (HRPS-adjusted, 0.69, 95% CI: 0.37 to 1.27, P=0.2359). IGF2 hypermethylation may serve as a potential blood-based predictive biomarker for the identification of individuals at high risk of developing CRC and for CRC prognosis.

Generalizable calibrated machine learning models for real-time atrial fibrillation risk prediction in ICU patients

BackgroundAtrial Fibrillation (AF) is the most common arrhythmia in the intensive care unit (ICU) and is associated with increased morbidity and mortality. Identification of patients at risk for AF is not routinely performed as AF prediction models are almost solely developed for the general population or for particular ICU populations. However, early AF risk identification could help to take targeted preemptive actions and possibly reduce morbidity and mortality. Predictive models need to be validated across hospitals with different standards of care and convey their predictions in a clinically useful manner. Therefore, we designed AF risk models for ICU patients using uncertainty quantification to provide a risk score and evaluated them on multiple ICU datasets. MethodsThree CatBoost models, utilizing feature windows comprising data 1.5-13.5, 6-18, or 12-24 hours before AF occurrence, were built using 2-repeat-10-fold cross-validation on AmsterdamUMCdb, the first freely available European ICU database. Furthermore, AF Patients were matched with no-AF patients for training. Transferability was validated using a direct and a recalibration evaluation on two independent external datasets, MIMIC-IV and GUH. The calibration of the predicted probability, used as an AF risk score, was measured using the Expected Calibration Error (ECE) and the presented Expected Signed Calibration Error (ESCE). Additionally, all models were evaluated across time during the ICU stay. ResultsThe model performance reached Areas Under the Curve (AUCs) of 0.81 at internal validation. Direct external validation showed partial generalizability with AUCs reaching 0.77. However, recalibration resulted in performances matching or exceeding that of the internal validation. All models furthermore showed calibration capabilities demonstrating adequate risk prediction competence. ConclusionUltimately, recalibrating models reduces the challenge of generalization to unseen datasets. Moreover, utilizing the patient-matching methodology together with the assessment of uncertainty calibration can serve as a step toward the development of clinical AF prediction models.

Prediction of Deep Myometrial Infiltration, Clinical Risk Category, Histological Type, and Lymphovascular Space Invasion in Women with Endometrial Cancer Based on Clinical and T2-Weighted MRI Radiomic Features.

To predict deep myometrial infiltration (DMI), clinical risk category, histological type, and lymphovascular space invasion (LVSI) in women with endometrial cancer using machine learning classification methods based on clinical and image signatures from T2-weighted MR images. A training dataset containing 413 patients and an independent testing dataset consisting of 82 cases were employed in this retrospective study. Manual segmentation of the whole tumor volume on sagittal T2-weighted MRI was performed. Clinical and radiomic features were extracted to predict: (i) DMI of endometrial cancer patients, (ii) endometrial cancer clinical high-risk level, (iii) histological subtype of tumor, and (iv) presence of LVSI. A classification model with different automatically selected hyperparameter values was created. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve, F1 score, average recall, and average precision were calculated to evaluate different models. Based on the independent external testing dataset, the AUCs for DMI, high-risk endometrial cancer, endometrial histological type, and LVSI classification were 0.79, 0.82, 0.91, and 0.85, respectively. The corresponding 95% confidence intervals (CI) of the AUCs were [0.69, 0.89], [0.75, 0.91], [0.83, 0.97], and [0.77, 0.93], respectively. It is possible to classify endometrial cancer DMI, risk, histology type, and LVSI using different machine learning methods.

Automated deep neural network-based identification, localization, and tracking of cardiac structures for ultrasound-guided interventional surgery.

The increase in the use of ultrasound-guided interventional therapy for cardiovascular diseases has increased the importance of intraoperative real-time cardiac ultrasound image interpretation. We thus aimed to develop a deep learning-based model to accurately identify, localize, and track the critical cardiac structures and lesions (9 kinds in total) and to validate the algorithm's performance using independent data sets. This diagnostic study developed a deep learning-based model using data collected from Fuwai Hospital between January 2018 and June 2019. The model was validated with independent French and American data sets. In total, 17,114 cardiac structures and lesions were used to develop the algorithm. The model findings were compared with those of 15 specialized physicians in multiple centers. For external validation, 516,805 tags and 27,938 tags were used from 2 different data sets. Regarding structure identification, the area under the receiver operating characteristic curve (AUC) of each structure in the training data set, optimal performance in the test data set, and median AUC of each structure identification were 1 (95% CI: 1-1), 1 (95% CI: 1-1), and 1 (95% CI: 1-1), respectively. Regarding structure localization, the optimal average accuracy was 0.83. As for structure identification, the accuracy of the model significantly outperformed the median performance of the experts (P<0.01). The optimal identification accuracies of the model in 2 independent external data sets were 89.5% and 90%, respectively (P=0.626). The model outperformed most human experts and was comparable to the optimal performance of all human experts in cardiac structure identification and localization, and could be used in the external data sets.

Dual center validation of deep learning for automated multi-label segmentation of thoracic anatomy in bedside chest radiographs

Background and ObjectivesBedside chest radiographs (CXRs) are challenging to interpret but important for monitoring cardiothoracic disease and invasive therapy devices in critical care and emergency medicine. Taking surrounding anatomy into account is likely to improve the diagnostic accuracy of artificial intelligence and bring its performance closer to that of a radiologist. Therefore, we aimed to develop a deep convolutional neural network for efficient automatic anatomy segmentation of bedside CXRs. MethodsTo improve the efficiency of the segmentation process, we introduced a "human-in-the-loop" segmentation workflow with an active learning approach, looking at five major anatomical structures in the chest (heart, lungs, mediastinum, trachea, and clavicles). This allowed us to decrease the time needed for segmentation by 32% and select the most complex cases to utilize human expert annotators efficiently. After annotation of 2,000 CXRs from different Level 1 medical centers at Charité – University Hospital Berlin, there was no relevant improvement in model performance, and the annotation process was stopped. A 5-layer U-ResNet was trained for 150 epochs using a combined soft Dice similarity coefficient (DSC) and cross-entropy as a loss function. DSC, Jaccard index (JI), Hausdorff distance (HD) in mm, and average symmetric surface distance (ASSD) in mm were used to assess model performance. External validation was performed using an independent external test dataset from Aachen University Hospital (n = 20). ResultsThe final training, validation, and testing dataset consisted of 1900/50/50 segmentation masks for each anatomical structure. Our model achieved a mean DSC/JI/HD/ASSD of 0.93/0.88/32.1/5.8 for the lung, 0.92/0.86/21.65/4.85 for the mediastinum, 0.91/0.84/11.83/1.35 for the clavicles, 0.9/0.85/9.6/2.19 for the trachea, and 0.88/0.8/31.74/8.73 for the heart. Validation using the external dataset showed an overall robust performance of our algorithm. ConclusionsUsing an efficient computer-aided segmentation method with active learning, our anatomy-based model achieves comparable performance to state-of-the-art approaches. Instead of only segmenting the non-overlapping portions of the organs, as previous studies did, a closer approximation to actual anatomy is achieved by segmenting along the natural anatomical borders. This novel anatomy approach could be useful for developing pathology models for accurate and quantifiable diagnosis.

The integrated single-cell analysis developed a lactate metabolism-driven signature to improve outcomes and immunotherapy in lung adenocarcinoma.

It has been suggested that lactate metabolism (LM) is crucial for the development of cancer. Using integrated single-cell RNA sequencing (scRNA-seq) analysis, we built predictive models based on LM-related genes (LMRGs) to propose novel targets for the treatment of LUAD patients. The most significant genes for LM were identified through the use of the AUCell algorithm and correlation analysis in conjunction with scRNA-seq analysis. To build risk models with superior predictive performance, cox- and lasso-regression were utilized, and these models were validated on multiple external independent datasets. We then explored the differences in the tumor microenvironment (TME), immunotherapy, mutation landscape, and enriched pathways between different risk groups. Finally, cell experiments were conducted to verify the impact of AHSA1 in LUAD. A total of 590 genes that regulate LM were identified for subsequent analysis. Using cox- and lasso-regression, we constructed a 5-gene signature that can predict the prognosis of patients with LUAD. Notably, we observed differences in TME, immune cell infiltration levels, immune checkpoint levels, and mutation landscapes between different risk groups, which could have important implications for the clinical treatment of LUAD patients. Based on LMRGs, we constructed a prognostic model that can predict the efficacy of immunotherapy and provide a new direction for treating LUAD.

A Deep Learning Radiomics Nomogram to Predict Response to Neoadjuvant Chemotherapy for Locally Advanced Cervical Cancer: A Two-Center Study

Purpose: This study aimed to establish a deep learning radiomics nomogram (DLRN) based on multiparametric MR images for predicting the response to neoadjuvant chemotherapy (NACT) in patients with locally advanced cervical cancer (LACC). Methods: Patients with LACC (FIGO stage IB-IIIB) who underwent preoperative NACT were enrolled from center 1 (220 cases) and center 2 (independent external validation dataset, 65 cases). Handcrafted and deep learning-based radiomics features were extracted from T2WI, DWI and contrast-enhanced (CE)-T1WI, and radiomics signatures were built based on the optimal features. Two types of radiomics signatures and clinical features were integrated into the DLRN for prediction. The AUC, calibration curve and decision curve analysis (DCA) were employed to illustrate the performance of these models and their clinical utility. In addition, disease-free survival (DFS) was assessed by Kaplan-Meier survival curves based on the DLRN. Results: The DLRN showed favorable predictive values in differentiating responders from nonresponders to NACT with AUCs of 0.963, 0.940 and 0.910 in the three datasets, with good calibration (all p > 0.05). Furthermore, the DLRN performed better than the clinical model and handcrafted radiomics signature in all datasets (all p < 0.05) and slightly higher than the DL-based radiomics signature in the internal validation dataset (p = 0.251). DCA indicated that the DLRN has potential in clinical applications. Furthermore, the DLRN was strongly correlated with the DFS of LACC patients (HR = 0.223; p = 0.004). Conclusion: The DLRN performed well in preoperatively predicting the therapeutic response in LACC and could provide valuable information for individualized treatment.

Differentiating Glaucomatous Optic Neuropathy From Non-glaucomatous Optic Neuropathies Using Deep Learning Algorithms

A deep learning framework to differentiate glaucomatous optic disc changes due to glaucomatous optic neuropathy (GON) from non-glaucomatous optic disc changes due to non-glaucomatous optic neuropathies (NGONs). Cross-sectional study. A deep-learning system was trained, validated, and externally tested to classify optic discs as normal, GON, or NGON, using 2183 digital color fundus photographs. A Single-Center data set of 1822 images (660 images of NGON, 676 images of GON, and 486 images of normal optic discs) was used for training and validation, whereas 361 photographs from 4 different data sets were used for external testing. Our algorithm removed the redundant information from the images using an optic disc segmentation (OD-SEG) network, after which we performed transfer learning with various pre-trained networks. Finally, we calculated sensitivity, specificity, F1-score, and precision to show the performance of the discrimination network in the validation and independent external data set. For classification, the algorithm with the best performance for the Single-Center data set was DenseNet121, with a sensitivity of 95.36%, precision of 95.35%, specificity of 92.19%, and F1 score of 95.40%. For the external validation data, the sensitivity and specificity of our network for differentiating GON from NGON were 85.53% and 89.02%, respectively. The glaucoma specialist who diagnosed those cases in masked fashion had a sensitivity of 71.05% and a specificity of 82.21%. The proposed algorithm for the differentiation of GON from NGON yields results that have a higher sensitivity than those of a glaucoma specialist, and its application for unseen data thus is extremely promising.

Identification and validation of metabolism-related hub genes in idiopathic pulmonary fibrosis.

Background: Idiopathic pulmonary fibrosis (IPF) is a fatal and irreversible interstitial lung disease. The specific mechanisms involved in the pathogenesis of IPF are not fully understood, while metabolic dysregulation has recently been demonstrated to contribute to IPF. This study aims to identify key metabolism-related genes involved in the progression of IPF, providing new insights into the pathogenesis of IPF. Methods: We downloaded four datasets (GSE32537, GSE110147, GSE150910, and GSE92592) from the Gene Expression Omnibus (GEO) database and identified differentially expressed metabolism-related genes (DEMRGs) in lung tissues of IPF by comprehensive analysis. Then, we performed GO, KEGG, and Reactome enrichment analyses of the DEMRGs. Subsequently, key DEMRGs were identified by machine-learning algorithms. Next, miRNAs regulating these key DEMRGs were predicted by integrating the GSE32538 (IPF miRNA dataset) and the miRWalk database. The Cytoscape software was used to visualize miRNA-mRNA regulatory networks. In addition, the relative levels of immune cells were assessed by the CIBERSORT algorithm, and the correlation of key DEMRGs with immune cells was calculated. Finally, the mRNA expression of the key DEMRGs was validated in two external independent datasets and an in vivo experiment. Results: A total of 101 DEMRGs (51 upregulated and 50 downregulated) were identified. Six key DEMRGs (ENPP3, ENTPD1, GPX3, PDE7B, PNMT, and POLR3H) were further identified using two machine-learning algorithms (LASSO and SVM-RFE). In the lung tissue of IPF patients, the expression levels of ENPP3, ENTPD1, and PDE7B were upregulated, and the expression levels of GPX3, PNMT, and POLR3H were downregulated. In addition, the miRNA-mRNA regulatory network of key DEMRGs was constructed. Then, the expression levels of key DEMRGs were validated in two independent external datasets (GSE53845 and GSE213001). Finally, we verified the key DEMRGs in the lung tissue of bleomycin-induced pulmonary fibrosis mice by qRT-PCR. Conclusion: Our study identified key metabolism-related genes that are differentially expressed in the lung tissue of IPF patients. Our study emphasizes the critical role of metabolic dysregulation in IPF, offers potential therapeutic targets, and provides new insights for future studies.