External Test Set Research Articles

Exploring TSPAN4 promoter methylation as a diagnostic biomarker for tuberculosis

Background:Tuberculosis (TB), caused by Mycobacterium tuberculosis (Mtb), is a persistent infectious disease threatening human health. The existing diagnostic methods still have significant shortcomings, including a low positivity rate in pathogen-based diagnoses and the inability of immunological diagnostics to detect active TB. Hence, it is urgent to develop new techniques to detect TB more accurate and earlier. This research aims to scrutinize and authenticate DNA methylation markers suitable for tuberculosis diagnosis. Concurrently, Providing a new approach for tuberculosis diagnosis.Methods:Blood samples from patients with newly diagnosed tuberculosis and healthy controls (HC) were utilized in this study. Examining methylation microarray data from 40 whole blood samples (22TB + 18HC), we employed two procedures: signature gene methylated position analysis and signature region methylated position analysis to pinpoint distinctive methylated positions. Based on the screening results, diagnostic classifiers are constructed through machine learning, and validation was conducted through pyrosequencing in a separate queue (22TB + 18HC). Culminating in the development of a new tuberculosis diagnostic method via quantitative real-time methylation specific PCR (qMSP).Results:The combination of the two procedures revealed a total of 10 methylated positions, all of which were located in the promoter region. These 10 signature methylated positions facilitated the construction of a diagnostic classifier, exhibiting robust diagnostic accuracy in both cross-validation and external test sets. The LDA model demonstrated the best classification performance, achieving an AUC of 0.83, specificity of 0.8, and sensitivity of 0.86 on the external test set. Furthermore, the validation of signature methylated positions through pyrosequencing demonstrated high agreement with screening outcomes. Additionally, qMSP detection of 2 potential hypomethylated positions (cg04552852 and cg12464638) exhibited promising results, yielding an AUC of 0.794, specificity of 0.720, and sensitivity of 0.816.Conclusion:Our study demonstrates that the validated signature methylated positions through pyrosequencing emerge as plausible biomarkers for tuberculosis diagnosis. The specific methylation markers in the TSPAN4 gene, identified in whole blood samples, hold promise for improving tuberculosis diagnosis. This approach could significantly enhance diagnostic accuracy and speed, offering a new avenue for early detection and treatment.

Impact of SUSAN Denoising and ComBat Harmonization on Machine Learning Model Performance for Malignant Brain Neoplasms.

Feature variability in radiomics studies due to technical and magnet strength parameters is well known and may be addressed through various pre-processing methods. However, very few studies have evaluated downstream impact of variable pre-processing on model classification performance in a multi-class setting. We sought to evaluate the impact of SUSAN denoising and ComBat harmonization on model classification performance. A total of 493 cases (410 internal and 83 external dataset) of glioblastoma (GB), intracranial metastatic disease (IMD) and primary CNS lymphoma (PCNSL) underwent semi-automated 3D-segmentation post baseline image processing (BIP) consisting of resampling, realignment, co-registration, skull stripping and image normalization. Post BIP, two sets were generated, one with and another without SUSAN denoising (SD). Radiomics features were extracted from both datasets and batch corrected to produce four datasets: (a) BIP, (b) BIP with SD, (c) BIP with ComBat and (d) BIP with both SD and ComBat harmonization. Performance was then summarized for models using a combination of six feature selection techniques and six machine learning models across four mask-sequence combinations with features derived from one-three (multi-parametric) MRI sequences. Most top performing models on the external test set used BIP+SD derived features. Overall, use of SD and ComBat harmonization led to a slight but generally consistent improvement in model performance on the external test set. The use of image pre-processing steps such as SD and ComBat harmonization may be more useful in a multiinstitutional setting and improve model generalizability. Models derived from only T1-CE images showed comparable performance to models derived from multiparametric MRI.

LUNet: deep learning for the segmentation of arterioles and venules in high resolution fundus images.

This study aims to automate the segmentation of retinal arterioles and venules (A/V) from digital fundus images (DFI), as changes in the spatial distribution of retinal microvasculature are indicative of cardiovascular diseases, positioning the eyes as windows to cardiovascular health.

Approach: We utilized active learning to create a new DFI dataset with 240 crowd-sourced manual A/V segmentations performed by 15 medical students and reviewed by an ophthalmologist. We then developed LUNet, a novel deep learning architecture optimized for high-resolution A/V segmentation. The LUNet model features a double dilated convolutional block to widen the receptive field and reduce parameter count, alongside a high-resolution tail to refine segmentation details. A custom loss function was designed to prioritize the continuity of blood vessel segmentation.

Main Results: LUNet significantly outperformed three benchmark A/V segmentation algorithms both on a local test set and on four external test sets that simulated variations in ethnicity, comorbidities and annotators.

Significance: The release of the new datasets and the LUNet model (URL upon publication) provides a valuable resource for the advancement of retinal microvasculature analysis. The improvements in A/V segmentation accuracy highlight LUNet's potential as a robust tool for diagnosing and understanding cardiovascular diseases through retinal imaging.

An AutomatedDeep Learning-Based Framework for Uptake Segmentation and Classification on PSMA PET/CT Imaging of Patients with Prostate Cancer.

Uptake segmentation and classification on PSMA PET/CT are important for automating whole-body tumor burden determinations. We developed and evaluated an automated deep learning (DL)-based framework that segments and classifies uptake on PSMA PET/CT. We identified 193 [18F] DCFPyL PET/CT scans of patients with biochemically recurrent prostate cancer from two institutions, including 137 [18F] DCFPyL PET/CT scans for training and internally testing, and 56 scans from another institution for external testing. Two radiologists segmented and labelled foci as suspicious or non-suspicious for malignancy. A DL-based segmentation was developed with two independent CNNs. An anatomical prior guidance was applied to make the DL framework focus on PSMA-avid lesions. Segmentation performance was evaluated by Dice, IoU, precision, and recall. Classification model was constructed with multi-modal decision fusion framework evaluated by accuracy, AUC, F1 score, precision, and recall. Automatic segmentation of suspicious lesions was improved under prior guidance, with mean Dice, IoU, precision, and recall of 0.700, 0.566, 0.809, and 0.660 on the internal test set and 0.680, 0.548, 0.749, and 0.740 on the external test set. Our multi-modal decision fusion framework outperformed single-modal and multi-modal CNNs with accuracy, AUC, F1 score, precision, and recall of 0.764, 0.863, 0.844, 0.841, and 0.847 in distinguishing suspicious and non-suspicious foci on the internal test set and 0.796, 0.851, 0.865, 0.814, and 0.923 on the external test set. DL-based lesion segmentation on PSMA PET is facilitated through our anatomical prior guidance strategy. Our classification framework differentiates suspicious foci from those not suspicious for cancer with good accuracy.

Genome-wide 5-hydroxymethylcytosines in circulating cell-free DNA as noninvasive diagnostic markers for gastric cancer.

5-Hydroxymethylcytosine-enriched gene profiles and regions show tissue-specific and tumor specific. There is a potential value to explore cell-free DNA 5-hydroxymethylcytosine feature biomarkers for early gastric cancer detection. A matched case‒control study design with 50 gastric cancer patients and 50 controls was performed to sequence the different 5-hydroxymethylcytosine modification features of cell free DNA. Significantly differential 5-hydroxymethylcytosine modification genes were identified to construct a gastric cancer diagnostic model. Data set from GEO was used as an external testing set to test the robustness of the diagnostic model. Accounting for more than 90% of 5-hydroxymethylcytosine peaks were distributed in the gene body in both the gastric cancer and control groups. The diagnostic model was developed based on five different 5-hydroxymethylcytosine modification genes, FBXL7, PDE3A, TPO, SNTG2 and STXBP5. The model could effectively distinguish gastric cancer patients from controls in the training (AUC = 0.95, sensitivity = 88.6%, specificity = 94.3%), validation (AUC = 0.87, sensitivity = 73.3%, specificity = 93.3%) and testing (AUC = 0.90, sensitivity = 81.9%, specificity = 90.2%) sets. The risk scores of the controls from the model were significantly lower than those of gastric cancer patients in bothour own data (P < 0.001) and GEO external testing data (P < 0.001), and no significant difference between different TNM stage patients (P = 0.09 and 0.66). Furthermore, there was no significant difference between the healthy control and benign gastric disease patients in the testing set from GEO (P = 0.10). The characteristics of 5-hydroxymethylcytosine in cell free DNA are specific to gastric cancer patients, and the diagnostic model constructed by five genes' 5-hydroxymethylcytosine features could effectively identify gastric cancer patients.

The value of machine learning based on CT radiomics in the preoperative identification of peripheral nerve invasion in colorectal cancer: a two-center study

BackgroundWe aimed to explore the application value of various machine learning (ML) algorithms based on multicenter CT radiomics in identifying peripheral nerve invasion (PNI) of colorectal cancer (CRC).MethodsA total of 268 patients with colorectal cancer who underwent CT examination in two hospitals from January 2016 to December 2022 were considered. Imaging and clinicopathological data were collected through the Picture Archiving and Communication System (PACS). The Feature Explorer software (FAE) was used to identify the peripheral nerve invasion of colorectal patients in center 1, and the best feature selection and classification channels were selected. Finally, the best feature selection and classifier pipeline were verified in center 2.ResultsThe six-feature models using RFE feature selection and GP classifier had the highest AUC values, which were 0.610, 0.699, and 0.640, respectively. FAE generated a more concise model based on one feature (wavelet-HLL-glszm-LargeAreaHighGrayLevelEmphasis) and achieved AUC values of 0.614 and 0.663 on the validation and test sets, respectively, using the “one standard error” rule. Using ANOVA feature selection, the GP classifier had the best AUC value in a one-feature model, with AUC values of 0.611, 0.663, and 0.643 on the validation, internal test, and external test sets, respectively. Similarly, when using the “one standard error” rule, the model based on one feature (wave-let-HLL-glszm-LargeAreaHighGrayLevelEmphasis) achieved AUC values of 0.614 and 0.663 on the validation and test sets, respectively.ConclusionsCombining artificial intelligence and radiomics features is a promising approach for identifying peripheral nerve invasion in colorectal cancer. This innovative technique holds significant potential for clinical medicine, offering broader application prospects in the field.Critical relevance statementThe multi-channel ML method based on CT radiomics has a simple operation process and can be used to assist in the clinical screening of patients with CRC accompanied by PNI.Key points• Multi-channel ML in the identification of peripheral nerve invasion in CRC.• Multi-channel ML method based on CT-radiomics can detect the PNI of CRC.• Early preoperative identification of PNI in CRC is helpful to improve the formulation of treatment strategies and the prognosis of patients.Graphical

Prediction of glycosylated hemoglobin level in patients with cardiovascular diseases and type 2 diabetes mellitus with respect to anti-diabetic medication

Blood glycosylated hemoglobin level can be affected by various factors in patients with type 2 diabetes and cardiovascular diseases. Frequent measurements are expensive, and a suitable estimation method could improve treatment outcomes.Patients and methods93 patients were recruited in this research. We analyzed a number of parameters such as age, glucose level, blood pressure, Body Mass Index, cholesterol level, echocardiography et al. Patients were prescribed metformin. One group (n=60) additionally was taking sitagliptin. We applied eight machine learning methods (k nearest neighbors, Random Forest, Support Vector Machine, Extra Trees, XGBoost, Linear Regression including Lasso, and ElasticNet) to predict exact values of glycosylated hemoglobin in two years.ResultsWe applied a feature selection approach using step-by-step removal of them, Linear Regression on remaining features, and Pearson’s correlation coefficient on the validation set. As a result, we got four different subsets for each group. We compared all eight Machine Learning methods using different hyperparameters on validation sets and chose the best models. We tested the best models on the external testing set and got R2 = 0.88, C Index = 0.857, Accuracy = 0.846, and MAE (Mean Absolute Error) = 0.65 for the first group, R2 = 0.86, C Index = 0.80, Accuracy = 0.75, and MAE = 0.41 for the second group.ConclusionThe resulting algorithms could be used to assist clinical decision-making on prescribing anti-diabetic medications in pursuit of achieving glycemic control.

Detection and Grading of Radiographic Hand Osteoarthritis Using an Automated Machine Learning Platform.

Automated machine learning (autoML) platforms allow health care professionals to play an active role in the development of machine learning (ML) algorithms according to scientific or clinical needs. The aim of this study was to develop and evaluate such a model for automated detection and grading of distal hand osteoarthritis (OA). A total of 13,690 hand radiographs from 2,863 patients within the Swiss Cohort of Quality Management (SCQM) and an external control data set of 346 non-SCQM patients were collected and scored for distal interphalangeal OA (DIP-OA) using the modified Kellgren/Lawrence (K/L) score. Giotto (Learn to Forecast [L2F]) was used as an autoML platform for training two convolutional neural networks for DIP joint extraction and subsequent classification according to the K/L scores. A total of 48,892 DIP joints were extracted and then used to train the classification model. Heatmaps were generated independently of the platform. User experience of a web application as a provisional user interface was investigated by rheumatologists and radiologists. The sensitivity and specificity of this model for detecting DIP-OA were 79% and 86%, respectively. The accuracy for grading the correct K/L score was 75%, with a κ score of 0.76. The accuracy per DIP-OA class differed, with 86% for no OA (defined as K/L scores 0 and 1), 71% for a K/L score of 2, 46% for a K/L score of 3, and 67% for a K/L score of 4. Similar values were obtained in an independent external test set. Qualitative and quantitative user experience testing of the web application revealed a moderate to high demand for automated DIP-OA scoring among rheumatologists. Conversely, radiologists expressed a low demand, except for the use of heatmaps. AutoML platforms are an opportunity to develop clinical end-to-end ML algorithms. Here, automated radiographic DIP-OA detection is both feasible and usable, whereas grading among individual K/L scores (eg, for clinical trials) remains challenging.

Development and evaluation of a deep learning-based model for simultaneous detection and localization of rib and clavicle fractures in trauma patients’ chest radiographs

PurposeTo develop a rib and clavicle fracture detection model for chest radiographs in trauma patients using a deep learning (DL) algorithm.Materials and methodsWe retrospectively collected 56 145 chest X-rays (CXRs)...

Multi-step validation of a Post-Endoscopic Retrograde Cholangiopancreatography Pancreatitis prediction system integrating multi-modal data: A multi-center study

Background and study aimsThe impact of various categories of information on the prediction of Post Endoscopic Retrograde Cholangiopancreatography Pancreatitis (PEP) remains uncertain. We aimed to comprehensively investigate the risk factors associated with PEP by constructing and validating a model incorporating multi-modal data through multiple steps. Patients and MethodsA total of 1,916 cases underwent ERCP were retrospectively collected from multiple centers for model construction. Through literature research, 49 electronic health record (EHR) features and one image feature related to PEP were identified. The EHR features were categorized into baseline, diagnosis, technique, and prevent strategies, covering pre-ERCP, intra-ERCP, and peri-ERCP phases. We first incrementally constructed models 1-4 incorporating these four feature categories, then added the image feature into models 1-4 and developed models 5-8. All models underwent testing and comparison using both internal and external test sets. Once the optimal model was selected, we conducted comparison among multiple machine learning algorithms. ResultsCompared with model 2 incorporating baseline and diagnosis features, adding technique and prevent strategies (model 4) greatly improved the sensitivity (63.89% vs 83.33%, p<0.05) and specificity (75.00% vs 85.92%, p<0.001). Similar tendency was observed in internal and external tests. In model 4, the top three features ranked by weight were previous pancreatitis, NSAIDS, and difficult cannulation. The image-based feature has the highest weight in model 5-8. Lastly, model 8 employed Random Forest algorithm showed the best performance. ConclusionsWe firstly developed a multi-modal prediction model for identifying PEP with clinical-acceptable performance. The image and technique features are crucial for PEP prediction.

Predicting Invasiveness of Lung Adenocarcinoma at Chest CT with Deep Learning Ternary Classification Models.

Background Preoperative discrimination of preinvasive, minimally invasive, and invasive adenocarcinoma at CT informs clinical management decisions but may be challenging for classifying pure ground-glass nodules (pGGNs). Deep learning (DL) may improve ternary classification. Purpose To determine whether a strategy that includes an adjudication approach can enhance the performance of DL ternary classification models in predicting the invasiveness of adenocarcinoma at chest CT and maintain performance in classifying pGGNs. Materials and Methods In this retrospective study, six ternary models for classifying preinvasive, minimally invasive, and invasive adenocarcinoma were developed using a multicenter data set of lung nodules. The DL-based models were progressively modified through framework optimization, joint learning, and an adjudication strategy (simulating a multireader approach to resolving discordant nodule classifications), integrating two binary classification models with a ternary classification model to resolve discordant classifications sequentially. The six ternary models were then tested on an external data set of pGGNs imaged between December 2019 and January 2021. Diagnostic performance including accuracy, specificity, and sensitivity was assessed. The χ2 test was used to compare model performance in different subgroups stratified by clinical confounders. Results A total of 4929 nodules from 4483 patients (mean age, 50.1 years ± 9.5 [SD]; 2806 female) were divided into training (n = 3384), validation (n = 579), and internal (n = 966) test sets. A total of 361 pGGNs from 281 patients (mean age, 55.2 years ± 11.1 [SD]; 186 female) formed the external test set. The proposed strategy improved DL model performance in external testing (P < .001). For classifying minimally invasive adenocarcinoma, the accuracy was 85% and 79%, sensitivity was 75% and 63%, and specificity was 89% and 85% for the model with adjudication (model 6) and the model without (model 3), respectively. Model 6 showed a relatively narrow range (maximum minus minimum) across diagnostic indexes (accuracy, 1.7%; sensitivity, 7.3%; specificity, 0.9%) compared with the other models (accuracy, 0.6%-10.8%; sensitivity, 14%-39.1%; specificity, 5.5%-17.9%). Conclusion Combining framework optimization, joint learning, and an adjudication approach improved DL classification of adenocarcinoma invasiveness at chest CT. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Sohn and Fields in this issue.

[Hologram quantitative structure-activity relationship on the gas chromatographic retention index of plant essential oil constituents].

The gas chromatography retention index (RI) is an important parameter for the identification of different types of compounds in the field of chromatographic analysis; however, the experimental collection of RI values is a extremely cumbersome process. Thus, there is an urgent need for the establishment of a simple, efficient, and accurate model for the prediction of the RI values of compounds. In this study, first, the experimental RI values for 60 plant essential oil constituents were obtained. Next, a model describing the hologram quantitative structure-activity relationship (HQSAR) between the structural properties of the essential oil constituents and their RI values was investigated and constructed. The optimal HQSAR model was established by setting the model parameters "fragment size", "fragment distinction", "hologram length" and "principal components" to "1-4", "C, Ch", "199", and "4", respectively. Finally, the predictive ability of the model was verified using external test set validation and leave-one-out cross-validation (LOO-CV). The experimental results were as follows, the root mean square error of prediction (RMSEP), predictive determination coefficient ([Formula: see text]), concordance correlation coefficient (CCC), and mean relative error (MRE) for external test set validation were 40.45, 0.984, 0.968, and 2.20%, respectively. Meanwhile, the root mean square error of cross validation (RMSECV) and MRE for LOO-CV were 72.56 and 4.17%, respectively. These findings demonstrate that the established HQSAR model has a good predictive ability and can accurately predict the RI values of plant essential oil constituents. In addition, the molecular contribution maps of the HQSAR model revealed that the RI values of aromatic compounds increase when hydroxyl groups are connected to their alkyl chains. Aliphatic compounds feature long chain alkyl groups, which can lead to an increase in RI values. The above phenomena highlight the promising application prospects of HQSAR for studying the RI values of plant essential oil constituents. Therefore, this study provides a reliable theoretical basis for predicting the RI values of other essential oil constituents.

Novel peripheral blood mononuclear cell mRNA signature for IFN-beta therapy responsiveness prediction in multiple sclerosis

Interferon-beta (IFN- β ) is one of the classical drugs for immunomodulatory therapy in relapsing-remitting multiple sclerosis (RRMS) patients, but the drug responsiveness of different patients varies. Currently, there is no valid model to predict IFN- β responsiveness. This research attempted to develop an IFN- β responsiveness prediction model based on mRNA expression in RRMS patient peripheral blood mononuclear cells. Peripheral blood mononuclear cell mRNA expression datasets including 50 RRMS patients receiving IFN- β treatment were obtained from GEO. Among the datasets, 24 cases from GSE24427 were included in a training set, and 18 and 9 cases from GSE19285 and GSE33464, respectively, were adopted as two independent test sets. In the training set, blood samples were collected immediately before first, second, month 1, 12, and 24 IFN- β injection, and the mRNA expression data at four time points, namely, two days, one month, one year and two years after the onset of IFN- β treatment, were compared with pre-treatment data to identify IFN-stimulated genes (ISGs). The ISGs at the one-month time point were used to construct the drug responsiveness prediction model. Next, the drug responsiveness model was verified in the two independent test sets to examine the performance of the model in predicting drug responsiveness. Finally, we used CIBERSORTx to estimate the content of cell subtypes in samples and evaluated whether differences in the proportions of cell subtypes were related to differences in IFN- β responsiveness. Among the four time points, one month was the time point when the training set GSE24427 and test set GSE33464 had the highest number of ISGs. Functional analysis showed that these one-month ISGs were enriched in biological functions such as the innate immune response, type-I interferon signalling pathway, and other IFN- β -associated functions. Based on these ISGs, we obtained a four-factor prediction model for IFN- β responsiveness including MX1, MX2, XAF1, and LAMP3. In addition, the model demonstrated favourable predictive performance within the training set and two external test sets. A higher proportion of activated NK cells and lower naive CD4/total CD4 ratio might indicate better drug responsiveness. This research developed a polygene-based biomarker model that could predict RRMS patient IFN- β responsiveness in the early treatment period. This model could probably help doctors screen out patients who would not benefit from IFN- β treatment early and determine whether a current treatment plan should be continued.

Automatic segmentation of fat metaplasia on sacroiliac joint MRI using deep learning

ObjectiveTo develop a deep learning (DL) model for segmenting fat metaplasia (FM) on sacroiliac joint (SIJ) MRI and further develop a DL model for classifying axial spondyloarthritis (axSpA) and non-axSpA.Materials and methodsThis study retrospectively collected 706 patients with FM who underwent SIJ MRI from center 1 (462 axSpA and 186 non-axSpA) and center 2 (37 axSpA and 21 non-axSpA). Patients from center 1 were divided into the training, validation, and internal test sets (n = 455, 64, and 129). Patients from center 2 were used as the external test set. We developed a UNet-based model to segment FM. Based on segmentation results, a classification model was built to distinguish axSpA and non-axSpA. Dice Similarity Coefficients (DSC) and area under the curve (AUC) were used for model evaluation. Radiologists’ performance without and with model assistance was compared to assess the clinical utility of the models.ResultsOur segmentation model achieved satisfactory DSC of 81.86% ± 1.55% and 85.44% ± 6.09% on the internal cross-validation and external test sets. The classification model yielded AUCs of 0.876 (95% CI: 0.811–0.942) and 0.799 (95% CI: 0.696–0.902) on the internal and external test sets, respectively. With model assistance, segmentation performance was improved for the radiological resident (DSC, 75.70% vs. 82.87%, p < 0.05) and expert radiologist (DSC, 85.03% vs. 85.74%, p > 0.05).ConclusionsDL is a novel method for automatic and accurate segmentation of FM on SIJ MRI and can effectively increase radiologist’s performance, which might assist in improving diagnosis and progression of axSpA.Critical relevance statementDL models allowed automatic and accurate segmentation of FM on sacroiliac joint MRI, which might facilitate quantitative analysis of FM and have the potential to improve diagnosis and prognosis of axSpA.Key points• Deep learning was used for automatic segmentation of fat metaplasia on MRI.• UNet-based models achieved automatic and accurate segmentation of fat metaplasia.• Automatic segmentation facilitates quantitative analysis of fat metaplasia to improve diagnosis and prognosis of axial spondyloarthritis.Graphical

Screening and staging of chronic obstructive pulmonary disease with deep learning based on chest X-ray images and clinical parameters

BackgroundChronic obstructive pulmonary disease (COPD) is underdiagnosed with the current gold standard measure pulmonary function test (PFT). A more sensitive and simple option for early detection and severity evaluation of COPD could benefit practitioners and patients.MethodsIn this multicenter retrospective study, frontal chest X-ray (CXR) images and related clinical information of 1055 participants were collected and processed. Different deep learning algorithms and transfer learning models were trained to classify COPD based on clinical data and CXR images from 666 subjects, and validated in internal test set based on 284 participants. External test including 105 participants was also performed to verify the generalization ability of the learning algorithms in diagnosing COPD. Meanwhile, the model was further used to evaluate disease severity of COPD by predicting different grads.ResultsThe Ensemble model showed an AUC of 0.969 in distinguishing COPD by simultaneously extracting fusion features of clinical parameters and CXR images in internal test, better than models that used clinical parameters (AUC = 0.963) or images (AUC = 0.946) only. For the external test set, the AUC slightly declined to 0.934 in predicting COPD based on clinical parameters and CXR images. When applying the Ensemble model to determine disease severity of COPD, the AUC reached 0.894 for three-classification and 0.852 for five-classification respectively.ConclusionThe present study used DL algorithms to screen COPD and predict disease severity based on CXR imaging and clinical parameters. The models showed good performance and the approach might be an effective case-finding tool with low radiation dose for COPD diagnosis and staging.

Abstract 4796: Improving cancer screening performance for women with dense breast tissue

Abstract Breast cancer is the most common cancer in women in the United States. To reduce mortality, screening by mammography in females is recommended by the United States Preventive Services Task Force, successfully reducing mortality by 15 - 32% in women aged 40 - 69 years. This is partially due to the high compliance rate (60 - 80%) among the candidate population. Mammography increases early-stage disease detection, which is correlated with better outcomes. While mammography has been largely successful, this screening method has limitations. Overall, mammography has false-negative and false-positive rates estimated at 12 - 20% and 7 - 12%, respectively. Consequently, annual mammograms result in 50 - 60% of women having a false-positive result within a 10-year span. Additionally, high breast density, found in approximately 50% of females over the age of 40, increases susceptibility to false positive and negative results. For this reason, in 2023 the FDA required that dense breast tissue status, an independent risk factor for cancer, be disclosed to mammogram recipients. The subsequent diagnostic pathway for women with dense breast tissue is not well defined for the care provider. Alternative imaging options have performance issues or are less accessible. Here we describe a liquid biopsy test to complement mammography in women with dense breast tissue to help resolve ambiguity in results. Blood from early- and late-stage breast cancer patients was prospectively collected in Streck cfDNA BCT Devices (n=100) or retrospectively acquired (n=100); and blood from presumed normal samples was collected (n=200). cfDNA was extracted and converted into libraries for low-pass whole genome sequencing (LP-WGS). Sequenced reads were analyzed to generate fragment end-motif and size (FEMS) and fragment coverage dataframes for classification using Genece Health’s proprietary analysis pipeline and machine-learning (ML) algorithm. 150 breast cancer samples distributed across stages and 150 presumed normal samples were selected to create a training cohort. Performance was tested using a 5-fold cross validation strategy. The best performance was observed using a convolution neural network (CNN) ML model with &amp;gt;80% sensitivity when specificity was set at 85%. The remaining 50 breast cancer samples and 50 presumed normal samples were used as an external test set. The performance in this cohort was comparable to the training cohort, with both specificity and sensitivity &amp;gt;80%. Genece presents an early proof of concept breast cancer screening liquid biopsy assay that uses LP-WGS fragmentomics and ML to detect cancer from a single blood sample. Continuing development with additional cohorts and optimization will yield even greater performance. The Genece liquid biopsy test has the potential to be paired with mammography, especially in women with dense breast tissue, to improve screening sensitivity, specificity, and overall outcomes. Citation Format: Molly Smith, Mengchi Wang, Andrew Carson, Byung In Lee, Michael Salmans, Bryan Leatham. Improving cancer screening performance for women with dense breast tissue [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4796.

Radiomics model based on intratumoral and peritumoral features for predicting major pathological response in non-small cell lung cancer receiving neoadjuvant immunochemotherapy.

To establish a radiomics model based on intratumoral and peritumoral features extracted from pre-treatment CT to predict the major pathological response (MPR) in patients with non-small cell lung cancer (NSCLC) receiving neoadjuvant immunochemotherapy. A total of 148 NSCLC patients who underwent neoadjuvant immunochemotherapy from two centers (SRRSH and ZCH) were retrospectively included. The SRRSH dataset (n=105) was used as the training and internal validation cohort. Radiomics features of intratumoral (T) and peritumoral regions (P1=0-5mm, P2=5-10mm, and P3=10-15mm) were extracted from pre-treatment CT. Intra- and inter- class correlation coefficients and least absolute shrinkage and selection operator were used to feature selection. Four single ROI models mentioned above and a combined radiomics (CR: T+P1+P2+P3) model were established by using machine learning algorithms. Clinical factors were selected to construct the combined radiomics-clinical (CRC) model, which was validated in the external center ZCH (n=43). The performance of the models was assessed by DeLong test, calibration curve and decision curve analysis. Histopathological type was the only independent clinical risk factor. The model CR with eight selected radiomics features demonstrated a good predictive performance in the internal validation (AUC=0.810) and significantly improved than the model T (AUC=0.810 vs 0.619, p<0.05). The model CRC yielded the best predictive capability (AUC=0.814) and obtained satisfactory performance in the independent external test set (AUC=0.768, 95% CI: 0.62-0.91). We established a CRC model that incorporates intratumoral and peritumoral features and histopathological type, providing an effective approach for selecting NSCLC patients suitable for neoadjuvant immunochemotherapy.

Exploring personalized treatment for cardiac graft rejection based on a four-archetype analysis model and bioinformatics analysis

Heart transplantation is the gold standard for treating patients with advanced heart failure. Although improvements in immunosuppressive therapies have significantly reduced the frequency of cardiac graft rejection, the incidences of T cell-mediated rejection (TCMR) and antibody-mediated rejection remain almost unchanged. A four-archetype analysis (4AA) model, developed by Philip F. Halloran, illustrated this problem well. It provided a new dimension to improve the accuracy of diagnoses and an independent system for recalibrating the histology guidelines. However, this model was based on the invasive method of endocardial biopsy, which undoubtedly increased the postoperative risk of heart transplant patients. Currently, little is known regarding the associated genes and specific functions of the different phenotypes. We performed bioinformatics analysis (using machine-learning methods and the WGCNA algorithm) to screen for hub-specific genes related to different phenotypes, based Gene Expression Omnibus accession number GSE124897. More immune cell infiltration was observed with the ABMR, TCMR, and injury phenotypes than with the stable phenotype. Hub-specific genes for each of the four archetypes were verified successfully using an external test set (accession number GSE2596). Logistic-regression models based on TCMR-specific hub genes and common hub genes were constructed with accurate diagnostic utility (area under the curve > 0.95). RELA, NFKB1, and SOX14 were identified as transcription factors important for TCMR/injury phenotypes and common genes, respectively. Additionally, 11 Food and Drug Administration-approved drugs were chosen from the DrugBank Database for each four-archetype model. Tyrosine kinase inhibitors may be a promising new option for transplant rejection treatment. KRAS signaling in cardiac transplant rejection is worth further investigation. Our results showed that heart transplant rejection subtypes can be accurately diagnosed by detecting expression of the corresponding specific genes, thereby enabling precise treatment or medication.

Diffusion-weighted imaging-based radiomics model using automatic machine learning to differentiate cerebral cystic metastases from brain abscesses

ObjectivesTo develop a radiomics model based on diffusion-weighted imaging (DWI) utilizing automated machine learning method to differentiate cerebral cystic metastases from brain abscesses.Materials and methodsA total of 186 patients with cerebral cystic metastases (n = 98) and brain abscesses (n = 88) from two clinical institutions were retrospectively included. The datasets (129 from institution A) were randomly portioned into separate 75% training and 25% internal testing sets. Radiomics features were extracted from DWI images using two subregions of the lesion (cystic core and solid wall). A thorough image preprocessing method was applied to DWI images to ensure the robustness of radiomics features before feature extraction. Then the Tree-based Pipeline Optimization Tool (TPOT) was utilized to search for the best optimized machine learning pipeline, using a fivefold cross-validation in the training set. The external test set (57 from institution B) was used to evaluate the model’s performance.ResultsSeven distinct TPOT models were optimized to distinguish between cerebral cystic metastases and abscesses either based on different features combination or using wavelet transform. The optimal model demonstrated an AUC of 1.00, an accuracy of 0.97, sensitivity of 1.00, and specificity of 0.93 in the internal test set, based on the combination of cystic core and solid wall radiomics signature using wavelet transform. In the external test set, this model reached 1.00 AUC, 0.96 accuracy, 1.00 sensitivity, and 0.93 specificity.ConclusionThe DWI-based radiomics model established by TPOT exhibits a promising predictive capacity in distinguishing cerebral cystic metastases from abscesses.

Evaluating the Robustness of a Deep Learning Bone Age Algorithm to Clinical Image Variation Using Computational Stress Testing.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To evaluate the robustness of an award-winning bone age deep learning (DL) model to extensive variations in image appearance. Materials and Methods In December 2021, the DL bone age model that won the 2017 RSNA Pediatric Bone Age Challenge was retrospectively evaluated using the Radiological Society of North America (RSNA) validation set (n = 1425 pediatric hand radiographs; internal test set) and the Digital Hand Atlas (DHA; n = 1202 pediatric hand radiographs; external test set). Each test image underwent seven types of transformations (rotations, flips, brightness, contrast, inversion, laterality marker, and resolution) to represent a range of image appearances, many of which simulate real-world variations. Computational "stress tests" were performed by comparing the model's predictions on baseline and transformed images. Mean absolute differences (MAD) of predicted bone ages compared with radiologist-determined ground truth on baseline versus transformed images were compared using Wilcoxon Signed Rank tests. The proportion of clinically significant errors (CSE) was compared using McNemar's tests. Results There was no evidence of a difference in MAD of the model on the two baseline test sets (RSNA = 6.8, DHA = 6.9; P = .05), indicating good model generalization to external data. Except for the RSNA images with an appended radiologic laterality marker (P = .86), there were significant differences in MAD for both the DHA and RSNA datasets among other transformation groups (rotations, flips, brightness, contrast, inversion, and resolution). There were significant differences in proportion of CSEs for 57.6% (19/33) of the image transformations performed on the DHA dataset. Conclusion Although an award-winning pediatric bone age DL model generalized well to curated external images, it had inconsistent predictions on images that had undergone simple transformations reflective of several real-world variations in image appearance. ©RSNA, 2024.