Independent Test Cohort Research Articles

Detectability of Anatomical Changes With Prompt-Gamma Imaging: First Systematic Evaluation of Clinical Application During Prostate-Cancer Proton Therapy

The development of online-adaptive proton therapy (PT) is essential to overcome limitations encountered by day-to-day variations of the patient's anatomy. Range verification could play an essential role in an online feedback loop for the detection of treatment deviations such as anatomical changes. Here, we present the results of the first systematic patient study regarding the detectability of anatomical changes by a prompt-gamma imaging (PGI) slit-camera system. For 15 patients with prostate cancer, PGI measurements were performed during 105 fractions (201 fields) with in-room control computed tomography (CT)acquisitions. Field-wise doses on control CT scans were manually classified as whether showing relevant or non-relevant anatomical changes. This manual classification of the treatment fields was then used to establish an automatic field-wise ground truth based on spot-wise dosimetric range shifts, which were retrieved from integrated depth-dose (IDD) profiles. To determine the detection capability of anatomical changes with PGI, spot-wise PGI-based range shifts were initially compared with corresponding dosimetric IDD range shifts. As final endpoint, the agreement of a developed field-wise PGI classification model with the field-wise ground truth was determined. Therefore, the PGI model was optimized and tested for a subcohort of 131 and 70 treatment fields, respectively. The correlation between PGI and IDD range shifts was high, ρpearson=0.67 (p < 0.01). Field-wise binary PGI classification resulted in an area under the curve of 0.72 and 0.80 for training and test cohorts, respectively. The model detected relevant anatomical changes in the independent test cohort, with a sensitivity and specificity of 74% and 79%, respectively. For the first time, evidence of the detection capability of anatomical changes in prostate-cancer PT from clinically acquired PGI data is shown. This emphasizes the benefit of PGI-based range verification and demonstrates its potential for online-adaptive PT.

A comparison of feature selection methodologies and learning algorithms in the development of a DNA methylation-based telomere length estimator

BackgroundThe field of epigenomics holds great promise in understanding and treating disease with advances in machine learning (ML) and artificial intelligence being vitally important in this pursuit. Increasingly, research now utilises DNA methylation measures at cytosine–guanine dinucleotides (CpG) to detect disease and estimate biological traits such as aging. Given the challenge of high dimensionality of DNA methylation data, feature-selection techniques are commonly employed to reduce dimensionality and identify the most important subset of features. In this study, our aim was to test and compare a range of feature-selection methods and ML algorithms in the development of a novel DNA methylation-based telomere length (TL) estimator. We utilised both nested cross-validation and two independent test sets for the comparisons.ResultsWe found that principal component analysis in advance of elastic net regression led to the overall best performing estimator when evaluated using a nested cross-validation analysis and two independent test cohorts. This approach achieved a correlation between estimated and actual TL of 0.295 (83.4% CI [0.201, 0.384]) on the EXTEND test data set. Contrastingly, the baseline model of elastic net regression with no prior feature reduction stage performed less well in general—suggesting a prior feature-selection stage may have important utility. A previously developed TL estimator, DNAmTL, achieved a correlation of 0.216 (83.4% CI [0.118, 0.310]) on the EXTEND data. Additionally, we observed that different DNA methylation-based TL estimators, which have few common CpGs, are associated with many of the same biological entities.ConclusionsThe variance in performance across tested approaches shows that estimators are sensitive to data set heterogeneity and the development of an optimal DNA methylation-based estimator should benefit from the robust methodological approach used in this study. Moreover, our methodology which utilises a range of feature-selection approaches and ML algorithms could be applied to other biological markers and disease phenotypes, to examine their relationship with DNA methylation and predictive value.

Artificial intelligence for tumour tissue detection and histological regression grading in oesophageal adenocarcinomas: a retrospective algorithm development and validation study

Oesophageal adenocarcinoma and adenocarcinoma of the oesophagogastric junction are among the most common malignant epithelial tumours. Most patients receive neoadjuvant therapy before complete tumour resection. Histological assessment after resection includes identification of residual tumour tissue and areas of regressive tumour, data which are used to calculate a clinically relevant regression score. We developed an artificial intelligence (AI) algorithm for tumour tissue detection and tumour regression grading in surgical specimens from patients with oesophageal adenocarcinoma or adenocarcinoma of the oesophagogastric junction. We used one training cohort and four independent test cohorts to develop, train, and validate a deep learning tool. The material consisted of histological slides from surgically resected specimens from patients with oesophageal adenocarcinoma and adenocarcinoma of the oesophagogastric junction from three pathology institutes (two in Germany, one in Austria) and oesophageal cancer cohort of The Cancer Genome Atlas (TCGA). All slides were from neoadjuvantly treated patients except for those from the TCGA cohort, who were neoadjuvant-therapy naive. Data from training cohort and test cohort cases were extensively manually annotated for 11 tissue classes. A convolutional neural network was trained on the data using a supervised principle. First, the tool was formally validated using manually annotated test datasets. Next, tumour regression grading was assessed in a retrospective cohort of post-neoadjuvant therapy surgical specimens. The grading of the algorithm was compared with that of a group of 12 board-certified pathologists from one department. To further validate the tool, three pathologists processed whole resection cases with and without AI assistance. Of the four test cohorts, one included 22 manually annotated histological slides (n=20 patients), one included 62 sides (n=15), one included 214 slides (n=69), and the final one included 22 manually annotated histological slides (n=22). In the independent test cohorts the AI tool had high patch-level accuracy for identifying both tumour and regression tissue. When we validated the concordance of the AI tool against analyses by a group of pathologists (n=12), agreement was 63·6% (quadratic kappa 0·749; p<0·0001) at case level. The AI-based regression grading triggered true reclassification of resected tumour slides in seven cases (including six cases who had small tumour regions that were initially missed by pathologists). Use of the AI tool by three pathologists increased interobserver agreement and substantially reduced diagnostic time per case compared with working without AI assistance. Use of our AI tool in the diagnostics of oesophageal adenocarcinoma resection specimens by pathologists increased diagnostic accuracy, interobserver concordance, and significantly reduced assessment time. Prospective validation of the tool is required. North Rhine-Westphalia state, Federal Ministry of Education and Research of Germany, and the Wilhelm Sander Foundation.

DWI-Based Radiomics Predicts the Functional Outcome of Endovascular Treatment in Acute Basilar Artery Occlusion.

Endovascular treatment is a reference treatment for acute basilar artery occlusion (ABAO). However, no established and specific methods are available for the preoperative screening of patients with ABAO suitable for endovascular treatment. This study explores the potential value of DWI-based radiomics in predicting the functional outcomes of endovascular treatment in ABAO. Patients with ABAO treated with endovascular treatment from the BASILAR registry (91 patients in the training cohort) and the hospitals in the Northwest of China (31 patients for the external testing cohort) were included in this study. The Mann-Whitney U test, random forests algorithm, and least absolute shrinkage and selection operator were used to reduce the feature dimension. A machine learning model was developed on the basis of the training cohort to predict the prognosis of endovascular treatment. The performance of the model was evaluated on the independent external testing cohort. A subset of radiomics features (n = 6) was used to predict the functional outcomes in patients with ABAO. The areas under the receiver operating characteristic curve of the radiomics model were 0.870 and 0.781 in the training cohort and testing cohort, respectively. The accuracy of the radiomics model was 77.4%, with a sensitivity of 78.9%, specificity of 75%, positive predictive value of 83.3%, and negative predictive value of 69.2% in the testing cohort. DWI-based radiomics can predict the prognosis of endovascular treatment in patients with ABAO, hence allowing a potentially better selection of patients who are most likely to benefit from this treatment.

Encoding LC-MS-Based Untargeted Metabolomics Data into Images toward AI-Based Clinical Diagnosis.

Liquid chromatography-mass spectrometry (LC-MS)-based untargeted metabolomics provides comprehensive and quantitative profiling of metabolites in clinical investigations. The use of whole metabolome profiles is a promising strategy for disease diagnosis but technically challenging. Here, we developed an approach, namely MetImage, to encode LC-MS-based untargeted metabolomics data into multi-channel digital images. Then, the images that represent the comprehensive metabolome profiles can be employed for developing deep learning-based AI models toward clinical diagnosis. In this work, we demonstrated the application of MetImage for clinical screening of esophageal squamous cell carcinoma (ESCC) in a clinical cohort with 1104 participants. A convolutional neuronal network-based AI model was trained to distinguish ESCC screening positive and negative subjects using their serum metabolomics data. Superior performances such as sensitivity (85%), specificity (92%), and area under curve (0.95) were validated in an independent testing cohort (N = 442). Importantly, we demonstrated that our AI-based ESCC screening model is not a "black box". The encoded images reserved the characteristics of mass spectra from the raw LC-MS data; therefore, metabolite identifications in key image features were readily achieved. Altogether, MetImage is a unique approach that encodes raw LC-MS-based untargeted metabolomics data into images and facilitates the utilization of whole metabolome profiles for AI-based clinical applications with improved interpretability.

Abstract 5414: Automated detection of high-grade urothelial carcinoma from urine cytology slides using attention-based deep learning

Abstract Urine cytology has long been an effective and non-invasive test for the detection of bladder urothelial carcinomas (UC) routinely performed in cases of unexplained hematuria or for monitoring patients with UC. In cytopathology practice, urine cytology specimens are examined manually with a light microscope to identify morphologic features associated with different diagnostic categories based on the Paris System (TPS) for Reporting Urinary Cytology. Specifically, the diagnosis of high-grade urothelial carcinoma (HGUC) requires the identification of &amp;gt; 5-10 cells with a nuclear/cytoplasm ratio of 0.7 or greater and hyperchromasia together with coarse chromatin or irregular nuclear membranes. However, the task of identifying HGUC involves a substantial degree of manual review and is often associated with intra-and inter-observer variability. To address this, we have designed an accurate and efficient deep learning system capable of automatically distinguishing between HGUC and non-HGUC using digitized cytology slides. Our model has been developed using a retrospective cohort of 158 digitized urine ThinPrep cytology slides consisting of HGUC (n=98) and negative for HGUC (n=60). The model was then prospectively validated on a cohort of 105 urine cytology slides that were also independently reviewed prospectively in a blinded manner by a cytopathologist and cytotechnologist. Our system uses Otsu’s method for automatic image thresholding followed by dividing images into non-overlapping tiles of 500 × 500 pixels at the highest magnification. Subsequently, we use a pre-trained ResNet50 model to extract features which are used for training our attention-based multiple instance learning framework. For the training task, our retrospective cohort (158 slides) has been divided into 10 different splits each consisting of training (70%), validation (15%), and testing (15%) sets. The training and validation sets were used for the model training and optimalization, respectively, while the testing set was used for assessing the performance. This process yielded 10 different models with an average Area Under the ROC Curve (AUC) of 0.80 in the testing set. The best performing model had an AUC of 0.90 and an accuracy of 0.88. This model was subsequently validated prospectively in an independent testing cohort with 105 slides. In the prospective testing cohort, the model was able to accurately distinguish between HGUC and non-HGUC with an AUC of 0.83, accuracy of 0.76, sensitivity of 0.89, and specificity of 0.62. Additionally, our system can detect slide regions with high attention score for HGUC which are enriched in atypical urothelial cells. These findings show that our system can be utilized to assist cytopathologists in assessing urine cytology slides and to detect regions with high-diagnostic relevance for further assessment which is expected to reduce the time needed for manual review. Citation Format: Mohamed Omar, David Kim, Luigi Marchionni, Momin T. Siddiqui. Automated detection of high-grade urothelial carcinoma from urine cytology slides using attention-based deep learning. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5414.

Abstract 5369: Detection of ERG:TMPRSS2 gene fusion in prostate cancer from histopathology slides using attention-based deep learning

Abstract ERG:TMPRSS2 fusion is present in almost 50% of prostate cancer (PCa) cases of European ascent and plays an important role in carcinogenesis and disease progression. ERG status is detected using fluorescence in situ hybridization (FISH) or reverse transcription-polymerase chain reaction (RT-PCR), and since these tests are costly and require special training, there is need for innovative tools to decrease the cost and streamline the diagnostic process. For this reason, we have developed a deep learning (DL) system capable of inferring ERG fusion status using only digitized hematoxylin and eosin (H&amp;E)-stained slides from PCa patients, and detecting tissue regions of high diagnostic relevance. To develop the model, we used the PCa TCGA dataset which includes 436 formalin-fixed paraffin-embedded (FFPE) H&amp;E-stained whole slide images (WSIs) from 393 PCa patients who underwent radical prostatectomy. Subsequently, we evaluated the model’s performance on an independent cohort of 314 WSIs provided by the Johns Hopkins University (natural history cohort). Slides were divided into tiles of 500 × 500 px from which feature extraction was performed using a pre-trained ResNet50 model. Feature vectors were then used to train attention-based multiple instance learning framework to predict the slide-level label as either ERG-positive or negative, and to score slide regions based on their contribution to the slide-level representation. Our model can predict the ERG fusion status with an Area Under the ROC Curve (AUC) of 0.84 and 0.73 in the training data and the independent testing cohort, respectively. Also, the model detects tissue regions with high attention score for each class. To decipher the cellular composition in these highly relevant regions for the cases predicted as ERG-positive or negative, we used HoVer-Net model to perform nuclear segmentation and classification into five categories: benign epithelial, tumor, stroma, immune, and necrotic. Notably, we found that the cellular composition of the highly relevant patches can capture prognostic information. Specifically, In the TCGA dataset, a high ratio of neoplastic cells in the relevant patches was significantly associated with worse progression free survival (PFS), while high ratios of necrotic, stromal, and stromal to neoplastic cells were significantly associated with better PFS. Similar findings were also obtained in the natural history cohort in which a high ratio of neoplastic cells was significantly associated with worse overall survival (OS) and metastasis free survival (MFS), while high ratios of immune, stromal, and stromal to neoplastic cells were significantly associated with longer OS and MFS. These results show that ERG fusion status can be inferred from H&amp;E-stained WSIs, ultimately demonstrating the benefit of DL systems in extracting tissue morphological features of high diagnostic and prognostic relevance. Citation Format: Mohamed Omar, Zhuoran Xu, Sophie B. Rand, Daniela C. Salles, Edward M. Schaeffer, Tamara L. Lotan, Massimo Loda, Luigi Marchionni. Detection of ERG:TMPRSS2 gene fusion in prostate cancer from histopathology slides using attention-based deep learning. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5369.

Deep Learning With an Attention Mechanism for Differentiating the Origin of Brain Metastasis Using MR images.

Brain metastasis (BM) is a serious neurological complication of cancer of different origins. The value of deep learning (DL) to identify multiple types of primary origins remains unclear. To distinguish primary site of BM and identify the best DL models. Retrospective. A total of 449 BM derived from 214 patients (49.5% for female, mean age 58 years) (100 from small cell lung cancer [SCLC], 125 from non-small cell lung cancer [NSCLC], 116 from breast cancer [BC], and 108 from gastrointestinal cancer [GIC]) were included. A 3-T, T1 turbo spin echo (T1-TSE), T2-TSE, T2FLAIR-TSE, DWI echo-planar imaging (DWI-EPI) and contrast-enhanced T1-TSE (CE T1-TSE). Lesions were divided into training (n=285, 153 patients), testing (n=122, 93 patients), and independent testing cohorts (n=42, 34 patients). Three-dimensional residual network (3D-ResNet), named 3D ResNet6 and 3D ResNet 18, was proposed for identifying the four origins based on single MRI and combined MRI (T1WI + T2-FLAIR + DWI, CE-T1WI + DWI, CE-T1WI + T2WI + DWI). DL model was used to distinguish lung cancer from non-lung cancer; then SCLC vs. NSCLC for lung cancer classification and BC vs. GIC for non-lung cancer classification was performed. A subjective visual analysis was implemented and compared with DL models. Gradient-weighted class activation mapping (Grad-CAM) was used to visualize the model by heatmaps. The area under the receiver operating characteristics curve (AUC) assess each classification performance. 3D ResNet18 with Grad-CAM and AIC showed better performance than 3DResNet6, 3DResNet18 and the radiologist for distinguishing lung cancer from non-lung cancer, SCLC from NSCLC, and BC from GIC. For single MRI sequence, T1WI, DWI, and CE-T1WI performed best for lung cancer vs. non-lung cancer, SCLC vs. NSCLC, and BC vs. GIC classifications. The AUC ranged from 0.675 to 0.876 and from 0.684 to 0.800 regarding the testing and independent testing datasets, respectively. For combined MRI sequences, the combination of CE-T1WI + T2WI + DWI performed better for BC vs. GIC (AUCs of 0.788 and 0.848 on testing and independent testing datasets, respectively), while the combined MRI approach (T1WI + T2-FLAIR + DWI, CE-T1WI + DWI) could not achieve higher AUCs for lung cancer vs. non-lung cancer, SCLC vs. NSCLC. Grad-CAM helped for model visualization by heatmaps that focused on tumor regions. DL models may help to distinguish the origins of BM based on MRI data. 3 TECHNICAL EFFICACY: Stage 2.

Immune microenvironment and clinical feature analyses based on a prognostic model in lymph node-positive breast cancer.

If lymph node metastasis occurs in breast cancer patients, the disease can progress rapidly. Based on the infiltrative immune cells of breast cancer patients with lymph node positivity, we constructed the LNPRS for selecting prognostic predictors. The LNPRS was established and the predictive value of the LNPRS was verified by independent testing cohorts. A nomogram was also established to confirm the therapeutic guidance significance of the LNPRS. The correlation of the LNPRS with tumor mutation burden, immune microenvironment score, immune checkpoints, the proportion of tumor-infiltrating immune cells, and GSEA and GSVA enrichment pathways were also evaluated. In the training cohort, the overall survival of breast cancer patients who had high LNPRS was shorter than that of patients who had low LNPRS (7.98 years versus 20.42 years, P-value< 8.16E-11). The AUC values for 5-, 10-, and 15-years were 0.787, 0.739, and 0.800, respectively. The ability to predict prognosis for the LNPRS was also tested in 3 independent testing cohorts. Furthermore, the predictive value of the LNPRS for chemotherapy and immunotherapy was also proven. The GSEA and GSVA showed that the LNPRS was closely related to the activation of T and B lymphocytes and IFN-γ secretion. Moreover, breast cancer patients with low LNPRS had higher TME scores than those with high LNPRS. We can conclude that the LNPRS is a robust prognostic biomarker in breast cancer patients with positive lymph nodes and may be helpful for patients to make a clinical decision.

CT-derived fractional flow reserve for prediction of major adverse cardiovascular events in diabetic patients

ObjectivesTo investigate the prognostic value of computed tomography fractional flow reserve (CT-FFR) in patients with diabetes and to establish a risk stratification model for major adverse cardiac event (MACE).MethodsDiabetic patients with intermediate pre-test probability of coronary artery disease were prospectively enrolled. All patients were referred for coronary computed tomography angiography and followed up for at least 2 years. In the training cohort comprising of 957 patients, two models were developed: model1 with the inclusion of clinical and conventional imaging parameters, model2 incorporating the above parameters + CT-FFR. An internal validation cohort comprising 411 patients and an independent external test cohort of 429 patients were used to validate the proposed models.Results1797 patients (mean age: 61.0 ± 7.0 years, 1031 males) were finally included in the present study. MACE occurred in 7.18% (129/1797) of the current cohort during follow- up. Multivariate Cox regression analysis revealed that CT-FFR ≤ 0.80 (hazard ratio [HR] = 4.534, p < 0.001), HbA1c (HR = 1.142, p = 0.015) and low attenuation plaque (LAP) (HR = 3.973, p = 0.041) were the independent predictors for MACE. In the training cohort, the Log-likelihood test showed statistical significance between model1 and model2 (p < 0.001). The C-index of model2 was significantly larger than that of model1 (C-index = 0.82 [0.77–0.87] vs. 0.80 [0.75–0.85], p = 0.021). Similar findings were found in internal validation and external test cohorts.ConclusionCT-FFR was a strong independent predictor for MACE in diabetic cohort. The model incorporating CT-FFR, LAP and HbA1c yielded excellent performance in predicting MACE.

Deep Learning-Based Segmentation of Locally Advanced Breast Cancer on MRI in Relation to Residual Cancer Burden: A Multiinstitutional Cohort Study.

While several methods have been proposed for automated assessment of breast-cancer response to neoadjuvant chemotherapy on breast MRI, limited information is available about their performance across multiple institutions. To assess the value and robustness of deep learning-derived volumes of locally advanced breast cancer (LABC) on MRI to infer the presence of residual disease after neoadjuvant chemotherapy. Retrospective. Training cohort: 102 consecutive female patients with LABC scheduled for neoadjuvant chemotherapy (NAC) from a single institution (age: 25-73 years). Independent testing cohort: 55 consecutive female patients with LABC from four institutions (age: 25-72 years). Training cohort: single vendor 1.5T or 3.0 T. Testing cohort: multivendor 3.0 T. Gradient echo dynamic contrast-enhanced sequences. A convolutional neural network (nnU-Net) was trained to segment LABC. Based on resulting tumor volumes, an extremely randomized tree model was trained to assess residual cancer burden (RCB)-0/I vs. RCB-II/III. An independent model was developed using functional tumor volume (FTV). Models were tested on an independent testing cohort and response assessment performance and robustness across multiple institutions were assessed. The receiver operating characteristic (ROC) was used to calculate the area under the ROC curve (AUC). DeLong's method was used to compare AUCs. Correlations were calculated using Pearson's method. P values<0.05 were considered significant. Automated segmentation resulted in a median (interquartile range [IQR]) Dice score of 0.87 (0.62-0.93), with similar volumetric measurements (R=0.95, P < 0.05). Automated volumetric measurements were significantly correlated with FTV (R=0.80). Tumor volume-derived from deep learning of DCE-MRI was associated with RCB, yielding an AUC of 0.76 to discriminate between RCB-0/I and RCB-II/III, performing similar to the FTV-based model (AUC=0.77, P=0.66). Performance was comparable across institutions (IQR AUC: 0.71-0.84). Deep learning-based segmentation estimates changes in tumor load on DCE-MRI that are associated with RCB after NAC and is robust against variations between institutions. 2. Stage 4.

Contrast-enhanced CT radiomics improves the prediction of abdominal aortic aneurysm progression.

To determine if three-dimensional (3D) radiomic features of contrast-enhanced CT (CECT) images improve prediction of rapid abdominal aortic aneurysm (AAA) growth. This longitudinal cohort study retrospectively analyzed 195 consecutive patients (mean age, 72.4years ± 9.1) with a baseline CECT and a subsequent CT or MR at least 6months later. 3D radiomic features were measured for 3 regions of the AAA, viz. the vessel lumen only; the intraluminal thrombus (ILT) and aortic wall only; and the entire AAA sac (lumen, ILT, and wall). Multiple machine learning (ML) models to predict rapid growth, defined as the upper tercile of observed growth (> 0.25cm/year), were developed using data from 60% of the patients. Diagnostic accuracy was evaluated using the area under the receiver operating characteristic curve (AUC) in the remaining 40% of patients. The median AAA maximum diameter was 3.9cm (interquartile range [IQR], 3.3-4.4cm) at baseline and 4.4cm (IQR, 3.7-5.4cm) at the mean follow-up time of 3.2 ± 2.4years (range, 0.5-9years). A logistic regression model using 7 radiomic features of the ILT and wall had the highest AUC (0.83; 95% confidence interval [CI], 0.73-0.88) in the development cohort. In the independent test cohort, this model had a statistically significantly higher AUC than a model including maximum diameter, AAA volume, and relevant clinical factors (AUC = 0.78, 95% CI, 0.67-0.87 vs AUC = 0.69, 95% CI, 0.57-0.79; p = 0.04). A radiomics-based method focused on the ILT and wall improved prediction of rapid AAA growth from CECT imaging. • Radiomic analysis of 195 abdominal CECT revealed that an ML-based model that included textural features of intraluminal thrombus (if present) and aortic wall improved prediction of rapid AAA progression compared to maximum diameter. • Predictive accuracy was higher when radiomic features were obtained from the thrombus and wall as opposed to the entire AAA sac (including lumen), or the lumen alone. • Logistic regression of selected radiomic features yielded similar accuracy to predict rapid AAA progression as random forests or support vector machines.

A Novel Radiogenomics Biomarker for Predicting Treatment Response and Pneumotoxicity From Programmed Cell Death Protein or Ligand-1 Inhibition Immunotherapy in NSCLC

IntroductionPatient selection for checkpoint inhibitor immunotherapy is currently guided by programmed death-ligand 1 (PD-L1) expression obtained from immunohistochemical staining of tumor tissue samples. This approach is susceptible to limitations resulting from the dynamic and heterogeneous nature of cancer cells and the invasiveness of the tissue sampling procedure. To address these challenges, we developed a novel computed tomography (CT) radiomic-based signature for predicting disease response in patients with NSCLC undergoing programmed cell death protein 1 (PD-1) or PD-L1 checkpoint inhibitor immunotherapy. MethodsThis retrospective study comprises a total of 194 patients with suitable CT scans out of 340. Using the radiomic features computed from segmented tumors on a discovery set of 85 contrast-enhanced chest CTs of patients diagnosed with having NSCLC and their CD274 count, RNA expression of the protein-encoding gene for PD-L1, as the response vector, we developed a composite radiomic signature, lung cancer immunotherapy—radiomics prediction vector (LCI-RPV). This was validated in two independent testing cohorts of 66 and 43 patients with NSCLC treated with PD-1 or PD-L1 inhibition immunotherapy, respectively. ResultsLCI-RPV predicted PD-L1 positivity in both NSCLC testing cohorts (area under the curve [AUC] = 0.70, 95% confidence interval [CI]: 0.57–0.84 and AUC = 0.70, 95% CI: 0.46–0.94). In one cohort, it also demonstrated good prediction of cases with high PD-L1 expression exceeding key treatment thresholds (>50%: AUC = 0.72, 95% CI: 0.59–0.85 and >90%: AUC = 0.66, 95% CI: 0.45–0.88), the tumor’s objective response to treatment at 3 months (AUC = 0.68, 95% CI: 0.52–0.85), and pneumonitis occurrence (AUC = 0.64, 95% CI: 0.48–0.80). LCI-RPV achieved statistically significant stratification of the patients into a high- and low-risk survival group (hazard ratio = 2.26, 95% CI: 1.21–4.24, p = 0.011 and hazard ratio = 2.45, 95% CI: 1.07–5.65, p = 0.035). ConclusionsA CT radiomics-based signature developed from response vector CD274 can aid in evaluating patients’ suitability for PD-1 or PD-L1 checkpoint inhibitor immunotherapy in NSCLC.

Exploration of Lipid Metabolism Alterations in Children with Active Tuberculosis Using UHPLC-MS/MS.

Metabolic profiling using nonsputum samples has demonstrated excellent performance in diagnosing infectious diseases. But little is known about the lipid metabolism alternation in children with tuberculosis (TB). Therefore, the study was performed to explore lipid metabolic changes caused by Mycobacterium tuberculosis infection and identify specific lipids as diagnostic biomarkers in children with TB using UHPLC-MS/MS. Plasma samples obtained from 70 active TB children, 21 non-TB infectious disease children, and 21 healthy controls were analyzed by a partial least-squares discriminant analysis model in the training set, and 12 metabolites were identified that can separate children with TB from non-TB controls. In the independent testing cohort with 49 subjects, three of the markers, PC (15:0/17:1), PC (17:1/18:2), and PE (18:1/20:3), presented with high diagnostic values. The areas under the curve of the three metabolites were 0.904, 0.833, and 0.895, respectively. The levels of the altered lipid metabolites were found to be associated with the severity of the TB disease. Taken together, plasma lipid metabolites are potentially useful for diagnosis of active TB in children and would provide insights into the pathogenesis of the disease.

Ultrasound image-based deep learning to differentiate tubal-ovarian abscess from ovarian endometriosis cyst.

Objectives: We developed ultrasound (US) image-based convolutional neural networks (CNNs) to distinguish between tubal-ovarian abscess (TOA) and ovarian endometriosis cyst (OEC). Methods: A total of 202 patients who underwent US scanning and confirmed tubal-ovarian abscess or ovarian endometriosis cyst by pathology were enrolled in retrospective research, in which 171 patients (from January 2014 to September 2021) were considered the primary cohort (training, validation, and internal test sets) and 31 patients (from September 2021 to December 2021) were considered the independent test cohort. There were 68 tubal-ovarian abscesses and 89 OEC, 4 TOA and 10 OEC, and 10 TOA and 21 OEC patients belonging to training and validation sets, internal sets, and independent test sets, respectively. For the model to gain better generalization, we applied the geometric image and color transformations to augment the dataset, including center crop, random rotation, and random horizontal flip. Three convolutional neural networks, namely, ResNet-152, DenseNet-161, and EfficientNet-B7 were applied to differentiate tubal-ovarian abscess from ovarian endometriosis cyst, and their performance was compared with three US physicians and a clinical indicator of carbohydrate antigen 125 (CA125) on the independent test set. The area under the receiver operating characteristic curves (AUROCs) of accuracy, sensitivity, and specificity were used to evaluate the performance. Results: Among the three convolutional neural networks, the performance of ResNet-152 was the highest, with AUROCs of 0.986 (0.954-1). The AUROCs of the three physicians were 0.781 (0.620-0.942), 0.738 (0.629-848), and 0.683 (0.501-0.865), respectively. The clinical indicator CA125 achieved only 0.564 (0.315-0.813). Conclusion: We demonstrated that the CNN model based on the US image could discriminate tubal-ovarian abscess and ovarian endometriosis cyst better than US physicians and CA125. This method can provide a valuable predictive reference for physicians to screen tubal-ovarian abscesses and ovarian endometriosis cysts in time.

RNA Expression Signatures of Intracranial Aneurysm Growth Trajectory Identified in Circulating Whole Blood.

After detection, identifying which intracranial aneurysms (IAs) will rupture is imperative. We hypothesized that RNA expression in circulating blood reflects IA growth rate as a surrogate of instability and rupture risk. To this end, we performed RNA sequencing on 66 blood samples from IA patients, for which we also calculated the predicted aneurysm trajectory (PAT), a metric quantifying an IA's future growth rate. We dichotomized dataset using the median PAT score into IAs that were either more stable and more likely to grow quickly. The dataset was then randomly divided into training (n = 46) and testing cohorts (n = 20). In training, differentially expressed protein-coding genes were identified as those with expression (TPM > 0.5) in at least 50% of the samples, a q-value < 0.05 (based on modified F-statistics with Benjamini-Hochberg correction), and an absolute fold-change ≥ 1.5. Ingenuity Pathway Analysis was used to construct networks of gene associations and to perform ontology term enrichment analysis. The MATLAB Classification Learner was then employed to assess modeling capability of the differentially expressed genes, using a 5-fold cross validation in training. Finally, the model was applied to the withheld, independent testing cohort (n = 20) to assess its predictive ability. In all, we examined transcriptomes of 66 IA patients, of which 33 IAs were "growing" (PAT ≥ 4.6) and 33 were more "stable". After dividing dataset into training and testing, we identified 39 genes in training as differentially expressed (11 with decreased expression in "growing" and 28 with increased expression). Model genes largely reflected organismal injury and abnormalities and cell to cell signaling and interaction. Preliminary modeling using a subspace discriminant ensemble model achieved a training AUC of 0.85 and a testing AUC of 0.86. In conclusion, transcriptomic expression in circulating blood indeed can distinguish "growing" and "stable" IA cases. The predictive model constructed from these differentially expressed genes could be used to assess IA stability and rupture potential.

Using deep convolutional neural networks to predict patients age based on ECGs from an independent test cohort

Electrocardiography is one of the most frequently used methods to evaluate cardiovascular diseases. However, the last decade has shown that deep convolutional neural networks (CNN) can extract information from the electrocardiogram (ECG) that goes beyond traditional diagnostics, such as predicting a persons age. In this study, we trained two different 1-dimensional CNNs on open datasets to predict age from a persons ECG.&#x0D; The models were trained and validated using 10 seconds long 12-lead ECG records, resampled to 100Hz. 59355 ECGs were used for training and cross-validation, while 21748 ECGs from a separate cohort were used as the test set. We compared the performance achieved on the cross-validation with the performance on the test set. Furthermore, we used cardiologist annotated cardiovascular conditions to categorize the patients in the test set in order to assess whether some cardiac condition leads to greater discrepancies between CNN-predicted age and chronological age.&#x0D; The best CNN model, using an Inception Time architecture, showed a significant drop in performance, in terms of mean absolute error (MAE), from cross-validation on the training set (7.90 ± 0.04 years) to the performance on the test set (8.3 years). On the other hand, the mean squared error (MSE) improved from the training set (117.5 ± 2.7 years^2) to the test set (111 years^2). We also observed that the cardiovascular condition that showed the highest deviation between predicted and biological age, in terms of MAE, was the patients with pacing rhythm (10.5 years), while the patients with prolonged QT-interval had the smallest deviation (7.4 years) in terms of MAE.&#x0D; This work contributes to existing knowledge of age prediction using deep CNNs on ECGs by showing how a trained model performs on a test set from a separate cohort to that used in the training set.

Simultaneous and sequential combination of genetic and epigenetic biomarkers for the presence of high-grade dysplasia in patients with pancreatic cyst: Discovery in cyst fluid and test in pancreatic juice

Background/ObjectivesScreening patients with intraductal papillary mucinous neoplasms (IPMN) has the primary goal of identifying potentially curable noninvasive precursors. We aimed to evaluate the diagnostic impact of genetic and epigenetic biomarkers in the presence of noninvasive precursors. MethodsMutated KRAS/GNAS and methylated SOX17/TBX15/BMP3/TFPI2 DNA were assessed by droplet digital PCR in a discovery cohort of 70 surgically aspirated cyst fluids, and diagnostic performances for differentiating high-grade dysplasia (HGD) from low-grade dysplasia (LGD) was evaluated. We then tested these markers using an independent test cohort consisting of 156 serially collected pancreatic juice samples from 30 patients with IPMN. ResultsMutated KRAS and GNAS are specific for IPMNs but are not helpful for the prediction of histological grades. Cyst fluids from IPMN with HGD showed higher methylation levels of SOX17 (median, 0.141 vs. 0.021; P = 0.086) and TBX15 (median, 0.030 vs. 0.003; P = 0.028) than those with LGD. The combination of all tested markers yielded a diagnostic performance with sensitivity of 69.6%, and specificity of 90.0%. Among the 30 pancreatic juice samples exhibiting the highest abundance of KRAS/GNAS mutations in each patient in the test cohort, patients with histologically proven HGD due to pancreatic resection had a significantly higher prevalence (100% vs. 31%, P = 0.018) and abundance (P = 0.037) of methylated TBX15 than those without cytohistological diagnosis undergoing surveillance. ConclusionsA simultaneous and sequential combination of mutated and methylated DNA markers in pancreatic cyst fluid and juice sample markers can help detect noninvasive pancreatic precursor neoplasms.

An MRI-based Radiomics Approach to Improve Breast Cancer Histological Grading

Nottingham histological grade (NHG) 2 breast cancer has an intermediate risk of recurrence, which is not informative for therapeutic decision-making. We sought to develop and independently validate an MRI-based radiomics signature (Rad-Grade) to improve prognostic re-stratification of NHG 2 tumors. Nine hundred-eight subjects with invasive breast cancer and preoperative MRI scans were retrospectively obtained. The NHG 1 and 3 tumors were randomly split into training and independent test cohort, with the NHG 2 as the prognostic validation set. From MRI image features, a radiomics-based signature predictive of the histological grade was built by use of the LASSO logistic regression algorithm. The model was developed for identifying NHG 1 and 3 radiological patterns, followed with re-stratification of NHG 2 tumors into Rad-Grade (RG)2-low (NHG 1-like) and RG2-high (NHG 3-like) subtypes using the learned patterns, and the prognostic value was assessed in terms of recurrence-free survival (RFS). The Rad-Grade showed independent prognostic value for re-stratification of NHG 2 tumors, where RG2-high had an increased risk for recurrence (HR 2.20, 1.10-4.40, p=0.026) compared with RG2-low after adjusting for established risk factors. RG2-low shared similar phenotypic characteristics and RFS outcomes with NHG 1, and RG2-high with NHG 3, revealing that the model captures radiomic features in NHG 2 that are associated with different aggressiveness. The prognostic value of Rad-Grade was further validated in the NHG2 ER+ (HR 2.53, 1.13-5.56, p=0.023) and NHG 2 ER+LN- (HR 5.72, 1.24-26.44, p=0.025) subgroups, and in specific treatment contexts. The radiomics-based re-stratification of NHG 2 tumors offers a cost-effective promising alternative to gene expression profiling for tumor grading and thus may improve clinical decisions.

External validation of the first prognostic nomogram for older adults with cancer.

The geriatric oncology population tends to be complex because of multimorbidity, functional and cognitive decline, malnutrition and social frailty. Prognostic indices for predicting survival of elderly cancer patients to guide treatment remain scarce. A nomogram based on all domains of the geriatric assessment was previously developed at the National Cancer Centre Singapore (NCCS) to predict overall survival (OS) in elderly cancer patients. This nomogram comprised of six variables (age, eastern cooperative oncology group performance status, disease stage, geriatric depression scale (GDS), DETERMINE nutritional index and serum albumin). To externally validate the NCCS prognostic nomogram. This is a prospective cohort study. The nomogram was developed based on a training cohort of 249 patients aged ⩾70 years who attended the NCCS outpatient geriatric oncology clinic between May 2007 and November 2010. External validation of the nomogram using the Royston and Altman approach was carried out on an independent testing cohort of 252 patients from the same clinic between July 2015 and June 2017. Model misspecification, discrimination and calibration were assessed. Median OS of the testing cohort was 3.1 years, which was significantly higher than the corresponding 1.0 year for the training cohort (log-rank p < 0.001). The nomogram achieved a high level of discrimination in the testing cohort (0.7112), comparable to the training cohort (0.7108). Predicted death probabilities were generally well calibrated with the observed death probabilities, as the joint test of calibration-in-the-large estimates at year 1, 2 and 3 from zeros and calibration slope from one was insignificant with p = 0.432. There were model misspecifications in GDS and serum albumin. This study externally validated the prognostic nomogram in an independent cohort of geriatric oncology patients. This supports the use of this nomogram in clinical practice.