Prediction Of Lymph Node Metastasis Research Articles

Ultra-high b-value DWI in rectal cancer: image quality assessment and regional lymph node prediction based on radiomics.

This study aims to evaluate image quality and regional lymph node metastasis (LNM) in patients with rectal cancer (RC) on multi-b-value diffusion-weighted imaging (DWI). This retrospective study included 199 patients with RC who had undergone multi-b-value DWI. Subjective (five-point Likert scale) and objective assessments of quality images were performed on DWIb1000, DWIb2000, and DWIb3000. Patients were randomly divided into a training (n = 140) or validation cohort (n = 59). Radiomics features were extracted within the whole volume tumor on ADC maps (b = 0, 1000 s/mm2), DWIb1000, DWIb2000, and DWIb3000, respectively. Five prediction models based on selected features were developed using logistic regression analysis. The performance of radiomics models was evaluated with a receiver operating characteristic curve, calibration, and decision curve analysis (DCA). The mean signal intensity of the tumor (SItumor), signal-to-noise ratio (SNR), and artifact and anatomic differentiability score gradually weredecreased as the b-value increased. However, the contrast-to-noise (CNR) on DWIb2000 was superior to those of DWIb1000 and DWIb3000 (4.58 ± 0.86, 3.82 ± 0.77, 4.18 ± 0.84, p < 0.001, respectively). The overall image quality score of DWIb2000 was higher than that of DWIb3000 (p < 0.001) and showed no significant difference between DWIb1000 and DWIb2000 (p = 0.059). The area under curve (AUC) value of the radiomics model based on DWIb2000 (0.728) was higher than conventional ADC maps (0.690), DWIb1000 (0.699), and DWIb3000 (0.707), but inferior to multi-b-value DWI (0.739) in predicting LNM. DWIb2000 provides better lesion conspicuity and LNM prediction than DWIb1000 and DWIb3000 in RC. DWIb2000 offers satisfactory visualization of lesions. Radiomics features based on DWIb2000 can be applied for preoperatively predicting regional lymph node metastasis in rectal cancer, thereby benefiting the stratified treatment strategy. Lymph node staging is required to determine the best treatment plan for rectal cancer. DWIb2000 provides superior contrast-to-noise ratio and lesion conspicuity and its derived radiomics best predict lymph node metastasis. DWIb2000 may be recommended as the optimal b-value in rectal MRI protocol.

A Preoperative Prediction Model for Lymph Node Metastasis in Patients with Gastric Cancer Using a Machine Learning-based Ultrasomics Approach.

This study aimed to develop an ultrasomics model for predicting lymph node metastasis preoperative in patients with gastric cancer (GC). This study enrolled GC patients who underwent preoperative ultrasound examination. Manual segmentation of the region of interest (ROI) was performed by an experienced radiologist to extract radiomics features using the Pyradiomics software. The Z-score algorithm was used for feature normalization, followed by the Wilcoxon test to identify the most informative features. Linear prediction models were constructed using the least absolute shrinkage and selection operator (LASSO). The performance of the ultrasomics model was evaluated using the area under curve (AUC), sensitivity, specificity, and the corresponding 95% confidence intervals (CIs). A total of 464 GC patients (mean age: 60.4 years ±11.3 [SD]; 328 men [70.7%]) were analyzed, of whom 291 had lymph node metastasis. The patients were randomly assigned to either the training (n=324) or test (n=140) sets, using a 7:3 ratio. An ultrasomics model that consisted of 19 radiomics features was developed using Wilcoxon and LASSO algorithms in the training set. Our ultrasomics model showed moderate performance for lymph node metastasis prediction in both the training (AUC: 0.802, 95%CI: 0.752-0.851, P<0.001) and test sets (AUC: 0.802, 95%CI: 0.724-0.879, P<0.001). The calibration curve analysis indicated good agreement between the predicted probabilities of ultrasomics and actual lymph node metastasis status. Our study highlights the potential of a machine learning-based ultrasomics model in predicting lymph node metastasis in GC patients, offering implications for personalized therapy approaches.

Occult lymph node metastasis prediction in non-small cell lung cancer based self-supervised pretrained and hyperbolic theory

Predicting occult lymph node metastasis in non-small cell lung cancer (NSCLC) patients is pivotal for tailoring appropriate surgical and therapeutic interventions. This prognostic factor remains underexplored, largely due to the intricate variability of occult lymph node characteristics and the absence of a pathologically confirmed predictive dataset. Addressing this gap, we retrospectively assembled a dataset of occult lymph node metastases (TJ-OLNM) from NSCLC patients who underwent chest Computed Tomography (CT) scans at Tongji Hospital, Tongji University from 2016 to 2021. Utilizing this dataset, we developed a novel self-supervised learning model, the Occult Lymph Node Metastasis Network (OLNM-Net), which leverages hyperbolic metric few-shot learning to enhance the prediction accuracy of occult metastases. Our comprehensive evaluations demonstrate that OLNM-Net significantly outperforms existing models in predicting occult lymph node metastasis, offering new insights into the preoperative assessment of NSCLC and advancing the application of machine learning in medical diagnostics.

Predictors of lung cancer subtypes and lymph node status in non-small-cell lung cancer: intravoxel incoherent motion parameters and extracellular volume fraction

ObjectiveTo determine the performance of intravoxel incoherent motion (IVIM) parameters and the extracellular volume fraction (ECV) in distinguishing between different subtypes of lung cancer and predicting lymph node metastasis (LNM) status in patients with non-small-cell lung cancer (NSCLC).MethodsOne hundred sixteen patients with lung cancer were prospectively recruited. IVIM, native, and postcontrast T1 mapping examinations were performed, and the T1 values were measured to calculate the ECV. The differences in IVIM parameters and ECV were compared between NSCLC and small-cell lung cancer (SCLC), adenocarcinoma (Adeno-Ca) and squamous cell carcinoma (SCC), and NSCLC without and with LNM. The assessment of each parameter’s diagnostic performance was based on the area under the receiver operating characteristic curve (AUC).ResultsThe apparent diffusion coefficient (ADC), true diffusion coefficient (D), and ECV values in SCLC were considerably lower compared with NSCLC (all p < 0.001, AUC > 0.887). The D value in SCC was substantially lower compared with Adeno-Ca (p < 0.001, AUC = 0.735). The perfusion fraction (f) and ECV values in LNM patients were markedly higher compared with those without LNM patients (p < 0.01, < 0.001, AUC > 0.708).ConclusionIVIM parameters and ECV can serve as non-invasive biomarkers for assisting in the pathological classification and LNM status assessment of lung cancer patients.Critical relevance statementIVIM parameters and ECV demonstrated remarkable potential in distinguishing pulmonary carcinoma subtypes and predicting LNM status in NSCLC.Key PointsLung cancer is prevalent and differentiating subtype and invasiveness determine the treatment course.True diffusion coefficient and ECV showed promise for subtyping and determining lymph node status.These parameters could serve as non-invasive biomarkers to help determine personalized treatment strategies.Graphical

Can physician judgment enhance model trustworthiness? A case study on predicting pathological lymph nodes in rectal cancer

Explainability is key to enhancing the trustworthiness of artificial intelligence in medicine. However, there exists a significant gap between physicians’ expectations for model explainability and the actual behavior of these models. This gap arises from the absence of a consensus on a physician-centered evaluation framework, which is needed to quantitatively assess the practical benefits that effective explainability should offer practitioners. Here, we hypothesize that superior attention maps, as a mechanism of model explanation, should align with the information that physicians focus on, potentially reducing prediction uncertainty and increasing model reliability. We employed a multimodal transformer to predict lymph node metastasis of rectal cancer using clinical data and magnetic resonance imaging. We explored how well attention maps, visualized through a state-of-the-art technique, can achieve agreement with physician understanding. Subsequently, we compared two distinct approaches for estimating uncertainty: a standalone estimation using only the variance of prediction probability, and a human-in-the-loop estimation that considers both the variance of prediction probability and the quantified agreement. Our findings revealed no significant advantage of the human-in-the-loop approach over the standalone one. In conclusion, this case study did not confirm the anticipated benefit of the explanation in enhancing model reliability. Superficial explanations could do more harm than good by misleading physicians into relying on uncertain predictions, suggesting that the current state of attention mechanisms should not be overestimated in the context of model explainability.

Deep Learning Histology for Prediction of Lymph Node Metastases and Tumor Regression after Neoadjuvant FLOT Therapy of Gastroesophageal Adenocarcinoma.

The aim of this study was to establish a deep learning prediction model for neoadjuvant FLOT chemotherapy response. The neural network utilized clinical data and visual information from whole-slide images (WSIs) of therapy-naïve gastroesophageal cancer biopsies. This study included 78 patients from the University Hospital of Cologne and 59 patients from the University Hospital of Heidelberg used as external validation. After surgical resection, 33 patients from Cologne (42.3%) were ypN0 and 45 patients (57.7%) were ypN+, while 23 patients from Heidelberg (39.0%) were ypN0 and 36 patients (61.0%) were ypN+ (p = 0.695). The neural network had an accuracy of 92.1% to predict lymph node metastasis and the area under the curve (AUC) was 0.726. A total of 43 patients from Cologne (55.1%) had less than 50% residual vital tumor (RVT) compared to 34 patients from Heidelberg (57.6%, p = 0.955). The model was able to predict tumor regression with an error of ±14.1% and an AUC of 0.648. This study demonstrates that visual features extracted by deep learning from therapy-naïve biopsies of gastroesophageal adenocarcinomas correlate with positive lymph nodes and tumor regression. The results will be confirmed in prospective studies to achieve early allocation of patients to the most promising treatment.

Feature Selection and Classification Technique for Predicting Lymph Node Metastasis of Papillary Thyroid Carcinoma

Feature Selection and Classification Technique for Predicting Lymph Node Metastasis of Papillary Thyroid Carcinoma

The Sex and Age-Associated Infiltration of B Cells May Result in the Dimorphic Behaviors Observed in Papillary Thyroid Carcinomas.

Sex and age show a dimorphism role in the pathogenesis, lymph node metastasis, and prognostic outcomes of papillary thyroid carcinoma. This investigation endeavors to elucidate the mechanisms underlying these disparities. The clinicopathological characteristics and risk factors of lymph node metastasis were explored by analyzing the 2261 patients. The gene expression information of 497 samples from The Cancer Genome Atlas Thyroid Cancer database was used to explore the differentially expressed genes in different phenotypes. What's more, the single-cell RNA sequencing data obtained from the Gene Expression Omnibus database was used to explore the gene expression in specific cells. Multivariate logistic regression analysis showed that in male patients, a larger tumor size, extrathyroidal extension, younger age, and the presence of calcification emerged as significant predictors for lymph node metastasis (LNM)(p < 0.05). Conversely, female patients exhibited a different profile, with larger tumor size, extrathyroidal extension, younger age, calcification, and bilateral tumors being identified as key risk factors (p < 0.05). Further stratification by age demonstrated distinct patterns: among the younger cohort, a larger tumor size, extrathyroidal extension, male gender, calcification, multifocality, and the presence of Hashimoto's thyroiditis held statistical significance (p < 0.05). In contrast, the older subgroup was characterized by a larger tumor size, extrathyroidal extension, male gender, calcification, bilateral tumors, and unclear margins as salient indicators of risk (p < 0.05). In the bulk gene analysis, there were two sex-age-related differentially expressed genes with a contrary trend in tissue sources and LNM status: TCL1A and CR2. The analysis of single-cell RNA sequencing showed that the infiltration of TCL1A- and CR2-related B cells varied in different clinical subtypes. Lymph node metastasis of papillary thyroid carcinoma in different sexes and ages may have distinct patterns, and the ages-sex-related B cell infiltration might explain the dimorphism biological behavior.

Preoperative computed tomography semantic features in predicting lymph node metastasis of part-solid nodules in non-small cell lung cancer: a multicenter retrospective study.

Lymph node metastasis (LNM) is the most common route of metastasis for lung cancer, and it is an independent risk factor for long-term survival and recurrence in patients with non-small cell lung cancer (NSCLC). The purpose of this study was to explore the value of preoperative computed tomography (CT) semantic features in the differential diagnosis of LNM in part-solid nodules (PSNs) of NSCLC. A total of 955 patients with NSCLC confirmed by postoperative pathology were retrospectively enrolled from January 2019 to March 2023. The clinical, pathological data and preoperative CT images of these patients were investigated and statistically analyzed in order to identify the risk factors for LNM. Multivariate logistic regression was used to select independent risk factors and establish different prediction models. Ten-fold cross-validation was used for model training and validation. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was calculated, and the Delong test was used to compare the predictive performance between the models. LNM occurred in 68 of 955 patients. After univariate analysis and adjustment for confounding factors, smoking history, pulmonary disease, solid component proportion, pleural contact type, and mean diameter were identified as the independent risk factors for LNM. The image predictors model established by the four independent factors of CT semantic features, except smoking history, showed a good diagnostic efficacy for LNM. The AUC in the validation group was 0.857, and the sensitivity, specificity, and accuracy of the model were all 77.6%. Preoperative CT semantic features have good diagnostic value for the LNM of NSCLC. The image predictors model based on pulmonary disease, solid component proportion, pleural contact type, and mean diameter demonstrated excellent diagnostic efficacy and can provide non-invasive evaluation in clinical practice.

Preoperative prediction of central lymph node metastasis in follicular variant of papillary thyroid carcinoma using clinical and ultrasound features.

The most common metastatic site of follicular variant of papillary thyroid carcinoma (FVPTC) is the central lymph nodes, which may be associated with the prognosis and survival of patients. In the present study, we establish a combined model based on preoperative clinical and ultrasound (US) features of FVPTC to predict the risk of central lymph node metastasis (CLNM). From January 2013 to December 2022, 315 patients with FVPTC were enrolled and randomly divided into the training and validation cohorts in a ratio of 7:3. The independent risk factors for CLNM in FVPTC were analysed using univariate and multivariate logistic regression analyses. Then, three different models were established based on clinical and US data. Subsequently, a nomogram was constructed to predict CLNM. Its predictive effect was evaluated via receiver operating characteristic and calibration curve analyses. Backward multivariate regression analysis revealed that age (P=0.001), thyroid peroxidase antibody (TPOAb) (P=0.11), diameter (P=0.047), irregular/lobulated margin (P=0.15), extrathyroidal extension (P=0.001), nodules with macrocalcifications (P=0.009), nodules with microcalcification (P=0.003) and Thyroid Imaging Reporting and Data System (ACR-TI-RADS) category 5 (P=0.33) were independent risk factors for CLNM in FVPTC. The areas under the curve of the matching nomogram in the training (N=221) and validation cohorts (N=94) were 0.841 [95% confidence interval (CI): 0.788-0.895] and 0.735 (95% CI: 0.621-0.872), respectively. Preoperative thyroid US provides useful features for prediction of CLNM. The nomogram constructed based on combining US and clinical features can better predict the risk of CLNM and may facilitate decision-making in clinical settings.

Nomogram for predicting the risk of central lymph node metastasis in papillary thyroid microcarcinoma: a combination of sonographic findings and clinical factors.

A considerable controversy over performing thyroidectomy and central lymph node dissection in patients with papillary thyroid microcarcinoma (PTMC) remained. However, accurate prediction of central lymph node metastasis (CLNM) is crucial for surgical extent and proper management. The aim of this study was to develop and validate a practical nomogram for predicting CLNM in patients with PTMC. A total of 1,029 patients with PTMC who underwent thyroidectomy and central lymph node dissection at Tangdu Hospital (the Second Affiliated Hospital of Air Force Medical University) and Xijing Hospital (the First Affiliated Hospital of Air Force Medical University) were selected. Seven hundred and nine patients were assigned to the training set and 320 patients to the validation set. Data encompassing demographic characteristics, ultrasonography results, and biochemical indicators were obtained. Stepwise backward selection and multiple logistic regression were used to screen the variables and establish the nomogram. Concordance index (C-index), receiver operating characteristic (ROC) curve analysis, and decision curve analysis (DCA) were employed to evaluate the nomogram's distinguishability, accuracy, and clinical utility. Young age, multifocality, bigger tumor, presence of microcalcification, aspect ratio (height divided by width) ≥1, loss of fatty hilum, high free thyroxine (FT4), and lower anti-thyroid peroxidase antibody (TPOAb) were significantly associated with CLNM. The nomogram showed strong predictive capacity, with a C-index and accuracy of 0.784 and 0.713 in the training set and 0.779 and 0.703 in the external validation set, respectively. DCA indicated that the nomogram demonstrated strong clinical applicability. We established a reliable, cost-effective, reproducible, and noninvasive nomogram for predicting CLNM in patients with PTMC. This tool could be a valuable guidance for deciding on management in PTMC.

Multiparametric MRI-based radiomic model for predicting lymph node metastasis after neoadjuvant chemoradiotherapy in locally advanced rectal cancer

ObjectivesTo construct and validate multiparametric MR-based radiomic models based on primary tumors for predicting lymph node metastasis (LNM) following neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC) patients.MethodsA total of 150 LARC patients from two independent centers were enrolled. The training cohort comprised 100 patients from center A. Fifty patients from center B were included in the external validation cohort. Radiomic features were extracted from the manually segmented volume of interests of the primary tumor before and after nCRT. Feature selection was performed using multivariate logistic regression analysis. The clinical risk factors were selected via the least absolute shrinkage and selection operator method. The radiologist’s assessment of LNM was performed. Eight models were constructed using random forest classifiers, including four single-sequence models, three combined-sequence models, and a clinical model. The models’ discriminative performance was assessed via receiver operating characteristic curve analysis quantified by the area under the curve (AUC).ResultsThe AUCs of the radiologist’s assessment, the clinical model, and the single-sequence models ranged from 0.556 to 0.756 in the external validation cohort. Among the single-sequence models, modelpost_DWI exhibited superior predictive power, with an AUC of 0.756 in the external validation set. In combined-sequence models, modelpre_T2_DWI_post had the best diagnostic performance in predicting LNM after nCRT, with a significantly higher AUC (0.831) than those of the clinical model, modelpre_T2_DWI, and the single-sequence models (all p < 0.05).ConclusionsA multiparametric model that incorporates MR radiomic features before and after nCRT is optimal for predicting LNM after nCRT in LARC.Critical relevance statementThis study enrolled 150 LARC patients from two independent centers and constructed multiparametric MR-based radiomic models based on primary tumors for predicting LNM following nCRT, which aims to guide therapeutic decisions and predict prognosis for LARC patients.Key PointsThe biological characteristics of primary tumors and metastatic LNs are similar in rectal cancer.Radiomics features and clinical data before and after nCRT provide complementary tumor information.Preoperative prediction of LN status after nCRT contributes to clinical decision-making.Graphical

Multiparametric MRI-based radiomics nomogram for the preoperative prediction of lymph node metastasis in rectal cancer: A two-center study

PurposeTo develop a radiomic nomogram based on multiparametric magnetic resonance imaging for the preoperative prediction of lymph node metastasis (LNM) in rectal cancer. MethodsThis retrospective study included 318 patients with pathologically proven rectal adenocarcinoma from two hospitals. Radiomic features were extracted from T2-weighted imaging, diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging scans of the training cohort, and the radsore model was then constructed. The combined model was obtained by integrating the Radscore and clinical models. The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic effectiveness of each model, and the best-performing model was used to develop the nomogram. ResultsThe Radscore and clinical models exhibited similar diagnostic efficacy (DeLong’s test, P > 0.05). The AUC of the combined model was significantly higher than those of the clinical and Radscore models in the training cohort (AUC: 0.837 vs. 0.763 and 0.787, P: 0.02120 and 0.02309) and the external validation cohort (AUC: 0.880 vs. 0.797 and 0.779, P: 0.02310 and 0.02471). However, the diagnostic performance of the three models was comparable in the internal validation cohort (P > 0.05). Thus, among the three models, the combined model exhibited the highest diagnostic efficiency. The calibration curve exhibited satisfactory consistency between the nomogram predictions and the actual results. DCA confirmed the considerable clinical usefulness of the nomogram. ConclusionThe radiomics nomogram can accurately and noninvasively predict LNM in rectal cancer before surgery, serving as a convenient visualization tool for informing treatment decisions, including the choice of surgical approach and the need for neoadjuvant therapy.

Machine learning to predict lymph node metastasis in T1 esophageal squamous cell carcinoma：a multicenter study.

Existing models do poorly when it comes to quantifying the risk of Lymph node metastases (LNM). This study aimed to develop a machine learning model for LNM in patients with T1 esophageal squamous cell carcinoma (ESCC). The study is multicenter, and population based. Elastic net regression (ELR), random forest (RF), extreme gradient boosting (XGB), and a combined (ensemble) model of these was generated. The contribution to the model of each factor was calculated. The models all exhibited potent discriminating power. The Elastic net regression performed best with externally validated AUC of 0.803, whereas the NCCN guidelines identified patients with LNM with an AUC of 0.576 and logistic model with an AUC of 0. 670. The most important features were lymphatic and vascular invasion and depth of tumor invasion. Models created utilizing machine learning approaches had excellent performance estimating the likelihood of LNM in T1 ESCC.

Radiomics analysis based on CT for predicting lymph node metastasis and prognosis in duodenal papillary carcinoma

ObjectivesRadiomics has been demonstrated to be strongly associated with TNM stage and patient prognosis. We aimed to develop a model for predicting lymph node metastasis (LNM) and survival.MethodsFor radiomics texture selection, 3D Slicer 5.0.3 software and the least absolute shrinkage and selection operator (LASSO) algorithm were used. Subsequently, the radiomics model, computed tomography (CT) image, and clinical risk model were compared. The performance of the three models was evaluated using receiver operating characteristic (ROC) curves, decision curve analysis (DCA), calibration plots, and clinical impact curves (CICs).ResultsFor the LNM prediction model, 224 patients with LNM information were used to construct a model that was applied to predict LNM. According to the CT data and clinical characteristics, we constructed a radiomics model, CT imaging model and clinical model. The radiomics model for evaluating LNM status showed excellent calibration and discrimination in the training cohort (AUC = 0.926, 95% CI = 0.869–0.982) and the validation cohort (AUC = 0.872, 95% CI = 0.802–0.941). DeLong’s test demonstrated that the difference among the three models was significant. Similarly, DCA and CIC showed that the radiomics model has better clinical utility than the CT imaging model and clinical model. Our model also exhibited good performance in predicting survival—in line with the findings of the model built with clinical risk factors.ConclusionsCT radiomics models exhibited better predictive performance for LNM than models built based on clinical risk characteristics and CT imaging and had comparative clinical utility for predicting patient prognosis.Critical relevance statementThe radiomics model showed excellent performance and discrimination for predicting LNM and survival of duodenal papillary carcinoma (DPC).Key PointsLNM status determines the most appropriate treatment for DPC.Our radiomics model for evaluating the LNM status of DPC performed excellently.The radiomics model had high sensitivity and specificity for predicting survival, exhibiting great clinical value.Graphical

Application of CT and MRI images based on artificial intelligence to predict lymph node metastases in patients with oral squamous cell carcinoma: a subgroup meta-analysis.

The performance of artificial intelligence (AI) in the prediction of lymph node (LN) metastasis in patients with oral squamous cell carcinoma (OSCC) has not been quantitatively evaluated. The purpose of this study was to conduct a systematic review and meta-analysis of published data on the diagnostic performance of CT and MRI based on AI algorithms for predicting LN metastases in patients with OSCC. We searched the Embase, PubMed (Medline), Web of Science, and Cochrane databases for studies on the use of AI in predicting LN metastasis in OSCC. Binary diagnostic accuracy data were extracted to obtain the outcomes of interest, namely, the area under the curve (AUC), sensitivity, and specificity, and compared the diagnostic performance of AI with that of radiologists. Subgroup analyses were performed with regard to different types of AI algorithms and imaging modalities. Fourteen eligible studies were included in the meta-analysis. The AUC, sensitivity, and specificity of the AI models for the diagnosis of LN metastases were 0.92 (95% CI 0.89-0.94), 0.79 (95% CI 0.72-0.85), and 0.90 (95% CI 0.86-0.93), respectively. Promising diagnostic performance was observed in the subgroup analyses based on algorithm types [machine learning (ML) or deep learning (DL)] and imaging modalities (CT vs. MRI). The pooled diagnostic performance of AI was significantly better than that of experienced radiologists. In conclusion, AI based on CT and MRI imaging has good diagnostic accuracy in predicting LN metastasis in patients with OSCC and thus has the potential for clinical application. https://www.crd.york.ac.uk/PROSPERO/#recordDetails, PROSPERO (No. CRD42024506159).

Noninvasive prediction of lymph node metastasis in pancreatic cancer using an ultrasound-based clinicoradiomics machine learning model

ObjectivesThis study was designed to explore and validate the value of different machine learning models based on ultrasound image-omics features in the preoperative diagnosis of lymph node metastasis in pancreatic cancer (PC).MethodsThis research involved 189 individuals diagnosed with PC confirmed by surgical pathology (training cohort: n = 151; test cohort: n = 38), including 50 cases of lymph node metastasis. Image-omics features were extracted from ultrasound images. After dimensionality reduction and screening, eight machine learning algorithms, including logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), extra trees (ET), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP), were used to establish image-omics models to predict lymph node metastasis in PC. The best omics prediction model was selected through ROC curve analysis. Machine learning models were used to analyze clinical features and determine variables to establish a clinical model. A combined model was constructed by combining ultrasound image-omics and clinical features. Decision curve analysis (DCA) and a nomogram were used to evaluate the clinical application value of the model.ResultsA total of 1561 image-omics features were extracted from ultrasound images. 15 valuable image-omics features were determined by regularization, dimension reduction, and algorithm selection. In the image-omics model, the LR model showed higher prediction efficiency and robustness, with an area under the ROC curve (AUC) of 0.773 in the training set and an AUC of 0.850 in the test set. The clinical model constructed by the boundary of lesions in ultrasound images and the clinical feature CA199 (AUC = 0.875). The combined model had the best prediction performance, with an AUC of 0.872 in the training set and 0.918 in the test set. The combined model showed better clinical benefit according to DCA, and the nomogram score provided clinical prediction solutions.ConclusionThe combined model established with clinical features has good diagnostic ability and can be used to predict lymph node metastasis in patients with PC. It is expected to provide an effective noninvasive method for clinical decision-making, thereby improving the diagnosis and treatment of PC.

Targeted sequencing of DNA/RNA combined with radiomics predicts lymph node metastasis of papillary thyroid carcinoma

ObjectiveThe aim of our study is to find a better way to identify a group of papillary thyroid carcinoma (PTC) with more aggressive behaviors and to provide a prediction model for lymph node metastasis to assist in clinic practice.MethodsTargeted sequencing of DNA/RNA was used to detect genetic alterations. Gene expression level was measured by quantitative real-time PCR, western blotting or immunohistochemistry. CCK8, transwell assay and flow cytometry were used to investigate the effects of concomitant gene alterations in PTC. LASSO-logistics regression algorithm was used to construct a nomogram model integrating radiomic features, mutated genes and clinical characteristics.Results172 high-risk variants and 7 fusion types were detected. The mutation frequencies in BRAF, TERT, RET, ATM and GGT1 were significantly higher in cancer tissues than benign nodules. Gene fusions were detected in 16 samples (2 at the DNA level and 14 at the RNA level). ATM mutation (ATMMUT) was frequently accompanied by BRAFMUT, TERTMUT or gene fusions. ATMMUT alone or ATM co-mutations were significantly positively correlated with lymph node metastasis. Accordingly, ATM knock-down PTC cells bearing BRAFV600E, KRASG12R or CCDC6-RET had higher proliferative ability and more aggressive potency than cells without ATM knock-down in vitro. Furthermore, combining gene alterations and clinical features significantly improved the predictive efficacy for lymph node metastasis of radiomic features, from 71.5 to 87.0%.ConclusionsTargeted sequencing of comprehensive genetic alterations in PTC has high prognostic value. These alterations, in combination with clinical and radiomic features, may aid in predicting invasive PTC with higher accuracy.

Multimodal data integration using machine learning to predict the risk of clear cell renal cancer metastasis: a retrospective multicentre study.

To develop and validate a predictive combined model for metastasis in patients with clear cell renal cell carcinoma (ccRCC) by integrating multimodal data. In this retrospective study, the clinical and imaging data (CT and ultrasound) of patients with ccRCC confirmed by pathology from three tertiary hospitals in different regions were collected from January 2013 to January 2023. We developed three models, including a clinical model, a radiomics model, and a combined model. The performance of the model was determined based on its discriminative power and clinical utility. The evaluation indicators included area under the receiver operating characteristic curve (AUC) value, accuracy, sensitivity, specificity, negative predictive value, positive predictive value and decision curve analysis(DCA) curve. A total of 251 patients were evaluated. Patients (n = 166) from Shandong University Qilu Hospital (Jinan) were divided into the training cohort, of which 50 patients developed metastases; patients (n = 37) from Shandong University Qilu Hospital (Qingdao) were used as internal testing, of which 15 patients developed metastases; patients (n = 48) from Changzhou Second People's Hospital were used as external testing, of which 13 patients developed metastases. In the training set, the combined model showed the highest performance (AUC, 0.924) in predicting lymph node metastasis(LNM), while the clinical and radiomics models both had AUCs of 0.845 and 0.870, respectively. In the internal testing, the combined model had the highest performance (AUC, 0.877) for predicting LNM, while the AUCs of the clinical and radiomics models were 0.726 and 0.836, respectively. In the external testing, the combined model had the highest performance (AUC, 0.849) for predicting LNM, while the AUCs of the clinical and radiomics models were 0.708 and 0.804, respectively. The DCA curve showed that the combined model had a significant prediction probability in predicting the risk of LNM in ccRCC patients compared with the clinical model or the radiomics model. The combined model was superior to the clinical and radiomics models in predicting LNM in ccRCC patients.

Deep learning-based pathological prediction of lymph node metastasis for patient with renal cell carcinoma from primary whole slide images

BackgroundMetastasis renal cell carcinoma (RCC) patients have extremely high mortality rate. A predictive model for RCC micrometastasis based on pathomics could be beneficial for clinicians to make treatment decisions.MethodsA total of 895 formalin-fixed and paraffin-embedded whole slide images (WSIs) derived from three cohorts, including Shanghai General Hospital (SGH), Clinical Proteomic Tumor Analysis Consortium (CPTAC) and Cancer Genome Atlas (TCGA) cohorts, and another 588 frozen section WSIs from TCGA dataset were involved in the study. The deep learning-based strategy for predicting lymphatic metastasis was developed based on WSIs through clustering-constrained-attention multiple-instance learning method and verified among the three cohorts. The performance of the model was further verified in frozen-pathological sections. In addition, the model was also tested the prognosis prediction of patients with RCC in multi-source patient cohorts.ResultsThe AUC of the lymphatic metastasis prediction performance was 0.836, 0.865 and 0.812 in TCGA, SGH and CPTAC cohorts, respectively. The performance on frozen section WSIs was with the AUC of 0.801. Patients with high deep learning-based prediction of lymph node metastasis values showed worse prognosis.ConclusionsIn this study, we developed and verified a deep learning-based strategy for predicting lymphatic metastasis from primary RCC WSIs, which could be applied in frozen-pathological sections and act as a prognostic factor for RCC to distinguished patients with worse survival outcomes.