Machine Learning Models That Integrate Tumor Texture and Perfusion Characteristics Using Low-Dose Breast Computed Tomography Are Promising for Predicting Histological Biomarkers and Treatment Failure in Breast Cancer Patients

Prediction of longitudinal clinical outcomes after acute myocardial infarction using a dynamic machine learning algorithm

Several regression-based models for predicting outcomes after acute myocardial infarction (AMI) have been developed. However, prediction models that encompass diverse patient-related factors over time are limited. This study aimed to develop a machine learning-based model to predict longitudinal outcomes after AMI. This study was based on a nationwide prospective registry of AMI in Korea (n = 13,104). Seventy-seven predictor candidates from prehospitalization to 1 year of follow-up were included, and six machine learning approaches were analyzed. Primary outcome was defined as 1-year all-cause death. Secondary outcomes included all-cause deaths, cardiovascular deaths, and major adverse cardiovascular event (MACE) at the 1-year and 3-year follow-ups. Random forest resulted best performance in predicting the primary outcome, exhibiting a 99.6% accuracy along with an area under the receiver-operating characteristic curve of 0.874. Top 10 predictors for the primary outcome included peak troponin-I (variable importance value = 0.048), in-hospital duration (0.047), total cholesterol (0.047), maintenance of antiplatelet at 1 year (0.045), coronary lesion classification (0.043), N-terminal pro-brain natriuretic peptide levels (0.039), body mass index (BMI) (0.037), door-to-balloon time (0.035), vascular approach (0.033), and use of glycoprotein IIb/IIIa inhibitor (0.032). Notably, BMI was identified as one of the most important predictors of major outcomes after AMI. BMI revealed distinct effects on each outcome, highlighting a U-shaped influence on 1-year and 3-year MACE and 3-year all-cause death. Diverse time-dependent variables from prehospitalization to the postdischarge period influenced the major outcomes after AMI. Understanding the complexity and dynamic associations of risk factors may facilitate clinical interventions in patients with AMI.

Machine learning analysis for the association between breast feeding and metabolic syndrome in women

This cross-sectional study aimed to develop and validate population-based machine learning models for examining the association between breastfeeding and metabolic syndrome in women. The artificial neural network, the decision tree, logistic regression, the Naïve Bayes, the random forest and the support vector machine were developed and validated to predict metabolic syndrome in women. Data came from 30,204 women, who aged 20 years or more and participated in the Korean National Health and Nutrition Examination Surveys 2010-2019. The dependent variable was metabolic syndrome. The 86 independent variables included demographic/socioeconomic determinants, cardiovascular disease, breastfeeding duration and other medical/obstetric information. The random forest had the best performance in terms of the area under the receiver-operating-characteristic curve, e.g., 90.7%. According to random forest variable importance, the top predictors of metabolic syndrome included body mass index (0.1032), medication for hypertension (0.0552), hypertension (0.0499), cardiovascular disease (0.0453), age (0.0437) and breastfeeding duration (0.0191). Breastfeeding duration is a major predictor of metabolic syndrome for women together with body mass index, diagnosis and medication for hypertension, cardiovascular disease and age.

Hounsfield Units Predict Survival of Patients With Estrogen Receptor-Positive and Human Epithelial Growth Factor Receptor 2-Negative Breast Cancer

BACKGROUNDS

Tumor vascularity plays a fundamental role in cancer progression, including breast cancer. This study aimed to elucidate tumor vascularity and its impact on patient survival in the context of breast cancer subtypes using Hounsfield units (HU) on contrast-enhanced computed tomography (CT).

MATERIALS AND METHODS

Patients with early-stage breast cancer who completed planned treatment between 2003 and 2013 were retrospectively assessed.

RESULTS

The final cohort comprised 440 patients. Of the 440 patients, 262 had estrogen receptor (ER)-positive disease and 119 had human epidermal growth factor receptor 2 (HER2)-overexpressing disease. The tumor-to-aorta ratio of Hounsfield units (TAR) was related to significantly worse recurrence-free interval (RFI) (P < .001) and overall survival (OS) (P < .001) in patients with TAR > 0.33 for RFI and > 0.35 for OS than their counterparts. In the subgroup analysis, the survival disadvantage was limited only to patients with ER-positive and HER2-negative disease (P < .001 for both RFI and OS).

CONCLUSION

This study showed that TAR, which reflects tumor vascularity, was significantly related to patients' RFI and OS, suggesting its capacity as a feasible biomarker. This study also showed that TAR was associated with the survival in patients with ER-positive and HER2-negative disease.

Mapping Tumor Heterogeneity via Local Entropy Assessment: Making Biomarkers Visible

Advanced imaging and analysis improve prediction of pathology data and outcomes in several tumors, with entropy-based measures being among the most promising biomarkers. However, entropy is often perceived as statistical data lacking clinical significance. We aimed to generate a voxel-by-voxel visual map of local tumor entropy, thus allowing to (1) make entropy explainable and accessible to clinicians; (2) disclose and quantitively characterize any intra-tumoral entropy heterogeneity; (3) evaluate associations between entropy and pathology data. We analyzed the portal phase of preoperative CT of 20 patients undergoing liver surgery for colorectal metastases. A three-dimensional core kernel (5 × 5 × 5 voxels) was created and used to compute the local entropy value for each voxel of the tumor. The map was encoded with a color palette. We performed two analyses: (a) qualitative assessment of tumors' detectability and pattern of entropy distribution; (b) quantitative analysis of the entropy values distribution. The latter data were compared with standard Hounsfield data as predictors of post-chemotherapy tumor regression grade (TRG). Entropy maps were successfully built for all tumors. Metastases were qualitatively hyper-entropic compared to surrounding parenchyma. In four cases hyper-entropic areas exceeded the tumor margin visible at CT. We identified four "entropic" patterns: homogeneous, inhomogeneous, peripheral rim, and mixed. At quantitative analysis, entropy-derived data (percentiles/mean/median/root mean square) predicted TRG (p < 0.05) better than Hounsfield-derived ones (p = n.s.). We present a standardized imaging technique to visualize tumor heterogeneity built on a voxel-by-voxel entropy assessment. The association of local entropy with pathology data supports its role as a biomarker.

Analyzing Histological Images Using Hybrid Techniques for Early Detection of Multi-Class Breast Cancer Based on Fusion Features of CNN and Handcrafted

Breast cancer is the second most common type of cancer among women, and it can threaten women's lives if it is not diagnosed early. There are many methods for detecting breast cancer, but they cannot distinguish between benign and malignant tumors. Therefore, a biopsy taken from the patient's abnormal tissue is an effective way to distinguish between malignant and benign breast cancer tumors. There are many challenges facing pathologists and experts in diagnosing breast cancer, including the addition of some medical fluids of various colors, the direction of the sample, the small number of doctors and their differing opinions. Thus, artificial intelligence techniques solve these challenges and help clinicians resolve their diagnostic differences. In this study, three techniques, each with three systems, were developed to diagnose multi and binary classes of breast cancer datasets and distinguish between benign and malignant types with 40× and 400× factors. The first technique for diagnosing a breast cancer dataset is using an artificial neural network (ANN) with selected features from VGG-19 and ResNet-18. The second technique for diagnosing breast cancer dataset is by ANN with combined features for VGG-19 and ResNet-18 before and after principal component analysis (PCA). The third technique for analyzing breast cancer dataset is by ANN with hybrid features. The hybrid features are a hybrid between VGG-19 and handcrafted; and a hybrid between ResNet-18 and handcrafted. The handcrafted features are mixed features extracted using Fuzzy color histogram (FCH), local binary pattern (LBP), discrete wavelet transform (DWT) and gray level co-occurrence matrix (GLCM) methods. With the multi classes data set, ANN with the hybrid features of the VGG-19 and handcrafted reached a precision of 95.86%, an accuracy of 97.3%, sensitivity of 96.75%, AUC of 99.37%, and specificity of 99.81% with images at magnification factor 400×. Whereas with the binary classes data set, ANN with the hybrid features of the VGG-19 and handcrafted reached a precision of 99.74%, an accuracy of 99.7%, sensitivity of 100%, AUC of 99.85%, and specificity of 100% with images at a magnification factor 400×.

Comparison of CT- and MRI-Based Quantification of Tumor Heterogeneity and Vascularity for Correlations with Prognostic Biomarkers and Survival Outcomes: A Single-Center Prospective Cohort Study

BACKGROUND

Tumor heterogeneity and vascularity can be noninvasively quantified using histogram and perfusion analyses on computed tomography (CT) and magnetic resonance imaging (MRI). We compared the association of histogram and perfusion features with histological prognostic factors and progression-free survival (PFS) in breast cancer patients on low-dose CT and MRI.

METHODS

This prospective study enrolled 147 women diagnosed with invasive breast cancer who simultaneously underwent contrast-enhanced MRI and CT before treatment. We extracted histogram and perfusion parameters from each tumor on MRI and CT, assessed associations between imaging features and histological biomarkers, and estimated PFS using the Kaplan-Meier analysis.

RESULTS

Out of 54 histogram and perfusion parameters, entropy on T2- and postcontrast T1-weighted MRI and postcontrast CT, and perfusion (blood flow) on CT were significantly associated with the status of subtypes, hormone receptors, and human epidermal growth factor receptor 2 (p < 0.05). Patients with high entropy on postcontrast CT showed worse PFS than patients with low entropy (p = 0.053) and high entropy on postcontrast CT negatively affected PFS in the Ki67-positive group (p = 0.046).

CONCLUSIONS

Low-dose CT histogram and perfusion analysis were comparable to MRI, and the entropy of postcontrast CT could be a feasible parameter to predict PFS in breast cancer patients.

Clinical-Radiomics Nomogram Based on Contrast-Enhanced Ultrasound for Preoperative Prediction of Cervical Lymph Node Metastasis in Papillary Thyroid Carcinoma

This study aimed to establish a new clinical-radiomics nomogram based on ultrasound (US) for cervical lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC). We collected 211 patients with PTC between June 2018 and April 2020, then we randomly divided these patients into the training set (n = 148) and the validation set (n = 63). 837 radiomics features were extracted from B-mode ultrasound (BMUS) images and contrast-enhanced ultrasound (CEUS) images. The maximum relevance minimum redundancy (mRMR) algorithm, least absolute shrinkage and selection operator (LASSO) algorithm, and backward stepwise logistic regression (LR) were applied to select key features and establish a radiomics score (Radscore), including BMUS Radscore and CEUS Radscore. The clinical model and clinical-radiomics model were established using the univariate analysis and multivariate backward stepwise LR. The clinical-radiomics model was finally presented as a clinical-radiomics nomogram, the performance of which was evaluated by the receiver operating characteristic curves, Hosmer-Lemeshow test, calibration curves, and decision curve analysis (DCA). The results show that the clinical-radiomics nomogram was constructed by four predictors, including gender, age, US-reported LNM, and CEUS Radscore. The clinical-radiomics nomogram performed well in both the training set (AUC = 0.820) and the validation set (AUC = 0.814). The Hosmer-Lemeshow test and the calibration curves demonstrated good calibration. The DCA showed that the clinical-radiomics nomogram had satisfactory clinical utility. The clinical-radiomics nomogram constructed by CEUS Radscore and key clinical features can be used as an effective tool for individualized prediction of cervical LNM in PTC.

Machine learning and statistic analysis to predict drug treatment outcome in pediatric epilepsy patients with tuberous sclerosis complex

OBJECTIVES

We aimed to investigate the association between multi-modality features and epilepsy drug treatment outcomes and propose a machine learning model to predict epilepsy drug treatment outcomes with multi-modality features.

METHODS

This retrospective study consecutively enrolled 103 epilepsy children with rare TSC. Multi-modality data were used to characterize risk factors for epilepsy drug treatment outcome of TSC, including clinical data, TSC1, and TSC2 genes test results, magnetic resonance imaging (MRI), computerized tomography (CT), and electroencephalogram (EEG). Three common feature selection methods and six common machine learning models were used to find the best combination of feature selection and machine learning model for epilepsy drug treatment outcomes prediction with multi-modality features for TSC clinical application.

RESULTS

The analysis of variance based on selected 35 features combined with multilayer perceptron (MLP) model achieved the best area-under-curve score (AUC) of 0.812 (±0.005). Infantile spasms, EEG discharge type, epileptiform discharge in the right frontal area of EEG, drug-resistant epilepsy, gene mutation type, and type II lesions were positively correlated with drug treatment outcome. Age of onset and age of visiting doctors were negatively correlated with drug treatment outcome (p < 0.05). Our machine learning results found that among MRI features, lesion type is the most important in the outcome prediction, followed by location and quantity.

CONCLUSION

We developed and validated an effective prediction model for epilepsy drug treatment outcomes of TSC. Our results suggested that multi-modality features analysis and MLP-based machine learning can predict epilepsy drug treatment outcomes of TSC.

Prospective clinical research of radiomics and deep learning in oncology: A translational review

Radiomics and deep learning (DL) hold transformative promise and substantial and significant advances in oncology; however, most methods have been tested in retrospective or simulated settings. There is considerable interest in the biomarker validation, clinical utility, and methodological robustness of these studies and their deployment in real-world settings. This review summarizes the characteristics of studies, the level of prospective validation, and the overview of research on different clinical endpoints. The discussion of methodological robustness shows the potential for independent external replication of prospectively reported results. These in-depth analyses further describe the barriers limiting the translation of radiomics and DL into primary care options and provide specific recommendations regarding clinical deployment. Finally, we propose solutions for integrating novel approaches into the treatment environment to unravel the critical process of translating AI models into the clinical routine and explore strategies to improve personalized medicine.

Potential of the Non-Contrast-Enhanced Chest CT Radiomics to Distinguish Molecular Subtypes of Breast Cancer: A Retrospective Study

Objectives

The molecular subtype plays an important role in breast cancer, which is the main reference to guide treatment and is closely related to prognosis. The objective of this study was to explore the potential of the non-contrast-enhanced chest CT-based radiomics to predict breast cancer molecular subtypes non-invasively.

Methods

A total of 300 breast cancer patients (153 luminal types and 147 non-luminal types) who underwent routine chest CT examination were included in the study, of which 220 cases belonged to the training set and 80 cases to the time-independent test set. Identification of the molecular subtypes is based on immunohistochemical staining of postoperative tissue samples. The region of interest (ROI) of breast masses was delineated on the continuous slices of CT images. Forty-two models to predict the luminal type of breast cancer were established by the combination of six feature screening methods and seven machine learning classifiers; 5-fold cross-validation (cv) was used for internal validation. Finally, the optimal model was selected for external validation on the independent test set. In addition, we also took advantage of SHapley Additive exPlanations (SHAP) values to make explanations of the machine learning model.

Results

During internal validation, the area under the curve (AUC) values for different models ranged from 0.599 to 0.842, and the accuracy ranged from 0.540 to 0.775. Eventually, the LASSO_SVM combination was selected as the final model, which included 9 radiomics features. The AUC, accuracy, sensitivity, and specificity of the model to distinguish luminal from the non-luminal type were 0.842 [95% CI: 0.728−0.957], 0.773, 0.818, and 0.773 in the training set and 0.757 [95% CI: 0.640–0.866], 0.713, 0.767, and 0.676 in the test set.

Conclusion

The radiomics based on chest CT may provide a new idea for the identification of breast cancer molecular subtypes.