Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction.

ObjectiveThis study aims to create a reliable framework for grading esophageal cancer. The framework combines feature extraction, deep learning with attention mechanisms, and radiomics to ensure accuracy, interpretability, and practical use in tumor analysis.Materials and methodsThis retrospective study used data from 2,560 esophageal cancer patients across multiple clinical centers, collected from 2018 to 2023. The dataset included CT scan images and clinical information, representing a variety of cancer grades and types. Standardized CT imaging protocols were followed, and experienced radiologists manually segmented the tumor regions. Only high-quality data were used in the study. A total of 215 radiomic features were extracted using the SERA platform. The study used two deep learning models—DenseNet121 and EfficientNet-B0—enhanced with attention mechanisms to improve accuracy. A combined classification approach used both radiomic and deep learning features, and machine learning models like Random Forest, XGBoost, and CatBoost were applied. These models were validated with strict training and testing procedures to ensure effective cancer grading.ResultsThis study analyzed the reliability and performance of radiomic and deep learning features for grading esophageal cancer. Radiomic features were classified into four reliability levels based on their ICC (Intraclass Correlation) values. Most of the features had excellent (ICC > 0.90) or good (0.75 < ICC ≤ 0.90) reliability. Deep learning features extracted from DenseNet121 and EfficientNet-B0 were also categorized, and some of them showed poor reliability. The machine learning models, including XGBoost and CatBoost, were tested for their ability to grade cancer. XGBoost with Recursive Feature Elimination (RFE) gave the best results for radiomic features, with an AUC (Area Under the Curve) of 91.36%. For deep learning features, XGBoost with Principal Component Analysis (PCA) gave the best results using DenseNet121, while CatBoost with RFE performed best with EfficientNet-B0, achieving an AUC of 94.20%. Combining radiomic and deep features led to significant improvements, with XGBoost achieving the highest AUC of 96.70%, accuracy of 96.71%, and sensitivity of 95.44%. The combination of both DenseNet121 and EfficientNet-B0 models in ensemble models achieved the best overall performance, with an AUC of 95.14% and accuracy of 94.88%.ConclusionsThis study improves esophageal cancer grading by combining radiomics and deep learning. It enhances diagnostic accuracy, reproducibility, and interpretability, while also helping in personalized treatment planning through better tumor characterization.Clinical trial numberNot applicable.

BACKGROUND Timely identification of local failure after Stereotactic Radiosurgery (SRS) offers the opportunity for appropriate treatment modifications that may result in improved treatment outcomes, patient survival, and quality of life. Previous studies showed that the addition of either radiomics or deep learning features to clinical features increased the accuracy of the models in predicting local control (LC) of brain metastases after SRS. To date, however, no study combined both radiomics and deep learning features together with clinical features to develop machine learning algorithms to predict LC of brain metastases. In this study, we examined whether a model trained with a combination of all these features could predict LC better than models trained with only a subset of these features. MATERIAL AND METHODS Pre-treatment brain MRIs and clinical data were collected retrospectively for 129 patients at the Gamma Knife Center of Elisabeth-TweeSteden Hospital (ETZ), Tilburg, The Netherlands. The patients were split into 103 patients for training and 26 patients for testing. The segment-based radiomics features were extracted using the radiomics feature extractor of the python radiomics package. The deep learning features were extracted using a fine-tuned 3D ResNet model and then combined with the clinical and radiomics features. A Random Forest classifier was trained with the training data set and then tested with the test data set. The performance was compared across 4 different models trained with clinical features only, clinical and radiomics features, clinical and deep learning features, and clinical, radiomics and deep learning features. RESULTS The prediction model with only clinical variables demonstrated an area under the receiver operating characteristic curve (AUC) of 0.82 and an accuracy of 75.6%. The prediction model with the combination of clinical and radiomics features demonstrated an AUC of 0.880 and an accuracy of 83.3% whereas the prediction model with the combination of clinical and deep learning features demonstrated an AUC of 0.863 and an accuracy of 78.3%. The best prediction performance was associated with the model that combined the clinical, radiomics and deep learning features with an AUC of 0.886 and 87% accuracy. CONCLUSION Machine learning models built on radiomics features and deep learning features combined with patient characteristics show potential to predict LC after SRS with high accuracy. The promising findings from this study demonstrate the potential for early prediction of SRS outcome for brain metastasis prior to treatment initiation and might offer the opportunity for appropriate treatment modifications that may result in improved treatment outcomes, patient survival, and quality of life.

The objective of this study is to investigate the value of radiomics features and deep learning features based on positron emission tomography/computed tomography (PET/CT) in predicting perineural invasion (PNI) in rectal cancer. We retrospectively collected 120 rectal cancer (56 PNI-positive patients 64 PNI-negative patients) patients with preoperative 18F-FDG PET/CT examination and randomly divided them into training and validation sets at a 7:3 ratio. We also collected 31 rectal cancer patients from two other hospitals as an independent external validation set. χ2 test and binary logistic regression were used to analyze PET metabolic parameters. PET/CT images were utilized to extract radiomics features and deep learning features. The Mann-Whitney U test and LASSO were employed to select valuable features. Metabolic parameter, radiomics, deep learning and combined models were constructed. ROC curves were generated to evaluate the performance of models. The results indicate that metabolic tumor volume (MTV) is correlated with PNI (P = 0.001). In the training set and validation set, the AUC values of the metabolic parameter model were 0.673 (95%CI: 0.572-0.773), 0.748 (95%CI: 0.599-0.896). We selected 16 radiomics features and 17 deep learning features as valuable factors for predicting PNI. The AUC values of radiomics model and deep learning model were 0.768 (95%CI: 0.667-0.868) and 0.860 (95%CI: 0.780-0.940) in the training set. And the AUC values in the validation set were 0.803 (95%CI: 0.656-0.950) and 0.854 (95% CI 0.721-0.987). Finally, the combined model exhibited AUCs of 0.893 (95%CI: 0.825-0.961) in the training set and 0.883 (95%CI: 0.775-0.990) in the validation set. In the external validation set, the combined model achieved an AUC of 0.829 (95% CI: 0.674-0.984), outperforming each individual model. The decision curve analysis of these models indicated that using the combined model to guide treatment provided a substantial net benefit. This combined model established by integrating PET metabolic parameters, radiomics features, and deep learning features can accurately predict the PNI in rectal cancer.

To develop and validate a multimodal machine learning model for opportunistic osteoporosis screening in postmenopausal women using dental periapical radiographs. This retrospective multicenter study analyzed 3885 periapical radiographs paired with DEXA‐derived T ‐scores from postmenopausal women. Clinical, handcrafted radiomic, and deep features were extracted, resulting in a fused feature set. Radiomic features ( n = 215) followed Image Biomarker Standardization Initiative (IBSI) guidelines, and deep features ( n = 128) were derived from a novel attention‐based autoencoder. Feature harmonization used ComBat adjustment; reliability was ensured by intra‐class correlation coefficient (ICC) filtering (ICC ≥ 0.80). Dimensionality was reduced via Pearson correlation and LASSO regression. Four classifiers—logistic regression, random forest, multilayer perceptron, and XGBoost—were trained and evaluated across stratified training, internal, and external test sets. A logistic regression model was selected for clinical translation and nomogram development. Decision curve analysis assessed clinical utility. XGBoost achieved the highest classification performance using the fused feature set, with an internal AUC of 94.6% and external AUC of 93.7%. Logistic regression maintained strong performance (external AUC = 91.3%) and facilitated nomogram construction. Deep and radiomic features independently outperformed clinical‐only models, confirming their predictive strength. SHAP analysis identified DEXA T ‐score, age, vitamin D, and selected radiomic/deep features as key contributors. Calibration curves and Hosmer–Lemeshow test ( p = 0.492) confirmed model reliability. Decision curve analysis showed meaningful net clinical benefit across decision thresholds. Dental periapical radiographs can be leveraged for accurate, non‐invasive osteoporosis screening in postmenopausal women. The proposed model demonstrates high accuracy, generalizability, and interpretability, offering a scalable solution for integration into dental practice.

Accurate differentiation between luminal A and B subtypes of breast cancer is critical for selecting therapeutic strategies. However, current approaches rely predominantly on invasive biopsy and immunohistochemical (IHC) analysis. Therefore, the development of non-invasive imaging-based methods capable of reliably classifying tumor subtypes remains an urgent task. To develop and validate a hybrid classification model combining radiomic and deep learning features extracted from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to differentiate between luminal A and B subtypes of invasive breast cancer. The study included 312 women from China, Russia and Bulgaria with confirmed luminal subtypes of breast cancer. All patients underwent standardized pre-treatment DCE-MRI, and subtypes were determined using IHC. Tumors were semi-automatically segmented, and radiomic features were extracted using PyRadiomics. Additionally, deep features were extracted from DCE-MRI using a 3D ResNet-50 convolutional neural network. Three models were constructed: a radiomics-based model, a deep learning-based model, and a hybrid model that integrated both approaches using a stacking ensemble method. Model performance was evaluated using AUC, sensitivity, specificity, and other metrics on a test dataset and an independent external validation cohort (n = 148). SHAP and Grad-CAM techniques were applied for model interpretability. The hybrid model significantly outperformed the individual approaches, achieving an AUC of 0.921, sensitivity of 88.6%, and specificity of 89.7% on the test dataset. Performance remained robust in the external validation cohort (AUC = 0.903). Statistical tests (DeLong and bootstrapping) confirmed the significance of these differences. The most important contributors were radiomic features related to shape and texture (e.g., entropy, sphericity) and high-level deep features. Visualizations highlighted clinically relevant model attention areas. The proposed hybrid approach represents a clinically applicable, non-invasive method for classifying breast cancer subtypes, potentially complementing or partially replacing biopsy in selected cases. It enhances diagnostic accuracy while maintaining interpretability. Future work will focus on prospective validation and integration with genomic and clinical data within the framework of precision oncology.

PurposeTo differentiate complicated appendicitis (CA) from uncomplicated appendicitis (UA) in children, we developed and validated an artificial intelligence (AI) model using a multimodal approach integrating ultrasound images and clinical data.MethodsA retrospective analysis was performed on 372 pathologically confirmed pediatric appendicitis cases (230 male, 142 female) from three centers, all with preoperative abdominal ultrasound. Deep learning (DL) features and radiomic features were extracted from appendiceal ultrasound images using deep transfer learning (DTL) and conventional radiomic methods, respectively. We selected 12 radiomic features, 9 DL features, and 3 clinical features—namely, white blood cell count (WBC), neutrophil count (NEU), and C-reactive protein (CRP)—for building the machine learning classification model. Based on these features, four distinct models were constructed: the Rad model (radiomic features only), the DL model (DL features only), the DTL model (combined radiomic and DL features), and the Combine model (integrating all three feature types: radiomic, DL, and clinical features). Model performance was evaluated using receiver operating characteristic (ROC) curves, decision curve analysis (DCA), and the DeLong test. Finally, the combined model was compared to the performance of clinicians with varying levels of experience.ResultsThe combined model demonstrated consistently favorable performance across all cohorts (AUC: 0.940, 0.895, 0.866, and 0.783 for training and validation sets, respectively). The model's accuracy (0.862) and positive predictive value (0.896) were comparable to senior surgeons (0.741, 0.970) and superior to junior surgeons (0.672, 0.865) in the internal validation cohort. DCA confirmed the clinical utility of the combined model over conventional strategies.ConclusionOur ultrasound-based AI model provides reliable differentiation between CA and UA in children, offering potential value as a diagnostic support tool for clinical decision making.

e20611 Background: Predicting immunotherapy response in advanced non-small cell lung cancer (NSCLC) through non-invasive means could be a groundbreaking advancement. Deep features extracted from medical images by deep Convolutional Neural Networks (CNNs) along with radiomics have demonstrated promising results in different oncologic diseases. However, the method for extracting these deep features influences the predictive capabilities of the model. Methods: A retrospective analysis of a multicenter study was conducted in advanced NSCLC patients with high PD-L1 expression with the aim of developing an imaging features-based model for the prediction of best overall response (BOR) to a checkpoint inhibitor immunotherapy. All visible lung lesions, beyond RECIST 1.1, were manually segmented in baseline CT scans. Radiomics features were extracted at lesion-level, and various preprocessing methods and CNN architectures were tested for deep features extraction. Radiomics and deep features were harmonized using ComBat methodology. A distinctive feature signature was created for each patient by calculating the mean across all lesions. Using this data, machine learning models were trained to predict treatment response, specifically distinguishing between complete response (CR) and partial response (PR) from stable disease (SD) and progressive disease (PD). The study compared the performance of different deep features extraction methods and assessed shapley additive explanations (SHAP) values of radiomics for interpretability. Results: In the cohort of 116 patients (mean age: 67, 93% ever-smokers, 73% male), 1024 to 5475 quantitative imaging features per lesion were extracted. Among these patients, 67 patients were CR+PR, and 49 were SD+PD. The top-performing predictive model, trained with radiomics and deep features from a deep convolutional autoencoder, achieved an average AUC of 85%. SHAP values showed that impactful radiomics features were correlated with intensity changes in adjacent pixels describing the tumor heterogeneity, along with shape features potentially associated with malignancy. Ultimately, combining both features demonstrated statistical significance, leading to a performance improvement of ~2-5% compared to models exclusively using deep features. Conclusions: Diverse techniques for extracting deep features were evaluated, revealing autoencoder training as the most effective strategy for predicting immunotherapy response. Consequently, the findings suggest that employing deep learning to extract imaging features from baseline CT scans, combined with radiomics, represents a promising non-invasive approach for the predicting immunotherapy outcomes in advanced NSCLC patients.

This study aimed to develop a model based on radiomics and deep learning features to predict the ablation rate in patients with adenomyosis undergoing high-intensity focused ultrasound (HIFU) therapy. A total of 119 patients with adenomyosis who received HIFU therapy were retrospectively analyzed. Participants were included in the training and testing queues in a 7:3 ratio. Radiomics features were extracted from T2-weighted imaging (T2WI) images, and VGG-19 was used to extract advanced deep features. An ensemble model based on multi-model fusion for predicting the efficacy of HIFU in adenomyosis was proposed, which consists of four base classifiers and was evaluated using accuracy, precision, recall, F-score, and area under the receiver operating characteristic curve (AUC). The predictive performance of the combined model combining radiomics and deep learning features outperformed the radiomics and deep learning feature models alone, with accuracy of 0.848 and 0.814 in training and test sets, and AUC of 0.916 and 0.861, respectively. Compared with the base classifiers that make up the multi-model fusion model, the fusion model also exhibited better prediction performance. The fusion model incorporating both radiomics and deep learning features had certain predictive value for the ablation rate of adenomyosis under HIFU therapy and could help select patients with adenomyosis who would benefit from HIFU therapy.

Development and Validation of an AI-Based Multimodal Model for Pathological Staging of Gastric Cancer Using CT and Endoscopic Images.

Along with the popularity of intelligent services and mobile services, service recommendation has become a key task, especially the task based on quality-of-service (QoS) in edge computing environment. Most existing service recommendation methods have some serious defects, and cannot be directly adopted in edge computing environment. For example, most of existing methods cannot learn deep features of users or services, but in edge computing environment, there are a variety of devices with different configurations and different functions, and it is necessary to learn deep features behind those complex devices. In order to fully utilize hidden features, this paper proposes a new matrix factorization (MF) model with deep features learning, which integrates a convolutional neural network (CNN). The proposed mode is named Joint CNN-MF (JCM). JCM is capable of using the learned deep latent features of neighbors to infer the features of a user or a service. Meanwhile, to improve the accuracy of neighbors selection, the proposed model contains a novel similarity computation method. CNN learns the neighbors features, forms a feature matrix and infers the features of the target user or target service. We conducted experiments on a real-world service dataset under a batch of cases of data densities, to reflect the complex invocation cases in edge computing environment. The experimental results verify that compared to counterpart methods, our method can consistently achieve higher QoS prediction results.

A comparative study of statistical, radiomics, and deep learning feature extraction techniques for medical image classification in optical and radiological modalities.

The purpose of this study was to explore whether the Nomogram, which was constructed by combining the Deep learning and Radiomic features of T2-weighted MR images with Clinical factors (NDRC), could accurately predict placenta invasion. This retrospective study included 72 pregnant women with pathologically confirmed placenta invasion and 40 pregnant women with normal placenta. After 24 gestational weeks, all participants underwent magnetic resonance imaging. The uterus and placenta regions were segmented in magnetic resonance images on sagittal T2WI. Ninety-three radiomics features were extracted from the placenta region, and 128 deep features were extracted from the uterus region using a deep neural network. The least absolute shrinkage and selection operator (LASSO) algorithm was used to filter these 221 features and to form the combined signature. Then the combined signature (CS) and clinical factors were combined to construct a nomogram. The accuracy, sensitivity, specificity and AUC of the nomogram were compared with four machine learning methods. The model NDRC was trained on the dataset of 78 pregnant women in the training cohort. Finally, the model NDRC was compared with four machine learning methods on the independent validation cohort of 34 pregnant women. The results showed that the prediction accuracy, sensitivity, specificity and AUC of the NDRC model were 0.941, 0.952, 0.923 and 0.985 respectively, which outperforms the traditional machine learning methods which rely on radiomics features and deep learning features alone.

An integrated model combined intra- and peritumoral regions for predicting chemoradiation response of non small cell lung cancers based on radiomics and deep learning

Basketball shooting angle calculation and analysis by deeply-learned vision model

Prediction of lung malignancy progression and survival with machine learning based on pre-treatment FDG-PET/CT.