Feature Transfer Learning Research Articles

Feature Transfer Learning for Fatigue Life Prediction of Additive Manufactured Metals With Small Samples

ABSTRACTA feature transfer learning (FTL)‐based model is proposed to address small‐sample problems in fatigue life prediction of additively manufactured (AM) metals. Transfer component analysis (TCA) is studied for data alignment before model training. Correspondingly, two TCA improvement strategies are further considered to aggregate training data from distinct AM processing conditions. An experimental database consisting of 103 fatigue data is built for model evaluation. The results demonstrate that the proposed model outperforms conventional machine learning models and other transfer learning‐based models in terms of accuracy and data demand, showing good applicability for AM fatigue life assessment.

Dynamic liquid level prediction for multiple oil wells based on transfer learning and multidimensional feature fusion network

Abstract Accurate prediction of the dynamic liquid level (DLL) in oil wells is crucial for the intelligent optimization of pumping systems. It not only provides real-time insights into the operational conditions of the pumping system but also supports the optimization of operational parameters with data. However, due to the long-term operation of oil wells and their complex internal environments, direct measurement of the DLL is challenging, leading to low reliability of the obtained data. Therefore, this paper conducts an in-depth analysis of the parameters involved in the pumping process, identifies the model's input features, and develops a DLL prediction model for multiple wells based on multidimensional feature fusion (MFF). This model captures the characteristics of DLL changes and the diversity of input features. To address the issues of slow model training and low prediction accuracy caused by insufficient datasets in practical applications, this paper integrates transfer learning techniques and proposes a new model, the DLL model for multiple wells based on Transfer Learning and Multidimensional Feature Fusion (TMFF). Initially, the Euclidean distance and Maximum mean discrepancy methods are employed to verify the feature similarity between the source and target domains, using highly similar DLL data as experimental data. By combining transfer learning techniques with the MFF model, the TMFF model is established. The model's capabilities are validated using field-collected data with broad representativeness. Experimental results demonstrate that the proposed MFF model possesses high accuracy and generalization capability. Additionally, the TMFF model effectively resolves the issue of insufficient data during model training. In summary, the methods proposed in this paper can provide accurate DLL data for practical applications in intelligent oilfields.

Typical Scenario Load Identification Based on Feature Fusion and Transfer Learning

Background: The electricity demand is continuously increasing. However, various institutions, enterprises, and individuals exhibit many irregularities in their electricity usage, leading to significant wastage of electricity. To achieve effective energy management, researchers are attempting to analyze and regulate users' electricity demands by monitoring their load usage through Non- Intrusive Load Monitoring (NILM) technology. The accuracy of load identification in this technology will greatly impact the results of load monitoring. Although there are currently many articles and patents related to NILM, they utilize a large amount of computational resources and require high sampling rates from devices, yet the results are still unsatisfactory. Therefore, it is necessary to improve the accuracy of load identification in data with relatively low sampling frequencies. Objective: To improve the accuracy of load identification with low sampling frequency data, this paper proposes a typical scenario load identification method based on feature fusion and transfer learning. Methods: This method adopts the fusion of current and power factor angles to provide abundant identification information for NILM, effectively reducing the situation of single-feature overlap of different loads. By inputting the fused feature data into GoogLeNet and utilizing transfer learning for training, not only is the accuracy improved, but also the training time and the requirement for the sampling rate of training data are greatly reduced. In addition, selecting typical scenario loads can monitor loads in a targeted manner, reduce the waste of computing resources caused by irrelevant loads, and more effectively guide electricity usage strategies. Results: The proposed load identification method was tested on the low sampling frequency dataset used in this paper. It achieved an overall load identification accuracy of 94.61% across three scenarios, improving accuracy by 3% to 7% compared to other models. Conclusion: The simulation results indicate that this method achieves high load identification accuracy at low sampling frequencies. It also exhibits good generalization ability. This method not only reduces the performance requirements for monitoring equipment but also enhances monitoring efficiency.

RU-Net, Multi-Scale Feature Fusion and Transfer Learning: Unlocking the Potential of Cuffless Blood Pressure Monitoring with PPG and ECG.

This study introduces an innovative deep-learning model for cuffless blood pressure estimation using PPG and ECG signals, demonstrating state-of-the-art performance on the largest clean dataset, PulseDB. The rU-Net architecture, a fusion of U-Net and ResNet, enhances both generalization and feature extraction accuracy. Accurate multi-scale feature capture is facilitated by short-time Fourier transform (STFT) time-frequency distributions and multi-head attention mechanisms, allowing data-driven feature selection. The inclusion of demographic parameters as supervisory information further elevates performance. On the calibration-based dataset, our model excels, achieving outstanding accuracy (SBP MAE ± std: 4.49 ± 4.86 mmHg, DBP MAE ± std: 2.69 ± 3.10 mmHg), surpassing AAMI standards and earning a BHS Grade A rating. Addressing the challenge of calibration-free data, we propose a fine-tuning-based transfer learning approach. Remarkably, with only 10% data transfer, our model attains exceptional accuracy (SBP MAE ± std: 4.14 ± 5.01 mmHg, DBP MAE ± std: 2.48 ± 2.93 mmHg). This study sets the stage for the development of highly accurate and reliable wearable cuffless blood pressure monitoring devices.

Discrete Variational Feature Transfer Learning for Skeleton-based Abnormal Behavior Detection

Discrete Variational Feature Transfer Learning for Skeleton-based Abnormal Behavior Detection

Cross-Channel Specific-Mutual Feature Transfer Learning for Motor Imagery EEG Signals Decoding.

In recent years, with the rapid development of deep learning, various deep learning frameworks have been widely used in brain-computer interface (BCI) research for decoding motor imagery (MI) electroencephalogram (EEG) signals to understand brain activity accurately. The electrodes, however, record the mixed activities of neurons. If different features are directly embedded in the same feature space, the specific and mutual features of different neuron regions are not considered, which will reduce the expression ability of the feature itself. We propose a cross-channel specific-mutual feature transfer learning (CCSM-FT) network model to solve this problem. The multibranch network extracts the specific and mutual features of brain's multiregion signals. Effective training tricks are used to maximize the distinction between the two kinds of features. Suitable training tricks can also improve the effectiveness of the algorithm compared with novel models. Finally, we transfer two kinds of features to explore the potential of mutual and specific features to enhance the expressive power of the feature and use the auxiliary set to improve identification performance. The experimental results show that the network has a better classification effect in the BCI Competition IV-2a and the HGD datasets.

An Expert Model Using Deep Learning for Image-based Pest Identification with the TSLM Approach for Enhancing Precision Farming

The rise of digital agriculture has sparked considerable interest in its potential to revolutionize farming practices by integrating of advanced technologies. Unmanned aerial vehicles (UAVs), commonly known as drones, have emerged as a crucial tool in precision agriculture, offering diverse applications for real-world scenarios. This research focuses on harnessing the power of drones in the context of digital agriculture support, particularly in addressing the challenges of crop protection and pest management. The objective is to develop an innovative approach for crop-disease diagnosis using an upgraded Transfer-Driven Self-Adaptive Learning Model (TSLM) that leverages multispectral remote sensing data of drone-captured images to improve pest classification and streamline pesticide application. The study explores nine potent deep neural network models' capabilities for identifying plant diseases using various approaches within the digital agriculture framework. Transfer learning and advanced feature extraction techniques are employed to tailor these deep neural networks to the specific crop protection context. Using of pre-trained deep learning models for feature extraction and fine-tuning enhances the effectiveness of the proposed model. Evaluating the model's performance, precision, sensitivity, specificity, and F1-score metrics are assessed, leading to the discovery that deep feature extraction and Self-Adaptive Learning Model (SLM) classification outperform traditional transfer learning methods. The novelty of this work lies in its application of communication protocols to coordinate a fleet of drones for crop protection within the digital agriculture framework. By combining deep learning techniques with transfer-driven self-adaptive learning, the proposed approach significantly enhances the accuracy and efficiency of pest classification in precision agriculture. The study's findings offer valuable insights into optimizing drone-based technologies to combat plant disease epidemics, thereby contributing to the advancement of digital agriculture and its role in supporting sustainable farming practices.

A vision transformer-based deep transfer learning nomogram for predicting lymph node metastasis in lung adenocarcinoma.

Lymph node metastasis (LNM) plays a crucial role in the management of lung cancer; however, the ability of chest computed tomography (CT) imaging to detect LNM status is limited. This study aimed to develop and validate a vision transformer-based deep transfer learning nomogram for predicting LNM in lung adenocarcinoma patients using preoperative unenhanced chest CT imaging. This study included 528 patients with lung adenocarcinoma who were randomly divided into training and validation cohorts at a 7:3 ratio. The pretrained vision transformer (ViT) was utilized to extract deep transfer learning (DTL) feature, and logistic regression was employed to construct a ViT-based DTL model. Subsequently, the model was compared with six classical convolutional neural network (CNN) models. Finally, the ViT-based DTL signature was combined with independent clinical predictors to construct a ViT-based deep transfer learning nomogram (DTLN). The ViT-based DTL model showed good performance, with an area under the curve (AUC) of 0.821 (95% CI, 0.775-0.867) in the training cohort and 0.825 (95% CI, 0.758-0.891) in the validation cohort. The ViT-based DTL model demonstrated comparable performance to classical CNN models in predicting LNM, and the ViT-based DTL signature was then used to construct ViT-based DTLN with independent clinical predictors such as tumor maximum diameter, location, and density. The DTLN achieved the best predictive performance, with AUCs of 0.865 (95% CI, 0.827-0.903) and 0.894 (95% CI, 0845-0942), respectively, surpassing both the clinical factor model and the ViT-based DTL model (p<0.001). This study developed a new DTL model based on ViT to predict LNM status in lung adenocarcinoma patients and revealed that the performance of the ViT-based DTL model was comparable to that of classical CNN models, confirming that ViT was viable for deep learning tasks involving medical images. The ViT-based DTLN performed exceptionally well and can assist clinicians and radiologists in making accurate judgments and formulating appropriate treatment plans.

Distributed and Collaborative Lightweight Edge Federated Learning for IoT Zombie Devices Detection

The fast development of artificial intelligence and Internet of Things (IoT) technologies has enabled various applications of smart cities, e.g., smart monitoring and surveillance. However, vulnerabilities of IoT devices bring new threats to the security of smart cities. To identify ubiquitous IoT botnet attacks, a distributed and collaborative lightweight edge federated learning model for IoT zombie devices detection is proposed, named FIOT. To reduce computational complexity and enhance the adaptability to new attack environment at the network edge, FIOT is designed in a lightweight manner based on feature dimensionality reduction and transfer learning. Three IoT botnet datasets are used to validate the effectiveness of the proposed FIOT. Experimental results show that FIOT has an accuracy loss of less than 3% in terms of F1 value compared to the centralized learning, but the training time of FIOT is only 14.3% of that of centralized learning. While ensuring high detection accuracy, the number of parameters of FIOT is compressed to 37.58% of the comparison method.

Breast Cancer Detection Cum Classification using Feature Optimization and Transfer Learning

Early detection of breast cancer can significantly reduce its high mortality rate. However, manual diagnosis from mammography images always requires a skilled professional. Various researchers have developed artificial intelligence-based methods to address this challenge, yet they encounter several issues such as overlapping cancerous and noncancerous regions, extraction of irrelevant features, and inadequate training models. In this paper, we propose a novel computationally automated biological mechanism for categorizing breast cancer. This approach leverages a new optimization technique based on the Moth Flame Optimization (MFO) algorithm, which enhances the classification of breast cancer cases. The proposed framework consists of two main stages: Utilizing Deep Neural Networks (DNN) based on transfer learning. Implementing a Convolutional Neural Network (DCNN) optimized with MFO. By integrating transfer learning with an optimized DCNN for classification, our method significantly improves accuracy compared to recent approaches. The proposed framework was evaluated using publicly available datasets, achieving an average classification accuracy of 97.95%. To ensure the statistical significance and robustness of our results, we conducted tests that demonstrated the effectiveness and superior performance of our methodology compared to current methods.

Transformer-based land use and land cover classification with explainability using satellite imagery

Transformer-based models have greatly improved Land Use and Land Cover (LULC) applications. Their revolutionary ability to analyze and extract key information has greatly advanced the field. However, the high computational cost of these models presents a considerable obstacle to their practical implementation. Therefore, this study aims to strike a balance between computational cost and accuracy when employing transformer-based models for LULC analysis. We exploit transfer learning and fine-tuning strategies to optimize the resource utilization of transformer-based models. Furthermore, transparency is the core principle of our methodology to promote fairness and trust in applying LULC models across various domains, including forestry, environmental studies, and urban or rural planning. To ensure transparency, we have employed Captum, which enables us to uncover and mitigate potential biases and interpret AI-driven decisions. Our results indicate that transfer learning can potentially improve transformer-based models in satellite image classification, and strategic fine-tuning can maintain efficiency with minimal accuracy trade-offs. This research highlights the potential of Explainable AI (XAI) in Transformer-based models for achieving more efficient and transparent LULC analysis, thereby encouraging continued innovation in the field.

SDP-MTF: A Composite Transfer Learning and Feature Fusion for Cross-Project Software Defect Prediction

Software defect prediction is critical for improving software quality and reducing maintenance costs. In recent years, Cross-Project software defect prediction has garnered significant attention from researchers. This approach leverages transfer learning to apply the knowledge from existing projects to new ones, thereby enhancing the universality of predictive models. It provides an effective solution for projects with limited historical defect data. Nevertheless, current methodologies face two main challenges: first, the inadequacy of feature information mining, where code statistical information or semantic information is used in isolation, ignoring the benefits of their integration; second, the substantial feature disparity between different projects, which can lead to insufficient effect during transfer learning, necessitating additional efforts to narrow this gap to improve precision. Addressing these challenges, this paper proposes a novel methodology, SDP-MTF (Software Defect Prediction using Multi-stage Transfer learning and Feature fusion), that combines code statistical features, deep semantic features, and multiple feature transfer learning methods to enhance the predictive effect. The SDP-MTF method was empirically tested on single-source cross-project software defect prediction across six projects from the PROMISE dataset, benchmarked against five baseline algorithms that employ distinct features and transfer methodologies. Our findings indicate that SDP-MTF significantly outperforms five classical baseline algorithms, improving the F1-Score by 8% to 15.2%, thereby substantively advancing the precision of cross-project software defect prediction.

Deep Learning in Cricket: A Comprehensive Survey of Shot Detection and Performance Analysis

Cricket shot detection and performance analysis have become increasingly significant in the realm of sports analytics. This paper presents a comprehensive survey of recent advancements in cricket shot detection and performance analysis using deep learning techniques. Through a systematic review of ten research papers, various methodologies, algorithms, and approaches employed in the field were examined. The surveyed papers showcase the application of deep convolutional neural networks (CNNs), transfer learning, and multimodal feature integration for accurate shot detection and outcome classification. Additionally, the survey highlights common processes such as data preprocessing, model training, and evaluation metrics, while also discussing the integration of features extracted from video, audio, and image modalities. Through a detailed literature review, this paper analyzes the similarities and differences in approaches, methodologies, and results across the surveyed papers. Furthermore, this survey identifies opportunities for future research and development to advance the field of cricket shot detection and performance analysis. Overall, this survey provides valuable insights into the state-of-the-art techniques and challenges in utilizing deep learning for cricket analytics, offering guidance for researchers and practitioners in the domain.

Reservoir properties inversion using attention-based parallel hybrid network integrating feature selection and transfer learning

The inversion of subsurface reservoir properties is of profound significance to the oil and gas energy development and utilization. The strong heterogeneity and complex pore structure of underground reservoirs pose a challenge to efficient oil and gas energy development and utilization across the world, which increases the necessity of developing an efficient reservoir properties inversion method. However, traditional model-driven methods are confronted with the challenges of strong nonlinearity and geological heterogeneity. Moreover, previous studies rarely emphasized the importance of nonlinear feature selection and transfer learning (TL). Aiming to address the research gaps, a reservoir properties inversion method was proposed by combining random forest (RF) feature selection, bidirectional temporal convolutional network (BiTCN), bidirectional gated recurrent units (BiGRU) network, multi-head attention (MHA) mechanism and TL strategy. First, the RF was used to screen the features with significant correlation with the target reservoir properties. Thereafter, combining BiTCN and BiGRU network to leverage their complementary strengths, a parallel dual branch feature learning network was constructed to learn richer geological information from logging data. Meanwhile, MHA was introduced to fuse the output features of the dual network structure. Finally, the fused features were passed through the fully connected module to output the inversion results. TL was used to associate the correlation between reservoir properties and model inversion to improve the inversion performance. The application results with actual field data showed that the proposed method was accurate and robust in reservoir properties inversion. This study can provide a new way for reliable reservoir properties inversion and promote the application of artificial intelligence in data-driven energy science.

Integrating intratumoral and peritumoral radiomics with deep transfer learning for DCE-MRI breast lesion differentiation: A multicenter study comparing performance with radiologists

PurposeTo conduct the fusion of radiomics and deep transfer learning features from the intratumoral and peritumoral areas in breast DCE-MRI images to differentiate between benign and malignant breast tumors, and to compare the diagnostic accuracy of this fusion model against the assessments made by experienced radiologists. Materials and MethodsThis multi-center study conducted a retrospective analysis of DCE-MRI images from 330 women diagnosed with breast cancer, with 138 cases categorized as benign and 192 as malignant. The training and internal testing sets comprised 270 patients from center 1, while the external testing cohort consisted of 60 patients from center 2. A fusion feature set consisting of radiomics features and deep transfer learning features was constructed from both intratumoral (ITR) and peritumoral (PTR) areas. The Least absolute shrinkage and selection operator (LASSO) based support vector machine was chosen as the classifier by comparing its performance with five other machine learning models. The diagnostic performance and clinical usefulness of fusion model were verified and assessed through the area under the receiver operating characteristics (ROC) and decision curve analysis. Additionally, the performance of the fusion model was compared with the diagnostic assessments of two experienced radiologists to evaluate its relative accuracy. The study strictly adhered to CLEAR and METRICS guidelines for standardization to ensure rigorous and reproducible methods. ResultsThe findings show that the fusion model, utilizing radiomics and deep transfer learning features from the ITR and PTR, exhibited exceptional performance in classifying breast tumors, achieving AUCs of 0.950 in the internal testing set and 0.921 in the external testing set. This performance significantly surpasses that of models relying on singular regional radiomics or deep transfer learning features alone. Moreover, the fusion model demonstrated superior diagnostic accuracy compared to the evaluations conducted by two experienced radiologists, thereby highlighting its potential to support and enhance clinical decision-making in the differentiation of benign and malignant breast tumors. ConclusionThe fusion model, combining multi-regional radiomics with deep transfer learning features, not only accurately differentiates between benign and malignant breast tumors but also outperforms the diagnostic assessments made by experienced radiologists. This underscores the model’s potential as a valuable tool for improving the accuracy and reliability of breast tumor diagnosis.

Deep transfer learning radiomics model based on temporal bone CT for assisting in the diagnosis of inner ear malformations

Objective:To evaluate the diagnostic efficacy of traditional radiomics, deep learning, and deep learning radiomics in differentiating normal and inner ear malformations on temporal bone computed tomography（CT）. Methods:A total of 572 temporal bone CT data were retrospectively collected, including 201 cases of inner ear malformation and 371 cases of normal inner ear, and randomly divided into a training cohort（n=458） and a test cohort（n=114） in a ratio of 4∶1. Deep transfer learning features and radiomics features were extracted from the CT images and feature fusion was performed to establish the least absolute shrinkage and selection operator. The CT results interpretated by two chief otologists from the National Clinical Research Center for Otorhinolaryngological Diseases served as the gold standard for diagnosis. The model performance was evaluated using receiver operating characteristic（ROC）, and the accuracy, sensitivity, specificity, and other indicators of the models were calculated. The predictive power of each model was compared using the Delong test. Results:1 179 radiomics features were obtained from traditional radiomics, 2 048 deep learning features were obtained from deep learning, and 137 features fusion were obtained after feature screening and fusion of the two. The area under the curve（AUC） of the deep learning radiomics model on the test cohort was 0.964 0（95%CI 0.931 4-0.996 8）, with an accuracy of 0.922, sensitivity of 0.881, and specificity of 0.945. The AUC of the radiomics features alone on the test cohort was 0.929 0（95%CI 0.882 2-0.974 9）, with an accuracy of 0.878, sensitivity of 0.881, and specificity of 0.877. The AUC of the deep learning features alone on the test cohort was 0.947 0（95%CI 0.898 2-0.994 8）, with an accuracy of 0.913, sensitivity of 0.810, and specificity of 0.973. The results indicated that the prediction accuracy and AUC of the deep learning radiomics model are the highest. The Delong test showed that the differences between any two models did not reach statistical significance. Conclusion:The feature fusion model can be used for the differential diagnosis of normal and inner ear malformations, and its diagnostic performance is superior to radiomics or deep learning models alone.

Deep Learning Based Cystoscopy Image Enhancement.

Background: Endoscopy image enhancement technology provides doctors with clearer and more detailed images for observation and diagnosis, allowing doctors to assess lesions more accurately. Unlike most other endoscopy images, cystoscopy images face more complex and diverse image degradation because of their underwater imaging characteristics. Among the various causes of image degradation, the blood haze resulting from bladder mucosal bleeding make the background blurry and unclear, severely affecting diagnostic efficiency, even leading to misjudgment. Materials and Methods: We propose a deep learning-based approach to mitigate the impact of blood haze on cystoscopy images. The approach consists of two parts as follows: a blood haze removal network and a contrast enhancement algorithm. First, we adopt Feature Fusion Attention Network (FFA-Net) and transfer learning in the field of deep learning to remove blood haze from cystoscopy images and introduce perceptual loss to constrain the network for better visual results. Second, we enhance the image contrast by remapping the gray scale of the blood haze-free image and performing weighted fusion of the processed image and the original image. Results: In the blood haze removal stage, the algorithm proposed in this article achieves an average peak signal-to-noise ratio of 29.44 decibels, which is 15% higher than state-of-the-art traditional methods. The average structural similarity and perceptual image patch similarity reach 0.9269 and 0.1146, respectively, both superior to state-of-the-art traditional methods. Besides, our method is the best in keeping color balance after removing the blood haze. In the image enhancement stage, our algorithm enhances the contrast of vessels and tissues while preserving the original colors, expanding the dynamic range of the image. Conclusion: The deep learning-based cystoscopy image enhancement method is significantly better than other traditional methods in both qualitative and quantitative evaluation. The application of artificial intelligence will provide clearer, higher contrast cystoscopy images for medical diagnosis.

Multi-source transfer learning via optimal transport feature ranking for EEG classification

Motor imagery (MI) brain-computer interface (BCI) paradigms have been extensively used in neurological rehabilitation. However, due to the required long calibration time and non-stationary nature of electroencephalogram (EEG) signals, it is challenging to obtain a substantial sample size of EEG data. Transfer learning (TL), which leverages knowledge from existing subjects to enhance the learning performance in new subjects, has been employed to solve this problem. Previous studies often extract sample features directly from the two domains for transfer learning, leading to poor features and negative transfer. To overcome this limitation, an optimal transport feature selection method was developed in this study to select the most suitable features for migration to enhance the generalization capability of the TL. This was achieved by analyzing the diagonal value similarity of the optimal transport coupling matrix. First, the Riemannian tangent space mapping method was used to map the sample covariance matrix of EEG trials from the Riemannian manifold to tangent space. Secondly, the optimal subset of EEG features was selected via the optimal transport feature selection method. Subsequently, the separate distribution alignment method was employed to minimize dissimilarities between the source and target domains. Finally, the weighted voting mechanisms were integrated for decision fusion. The proposed multi-source transfer feature learning (MSTFL) method was validated based on two public BCI Competition IV datasets. Our results demonstrated superior classification accuracy of 85.93% and 79.48%, respectively, on the two public datasets, compared to state-of-the-art models. These findings indicate the effectiveness of our proposed MSTFL model for both feature extraction and classification of MI signals.

Ultrasound image-based nomogram combining clinical, radiomics, and deep transfer learning features for automatic classification of ovarian masses according to O-RADS.

Accurate and rapid discrimination between benign and malignant ovarian masses is crucial for optimal patient management. This study aimed to establish an ultrasound image-based nomogram combining clinical, radiomics, and deep transfer learning features to automatically classify the ovarian masses into low risk and intermediate-high risk of malignancy lesions according to the Ovarian- Adnexal Reporting and Data System (O-RADS). The ultrasound images of 1,080 patients with 1,080 ovarian masses were included. The training cohort consisting of 683 patients was collected at the South China Hospital of Shenzhen University, and the test cohort consisting of 397 patients was collected at the Shenzhen University General Hospital. The workflow included image segmentation, feature extraction, feature selection, and model construction. The pre-trained Resnet-101 model achieved the best performance. Among the different mono-modal features and fusion feature models, nomogram achieved the highest level of diagnostic performance (AUC: 0.930, accuracy: 84.9%, sensitivity: 93.5%, specificity: 81.7%, PPV: 65.4%, NPV: 97.1%, precision: 65.4%). The diagnostic indices of the nomogram were higher than those of junior radiologists, and the diagnostic indices of junior radiologists significantly improved with the assistance of the model. The calibration curves showed good agreement between the prediction of nomogram and actual classification of ovarian masses. The decision curve analysis showed that the nomogram was clinically useful. This model exhibited a satisfactory diagnostic performance compared to junior radiologists. It has the potential to improve the level of expertise of junior radiologists and provide a fast and effective method for ovarian cancer screening.

Predicting Osteoporosis and Osteopenia by Fusing Deep Transfer Learning Features and Classical Radiomics Features Based on Single-Source Dual-energy CT Imaging

Rationale and ObjectivesTo develop and validate a predictive model for osteoporosis and osteopenia prediction by fusing deep transfer learning (DTL) features and classical radiomics features based on single-source dual-energy computed tomography (CT) virtual monochromatic imaging. MethodsA total of 606 lumbar vertebrae with dual-energy CT imaging and quantitative CT (QCT) evaluation were included in the retrospective study and randomly divided into the training (n=424) and validation (n=182) cohorts. Radiomics features and DTL features were extracted from 70-keV monochromatic CT images, followed by feature selection and model construction, radiomics and DTL features models were established. Then, we integrated the selected two types of features into a features fusion model. We developed a two-level classifier for the hierarchical pairwise classification of each vertebra. All the vertebrae were first classified into osteoporosis and non-osteoporosis groups, then non-osteoporosis group was classified into osteopenia and normal groups. QCT was used as reference. The predictive performance and clinical usefulness of three models were evaluated and compared. ResultsThe area under the curve (AUC) of the features fusion, radiomics and DTL models for the classification between osteoporosis and non-osteoporosis were 0.981, 0.999, 0.997 in the training cohort and 0.979, 0.943, 0.848 in the validation cohort. Furthermore, the AUCs of the abovementioned models for the differentiation between osteopenia and normal were 0.994, 0.971, 0.996 in the training cohort and 0.990, 0.968, 0.908 in the validation cohort. The overall accuracy of the abovementioned models for two-level classifications was 0.979, 0.955, 0.908 in the training cohort and 0.918, 0.885, 0.841 in the validation cohort. Decision curve analysis (DCA) showed that all models had high clinical value. ConclusionThe feature fusion model can be used for osteoporosis and osteopenia prediction with improved predictive ability over a radiomics model or a DTL model alone.