Prenatal alcohol exposure (PAE) refers to the exposure of the developing fetus due to alcohol consumption during pregnancy and can have life-long consequences for learning, behavior, and health. Understanding the impact of PAE on the developing brain manifests challenges due to its complex structural and functional attributes, which can be addressed by leveraging machine learning (ML) and deep learning (DL) approaches. While most ML and DL models have been tailored for adult-centric problems, this work focuses on applying DL to detect PAE in the pediatric population. This study integrates the pre-trained simple fully convolutional network (SFCN) as a transfer learning approach for extracting features and a newly trained classifier to distinguish between unexposed and PAE participants based on T1-weighted structural brain magnetic resonance (MR) scans of individuals aged 2-8 years. Among several varying dataset sizes and augmentation strategy during training, the classifier secured the highest sensitivity of 88.47% with 85.04% average accuracy on testing data when considering a balanced dataset with augmentation for both classes. Moreover, we also preliminarily performed explainability analysis using the Grad-CAM method, highlighting various brain regions such as corpus callosum, cerebellum, pons, and white matter as the most important features in the model\'s decision-making process. Despite the challenges of constructing DL models for pediatric populations due to the brain\'s rapid development, motion artifacts, and insufficient data, this work highlights the potential of transfer learning in situations where data is limited. Furthermore, this study underscores the importance of preserving a balanced dataset for fair classification and clarifying the rationale behind the model\'s prediction using explainability analysis.

Despite advances in deep learning for plant leaf disease recognition, accurately distinguishing morphological features under varying environmental conditions continues to pose significant challenges. Traditional deep learning models often fail to effectively merge local and global information, especially in small-scale datasets, impairing performance and elevating training costs. Focusing on citrus diseases, we propose an improved FasterViT Model, an advanced hybrid CNN-ViT framework that builds upon the FasterViT model. The proposed model seamlessly integrates CNN\'s rapid local learning capabilities with ViT\'s global information processing strength, thereby effectively extracting complex textures and morphological features from images. Cross-stage alternating Mixup and Cutout methods are strategically employed to enhance model robustness and generalization capabilities, particularly valuable for fast learning on small-scale datasets by simulating a more diverse training environment. Triplet Attention and AdaptiveAvgPool mechanisms are utilized to reduce training costs and optimize training performance. The proposed model is tested on both our specially constructed small-scale citrus disease dataset called in-field small dataset and the comprehensive PlantVillage dataset. The experimental results demonstrated that the model exhibits the capability of fast learning and adaptation to small sample training in plant disease detection tasks, and demonstrates the effectiveness of our improvement approach in improving model accuracy and reducing training costs. Additionally, its exemplary performance in transfer learning scenarios underscores its adaptability and broad applicability. This study not only highlights the efficacy of the improved FasterViT model in addressing the complexities of plant disease image recognition but also pioneers a new paradigm for developing efficient, scalable, and robust classification systems.

Cassava is a most important carbohydrate human food consumed in many African and Asian countries. Cassava leaf disease is the major issue which affects production. Automatic early cassava leaf disease detection through deep learning models and transfer learning models were used for multiclass classification with different approaches. Existing approaches deal with imbalanced dataset for predicting the classes. This research work develops an approach based on hybrid Ensemble - deep transfer model approach for early leaf disease detection. Data augmentation was applied to the raw data for balancing the dataset. Three distinct new hybrid models namely Ensemble(InceptionV3+DenseNet-BC-121-32 + Xception), Ensemble(ResNet50V2+DenseNet-BC-121-32), Ensemble(ResNet50V2+ResNet50) were developed. The proposed model shows high performance results. A broad comparison of the proposed model was performed with custom based Convolutional Neural Network and pre-trained models. Highest accuracy of 88.83% and 97.89% was obtained in ensemble based approach that combined InceptionV3, Xception, DenseNet-BC-121-32 for five class and two class classification respectively.

Interaction and communication for normal human beings are easier than for a person with disabilities like speaking and hearing who may face communication problems with other people. Sign Language helps reduce this communication gap between a normal and disabled person. The prior solutions proposed using several deep learning techniques, such as Convolutional Neural Networks, Support Vector Machines, and K-Nearest Neighbors, have either demonstrated low accuracy or have not been implemented as real-time working systems. This system addresses both issues effectively. This work extends the difficulties faced while classifying the characters in Indian Sign Language(ISL). It can identify a total of 23 hand poses of the ISL. The system uses a pre-trained VGG16 Convolution Neural Network(CNN) with an attention mechanism. The model\'s training uses the Adam optimizer and cross-entropy loss function. The results demonstrate the effectiveness of transfer learning for ISL classification, achieving an accuracy of 97.5 % with VGG16 and 99.8 % with VGG16 plus attention mechanism.•Enabling quick and accurate sign language recognition with the help of trained model VGG16 with an attention mechanism.•The system does not require any external gloves or sensors, which helps to eliminate the need for physical sensors while simplifying the process with reduced costs.•Real-time processing makes the system more helpful for people with speaking and hearing disabilities, making it easier for them to communicate with other humans.

UNASSIGNED: Exoskeleton robot control should ideally be based on human voluntary movement intention. The readiness potential (RP) component of the motion-related cortical potential is observed before movement in the electroencephalogram and can be used for intention prediction. However, its single-trial features are weak and highly variable, and existing methods cannot achieve high cross-temporal and cross-subject accuracies in practical online applications. Therefore, this work aimed to combine a deep convolutional neural network (CNN) framework with a transfer learning (TL) strategy to predict the lower limb voluntary movement intention, thereby improving the accuracy while enhancing the model generalization capability; this would also provide sufficient processing time for the response of the exoskeleton robotic system and help realize robot control based on the intention of the human body.
UNASSIGNED: The signal characteristics of the RP for lower limb movement were analyzed, and a parameter TL strategy based on CNN was proposed to predict the intention of voluntary lower limb movements. We recruited 10 subjects for offline and online experiments. Multivariate empirical-mode decomposition was used to remove the artifacts, and the moment of onset of voluntary movement was labeled using lower limb electromyography signals during network training.
UNASSIGNED: The RP features can be observed from multiple data overlays before the onset of voluntary lower limb movements, and these features have long latency periods. The offline experimental results showed that the average movement intention prediction accuracy was 95.23% ± 1.25% for the right leg and 91.21% ± 1.48% for the left leg, which showed good cross-temporal and cross-subject generalization while greatly reducing the training time. Online movement intention prediction can predict results about 483.9 ± 11.9 ms before movement onset with an average accuracy of 82.75%.
UNASSIGNED: The proposed method has a higher prediction accuracy with a lower training time, has good generalization performance for cross-temporal and cross-subject aspects, and is well-prioritized in terms of the temporal responses; these features are expected to lay the foundation for further investigations on exoskeleton robot control.

Identifying anatomical correspondences in the human brain throughout the lifespan is an essential prerequisite for studying brain development and aging. But given the tremendous individual variability in cortical folding patterns, the heterogeneity of different neurodevelopmental stages, and the scarce of neuroimaging data, it is difficult to infer reliable lifespan anatomical correspondence at finer scales. To solve this problem, in this work, we take the advantage of the developmental continuity of the cerebral cortex and propose a novel transfer learning strategy: the model is trained from scratch using the age group with the largest sample size, and then is transferred and adapted to the other groups following the cortical developmental trajectory. A novel loss function is designed to ensure that during the transfer process the common patterns will be extracted and preserved, while the group-specific new patterns will be captured. The proposed framework was evaluated using multiple datasets covering four lifespan age groups with 1,000+ brains (from 34 gestational weeks to young adult). Our experimental results show that: 1) the proposed transfer strategy can dramatically improve the model performance on populations (e.g., early neurodevelopment) with very limited number of training samples; and 2) with the transfer learning we are able to robustly infer the complicated many-to-many anatomical correspondences among different brains at different neurodevelopmental stages. (Code will be released soon: https://github.com/qidianzl/CDC-transfer).

Gene expression profiling of new or modified cell lines becomes routine today; however, obtaining comprehensive molecular characterization and cellular responses for a variety of cell lines, including those derived from underrepresented groups, is not trivial when resources are minimal. Using gene expression to predict other measurements has been actively explored; however, systematic investigation of its predictive power in various measurements has not been well studied. Here, we evaluated commonly used machine learning methods and presented TransCell, a two-step deep transfer learning framework that utilized the knowledge derived from pan-cancer tumor samples to predict molecular features and responses. Among these models, TransCell had the best performance in predicting metabolite, gene effect score (or genetic dependency), and drug sensitivity, and had comparable performance in predicting mutation, copy number variation, and protein expression. Notably, TransCell improved the performance by over 50% in drug sensitivity prediction and achieved a correlation of 0.7 in gene effect score prediction. Furthermore, predicted drug sensitivities revealed potential repurposing candidates for new 100 pediatric cancer cell lines, and predicted gene effect scores reflected BRAF resistance in melanoma cell lines. Together, we investigated the predictive power of gene expression in six molecular measurement types and developed a web portal (http://apps.octad.org/transcell/) that enables the prediction of 352,000 genomic and cellular response features solely from gene expression profiles.

BACKGROUND: Structural variants (SVs) play an important role in genetic research and precision medicine. As existing SV detection methods usually contain a substantial number of false positive calls, approaches to filter the detection results are needed.
RESULTS: We developed a novel deep learning-based SV filtering tool, CSV-Filter, for both short and long reads. CSV-Filter uses a novel multi-level grayscale image encoding method based on CIGAR strings of the alignment results and employs image augmentation techniques to improve SV feature extraction. CSV-Filter also utilizes self-supervised learning networks for transfer as classification models, and employs mixed-precision operations to accelerate training. The experiments showed that the integration of CSV-Filter with popular SV detection tools could considerably reduce false positive SVs for short and long reads, while maintaining true positive SVs almost unchanged. Compared with DeepSVFilter, a SV filtering tool for short reads, CSV-Filter could recognize more false positive calls and support long reads as an additional feature.
METHODS: https://github.com/xzyschumacher/CSV-Filter.

Brain tumor (BT) is an awful disease and one of the foremost causes of death in human beings. BT develops mainly in 2 stages and varies by volume, form, and structure, and can be cured with special clinical procedures such as chemotherapy, radiotherapy, and surgical mediation. With revolutionary advancements in radiomics and research in medical imaging in the past few years, computer-aided diagnostic systems (CAD), especially deep learning, have played a key role in the automatic detection and diagnosing of various diseases and significantly provided accurate decision support systems for medical clinicians. Thus, convolution neural network (CNN) is a commonly utilized methodology developed for detecting various diseases from medical images because it is capable of extracting distinct features from an image under investigation. In this study, a deep learning approach is utilized to extricate distinct features from brain images in order to detect BT. Hence, CNN from scratch and transfer learning models (VGG-16, VGG-19, and LeNet-5) are developed and tested on brain images to build an intelligent decision support system for detecting BT. Since deep learning models require large volumes of data, data augmentation is used to populate the existing dataset synthetically in order to utilize the best fit detecting models. Hyperparameter tuning was conducted to set the optimum parameters for training the models. The achieved results show that VGG models outperformed others with an accuracy rate of 99.24%, average precision of 99%, average recall of 99%, average specificity of 99%, and average f1-score of 99% each. The results of the proposed models compared to the other state-of-the-art models in the literature show better performance of the proposed models in terms of accuracy, sensitivity, specificity, and f1-score. Moreover, comparative analysis shows that the proposed models are reliable in that they can be used for detecting BT as well as helping medical practitioners to diagnose BT.

BACKGROUND: During preclinical training, dental students take radiographs of acrylic (plastic) blocks containing extracted patient teeth. With the digitisation of medical records, a central archiving system was created to store and retrieve all x-ray images, regardless of whether they were images of teeth on acrylic blocks, or those from patients. In the early stage of the digitisation process, and due to the immaturity of the data management system, numerous images were mixed up and stored in random locations within a unified archiving system, including patient record files. Filtering out and expunging the undesired training images is imperative as manual searching for such images is problematic. Hence the aim of this stidy was to differentiate intraoral images from artificial images on acrylic blocks.
METHODS: An artificial intelligence (AI) solution to automatically differentiate between intraoral radiographs taken of patients and those taken of acrylic blocks was utilised in this study. The concept of transfer learning was applied to a dataset provided by a Dental Hospital.
RESULTS: An accuracy score, F1 score, and a recall score of 98.8%, 99.2%, and 100%, respectively, were achieved using a VGG16 pre-trained model. These results were more sensitive compared to those obtained initally using a baseline model with 96.5%, 97.5%, and 98.9% accuracy score, F1 score, and a recall score respectively.
CONCLUSIONS: The proposed system using transfer learning was able to accurately identify \"fake\" radiographs images and distinguish them from the real intraoral images.