Down syndrome (DS) is one of the prevalent chromosomal disorders, representing distinctive craniofacial features and a range of developmental and medical challenges. Due to the lack of clinical expertise and high infrastructure costs, access to genetic testing is restricted to resource-constrained clinical settings. There is a demand for developing a non-invasive and equitable DS screening tool, facilitating DS diagnosis for a wide range of populations. In this study, we develop and validate a robust, interpretable deep learning model for the early detection of DS using facial images of infants. A hybrid feature extraction architecture combining RegNet X-MobileNet V3 and vision transformer (ViT)-Linformer is developed for effective feature representation. We use an adaptive attention-based feature fusion to enhance the proposed model's focus on diagnostically relevant facial regions. Bayesian optimization with hyperband (BOHB) fine-tuned extremely randomized trees (ExtraTrees) is employed to classify the features. To ensure the model's generalizability, stratified five-fold cross-validation is performed. Compared to the recent DS classification approaches, the proposed model demonstrates outstanding performance, achieving an accuracy of 99.10%, precision of 98.80%, recall of 98.87%, F1-score of 98.83%, and specificity of 98.81%, on the unseen data. The findings underscore the strengths of the proposed model as a reliable screening tool to identify DS in the early stages using the facial images. This study paves the foundation to build equitable, scalable, and trustworthy digital solution for effective pediatric care across the globe.
face imagesinfantsnon-invasive screeninghybrid feature extraction
International Journal of Imaging Systems and Technology · مجلد 35 (5)
ABSTRACT Recent advancements in Deep Learning (DL) have enabled the development of Computer‐Aided Diagnosis (CAD) systems for detecting Acute Lymphoblastic Leukemia (ALL) and its subtypes. However, this field faces challenges, particularly due to limited annotated datasets and a lack of efficient modalities. To address these issues, we propose MHAOSL‐net, a novel hybrid DL model specifically designed for the accurate classification of B‐ALL, T‐ALL, and normal cells in blood smear images. The key contributions lie in the integration of four primary components: (1) lightweight MobileNetV2 for backbone feature extraction, (2) a Global Context Information Convolutional Block Attention Module (GCI‐CBAM) for refined local representation using contextual information, (3) an Attention‐Free Transformer (AFT) that captures global dependencies replacing traditional self‐attention, and (4) an Orthogonal SoftMax Layer (OSL) that improves class separability by enforcing orthogonality in the decision space. This unified architecture not only reduces computational overhead but also improves classification performance and generalizability. To the best of our knowledge, this is the first framework that combines an AFT with an OSL in the context of leukemia subtype detection. The performance analysis of the proposed 3‐class classification scheme has been assessed on two novel datasets, namely BBCI_B&T_ALL_2024 and heterogeneous datasets. The experimental results show that the proposed scheme provides better performance, with 99.52% accuracy, 99.36% average precision, and 99.36% average F1‐score on the BBCI_B&T_ALL_2024. Similarly, it achieves better performance with 99.55% accuracy, 99.40% average precision, and 99.40% average F1‐score on the heterogeneous dataset. The qualitative investigation using Gradient‐weighted Class Activation Mapping (Grad‐CAM) visualization also confirms the efficacy of the proposed model for detecting B‐ALL, T‐ALL, and normal cells. The comparative studies establish the superiority of the proposed scheme over other state‐of‐the‐art approaches. These findings indicate that MHAOSL‐Net offers a promising and efficient solution for reliable ALL subtype detection in clinical settings.
Brain stroke (BS) imposes a substantial burden on healthcare systems due to the long-term care and high expenditure. Earlier detection and intervention can reduce the impact of BS. Magnetic resonance imaging (MRI) is commonly applied for BS detection. Deep learning techniques can employ MRI images to identify the BS risks in the initial stages. This study developed a BS detection model using an ensemble learning approach that combines the predictions of the base models. A MobileNet V3 model backbone was used to extract the intricate patterns of BS from MRI images. LightGBM and CatBoost models were used as base models to predict BS using the extracted features. In addition, the random forest model was used to integrate the predictions of base models to identify BS. The proposed model was generalized on a public MRI dataset that covers 2888 clinical MRI images. The experimental outcomes showed the effectiveness of the suggested BS detection model. The proposed model has obtained an accuracy of 98.7%, an area under the receiver operating characteristic score of 0.95, and an area under the precision–recall curve of 0.92. The recommended model is believed to be deployed in real-time healthcare settings to assist radiologists and clinicians in making effective decisions.
The classification of speech disorders (SDs) is crucial for treating children with speech impairment (SI). An automated SD classification can assist speech therapists in rendering services to children with SI in rural areas. Automated techniques for detecting SDs provide objective assessments of speech attributes, including articulation, fluency, and prosody. Clinical examinations and quantitative assessments provide an in-depth understanding of the patient’s speaking abilities and limitations. Existing deep learning (DL) models for SD detection often lack generalization across diverse populations and speech variations, leading to suboptimal performance when applied to individuals with different linguistic backgrounds or dialects. This study introduces a DL-based model for classifying normal and abnormal speeches using voice samples. To overcome the overfitting and bias, the authors construct convolutional neural network models with the weights of MobileNet V3 and EfficientNet B7 models for feature extraction (FE). To improve performance, they integrate the squeeze and excitation block with the MobileNet V3-based FE model. Similarly, the EfficientNet B7-model-based FE is improved using the structure pruning technique. The enhanced CatBoost model differentiates the normal and abnormal speeches using the extracted features. The experimental analysis is performed using the public dataset that contains 4620 utterances of healthy children and 2178 utterances of children with SI. The comparative study reveals the exceptional performance of the proposed SD classification model. The model outperforms the current SD classification models. It can be employed in clinical settings to support speech therapists. Substantial training with diverse voice samples can improve the generalizability of the proposed model.
Accurate and rapid diagnosis is essential in the healthcare system for the detection of strokes to mitigate the devastating effects. This study introduces an innovative model for identifying strokes using advanced deep learning (DL) architectures, including SqueezeNet v1.1 and MobileNet V3-Small, feature fusion approaches, and CatBoost models. Using SqueezeNet v1.1 and MobileNet V3-Small, the authors extract meaningful features from computed tomography images that capture local details and global patterns suggesting stroke conditions. Subsequently, they employ feature fusion to combine the complementary representations derived by both architectures, consequently boosting the discriminative capability of the feature set. The Optuna-based CatBoost model is employed to predict stroke using the fused features. The experimental findings show outstanding performance, with a considerable accuracy of 99.1%. The high accuracy level demonstrates our suggested method’s effectiveness in precisely detecting strokes from medical imaging data. Combining DL architectures, feature fusion, and gradient-boosting models offers a promising approach to enhancing stroke diagnosis systems. This can potentially improve patient outcomes and clinical decision-making in stroke treatment.
In this study, the authors proposed a pain identification model using facial expressions. An image extraction technique was developed using the liquid neural network to extract diverse images from the video files. The authors used the DenseNet 201 and MobileNet V3 models to build a hybrid feature engineering technique. They applied quantization aware training to improve the efficiency of the models. The Prkachin and Solomon Pain Intensity score was used for the image classification. They fine-tuned the LightGBM model using the random search algorithm for identifying pain from the facial images. The authors used the Denver Intensity of Spontaneous Facial Action dataset to generalize the proposed model. The performance evaluation outlined the significant performance of the proposed model in identifying pain using the images. In addition, it demands limited computational resources to identify pain. Healthcare and rehabilitation centers can implement the proposed model to provide adequate services to disabled individuals.
Decision-making medical systems (DMS) refer to the design of decision techniques in the healthcare sector. They involve a procedure of employing ideas and decisions related to certain processes such as data acquisition, processing, judgment, and conclusion. Pancreatic cancer is a lethal type of cancer, and its prediction is ineffective with current techniques. Automated detection and classification of pancreatic tumors can be provided by the computer-aided diagnosis (CAD) model using radiological images such as computed tomography (CT) and magnetic resonance imaging (MRI). The recently developed machine learning (ML) and deep learning (DL) models can be utilized for the automated and timely detection of pancreatic cancer. In light of this, this article introduces an intelligent deep-learning-enabled decision-making medical system for pancreatic tumor classification (IDLDMS-PTC) using CT images. The major intention of the IDLDMS-PTC technique is to examine the CT images for the existence of pancreatic tumors. The IDLDMS-PTC model derives an emperor penguin optimizer (EPO) with multilevel thresholding (EPO-MLT) technique for pancreatic tumor segmentation. Additionally, the MobileNet model is applied as a feature extractor with optimal auto encoder (AE) for pancreatic tumor classification. In order to optimally adjust the weight and bias values of the AE technique, the multileader optimization (MLO) technique is utilized. The design of the EPO algorithm for optimal threshold selection and the MLO algorithm for parameter tuning shows the novelty. A wide range of simulations was executed on benchmark datasets, and the outcomes reported the promising performance of the IDLDMS-PTC model on the existing methods.
Journal of Healthcare Engineering · مجلد 2022 · 1-14
Intelligent decision support systems (IDSS) for complex healthcare applications aim to examine a large quantity of complex healthcare data to assist doctors, researchers, pathologists, and other healthcare professionals. A decision support system (DSS) is an intelligent system that provides improved assistance in various stages of health-related disease diagnosis. At the same time, the SARS-CoV-2 infection that causes COVID-19 disease has spread globally from the beginning of 2020. Several research works reported that the imaging pattern based on computed tomography (CT) can be utilized to detect SARS-CoV-2. Earlier identification and detection of the diseases is essential to offer adequate treatment and avoid the severity of the disease. With this motivation, this study develops an efficient deep-learning-based fusion model with swarm intelligence (EDLFM-SI) for SARS-CoV-2 identification. The proposed EDLFM-SI technique aims to detect and classify the SARS-CoV-2 infection or not. Also, the EDLFM-SI technique comprises various processes, namely, data augmentation, preprocessing, feature extraction, and classification. Moreover, a fusion of capsule network (CapsNet) and MobileNet based feature extractors are employed. Besides, a water strider algorithm (WSA) is applied to fine-tune the hyperparameters involved in the DL models. Finally, a cascaded neural network (CNN) classifier is applied for detecting the existence of SARS-CoV-2. In order to showcase the improved performance of the EDLFM-SI technique, a wide range of simulations take place on the COVID-19 CT data set and the SARS-CoV-2 CT scan data set. The simulation outcomes highlighted the supremacy of the EDLFM-SI technique over the recent approaches.
COVID-19 detectionCOVID-19 pandemiccomputed tomographyintelligent decision support system