Diagnostic Assistance Research Articles

Enhancing Diagnostic Accuracy of Fresh Vertebral Compression Fractures with Deep Learning Models.

Retrospective study. The study aimed to develop and authenticated a deep learning model based on X-ray images to accurately diagnose fresh thoracolumbar vertebral compression fractures. In clinical practice, diagnosing fresh vertebral compression fractures often requires MRI. However, due to the scarcity of MRI resources and the high time and economic costs involved, some patients may not receive timely diagnosis and treatment. Using a deep learning model combined with X-rays for diagnostic assistance could potentially serve as an alternative to MRI. In this study, the main collection included X-ray images suspected of thoracolumbar vertebral compression fractures from the municipal shared database between December 2012 and February 2024. Deep learning models were constructed using frameworks of EfficientNet, MobileNet, and MnasNet respectively. We conducted a preliminary evaluation of the deep learning model using the validation set. The diagnostic performance of the models was evaluated using metrics such as AUC value, accuracy, sensitivity, specificity, F1 score, precision, and ROC curve. Finally, the deep learning models were compared with evaluations from two spine surgeons of different experience levels on the control set. This study included a total of 3025 lateral X-ray images from 2224 patients. The dataset was divided into a training set of 2388 cases, a validation set of 482 cases, and a control set of 155 cases. In the validation set, the three groups of DL models had accuracies of 83.0%, 82.4%, and 82.2%, respectively. The AUC values were 0.861, 0.852, and 0.865, respectively. In the control set, the accuracies of the three groups of DL models were 78.1%, 78.1%, and 80.7%, respectively, all higher than spinal surgeons and significantly higher than junior spine surgeon. This study developed deep learning models for detecting fresh vertebral compression fractures, demonstrating high accuracy.

Comparison of MIB‐1‐Specific Membrane Staining in Hyalinising Trabecular Tumor Using Mainstream Automated Immunohistochemical Staining Platforms

ABSTRACTBackgroundMIB‐1, a monoclonal antibody against Ki‐67, exhibits specific membrane staining in the immunohistochemistry of hyalinising trabecular tumor (HTT). This specific staining pattern is crucial in diagnosing HTT. Although manual immunohistochemical staining remains the established method for MIB‐1 staining, this process is complicated, inconsistent, and prone to false negatives.MethodsThis study aimed to explore whether the classical reaction pattern can be replicated by utilizing the current mainstream automated immunohistochemical staining platforms. Furthermore, we examined the effect of different conditions on staining efficiency and their value in clinical diagnosis assistance.ResultsSpecimens obtained from eight and six cases of HTT and non‐HTT, respectively, from a single center were stained using the manual staining method and the Dako Autostainer Link 48 (AS48), Dako Omnis, Ventana BenchMark ULTRA, and Leica BOND‐III automated immunohistochemical staining platforms. The Autostainer Link 48 was found to be the most stable staining platform, while the BenchMark ULTRA with primary antibody incubation at room temperature (RT) and the Omnis platform with antigen retrieval at pH 9.0 were able to reproduce membrane‐positive staining for MIB‐1 in the HTT specimens.ConclusionsOur results offer crucial reference value for clinical diagnostic assistance.

Role of artificial intelligence in haematolymphoid diagnostics.

The advent of digital pathology and the deployment of high-throughput molecular techniques are generating an unprecedented mass of data. Thanks to advances in computational sciences, artificial intelligence (AI) approaches represent a promising avenue for extracting relevant information from complex data structures. From diagnostic assistance to powerful research tools, the potential fields of application of machine learning techniques in pathology are vast and constitute the subject of considerable research work. The aim of this article is to provide an overview of the potential applications of AI in the field of haematopathology and to define the role that these emerging technologies could play in our laboratories in the short to medium term.

Prediction Model of Spinal Osteoporosis Using Lumbar Spine X-Ray from Transfer Learning Deep Convolutional Neural Networks

Objective: Osteoporosis is highly prevalent among older adults and women. This condition leads to a deterioration in bone mineral density and microarchitecture, significantly increasing the risk of fractures. Additionally, osteoporosis commonly results in complications such as screw loosening and non-union during spinal surgery. Deep-learning algorithms have now achieved an accuracy comparable to the current human margin of error. Therefore, this study explored the potential of using transfer learning in deep learning algorithms to predict, diagnose, and screen for osteoporosis using commonly obtained sagittal spine X-rays from patients with spinal conditions.Methods: We retrospectively evaluated 2,300 consecutive patients who underwent dual energy X-ray absorptiometry (DXA) and lumbar sagittal plain X-ray exams between 2013 and 2021. The exclusion criteria included: (1) a gap of more than 1 year between the DXA and X-ray exams; (2) vertebrae that had undergone vertebroplasty; (3) lack of spine anterior-posterior DXA; and (4) images that were unassessable. Ultimately, 256 patients (images) were included in the study. Transfer learning was applied using convolutional neural network (CNN) techniques, specifically visual geometry group (VGG) 16, VGG 19, ResNet50, and Xception.Results: The most accurate CNN model in the training group was ResNet50, with an accuracy of 0.95. ResNet50 showed the best performance, with an accuracy of 0.82, precision of 0.80, recall of 0.86, and F1-score of 0.83. Additionally, its area under the curve (0.76) was higher than that other CNN models. The confusion matrix for ResNet50’s performance displayed the outcomes for images predicted as osteoporosis (n=12) among the test data osteoporosis images (n=14)Conclusion: Artificial intelligence (AI) technology employing deep learning techniques is significantly nearing human capabilities in the role of diagnostic assistance. The diagnosis of osteoporosis using bone mineral density is expected to evolve into a comprehensive diagnostic aid or decision-making tool with the integration of AI in the future.

Leukocytosis and thrombocytosis after splenectomy: expected finding, infection, or something else: a case report

BackgroundLeukocytosis and thrombocytosis often follow splenectomy in blunt trauma patients, complicating the postoperative identification of infection. While the platelet count to white blood cell ratio provides diagnostic assistance to discern between expected laboratory alterations and infection, diagnoses such as leukemia are often overlooked.Case presentationA 53-year-old Hispanic male presented with abdominal pain, nausea, tachycardia, and focal peritonitis 4 days after being assaulted and struck multiple times in the abdomen. Initial white blood cell count was 38.4 × 109/L, platelet count was 691 × 109/L, and lipase was 55 U/L. Computed tomography abdomen/pelvis demonstrated a hematoma encasing the distal pancreas and abutting the stomach and colon. Emergent laparotomy revealed a nearly transected pancreas and devascularized colon, necessitating a distal pancreatectomy, splenectomy, and colonic resection with primary anastomosis. Postoperatively, he had a persistently elevated leukocytosis, thrombocytosis, segmented neutrophils, eosinophilia, and basophilia (peak at 70, 2293, 64, 1.1, and 1.2 × 109/L, respectively). Despite sepsis workup, including repeat computed tomography, no source was identified. Hematology/oncology was consulted for concern for hematologic etiology, with genetic testing and bone marrow biopsy performed. The diagnosis of breakpoint cluster–Abelson gene-positive chronic myeloid leukemia was made based on genetic tests, including polymerase chain reaction and fluorescence in situ hybridization analysis, which confirmed the presence of the Philadelphia chromosome. Bone marrow biopsy suggested a chronic phase. The patient was treated with hydroxyurea and transitioned to imatinib.ConclusionsThrombocytosis following splenectomy is a common complication and a plate count to white blood cell count ratio < 20 indicates infectious etiology. A significantly elevated white blood cell count (> 50 × 109/L) and thrombocytosis (> 2000 × 109/L) may suggest something more ominous, including chronic myeloid leukemia , particularly when elevated granulocyte counts are present. Chronic myeloid leukemia workup includes peripheral smear, bone marrow aspiration, and determination of Philadelphia chromosome. Post-splenectomy vaccines are still indicated within 14 days; however, the timing of immunization with cancer treatment must be considered. Tyrosine kinase inhibitors are the first-line therapy and benefits of pretreatment with hydroxyurea for cytoreduction remain under investigation. Additionally, tyrosine kinase inhibitors have been associated with gastrointestinal perforation and impaired wound healing, necessitating heightened attention in patients with a new bowel anastomosis.

An optimized two stage U-Net approach for segmentation of pancreas and pancreatic tumor

The segmentation of pancreas and pancreatic tumor remain a persistent challenge for radiologists. Consequently, it is essential to develop automated segmentation methods to address this task. U-Net based models are most often used among various deep learning-based techniques in tumor segmentation. This paper introduces an innovative hybrid two-stage U-Net model for segmenting both the pancreas and pancreatic tumors. The optimization technique, used in this approach, involves a combination of meta-heuristic optimization algorithms namely, Grey Wolf Border Collie Optimization (GWBCO) technique, combining the Grey Wolf Optimization algorithm and the Border Collie Optimization algorithm. Our approach is evaluated using key parameters, such as Dice Similarity Coefficient (DSC), Jaccard Index (JI), sensitivity, specificity and precision to assess its effectiveness and achieves a DSC of 93.33 % for pancreas segmentation. Additionally, the model also achieves high DSC of 91.46 % for pancreatic tumor segmentation. This method helps in improving the diagnostic accuracy and assists medical professionals to provide treatment at an early stage with precise intervention. The method offers•Two-stage U-Net model addresses both pancreas and tumor segmentation.•Combination of two metaheuristic optimization algorithms, Grey Wolf and Border Collie for enhanced performance.•High dice similarity coefficient for pancreas and tumor segmentation.

Exploring the Ethical Dimensions of Artificial Intelligence and Robotics in Dental Education

Artificial intelligence (AI) and robotics have revolutionized healthcare, particularly dentistry. Their integration in dental education offers opportunities to enhance learning, diagnostics, treatment planning, and patient care. However, ethical implications must be addressed to ensure responsible and ethical integration of these technologies. This review explores AI and robotics in dental education and highlights the associated ethical considerations. These technologies provide improved learning experiences and simulations. Intelligent tutoring systems offer personalized feedback, virtual reality simulations enable practice in a safe environment, and AI algorithms aid in analysing radiographic images. Despite their potential, ethical challenges arise, including data privacy, autonomy, equity, and professional integrity. Addressing these challenges requires transparency, informed consent, bias detection, and accountability. Dental curricula should in-corporate ethics, fostering collaborations between educators and AI/robotics experts. Professional development programs should prioritize ethics training, considering emerging technologies such as AI-powered learning and diagnostic assistance. By embracing ethical considerations, AI and robotics can be integrated in dental education guided by transparency, accountability, privacy, and patient-centric care. A comprehensive understanding of the ethical dimensions is essential to harness the transformative potential of AI and robotics while upholding ethical standards in dental education. Bangladesh Journal of Medical Science Vol. 23 No. 04 October’24 Page : 999-1007

Bridging healthcare gaps: a scoping review on the role of artificial intelligence, deep learning, and large language models in alleviating problems in medical deserts.

"Medical deserts" are areas with low healthcare service levels, challenging the access, quality, and sustainability of care. This qualitative narrative review examines how artificial intelligence (AI), particularly large language models (LLMs), can address these challenges by integrating with e-Health and the Internet of Medical Things to enhance services in under-resourced areas. It explores AI-driven telehealth platforms that overcome language and cultural barriers, increasing accessibility. The utility of LLMs in providing diagnostic assistance where specialist deficits exist is highlighted, demonstrating AI's role in supplementing medical expertise and improving outcomes. Additionally, the development of AI chatbots offers preliminary medical advice, serving as initial contact points in remote areas. The review also discusses AI's role in enhancing medical education and training, supporting the professional development of healthcare workers in these regions. It assesses AI's strategic use in data analysis for effective resource allocation, identifying healthcare provision gaps. AI, especially LLMs, is seen as a promising solution for bridging healthcare gaps in "medical deserts," improving service accessibility, quality, and distribution. However, continued research and development are essential to fully realize AI's potential in addressing the challenges of medical deserts.

Research on the Design of Medical Imaging Assisted Diagnosis System Based on Machine Learning

The design and application of medical imaging diagnostic assistance systems have become an indispensable facet of modern medicine. Technologies based on machine learning can handle vast and intricate medical imaging data, offering precise diagnostic support and significantly enhancing the efficiency and accuracy of clinical diagnoses. This study focuses on the development and implementation of an efficient medical imaging diagnostic assistance system utilizing machine learning algorithms such as Principal Component Analysis (PCA), Support Vector Machines (SVM), and Multi-Layer Perceptrons (MLP). Through the architectural design of intelligent diagnostic assistance systems, data preprocessing, and feature vectorization, combined with the application of classification algorithms, a robust diagnostic support system capable of addressing diverse medical scenarios has been constructed. Performance evaluation experiments indicate that this system demonstrates high accuracy and robustness in processing medical imaging data, holding potential for clinical implementation. The findings of this study provide new insights for the advancement of intelligent diagnostic systems in medical imaging and lay a solid foundation for the development of future clinical diagnostic tools.

AI-Driven Diagnostic Assistance in Medical Inquiry: Reinforcement Learning Algorithm Development and Validation.

For medical diagnosis, clinicians typically begin with a patient's chief concerns, followed by questions about symptoms and medical history, physical examinations, and requests for necessary auxiliary examinations to gather comprehensive medical information. This complex medical investigation process has yet to be modeled by existing artificial intelligence (AI) methodologies. The aim of this study was to develop an AI-driven medical inquiry assistant for clinical diagnosis that provides inquiry recommendations by simulating clinicians' medical investigating logic via reinforcement learning. We compiled multicenter, deidentified outpatient electronic health records from 76 hospitals in Shenzhen, China, spanning the period from July to November 2021. These records consisted of both unstructured textual information and structured laboratory test results. We first performed feature extraction and standardization using natural language processing techniques and then used a reinforcement learning actor-critic framework to explore the rational and effective inquiry logic. To align the inquiry process with actual clinical practice, we segmented the inquiry into 4 stages: inquiring about symptoms and medical history, conducting physical examinations, requesting auxiliary examinations, and terminating the inquiry with a diagnosis. External validation was conducted to validate the inquiry logic of the AI model. This study focused on 2 retrospective inquiry-and-diagnosis tasks in the emergency and pediatrics departments. The emergency departments provided records of 339,020 consultations including mainly children (median age 5.2, IQR 2.6-26.1 years) with various types of upper respiratory tract infections (250,638/339,020, 73.93%). The pediatrics department provided records of 561,659 consultations, mainly of children (median age 3.8, IQR 2.0-5.7 years) with various types of upper respiratory tract infections (498,408/561,659, 88.73%). When conducting its own inquiries in both scenarios, the AI model demonstrated high diagnostic performance, with areas under the receiver operating characteristic curve of 0.955 (95% CI 0.953-0.956) and 0.943 (95% CI 0.941-0.944), respectively. When the AI model was used in a simulated collaboration with physicians, it notably reduced the average number of physicians' inquiries to 46% (6.037/13.26; 95% CI 6.009-6.064) and 43% (6.245/14.364; 95% CI 6.225-6.269) while achieving areas under the receiver operating characteristic curve of 0.972 (95% CI 0.970-0.973) and 0.968 (95% CI 0.967-0.969) in the scenarios. External validation revealed a normalized Kendall τ distance of 0.323 (95% CI 0.301-0.346), indicating the inquiry consistency of the AI model with physicians. This retrospective analysis of predominantly respiratory pediatric presentations in emergency and pediatrics departments demonstrated that an AI-driven diagnostic assistant had high diagnostic performance both in stand-alone use and in simulated collaboration with clinicians. Its investigation process was found to be consistent with the clinicians' medical investigation logic. These findings highlight the diagnostic assistant's promise in assisting the decision-making processes of health care professionals.

Globalization of a telepathology network with artificial intelligence applications in Colombia: The GLORIA program study protocol

In Colombia, cancer is recognized as a high-cost pathology by the national government and the Colombian High-Cost Disease Fund. As of 2020, the situation is most critical for adult cancer patients, particularly those under public healthcare and residing in remote regions of the country. The highest lag time for a diagnosis was observed for cervical cancer (79.13 days), followed by prostate (77.30 days), and breast cancer (70.25 days). Timely and accurate histopathological reporting plays a vital role in the diagnosis of cancer. In recent years, digital pathology has been globally implemented as a technological tool in two main areas: telepathology (TP) and computational pathology. TP has been shown to improve rapid and timely diagnosis in anatomic pathology by facilitating interaction between general laboratories and specialized pathologists worldwide through information and telecommunication technologies. Computational pathology provides diagnostic and prognostic assistance based on histopathological patterns, molecular, and clinical information, aiding pathologists in making more accurate diagnoses. We present the study protocol of the GLORIA digital pathology network, a pioneering initiative, and national grant-approved program aiming to design and pilot a Colombian digital pathology transformation focused on TP and computational pathology, in response to the general needs of pathology laboratories for diagnosing complex malignant tumors. The study protocol describes the design of a TP network to expand oncopathology services across all Colombian regions. It also describes an artificial intelligence proposal for lung cancer, one of Colombia's most prevalent cancers, and a freely accessible national histopathological image database to facilitate image analysis studies.

Can temporomandibular joint osteoarthritis be diagnosed on MRI proton density weighted images with diagnostic support from the latest deep learning classification models?

This study aimed to clarify the performance of magnetic resonance imaging (MRI)-based deep learning classification models in diagnosing temporomandibular joint osteoarthritis (TMJ-OA) and to compare the developed diagnostic assistance with human observers. The subjects were 118 patients who underwent MRI for examination of TMJ disorders. One hundred condyles with TMJ-OA and 100 condyles without TMJ-OA were enrolled. Deep learning was performed with four networks (ResNet18, EfficientNet b4, Inception v3, and GoogLeNet) using five-fold cross validation. Receiver operating characteristics (ROC) curves were drawn for each model and diagnostic metrics were determined. The performances of the four network models were compared using Kruskal-Wallis tests and post-hoc Scheffe tests, and ROCs between the best model and human were compared using chi-square tests, with p < 0.05 considered significant. ResNet18 had areas under the curves (AUCs) of 0.91-0.93 and accuracy of 0.85-0.88, which were the highest among the four networks. There were significant differences in AUC and accuracy between ResNet and GoogLeNet (p = 0.0264 and p = 0.0418, respectively). The kappa values of the models were large, 0.95 for ResNet and 0.93 for EfficientNet. The experts achieved similar AUC and accuracy values ​​to the ResNet metrics, 0.94 and 0.85, and 0.84 and 0.84, respectively, but with a lower kappa of 0.67. Those of the dental residents showed lower values. There were significant differences in AUCs between ResNet and residents (p < 0.0001) and between experts and residents (p < 0.0001). Using a deep learning model, high performance was confirmed for MRI diagnosis of TMJ-OA.

Circulating CD8 + LGALS9 + T Cell Population Exhibiting Low Cytotoxic Characteristics are Decreased in Patients with Systemic Lupus Erythematosus.

LGALS9, also known as Galectin-9 and a member of the β-galactosidase family, plays a crucial role in immune regulation. However, its expression and function in CD8 T cells, as well as its association with cytotoxic T lymphocytes (CTL), remain unclear. This study aims to investigate LGALS9 expression patterns in human circulating CD8 T lymphocytes and elucidate its clinical significance in Systemic Lupus Erythematosus (SLE). Blood samples from 56 healthy controls and 50 new-onset SLE patients were collected. Flow cytometry was utilized to analyze LGALS9 expression in circulating CD8 T lymphocytes via intracellular staining. Compared to LGALS9 + CD8 + T cells, LGALS9-CD8 + T cells showed increased secretion of Granzyme B (GZMB) and Perforin, along with elevated expression levels of GPR56, CX3CR1, KLRD1, KLRF1, PD1, and CD29. A higher proportion of Tn (naive T cells) and TCM (central memory T cells) showed LGALS9 positivity, compared to TEM (effector memory T cells) and TEMRA (terminally differentiated effector memory T cells re-expressing CD45RA). Clinically, the downregulation of LGALS9 expression was significant in SLE patients. LGALS9 + CD8 + T cells exhibited an Area Under the Curve (AUC) of 0.6916, while CX3CR1 + in LGALS9 + CD8 + T cells had an AUC of 0.6478, and KLRF1 + had an AUC of 0.6419, for distinguishing SLE from healthy individuals. In conclusion, CD8 + LGALS9 + T cells display characteristics of low cytotoxicity, and their reduction is evident in SLE patients, potentially implicating them in SLE pathogenesis and providing diagnostic assistance.

Ensemble XMOB Approach for Brain Tumor Detection Based on Feature Extraction

Brain tumors are a serious health threat in adults. These fast-growing abnormal cell masses disrupt normal brain function. Doctors use various imaging techniques to identify the specific type, size, and location of brain tumors in patients. Accurately identifying and classifying brain tumors is crucial for understanding how they develop and progress. Magnetic Resonance Imaging (MRI), a well-established medical imaging technique, plays a vital role in this process by assisting radiologists in investigating the location of the tumor. Previous models frequently encounter a compromise between accuracy and computational efficiency, lacking an approach that successfully integrates both aspects.This study introduces an innovative ensemble model termed as “XMob Approach” that combines the deep features extraction abilities of Xception with computational efficiency of MobleNet for binary classification of brain Tumor. The Xmob Approach leverages the strengths of both architectures : Xception depthwise seperable convolutions allow for detailed feature extraction whereas MobileNet’s lightweight structure ensures efficient computation making it suitable for real life application. This combination aims to enhance in medical diagnostics, promising enhanced accuracy and efficiency. This study explores the potential of integrating these pre-trained architectures to provide real-time, automated diagnostic assistance, improving the speed and precision of brain tumor detection. In our methodology pre-processed MRI scans undergo feature extraction through Xception model, capturing complicated patterns indicative of tumor presence. Simultaneously MobileNet processed these images emphasizing computational efficiency without compromising on performance.The output of both the modesl are then integrated using ensemble technique to improve overall classification accuracy. By integrating the complementary strengths of Xception and MobileNet , the XMob Approach represent a significant step towards the field of medical diagnostic promising improved outcomes for patients through advanced technology. DOI: https://doi.org/10.52783/tjjpt.v45.i03.7253

Performance of Artificial Intelligence Models (Bidirectional Encoder Representations from Transformers + TextCNN) in Detecting Eight Psychiatric Diagnoses from Unstructured Texts Chinese Electronic Medical Records

Objectives: Advances in artificial intelligence (AI) have revolutionized various industries, including health care. In this study, we intended to explore the capability of AI assistants in psychiatric diagnoses. To achieve this goal, we proposed a series of deep active learning models, namely bidirectional encoder representations from transformers (BERT) – TextCNN. These models combine the strengths of two powerful techniques: BERT and convolutional neural network (CNN) for the text. Methods: We collected 21,003 Chinese psychiatry electronic medical records (EMRs) and developed two types of models: a multi-diagnosis classifier and eight single-diagnosis classifiers for schizophrenia (SCZ), major depressive disorder (MDD), manic state (MANIA), adjustment disorder (ADJ), substance use disorder (SUD), personality disorder (PD), attention-deficit/hyperactivity disorder (ADHD), and autistic spectrum disorder (ASD). Their performance was compared through plotting receiver operating characteristic curves and assessing the performance, area under curve (AUC) using the DeLong test. Results: This study showed the excellent performance of our BERT + TextCNN models in detecting almost all eight psychiatric diagnoses, achieving AUCs being greater than 0.9, except for the single-diagnosis classifier for ADHD (AUC = 0.83). Conclusion: This study highlights the promising applicability of the BERT + TextCNN model as a diagnostic assistant for psychiatry diagnoses derived from EMRs. Being consistent with previous findings, the single-diagnosis classifiers generally outperform the multi-diagnosis classifier in predicting most diagnoses, though not all. Further studies are warranted to confirm whether the specific characteristics of illnesses contribute to the performance gap between multi- and single-diagnosis classifiers.

A feature-aware multimodal framework with auto-fusion for Alzheimer’s disease diagnosis

Alzheimer’s disease (AD), one of the most common dementias, has about 4.6 million new cases yearly worldwide. Due to the significant amount of suspected AD patients, early screening for the disease has become particularly important. There are diversified types of AD diagnosis data, such as cognitive tests, images, and risk factors, many prior investigations have primarily concentrated on integrating only high-dimensional features and simple fusion concatenation, resulting in less-than-optimal outcomes for AD diagnosis. Therefore, We propose an enhanced multimodal AD diagnostic framework comprising a feature-aware module and an automatic model fusion strategy (AMFS). To preserve the correlation and significance features within a low-dimensional space, the feature-aware module employs a low-dimensional SHapley Additive exPlanation (SHAP) boosting feature selection as the initial step, following this analysis, diverse tiers of low-dimensional features are extracted from patients’ biological data. Besides, in the high-dimensional stage, the feature-aware module integrates cross-modal attention mechanisms to capture subtle relationships among different cognitive domains, neuroimaging modalities, and risk factors. Subsequently, we integrate the aforementioned feature-aware module with graph convolutional networks (GCN) to address heterogeneous data in multimodal AD, while also possessing the capability to perceive relationships between different modalities. Lastly, our proposed AMFS autonomously learns optimal parameters for aligning two sub-models. The validation tests using two ADNI datasets show the high accuracies of 95.9% and 91.9% respectively, in AD diagnosis. The methods efficiently select features from multimodal AD data, optimizing model fusion for potential clinical assistance in diagnostics.

Modern methods of neuroimaging in the diagnosis of acute ischemic stroke

Ischemic stroke is one of the leading causes of morbidity and mortality worldwide, resulting in significant social and economic consequences for the healthcare system. Moreover, ischemic stroke has a devastating psycho-emotional impact on both the patient and their family, causing anxiety and depressive disorders. To reduce the severity of neurological deficit, increase the percentage of patients returning to their previous level of social and daily activity, and decrease the rates of disability after a cerebrovascular catastrophe, it is necessary to provide the full spectrum of therapeutic and diagnostic assistance in the shortest possible time. Developing neuroimaging techniques help to timely and accurately diagnose cerebral stroke, differentiate ischemic damage from hemorrhagic, and also establish the time of onset of acute cerebrovascular accident.

Towards knowledge-infused automated disease diagnosis assistant

With the advancement of internet communication and telemedicine, people are increasingly turning to the web for various healthcare activities. With an ever-increasing number of diseases and symptoms, diagnosing patients becomes challenging. In this work, we build a diagnosis assistant to assist doctors, which identifies diseases based on patient–doctor interaction. During diagnosis, doctors utilize both symptomatology knowledge and diagnostic experience to identify diseases accurately and efficiently. Inspired by this, we investigate the role of medical knowledge in disease diagnosis through doctor–patient interaction. We propose a two-channel, knowledge-infused, discourse-aware disease diagnosis model (KI-DDI), where the first channel encodes patient–doctor communication using a transformer-based encoder, while the other creates an embedding of symptom-disease using a graph attention network (GAT). In the next stage, the conversation and knowledge graph embeddings are infused together and fed to a deep neural network for disease identification. Furthermore, we first develop an empathetic conversational medical corpus comprising conversations between patients and doctors, annotated with intent and symptoms information. The proposed model demonstrates a significant improvement over the existing state-of-the-art models, establishing the crucial roles of (a) a doctor’s effort for additional symptom extraction (in addition to patient self-report) and (b) infusing medical knowledge in identifying diseases effectively. Many times, patients also show their medical conditions, which acts as crucial evidence in diagnosis. Therefore, integrating visual sensory information would represent an effective avenue for enhancing the capabilities of diagnostic assistants.

Health of Things Melanoma Detection System—detection and segmentation of melanoma in dermoscopic images applied to edge computing using deep learning and fine-tuning models

According to the World Health Organization (WHO), melanoma is a type of cancer that affects people globally in different parts of the human body, leading to deaths of thousands of people every year worldwide. Intelligent diagnostic tools through automatic detection in medical images are extremely effective in aiding medical diagnosis. Computer-aided diagnosis (CAD) systems are of utmost importance for image-based pre-diagnosis, and the use of artificial intelligence–based tools for monitoring, detection, and segmentation of the pathological region are increasingly used in integrated smart solutions within smart city systems through cloud data processing with the use of edge computing. This study proposes a new approach capable of integrating into computational monitoring and medical diagnostic assistance systems called Health of Things Melanoma Detection System (HTMDS). The method presents a deep learning–based approach using the YOLOv8 network for melanoma detection in dermatoscopic images. The study proposes a workflow through communication between the mobile device, which extracts captured images from the dermatoscopic device and uploads them to the cloud API, and a new approach using deep learning and different fine-tuning models for melanoma detection and segmentation of the region of interest, along with the cloud communication structure and comparison with methods found in the state of the art, addressing local processing. The new approach achieved satisfactory results with over 98% accuracy for detection and over 99% accuracy for skin cancer segmentation, surpassing various state-of-the-art works in different methods, such as manual, semi-automatic, and automatic approaches. The new approach demonstrates effective results in the performance of different intelligent automatic models with real-time processing, which can be used in affiliated institutions or offices in smart cities for population use and medical diagnosis purposes.

A CNN-based spline active surface method with an after-balancing step for 3D medical image segmentation

Over the past few years, tasks such as automatic information extraction and object surface detection from 3D medical images have become increasingly popular, providing clinicians with numerous new opportunities for exploration and diagnostic assistance. Nonetheless, the segmentation process can present various challenges. This paper introduces an automatic 3D deep parametric active surface model (3D B-snake) approximated by bivariate Unified and Extended spline (UE-spline) functions with a parameter controlling the shape of the snake. We introduce an energy term that enables to separate the different textures present in an image using a Convolutional Neural Network (CNN) learning model, namely U-Net. After balancing our snake surface to align it with the complex parts of the object to be segmented, an object snake alignment strategy is proposed using an interpolation scheme that exploits some geometric properties of the object. Experiments performed on the BraTS21 dataset show that our model is very powerful to deal with various difficulties encountered in medical image segmentation.