IEEE Trans Med Imaging. 2024 Feb 9;PP. doi: 10.1109/TMI.2024.3364911. Online ahead of print.

ABSTRACT

Magnetic resonance imaging is subject to slow acquisition times due to the inherent limitations in data sampling. Recently, supervised deep learning has emerged as a promising technique for reconstructing sub-sampled MRI. However, supervised deep learning requires a large dataset of fully-sampled data. Although unsupervised or self-supervised deep learning methods have emerged to address the limitations of supervised deep learning approaches, they still require a database of images. In contrast, scan-specific deep learning methods learn and reconstruct using only the sub-sampled data from a single scan. Here, we introduce Scan-Specific Self-Supervised Bayesian Deep Non-Linear Inversion (DNLINV) that does not require an auto calibration scan region. DNLINV utilizes a Deep Image Prior-type generative modeling approach and relies on approximate Bayesian inference to regularize the deep convolutional neural network. We demonstrate our approach on several anatomies, contrasts, and sampling patterns and show improved performance over existing approaches in scan-specific calibrationless parallel imaging and compressed sensing.

PMID:38335079 | DOI:10.1109/TMI.2024.3364911

IEEE Trans Biomed Circuits Syst. 2024 Feb 9;PP. doi: 10.1109/TBCAS.2024.3364235. Online ahead of print.

ABSTRACT

Deep learning (DL) has been used for electromyographic (EMG) signal recognition and achieved high accuracy for multiple classification tasks. However, implementation in resource-constrained prostheses and human-computer interaction devices remains challenging. To overcome these problems, this paper implemented a low-power system for EMG gesture and force level recognition using Zynq architecture. Firstly, a lightweight network model structure was proposed by Ultra-lightweight depth separable convolution (UL-DSC) and channel attention-global average pooling (CA-GAP) to reduce the computational complexity while maintaining accuracy. A wearable EMG acquisition device for real-time data acquisition was subsequently developed with size of 36mm×28mm×4mm. Finally, a highly parallelized dedicated hardware accelerator architecture was designed for inference computation. 18 gestures were tested, including force levels from 22 healthy subjects. The results indicate that the average accuracy rate was 94.92% for a model with 5.0k parameters and a size of 0.026MB. Specifically, the average recognition accuracy for static and force-level gestures was 98.47% and 89.92%, respectively. The proposed hardware accelerator architecture was deployed with 8-bit precision, a single-frame signal inference time of 41.9μs, a power consumption of 0.317W, and a data throughput of 78.6 GOP/s.

PMID:38335070 | DOI:10.1109/TBCAS.2024.3364235

Graefes Arch Clin Exp Ophthalmol. 2024 Feb 9. doi: 10.1007/s00417-024-06393-1. Online ahead of print.

ABSTRACT

PURPOSE: Tracking functional changes in visual fields (VFs) through standard automated perimetry remains a clinical standard for glaucoma diagnosis. This study aims to develop and evaluate a deep learning (DL) model to predict regional VF progression, which has not been explored in prior studies.

METHODS: The study included 2430 eyes of 1283 patients with four or more consecutive VF examinations from the baseline. A multi-label transformer-based network (MTN) using longitudinal VF data was developed to predict progression in six VF regions mapped to the optic disc. Progression was defined using the mean deviation (MD) slope and calculated for all six VF regions, referred to as clusters. Separate MTN models, trained for focal progression detection and forecasting on various numbers of VFs as model input, were tested on a held-out test set.

RESULTS: The MTNs overall demonstrated excellent macro-average AUCs above 0.884 in detecting focal VF progression given five or more VFs. With a minimum of 6 VFs, the model demonstrated superior and more stable overall and per-cluster performance, compared to 5 VFs. The MTN given 6 VFs achieved a macro-average AUC of 0.848 for forecasting progression across 8 VF tests. The MTN also achieved excellent performance (AUCs ≥ 0.86, 1.0 sensitivity, and specificity ≥ 0.70) in four out of six clusters for the eyes already with severe VF loss (baseline MD ≤ - 12 dB).

CONCLUSION: The high prediction accuracy suggested that multi-label DL networks trained with longitudinal VF results may assist in identifying and forecasting progression in VF regions.

PMID:38334809 | DOI:10.1007/s00417-024-06393-1

Soc Cogn Affect Neurosci. 2024 Feb 8:nsae014. doi: 10.1093/scan/nsae014. Online ahead of print.

ABSTRACT

This review offers an accessible primer to social neuroscientists interested in neural networks. It begins by providing an overview of key concepts in deep learning. It then discusses three ways neural networks can be useful to social neuroscientists: i) building statistical models to predict behavior from brain activity; ii) quantifying naturalistic stimuli and social interactions; and iii) generating cognitive models of social brain function. These applications have the potential to enhance the clinical value of neuroimaging and improve the generalizability of social neuroscience research. We also discuss the significant practical challenges, theoretical limitations, and ethical issues faced by deep learning. If the field can successfully navigate these hazards, we believe that artificial neural networks may prove indispensable for the next stage of the field's development: deep social neuroscience.

PMID:38334747 | DOI:10.1093/scan/nsae014

Environ Sci Technol. 2024 Feb 9. doi: 10.1021/acs.est.3c09207. Online ahead of print.

ABSTRACT

Residential building material stock constitutes a significant part of the built environment, providing crucial shelter and habitat services. The hypothesis concerning stock mass and composition has garnered considerable attention over the past decade. While previous research has mainly focused on the spatial analysis of building masses, it often neglected the component-level stock analysis or where heavy labor cost for onsite survey is required. This paper presents a novel approach for efficient component-level residential building stock accounting in the United Kingdom, utilizing drive-by street view images and building footprint data. We assessed four major construction materials: brick, stone, mortar, and glass. Compared to traditional approaches that utilize surveyed material intensity data, the developed method employs automatically extracted physical dimensions of building components incorporating predicted material types to calculate material mass. This not only improves efficiency but also enhances accuracy in managing the heterogeneity of building structures. The results revealed error rates of 5 and 22% for mortar and glass mass estimations and 8 and 7% for brick and stone mass estimations, with known wall types. These findings represent significant advancements in building material stock characterization and suggest that our approach has considerable potential for further research and practical applications. Especially, our method establishes a basis for evaluating the potential of component-level material reuse, serving the objectives of a circular economy.

PMID:38334723 | DOI:10.1021/acs.est.3c09207

Cells. 2024 Feb 1;13(3):275. doi: 10.3390/cells13030275.

ABSTRACT

Cigarette smoking during pregnancy is known to be associated with the incidence of attention-deficit/hyperactive disorder (ADHD). Recent developments in deep learning algorithms enable us to assess the behavioral phenotypes of animal models without cognitive bias during manual analysis. In this study, we established prenatal nicotine exposure (PNE) mice and evaluated their behavioral phenotypes using DeepLabCut and SimBA. We optimized the training parameters of DeepLabCut for pose estimation and succeeded in labeling a single-mouse or two-mouse model with high fidelity during free-moving behavior. We applied the trained network to analyze the behavior of the mice and found that PNE mice exhibited impulsivity and a lessened working memory, which are characteristics of ADHD. PNE mice also showed elevated anxiety and deficits in social interaction, reminiscent of autism spectrum disorder (ASD). We further examined PNE mice by evaluating adult neurogenesis in the hippocampus, which is a pathological hallmark of ASD, and demonstrated that newborn neurons were decreased, specifically in the ventral part of the hippocampus, which is reported to be related to emotional and social behaviors. These results support the hypothesis that PNE is a risk factor for comorbidity with ADHD and ASD in mice.

PMID:38334667 | DOI:10.3390/cells13030275

mSphere. 2024 Feb 9:e0059123. doi: 10.1128/msphere.00591-23. Online ahead of print.

ABSTRACT

Machine learning and artificial intelligence (AI) are becoming more common in infection biology laboratories around the world. Yet, as they gain traction in research, novel frontiers arise. Novel artificial intelligence algorithms are capable of addressing advanced tasks like image generation and question answering. However, similar algorithms can prove useful in addressing advanced questions in infection biology like prediction of host-pathogen interactions or inferring virus protein conformations. Addressing such tasks requires large annotated data sets, which are often scarce in biomedical research. In this review, I bring together several successful examples where such tasks were addressed. I underline the importance of formulating novel AI tasks in infection biology accompanied by freely available benchmark data sets to address these tasks. Furthermore, I discuss the current state of the field and potential future trends. I argue that one such trend involves AI tools becoming more versatile.

PMID:38334404 | DOI:10.1128/msphere.00591-23

Semin Ophthalmol. 2024 Feb 9:1-8. doi: 10.1080/08820538.2024.2308248. Online ahead of print.

ABSTRACT

BACKGROUND: Imaging plays a pivotal role in eye assessment. With the introduction of advanced machine learning and artificial intelligence (AI), the focus has shifted to imaging datasets in ophthalmology. While disparities and health inequalities hidden within data are well-documented, the ophthalmology field faces specific challenges to the creation and maintenance of datasets. Optical Coherence Tomography (OCT) is useful for the diagnosis and monitoring of retinal pathologies, making it valuable for AI applications. This review aims to identify and compare the landscape of publicly available optical coherence tomography databases for AI applications.

METHODS: We conducted a literature review on OCT and AI articles with publicly accessible datasets, using PubMed, Scopus, and Web of Science databases. The review retrieved 183 articles, and after full-text analysis, 50 articles were included. From the included articles were identified 8 publicly available OCT datasets, focusing on patient demographics and clinical details for thorough assessment and comparison.

RESULTS: The resulting datasets encompass 154,313 images collected from Spectralis, Cirrus HD, Topcon 3D, and Bioptigen devices. These datasets included normal exams, age-related macular degeneration, and diabetic maculopathy, among others. Comprehensive demographic information is available in one dataset and the USA is the most represented population.

DISCUSSION: Current publicly available OCT databases for AI applications exhibit limitations, stemming from their non-representative nature and the lack of comprehensive demographic information. Limited datasets hamper research and equitable AI development. To promote equitable AI algorithmic development in ophthalmology, there is a need for the creation and dissemination of more representative datasets.

PMID:38334303 | DOI:10.1080/08820538.2024.2308248

J Biomol Struct Dyn. 2024 Feb 9:1-26. doi: 10.1080/07391102.2024.2310785. Online ahead of print.

ABSTRACT

Recently, real-world disease monitoring techniques designed based on wearable medical equipment efficiently minimize the mortality rate. Initially, the data are manually collected from the patients to predict five diseases using 5 G frameworks. Then, the collected data are pre-processed to obtain high-quality data using the techniques like contrast enhancement, median filtering, fill empty space, remove repeated value and stemming. The pre-processed data are taken for extracting the features using a One-Dimensional Convolutional Neural Network (1D-CNN) to obtain the deep features. The parameters like hidden neuron count and epoch are tuned by the proposed Modified Predator Presence Probability-based Squirrel Search-Glowworm Swarm Optimization (MPPP-SSGSO) algorithm to enhance the variance. Then, the extracted features acquired using the 1D-CNN are given to the ensemble boosting-based models for predicting the score, which is combined by comprising approaches like Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost) and Category Boosting (CatBoost). Further, the predicted scores obtained from such models are concatenated and passed to the Ensemble Boosting Scores-based Fuzzy Classifier (EBS-FC) for classifying the five different diseases. Here, the membership function of the fuzzy is optimized by the same developed MPPP-SSGSO algorithm for enhancing accuracy. Experiments are conducted, and validation is performed, which showcased that the recommended framework achieved a better outcome rate than the conventional techniques. Finally, the suggested strategy outperforms the current state-of-the-art methods with an accuracy rate of 91.34%.Communicated by Ramaswamy H. Sarma.

PMID:38334127 | DOI:10.1080/07391102.2024.2310785

Bioanalysis. 2024 Feb 9. doi: 10.4155/bio-2023-0193. Online ahead of print.

ABSTRACT

Background: Blood-invasive fungal infections can cause the death of patients, while diagnosis of fungal infections is challenging. Methods: A high-speed microscopy detection system was constructed that included a microfluidic system, a microscope connected to a high-speed camera and a deep learning analysis section. Results: For training data, the sensitivity and specificity of the convolutional neural network model were 93.5% (92.7-94.2%) and 99.5% (99.1-99.5%), respectively. For validating data, the sensitivity and specificity were 81.3% (80.0-82.5%) and 99.4% (99.2-99.6%), respectively. Cryptococcal cells were found in 22.07% of blood samples. Conclusion: This high-speed microscopy system can analyze fungal pathogens in blood samples rapidly with high sensitivity and specificity and can help dramatically accelerate the diagnosis of fungal infectious diseases.

PMID:38334080 | DOI:10.4155/bio-2023-0193

Curr Med Imaging. 2024 Feb 7. doi: 10.2174/1573405620666230811142737. Online ahead of print.

ABSTRACT

BACKGROUND: Cancer is a major disease that threatens human life and health. Raman spectroscopy can provide an effective detection method.

OBJECTIVE: The study aimed to introduce the application of Raman spectroscopy to tumor detection. We have introduced the current mainstream Raman spectroscopy technology and related application research.

METHODS: This article has first introduced the grim situation of malignant tumors in the world. The advantages of tumor diagnosis based on Raman spectroscopy have also been analyzed. Secondly, various Raman spectroscopy techniques applied in the medical field are introduced. Several studies on the application of Raman spectroscopy to tumors in different parts of the human body are discussed. Then the advantages of combining deep learning with Raman spectroscopy in the diagnosis of tumors are discussed. Finally, the related problems of tumor diagnosis methods based on Raman spectroscopy are pointed out. This may provide useful clues for future work.

CONCLUSION: Raman spectroscopy can be an effective method for diagnosing tumors. Moreover, Raman spectroscopy diagnosis combined with deep learning can provide more convenient and accurate detection results.

PMID:38333978 | DOI:10.2174/1573405620666230811142737

Curr Med Imaging. 2024 Feb 7. doi: 10.2174/0115734056248183231010111937. Online ahead of print.

ABSTRACT

BACKGROUND: Diabetic Retinopathy (DR) is a growing problem in Asian countries. DR accounts for 5% to 7% of all blindness in the entire area. In India, the record of DR-affected patients will reach around 79.4 million by 2030.

AIMS: The main objective of the investigation is to utilize 2-D colored fundus retina scans to determine if an individual possesses DR or not. In this regard, Engineering-based techniques such as deep learning and neural networks play a methodical role in fighting against this fatal disease.

METHODS: In this research work, a Computational Model for detecting DR using Convolutional Neural Network (DRCNN) is proposed. This method contrasts the fundus retina scans of the DR-afflicted eye with the usual human eyes. Using CNN and layers like Conv2D, Pooling, Dense, Flatten, and Dropout, the model aids in comprehending the scan's curve and color-based features. For training and error reduction, the Visual Geometry Group (VGG-16) model and Adaptive Moment Estimation Optimizer are utilized.

RESULTS: The variations in a dataset like 50%, 60%, 70%, 80%, and 90% images are reserved for the training phase, and the rest images are reserved for the testing phase. In the proposed model, the VGG-16 model comprises 138M parameters. The accuracy is achieved maximum rate of 90% when the training dataset is reserved at 80%. The model was validated using other datasets.

CONCLUSION: The suggested contribution to research determines conclusively whether the provided OCT scan utilizes an effective method for detecting DRaffected individuals within just a few moments.

PMID:38333976 | DOI:10.2174/0115734056248183231010111937

Heliyon. 2024 Feb 1;10(3):e25374. doi: 10.1016/j.heliyon.2024.e25374. eCollection 2024 Feb 15.

ABSTRACT

The deep learning method (DLM) is one way to fix issues in optical nonorthogonal multiple access (O-NOMA) systems that are caused by signals that overlap and interfere with each other. NOMA increases the optical framework's spectrum efficiency, allowing several users to share the same time-frequency resources. However, NOMA-DLM-based detection's complicated interference patterns and variable channel conditions are challenging for conventional detection methods to manage. By utilizing deep neural networks' advantages, these methods are able to overcome these challenges and improve detection performance. An overview of the main features and advantages of DLM detection in massive multiple input and output (M-MIMO) O-NOMA systems is given in this article. It describes the essential elements, such as the training procedure and the network design. In order to process the sent symbols or decode data streams, DLM networks are built to process the incoming signal, power allocation coefficients, and extra information. Gradient descent optimization is used to update the network parameters iteratively while training the network, and a diverse and representative dataset is created. Additionally, the challenges of detecting deep learning in O-NOMA systems are examined. It recognizes that in order to get the best results, significant computational resources, a large amount of training data, and careful model design are required. It looks at and compares the 16 × 16, 32 × 32, and 64 × 64 M-MIMO-NOMA models in terms of bit error rate (BER), complexity, and power spectral density (PSD). The suggested DLM algorithms have been demonstrated to perform better than traditional methods by achieving an excellent BER of 10-3 at 4.1 dB and PSD (-2500) performance with low complexity.

PMID:38333851 | PMC:PMC10850584 | DOI:10.1016/j.heliyon.2024.e25374

Front Oncol. 2024 Jan 25;14:1332188. doi: 10.3389/fonc.2024.1332188. eCollection 2024.

ABSTRACT

OBJECTIVES: In patients with hepatocellular carcinoma (HCC), accurately predicting the preoperative microvascular invasion (MVI) status is crucial for improving survival rates. This study proposes a multi-modal domain-adaptive fusion model based on deep learning methods to predict the preoperative MVI status in HCC.

MATERIALS AND METHODS: From January 2008 to May 2022, we collected 163 cases of HCC from our institution and 42 cases from another medical facility, with each case including Computed Tomography (CT) images from the pre-contrast phase (PCP), arterial phase (AP), and portal venous phase (PVP). We divided our institution's dataset (n=163) into training (n=119) and test sets (n=44) in an approximate 7:3 ratio. Additionally, we included cases from another institution (n=42) as an external validation set (test1 set). We constructed three single-modality models, a simple concatenated multi-modal model, two current state-of-the-art image fusion model and a multi-modal domain-adaptive fusion model (M-DAFM) based on deep learning methods. We evaluated and analyzed the performance of these constructed models in predicting preoperative MVI using the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), and net reclassification improvement (NRI) methods.

RESULTS: In comparison with all models, M-DAFM achieved the highest AUC values across the three datasets (0.8013 for the training set, 0.7839 for the test set, and 0.7454 for the test1 set). Notably, in the test set, M-DAFM's Decision Curve Analysis (DCA) curves consistently demonstrated favorable or optimal net benefits within the 0-0.65 threshold probability range. Additionally, the Net Reclassification Improvement (NRI) values between M-DAFM and the three single-modal models, as well as the simple concatenation model, were all greater than 0 (all p < 0.05). Similarly, the NRI values between M-DAFM and the two current state-of-the-art image fusion models were also greater than 0. These findings collectively indicate that M-DAFM effectively integrates valuable information from multi-phase CT images, thereby enhancing the model's preoperative predictive performance for MVI.

CONCLUSION: The M-DAFM proposed in this study presents an innovative approach to improve the preoperative predictive performance of MVI.

PMID:38333689 | PMC:PMC10851167 | DOI:10.3389/fonc.2024.1332188

EClinicalMedicine. 2024 Feb 1;68:102445. doi: 10.1016/j.eclinm.2024.102445. eCollection 2024 Feb.

ABSTRACT

BACKGROUND: Diabetes is a major public health concern. We aimed to evaluate the long-term risk of incident type 2 diabetes in a non-diabetic population using a deep learning model (DLM) detecting prevalent type 2 diabetes using electrocardiogram (ECG).

METHODS: In this retrospective study, participants who underwent health checkups at two tertiary hospitals in Seoul, South Korea, between Jan 1, 2001 and Dec 31, 2022 were included. Type 2 diabetes was defined as glucose ≥126 mg/dL or glycated haemoglobin (HbA1c) ≥ 6.5%. For survival analysis on incident type 2 diabetes, we introduced an additional variable, diabetic ECG, which is determined by the DLM trained on ECG and corresponding prevalent diabetes. It was assumed that non-diabetic individuals with diabetic ECG had a higher risk of incident type 2 diabetes than those with non-diabetic ECG. The one-dimensional ResNet-based model was adopted for the DLM, and the Guided Grad-CAM was used to localise important regions of ECG. We divided the non-diabetic group into the diabetic ECG group (false positive) and the non-diabetic ECG (true negative) group according to the DLM decision, and performed a Cox proportional hazard model, considering the occurrence of type 2 diabetes more than six months after the visit.

FINDINGS: 190,581 individuals were included in the study with a median follow-up period of 11.84 years. The areas under the receiver operating characteristic curve for prevalent type 2 diabetes detection were 0.816 (0.807-0.825) and 0.762 (0.754-0.770) for the internal and external validations, respectively. The model primarily focused on the QRS duration and, occasionally, P or T waves. The diabetic ECG group exhibited an increased risk of incident type 2 diabetes compared with the non-diabetic ECG group, with hazard ratios of 2.15 (1.82-2.53) and 1.92 (1.74-2.11) for internal and external validation, respectively.

INTERPRETATION: In the non-diabetic group, those whose ECG was classified as diabetes by the DLM were at a higher risk of incident type 2 diabetes than those whose ECG was not. Additional clinical research on the relationship between the phenotype of ECG and diabetes to support the results and further investigation with tracked data and various ECG recording systems are suggested for future works.

FUNDING: National Research Foundation of Korea.

PMID:38333540 | PMC:PMC10850404 | DOI:10.1016/j.eclinm.2024.102445

Ann Med Surg (Lond). 2024 Jan 4;86(2):943-949. doi: 10.1097/MS9.0000000000001700. eCollection 2024 Feb.

ABSTRACT

Artificial intelligence (AI) refers to the simulation of human intelligence processes by machines, especially computer systems, providing assistance in a variety of patient care and health systems. The aim of this review is to contribute valuable insights to the ongoing discourse on the transformative potential of AI in healthcare, providing a nuanced understanding of its current applications, future possibilities, and associated challenges. The authors conducted a literature search on the current role of AI in disease diagnosis and its possible future applications using PubMed, Google Scholar, and ResearchGate within 10 years. Our investigation revealed that AI, encompassing machine-learning and deep-learning techniques, has become integral to healthcare, facilitating immediate access to evidence-based guidelines, the latest medical literature, and tools for generating differential diagnoses. However, our research also acknowledges the limitations of current AI methodologies in disease diagnosis and explores uncertainties and obstacles associated with the complete integration of AI into clinical practice. This review has highlighted the critical significance of integrating AI into the medical healthcare framework and meticulously examined the evolutionary trajectory of healthcare-oriented AI from its inception, delving into the current state of development and projecting the extent of reliance on AI in the future. The authors have found that central to this study is the exploration of how the strategic integration of AI can accelerate the diagnostic process, heighten diagnostic accuracy, and enhance overall operational efficiency, concurrently relieving the burdens faced by healthcare practitioners.

PMID:38333305 | PMC:PMC10849462 | DOI:10.1097/MS9.0000000000001700

Front Comput Neurosci. 2024 Jan 25;18:1358780. doi: 10.3389/fncom.2024.1358780. eCollection 2024.

ABSTRACT

The automatic classification of epilepsy electroencephalogram (EEG) signals plays a crucial role in diagnosing neurological diseases. Although promising results have been achieved by deep learning methods in this task, capturing the minute abnormal characteristics, contextual information, and long dependencies of EEG signals remains a challenge. To address this challenge, a positional multi-length and mutual-attention (PMM) network is proposed for the automatic classification of epilepsy EEG signals. The PMM network incorporates a positional feature encoding process that extracts minute abnormal characteristics from the EEG signal and utilizes a multi-length feature learning process with a hierarchy residual dilated LSTM (RDLSTM) to capture long contextual dependencies. Furthermore, a mutual-attention feature reinforcement process is employed to learn the global and relative feature dependencies and enhance the discriminative abilities of the network. To validate the effectiveness PMM network, we conduct extensive experiments on the public dataset and the experimental results demonstrate the superior performance of the PMM network compared to state-of-the-art methods.

PMID:38333103 | PMC:PMC10850335 | DOI:10.3389/fncom.2024.1358780

Front Physiol. 2024 Jan 25;15:1337554. doi: 10.3389/fphys.2024.1337554. eCollection 2024.

ABSTRACT

Background and object: Mitotic count (MC) is a critical histological parameter for accurately assessing the degree of invasiveness in breast cancer, holding significant clinical value for cancer treatment and prognosis. However, accurately identifying mitotic cells poses a challenge due to their morphological and size diversity. Objective: We propose a novel end-to-end deep-learning method for identifying mitotic cells in breast cancer pathological images, with the aim of enhancing the performance of recognizing mitotic cells. Methods: We introduced the Dilated Cascading Network (DilCasNet) composed of detection and classification stages. To enhance the model's ability to capture distant feature dependencies in mitotic cells, we devised a novel Dilated Contextual Attention Module (DiCoA) that utilizes sparse global attention during the detection. For reclassifying mitotic cell areas localized in the detection stage, we integrate the EfficientNet-B7 and VGG16 pre-trained models (InPreMo) in the classification step. Results: Based on the canine mammary carcinoma (CMC) mitosis dataset, DilCasNet demonstrates superior overall performance compared to the benchmark model. The specific metrics of the model's performance are as follows: F1 score of 82.9%, Precision of 82.6%, and Recall of 83.2%. With the incorporation of the DiCoA attention module, the model exhibited an improvement of over 3.5% in the F1 during the detection stage. Conclusion: The DilCasNet achieved a favorable detection performance of mitotic cells in breast cancer and provides a solution for detecting mitotic cells in pathological images of other cancers.

PMID:38332988 | PMC:PMC10850563 | DOI:10.3389/fphys.2024.1337554

IEEE Int Conf Healthc Inform. 2023 Jun;2023:128-137. doi: 10.1109/ichi57859.2023.00027. Epub 2023 Dec 11.

ABSTRACT

The utilization of web search activity for pandemic forecasting has significant implications for managing disease spread and informing policy decisions. However, web search records tend to be noisy and influenced by geographical location, making it difficult to develop large-scale models. While regularized linear models have been effective in predicting the spread of respiratory illnesses like COVID-19, they are limited to specific locations. The lack of incorporation of neighboring areas' data and the inability to transfer models to new locations with limited data has impeded further progress. To address these limitations, this study proposes a novel self-supervised message-passing neural network (SMPNN) framework for modeling local and cross-location dynamics in pandemic forecasting. The SMPNN framework utilizes an MPNN module to learn cross-location dependencies through self-supervised learning and improve local predictions with graph-generated features. The framework is designed as an end-to-end solution and is compared with state-of-the-art statistical and deep learning models using COVID-19 data from England and the US. The results of the study demonstrate that the SMPNN model outperforms other models by achieving up to a 6.9% improvement in prediction accuracy and lower prediction errors during the early stages of disease outbreaks. This approach represents a significant advancement in disease surveillance and forecasting, providing a novel methodology, datasets, and insights that combine web search data and spatial information. The proposed SMPNN framework offers a promising avenue for modeling the spread of pandemics, leveraging both local and cross-location information, and has the potential to inform public health policy decisions.

PMID:38332952 | PMC:PMC10853009 | DOI:10.1109/ichi57859.2023.00027

Front Neurosci. 2024 Jan 25;18:1326108. doi: 10.3389/fnins.2024.1326108. eCollection 2024.

ABSTRACT

INTRODUCTION: Multiple sclerosis (MS) is a chronic neurological disorder characterized by the progressive loss of myelin and axonal structures in the central nervous system. Accurate detection and monitoring of MS-related changes in brain structures are crucial for disease management and treatment evaluation. We propose a deep learning algorithm for creating Voxel-Guided Morphometry (VGM) maps from longitudinal MRI brain volumes for analyzing MS disease activity. Our approach focuses on developing a generalizable model that can effectively be applied to unseen datasets.

METHODS: Longitudinal MS patient high-resolution 3D T1-weighted follow-up imaging from three different MRI systems were analyzed. We employed a 3D residual U-Net architecture with attention mechanisms. The U-Net serves as the backbone, enabling spatial feature extraction from MRI volumes. Attention mechanisms are integrated to enhance the model's ability to capture relevant information and highlight salient regions. Furthermore, we incorporate image normalization by histogram matching and resampling techniques to improve the networks' ability to generalize to unseen datasets from different MRI systems across imaging centers. This ensures robust performance across diverse data sources.

RESULTS: Numerous experiments were conducted using a dataset of 71 longitudinal MRI brain volumes of MS patients. Our approach demonstrated a significant improvement of 4.3% in mean absolute error (MAE) against the state-of-the-art (SOTA) method. Furthermore, the algorithm's generalizability was evaluated on two unseen datasets (n = 116) with an average improvement of 4.2% in MAE over the SOTA approach.

DISCUSSION: Results confirm that the proposed approach is fast and robust and has the potential for broader clinical applicability.

PMID:38332857 | PMC:PMC10850259 | DOI:10.3389/fnins.2024.1326108