IEEE Trans Neural Syst Rehabil Eng. 2024 Aug 16;PP. doi: 10.1109/TNSRE.2024.3444890. Online ahead of print.

ABSTRACT

Sarcopenia is a comprehensive degenerative disease with the progressive loss of skeletal muscle mass with age, accompanied by the loss of muscle strength and muscle dysfunction. Individuals with unmanaged sarcopenia may experience adverse outcomes. Periodically monitoring muscle function to detect muscle degeneration caused by sarcopenia and treating degenerated muscles is essential. We proposed a digital biomarker measurement technique using surface electromyography (sEMG) with electrical stimulation and wearable device to conveniently monitor muscle function at home. When motor neurons and muscle fibers are electrically stimulated, stimulated muscle contraction signals (SMCSs) can be obtained using an sEMG sensor. As motor neuron activation is important for muscle contraction and strength, their action potentials for electrical stimulation represent the muscle function. Thus, the SMCSs are closely related to muscle function, presumptively. Using the SMCSs data, a feature vector concatenating spectrogram-based features and deep learning features extracted from a convolutional neural network model using continuous wavelet transform images was used as the input to train a regression model for measuring the digital biomarker. To verify muscle function measurement technique, we recruited 98 healthy participants aged 20-60 years including 48 [49%] men who volunteered for this study. The Pearson correlation coefficient between the label and model estimates was 0.89, suggesting that the proposed model can robustly estimate the label using SMCSs, with mean error and standard deviation of -0.06 and 0.68, respectively. In conclusion, measuring muscle function using the proposed system that involves SMCSs is feasible.

PMID:39150814 | DOI:10.1109/TNSRE.2024.3444890

IEEE J Biomed Health Inform. 2024 Aug 16;PP. doi: 10.1109/JBHI.2024.3445112. Online ahead of print.

ABSTRACT

Accurate fovea localization is essential for analyzing retinal diseases to prevent irreversible vision loss. While current deep learning-based methods outperform traditional ones, they still face challenges such as the lack of local anatomical landmarks around the fovea, the inability to robustly handle diseased retinal images, and the variations in image conditions. In this paper, we propose a novel transformer-based architecture called DualStreamFoveaNet (DSFN) for multi-cue fusion. This architecture explicitly incorporates long-range connections and global features using retina and vessel distributions for robust fovea localization. We introduce a spatial attention mechanism in the dual-stream encoder to extract and fuse self-learned anatomical information, focusing more on features distributed along blood vessels and significantly reducing computational costs by decreasing token numbers. Our extensive experiments show that the proposed architecture achieves state-of-the-art performance on two public datasets and one large-scale private dataset. Furthermore, we demonstrate that the DSFN is more robust on both normal and diseased retina images and has better generalization capacity in cross-dataset experiments.

PMID:39150813 | DOI:10.1109/JBHI.2024.3445112

IEEE J Biomed Health Inform. 2024 Aug 16;PP. doi: 10.1109/JBHI.2024.3444771. Online ahead of print.

ABSTRACT

Motion artifacts compromise the quality of magnetic resonance imaging (MRI) and pose challenges to achieving diagnostic outcomes and image-guided therapies. In recent years, supervised deep learning approaches have emerged as successful solutions for motion artifact reduction (MAR). One disadvantage of these methods is their dependency on acquiring paired sets of motion artifact-corrupted (MA-corrupted) and motion artifact-free (MA-free) MR images for training purposes. Obtaining such image pairs is difficult and therefore limits the application of supervised training. In this paper, we propose a novel UNsupervised Abnormality Extraction Network (UNAEN) to alleviate this problem. Our network is capable of working with unpaired MA-corrupted and MA-free images. It converts the MA-corrupted images to MA-reduced images by extracting abnormalities from the MA-corrupted images using a proposed artifact extractor, which intercepts the residual artifact maps from the MA-corrupted MR images explicitly, and a reconstructor to restore the original input from the MA-reduced images. The performance of UNAEN was assessed by experimenting with various publicly available MRI datasets and comparing them with state-of-the-art methods. The quantitative evaluation demonstrates the superiority of UNAEN over alternative MAR methods and visually exhibits fewer residual artifacts. Our results substantiate the potential of UNAEN as a promising solution applicable in real-world clinical environments, with the capability to enhance diagnostic accuracy and facilitate image-guided therapies. Our codes are publicly available at https://github.com/YuSheng-Zhou/UNAEN.

PMID:39150812 | DOI:10.1109/JBHI.2024.3444771

IEEE J Biomed Health Inform. 2024 Aug 16;PP. doi: 10.1109/JBHI.2024.3444908. Online ahead of print.

ABSTRACT

Multi-modality image registration is an important task in medical imaging because it allows for information from different domains to be correlated. Histopathology plays a crucial role in oncologic surgery as it is the gold standard for investigating tissue composition from surgically excised specimens. Research studies are increasingly focused on registering medical imaging modalities such as white light cameras, magnetic resonance imaging, computed tomography, and ultrasound to pathology images. The main challenge in registration tasks involving pathology images comes from addressing the considerable amount of deformation present. This work provides a framework for deep learning-based multi-modality registration of microscopic pathology images to another imaging modality. The proposed framework is validated on the registration of prostate ex-vivo white light camera snapshot images to pathology hematoxylin-eosin images of the same specimen. A pipeline is presented detailing data acquisition, protocol considerations, image dissimilarity, training experiments, and validation. A comprehensive analysis is done on the impact of pre-processing, data augmentation, loss functions, and regularization. This analysis is supplemented by clinically motivated evaluation metrics to avoid the pitfalls of only using ubiquitous image comparison metrics. Consequently, a robust training configuration capable of performing the desired registration task is found. Utilizing the proposed approach, we achieved a dice similarity coefficient of 0.96, a mutual information score of 0.54, a target registration error of 2.4 mm, and a regional dice similarity coefficient of 0.70.

PMID:39150810 | DOI:10.1109/JBHI.2024.3444908

IEEE Trans Pattern Anal Mach Intell. 2024 Aug 16;PP. doi: 10.1109/TPAMI.2024.3443922. Online ahead of print.

ABSTRACT

Directly regressing the non-rigid shape and camera pose from the individual 2D frame is ill-suited to the Non-Rigid Structure-from-Motion (NRSfM) problem. This frame-by-frame 3D reconstruction pipeline overlooks the inherent spatial-temporal nature of NRSfM, i.e., reconstructing the 3D sequence from the input 2D sequence. In this paper, we propose to solve deep sparse NRSfM from a sequence-to-sequence translation perspective, where the input 2D keypoints sequence is taken as a whole to reconstruct the corresponding 3D keypoints sequence in a self-supervised manner. First, we apply a shape-motion predictor on the input sequence to obtain an initial sequence of shapes and corresponding motions. Then, we propose the Context Layer, which enables the deep learning framework to effectively impose overall constraints on sequences based on the structural characteristics of non-rigid sequences. The Context Layer constructs modules for imposing the self-expressiveness regularity on non-rigid sequences with multi-head attention (MHA) as the core, together with the use of temporal encoding, both of which act simultaneously to constitute constraints on non-rigid sequences in the deep framework. Experimental results across different datasets such as Human3.6M, CMU Mocap, and InterHand prove the superiority of our framework. The code will be made publicly available.

PMID:39150802 | DOI:10.1109/TPAMI.2024.3443922

IEEE Trans Neural Netw Learn Syst. 2024 Aug 16;PP. doi: 10.1109/TNNLS.2024.3426529. Online ahead of print.

ABSTRACT

Dichotomous image segmentation (DIS) with rich fine-grained details within a single image is a challenging task. Despite the plausible results achieved by deep learning-based methods, most of them fail to segment generic objects when the boundary is cluttered with the background. In fact, the gradual decrease in feature map resolution during the encoding stage and the misleading texture clue may be the main issues. To handle these issues, we devise a novel frequency-and scale-aware deep neural network (FSANet) for high-precision DIS. The core of our proposed FSANet is twofold. First, a multimodality fusion (MF) module that integrates the information in spatial and frequency domains is adopted to enhance the representation capability of image features. Second, a collaborative scale fusion module (CSFM) which deviates from the traditional serial structures is introduced to maintain high resolution during the entire feature encoding stage. In the decoder side, we introduce hierarchical context fusion (HCF) and selective feature fusion (SFF) modules to infer the segmentation results from the output features of the CSFM module. We conduct extensive experiments on several benchmark datasets and compare our proposed method with existing state-of-the-art (SOTA) methods. The experimental results demonstrate that our FSANet achieves superior performance both qualitatively and quantitatively. The code will be made available at https://github.com/chasecjg/FSANet.

PMID:39150797 | DOI:10.1109/TNNLS.2024.3426529

Ophthalmol Ther. 2024 Aug 16. doi: 10.1007/s40123-024-01012-y. Online ahead of print.

ABSTRACT

INTRODUCTION: Advanced age-related macular degeneration (AMD) is a major cause of vision loss. Therefore, there is interest in precursor lesions that may predict or prevent the onset of advanced AMD. One such lesion is a shallow separation of the retinal pigment epithelium (RPE) and Bruch's membrane (BM), which is described by various terms, including double-layer sign (DLS).

METHODS: In this article, we aim to examine and clarify the different terms referring to shallow separation of the RPE and BM. We also review current evidence on the outcomes associated with DLS: firstly, whether DLS is predictive of exudative neovascular AMD; and secondly, whether DLS has potential protective properties against geographic atrophy.

RESULTS: The range of terms used to describe a shallow separation of the RPE and BM reflects that DLS can present with different characteristics. While vascularised DLS appears to protect against atrophy but can progress to exudation, non-vascularised DLS is associated with an increased risk of atrophy. Optical coherence tomography (OCT) angiography (OCTA) is the principal method for identifying and differentiating various forms of DLS. If OCTA is unavailable or not practically possible, simplified classification of DLS as thick or thin, using OCT, enables the likelihood of vascularisation to be approximated. Research is ongoing to automate DLS detection by applying deep-learning algorithms to OCT scans.

CONCLUSIONS: The term DLS remains applicable for describing shallow separation of the RPE and BM. Detection and classification of this feature provides valuable information regarding the risk of progression to advanced AMD. However, the appearance of DLS and its value in predicting AMD progression can vary between patients. With further research, individualised risks can be confirmed to inform appropriate treatment.

PMID:39150604 | DOI:10.1007/s40123-024-01012-y

J Imaging Inform Med. 2024 Aug 16. doi: 10.1007/s10278-024-01107-9. Online ahead of print.

ABSTRACT

Primary diffuse central nervous system large B-cell lymphoma (CNS-pDLBCL) and high-grade glioma (HGG) often present similarly, clinically and on imaging, making differentiation challenging. This similarity can complicate pathologists' diagnostic efforts, yet accurately distinguishing between these conditions is crucial for guiding treatment decisions. This study leverages a deep learning model to classify brain tumor pathology images, addressing the common issue of limited medical imaging data. Instead of training a convolutional neural network (CNN) from scratch, we employ a pre-trained network for extracting deep features, which are then used by a support vector machine (SVM) for classification. Our evaluation shows that the Resnet50 (TL + SVM) model achieves a 97.4% accuracy, based on tenfold cross-validation on the test set. These results highlight the synergy between deep learning and traditional diagnostics, potentially setting a new standard for accuracy and efficiency in the pathological diagnosis of brain tumors.

PMID:39150595 | DOI:10.1007/s10278-024-01107-9

Eur Radiol. 2024 Aug 16. doi: 10.1007/s00330-024-11019-5. Online ahead of print.

ABSTRACT

OBJECTIVES: Holistic segmentation of CT structural alterations with 3D deep learning has recently been described in cystic fibrosis (CF), allowing the measurement of normalized volumes of airway abnormalities (NOVAA-CT) as an automated quantitative outcome. Clinical validations are needed, including longitudinal and multicenter evaluations.

MATERIALS AND METHODS: The validation study was retrospective between 2010 and 2023. CF patients undergoing Elexacaftor/Tezacaftor/Ivacaftor (ETI) or corticosteroids for allergic broncho-pulmonary aspergillosis (ABPA) composed the monocenter ETI and ABPA groups, respectively. Patients from six geographically distinct institutions composed a multicenter external group. All patients had completed CT and pulmonary function test (PFT), with a second assessment at 1 year in case of ETI or ABPA treatment. NOVAA-CT quantified bronchiectasis, peribronchial thickening, bronchial mucus, bronchiolar mucus, collapse/consolidation, and their overall total abnormal volume (TAV). Two observers evaluated the visual Bhalla score.

RESULTS: A total of 139 CF patients (median age, 15 years [interquartile range: 13-25]) were evaluated. All correlations between NOVAA-CT to both PFT and Bhalla score were significant in the ETI (n = 60), ABPA (n = 20), and External groups (n = 59), such as the normalized TAV (ρ ≥ 0.76; p < 0.001). In both ETI and ABPA groups, there were significant longitudinal improvements in peribronchial thickening, bronchial mucus, bronchiolar mucus and collapse/consolidation (p ≤ 0.001). An additional reversibility in bronchiectasis volume was quantified with ETI (p < 0.001). Intraclass correlation coefficient of reproducibility was > 0.99.

CONCLUSION: NOVAA-CT automated scoring demonstrates validity, reliability and responsiveness for monitoring CF severity over an entire lung and quantifies therapeutic effects on lung structure at CT, such as the volumetric reversibility of airway abnormalities with ETI.

CLINICAL RELEVANCE STATEMENT: Normalized volume of airway abnormalities at CT automated 3D outcome enables objective, reproducible, and holistic monitoring of cystic fibrosis severity over an entire lung for management and endpoints during therapeutic trials.

KEY POINTS: Visual scoring methods lack sensitivity and reproducibility to assess longitudinal bronchial changes in cystic fibrosis (CF). AI-driven volumetric CT scoring correlates longitudinally to disease severity and reliably improves with Elexacaftor/Tezacaftor/Ivacaftor or corticosteroid treatments. AI-driven volumetric CT scoring enables reproducible monitoring of lung disease severity in CF and quantifies longitudinal structural therapeutic effects.

PMID:39150489 | DOI:10.1007/s00330-024-11019-5

J Phys Ther Educ. 2024 Sep 1;38(3):231-238. doi: 10.1097/JTE.0000000000000335. Epub 2024 Mar 7.

ABSTRACT

INTRODUCTION: The definition of excellence in physical therapy (PT) education is evolving, yet the role of postprofessional residency education remains uncertain. Arguments in favor of required residency have emerged through the re-visioning of PT education across the continuum. Yet, little evidence exists whether residency education further develops clinical skills, clinical knowledge, and clinical reasoning abilities.

REVIEW OF LITERATURE: Previous studies have explored the development of the novice physical therapist in the first 2 years of practice; however, there is little evidence about the outcomes of PT residency education. Thus, this study looked to explore the development of learners through their residency education and to identify the critical elements of the teaching and learning environment in residency education.

SUBJECTS: Eleven PT residency programs and 13 residents participated in a qualitative study to explore the learner development through residency. Each residency program consisted of a residency program director, one or more mentors identified by the residency program director, and at least one physical therapist resident. Semistructured interviews were conducted with program participants, and journal entries were collected from residents.

METHODS: Using a purposeful sample of convenience, an exploratory, multiple-site/specialty area qualitative case study design was conducted.

RESULTS: Three emerging themes were identified including growth of self, becoming a member of the community of practice, and facilitation of learning through mentoring. Through the transformative journey of residency education, there are critical elements of the learning environment supporting deep learning within the community of practice. These elements include the provision of opportunities and adequate time and space for learning to occur.

DISCUSSION AND CONCLUSION: The intentional design of the community of practice through residency education facilitates the development of the novice clinician to experienced clinician in an accelerated period of time. In addition, residency graduates develop characteristics similar to adaptive learners through planned teaching and learning opportunities. Finally, the structure of residency education mattered to the resident participants such that the learning environment enhanced peer learning and the development of professional relationships.

PMID:39150258 | DOI:10.1097/JTE.0000000000000335

Curr Med Imaging. 2024 Aug 15. doi: 10.2174/0115734056291283240808045952. Online ahead of print.

ABSTRACT

BACKGROUND: Chest X-ray image classification for multiple diseases is an important research direction in the field of computer vision and medical image processing. It aims to utilize advanced image processing techniques and deep learning algorithms to automatically analyze and identify X-ray images, determining whether specific pathologies or structural abnormalities exist in the images.

OBJECTIVE: We present the MMPDenseNet network designed specifically for chest multi-label disease classification.

METHODS: Initially, the network employs the adaptive activation function Meta-ACON to enhance feature representation. Subsequently, the network incorporates a multi-head self-attention mechanism, merging the conventional convolutional neural network with the Transformer, thereby bolstering the ability to extract both local and global features. Ultimately, the network integrates a pyramid squeeze attention module to capture spatial information and enrich the feature space.

RESULTS: The concluding experiment yielded an average AUC of 0.898, marking an average accuracy improvement of 0.6% over the baseline model. When compared with the original network, the experimental results highlight that MMPDenseNet considerably elevates the classification accuracy of various chest diseases.

CONCLUSION: It can be concluded that the network, thus, holds substantial value for clinical applications.

PMID:39150027 | DOI:10.2174/0115734056291283240808045952

Saudi J Anaesth. 2024 Jul-Sep;18(3):410-416. doi: 10.4103/sja.sja_110_24. Epub 2024 Jun 4.

ABSTRACT

Artificial intelligence is an ever-growing modality revolutionizing the field of medical science. It utilizes various computational models and algorithms and helps out in different sectors of healthcare. Here, in this scoping review, we are trying to evaluate the use of Artificial intelligence (AI) in the field of pediatric anesthesia, specifically in the more challenging domain, the pediatric airway. Different components within the domain of AI include machine learning, neural networks, deep learning, robotics, and computer vision. Electronic databases like Google Scholar, Cochrane databases, and Pubmed were searched. Different studies had heterogeneity of age groups, so all studies with children under 18 years of age were included and assessed. The use of AI was reviewed in the preoperative, intraoperative, and postoperative domains of pediatric anesthesia. The applicability of AI needs to be supplemented by clinical judgment for the final anticipation in various fields of medicine.

PMID:39149736 | PMC:PMC11323903 | DOI:10.4103/sja.sja_110_24

Data Brief. 2024 Jul 14;55:110753. doi: 10.1016/j.dib.2024.110753. eCollection 2024 Aug.

ABSTRACT

Today, speech synthesis is a part of our daily lives in computers all around the world. Central Kurdish Speech Corpus Construction is a speech corpus that is a primary data source for developing a speech system. There are still two main issues that prevent them from achieving the best possible performance, the lack of efficiency in training and analysis, and the difficulty in modelling. The biggest obstacle against text-to-speech in the Kurdish language is that there is a lack of text and speech recognition tools compounded by the fact that around 30 million people speak the Kurdish language in different countries. To address this issue, this corpus introduced a large vocabulary of Kurdish Text-to-Speech Dataset (KTTS, Gigant), including a pronunciation lexicon and speech corpus for the Central Kurdish dialect. A variety of subjects is comprised to record these sentences. The sentences are recorded in a voice recording studio by a Kurdish man who is a dubber. The goal of the speech corpus is to create a collection of sentences that accurately reflect the real data about the Central Kurdish dialect. A combination of audio and visual sources is used to record the 6,078 sentences of 12 document topics. They were recorded in a controlled environment using microphones that were not noisy. The total record duration is 13.63 h. The recorded sentences are in the ".wav" format.

PMID:39149720 | PMC:PMC11324836 | DOI:10.1016/j.dib.2024.110753

Front Med (Lausanne). 2024 Jul 24;11:1405848. doi: 10.3389/fmed.2024.1405848. eCollection 2024.

ABSTRACT

Epilepsy is one of the most frequent neurological illnesses caused by epileptic seizures and the second most prevalent neurological ailment after stroke, affecting millions of people worldwide. People with epileptic disease are considered a category of people with disabilities. It significantly impairs a person's capacity to perform daily tasks, especially those requiring focusing or remembering. Electroencephalogram (EEG) signals are commonly used to diagnose people with epilepsy. However, it is tedious, time-consuming, and subjected to human errors. Several machine learning techniques have been applied to recognize epilepsy previously, but they have some limitations. This study proposes a deep neural network (DNN) machine learning model to determine the existing limitations of previous studies by improving the recognition efficiency of epileptic disease. A public dataset is used in this study and classified into training and testing sets. Experiments were performed to evaluate the DNN model with different dataset classification ratios (80:20), (70:30), (60:40), and (50:50) for training and testing, respectively. Results were evaluated by using different performance metrics including validations, and comparison processes that allow the assessment of the model's effectiveness. The experimental results showed that the overall efficiency of the proposed model is the highest compared with previous works, with an accuracy rate of 97%. Thus, this study is more accurate and efficient than the existing seizure detection approaches. DNN model has great potential for recognizing epileptic patient activity using a numerical EEG dataset offering a data-driven approach to improve the accuracy and reliability of seizure detection systems for the betterment of patient care and management of epilepsy.

PMID:39149605 | PMC:PMC11326242 | DOI:10.3389/fmed.2024.1405848

Res Sq [Preprint]. 2024 Aug 9:rs.3.rs-4744915. doi: 10.21203/rs.3.rs-4744915/v1.

ABSTRACT

BACKGROUND: Cannabis sativa with a rich history of traditional medicinal use, has garnered significant attention in contemporary research for its potential therapeutic applications in various human diseases, including pain, inflammation, cancer, and osteoarthritis. However, the specific molecular targets and mechanisms underlying the synergistic effects of its diverse phytochemical constituents remain elusive. Understanding these mechanisms is crucial for developing targeted, effective cannabis-based therapies.

METHODS: To investigate the molecular targets and pathways involved in the synergistic effects of cannabis compounds, we utilized DRIFT, a deep learning model that leverages attention-based neural networks to predict compound-target interactions. We considered both whole plant extracts and specific plant-based formulations. Predicted targets were then mapped to the Reactome pathway database to identify the biological processes affected. To facilitate the prediction of molecular targets and associated pathways for any user-specified cannabis formulation, we developed CANDI (Cannabis-derived compound Analysis and Network Discovery Interface), a web-based server. This platform offers a user-friendly interface for researchers and drug developers to explore the therapeutic potential of cannabis compounds.

RESULTS: Our analysis using DRIFT and CANDI successfully identified numerous molecular targets of cannabis compounds, many of which are involved in pathways relevant to pain, inflammation, cancer, and other diseases. The CANDI server enables researchers to predict the molecular targets and affected pathways for any specific cannabis formulation, providing valuable insights for developing targeted therapies.

CONCLUSIONS: By combining computational approaches with knowledge of traditional cannabis use, we have developed the CANDI server, a tool that allows us to harness the therapeutic potential of cannabis compounds for the effective treatment of various disorders. By bridging traditional pharmaceutical development with cannabis-based medicine, we propose a novel approach for botanical-based treatment modalities.

PMID:39149470 | PMC:PMC11326374 | DOI:10.21203/rs.3.rs-4744915/v1

bioRxiv [Preprint]. 2024 Aug 8:2024.08.06.606717. doi: 10.1101/2024.08.06.606717.

ABSTRACT

Many realistic phylogenetic models lack tractable likelihood functions, prohibiting their use with standard inference methods. We present phyddle, a pipeline-based toolkit for performing phylogenetic modeling tasks using likelihood-free deep learning approaches. phyddle coordinates modeling tasks through five analysis steps ( Simulate, Format, Train, Estimate , and Plot ) that transform raw phylogenetic datasets as input into numerical and visualized model-based output. Benchmarks show that phyddle accurately performs a range of inference tasks, such as estimating macroevolutionary parameters, selecting among continuous trait evolution models, and passing coverage tests for epidemiological models, even for models that lack tractable likelihoods. phyddle has a flexible command-line interface, making it easy to integrate deep learning approaches for phylogenetics into research workflows. Learn more about phyddle at https://phyddle.org .

PMID:39149349 | PMC:PMC11326143 | DOI:10.1101/2024.08.06.606717

bioRxiv [Preprint]. 2024 Aug 7:2024.08.05.606654. doi: 10.1101/2024.08.05.606654.

ABSTRACT

Digital pathology is a rapidly advancing field where deep learning methods can be employed to extract meaningful imaging features. However, the efficacy of training deep learning models is often hindered by the scarcity of annotated pathology images, particularly images with detailed annotations for small image patches or tiles. To overcome this challenge, we propose an innovative approach that leverages paired spatially resolved transcriptomic data to annotate pathology images. We demonstrate the feasibility of this approach and introduce a novel transfer-learning neural network model, STpath (Spatial Transcriptomics and pathology images), designed to predict cell type proportions or classify tumor microenvironments. Our findings reveal that the features from pre-trained deep learning models are associated with cell type identities in pathology image patches. Evaluating STpath using three distinct breast cancer datasets, we observe its promising performance despite the limited training data. STpath excels in samples with variable cell type proportions and high-resolution pathology images. As the influx of spatially resolved transcriptomic data continues, we anticipate ongoing updates to STpath, evolving it into an invaluable AI tool for assisting pathologists in various diagnostic tasks.

PMID:39149252 | PMC:PMC11326158 | DOI:10.1101/2024.08.05.606654

Front Artif Intell. 2024 Aug 1;7:1429602. doi: 10.3389/frai.2024.1429602. eCollection 2024.

ABSTRACT

Maintaining consistent and accurate temperature is critical for the safe and effective storage of vaccines. Traditional monitoring methods often lack real-time capabilities and may not be sensitive enough to detect subtle anomalies. This paper presents a novel deep learning-based system for real-time temperature fault detection in refrigeration systems used for vaccine storage. Our system utilizes a semi-supervised Convolutional Autoencoder (CAE) model deployed on a resource-constrained ESP32 microcontroller. The CAE is trained on real-world temperature sensor data to capture temporal patterns and reconstruct normal temperature profiles. Deviations from the reconstructed profiles are flagged as potential anomalies, enabling real-time fault detection. Evaluation using real-time data demonstrates an impressive 92% accuracy in identifying temperature faults. The system's low energy consumption (0.05 watts) and memory usage (1.2 MB) make it suitable for deployment in resource-constrained environments. This work paves the way for improved monitoring and fault detection in refrigeration systems, ultimately contributing to the reliable storage of life-saving vaccines.

PMID:39149162 | PMC:PMC11324578 | DOI:10.3389/frai.2024.1429602

Front Artif Intell. 2024 Aug 1;7:1369702. doi: 10.3389/frai.2024.1369702. eCollection 2024.

ABSTRACT

PURPOSE: Computed Tomography Angiography (CTA) is the first line of imaging in the diagnosis of Large Vessel Occlusion (LVO) strokes. We trained and independently validated end-to-end automated deep learning pipelines to predict 3-month outcomes after anterior circulation LVO thrombectomy based on admission CTAs.

METHODS: We split a dataset of 591 patients into training/cross-validation (n = 496) and independent test set (n = 95). We trained separate models for outcome prediction based on admission "CTA" images alone, "CTA + Treatment" (including time to thrombectomy and reperfusion success information), and "CTA + Treatment + Clinical" (including admission age, sex, and NIH stroke scale). A binary (favorable) outcome was defined based on a 3-month modified Rankin Scale ≤ 2. The model was trained on our dataset based on the pre-trained ResNet-50 3D Convolutional Neural Network ("MedicalNet") and included CTA preprocessing steps.

RESULTS: We generated an ensemble model from the 5-fold cross-validation, and tested it in the independent test cohort, with receiver operating characteristic area under the curve (AUC, 95% confidence interval) of 70 (0.59-0.81) for "CTA," 0.79 (0.70-0.89) for "CTA + Treatment," and 0.86 (0.79-0.94) for "CTA + Treatment + Clinical" input models. A "Treatment + Clinical" logistic regression model achieved an AUC of 0.86 (0.79-0.93).

CONCLUSION: Our results show the feasibility of an end-to-end automated model to predict outcomes from admission and post-thrombectomy reperfusion success. Such a model can facilitate prognostication in telehealth transfer and when a thorough neurological exam is not feasible due to language barrier or pre-existing morbidities.

PMID:39149161 | PMC:PMC11324606 | DOI:10.3389/frai.2024.1369702

Heliyon. 2024 Jul 17;10(14):e34782. doi: 10.1016/j.heliyon.2024.e34782. eCollection 2024 Jul 30.

ABSTRACT

To address the issue of detecting complex-shaped cracks that rely on manual, which may result in high costs and low efficiency, this paper proposed a lightweight ground crack rapid detection method based on semantic enhancement. Firstly, the introduction of the Context Guided Block module enhanced the YOLOv8 backbone network, improving its feature extraction capability. Next, the incorporation of GSConv and VoV-GSCSP was introduced to construct a lightweight yet efficient neck network, facilitating the effective fusion of information from multiple feature maps. Finally, the detection head achieved more precise target localization by optimizing the probability around the labels. The proposed method was validated through experiments on the public dataset RDD-2022. The experimental results demonstrate that our method effectively detects cracks. Compared to YOLOv8, the model parameters have been reduced by 73.5 %, while accuracy, F1 score, and FPS have improved by 6.6 %, 4.3 %, and 116, respectively. Therefore, our proposed method is more lightweight and holds significant application value.

PMID:39149085 | PMC:PMC11325053 | DOI:10.1016/j.heliyon.2024.e34782