IEEE Trans Pattern Anal Mach Intell. 2024 Oct 9;PP. doi: 10.1109/TPAMI.2024.3475249. Online ahead of print.

ABSTRACT

The restoration of hyperspectral image (HSI) plays a pivotal role in subsequent hyperspectral image applications. Despite the remarkable capabilities of deep learning, current HSI restoration methods face challenges in effectively exploring the spatial non-local self-similarity and spectral low-rank property inherently embedded with HSIs. This paper addresses these challenges by introducing a latent diffusion enhanced rectangle Transformer for HSI restoration, tackling the non-local spatial similarity and HSI-specific latent diffusion low-rank property. In order to effectively capture non-local spatial similarity, we propose the multi-shape spatial rectangle self-attention module in both horizontal and vertical directions, enabling the model to utilize informative spatial regions for HSI restoration. Meanwhile, we propose a spectral latent diffusion enhancement module that generates the image-specific latent dictionary based on the content of HSI for low-rank vector extraction and representation. This module utilizes a diffusion model to generatively obtain representations of global low-rank vectors, thereby aligning more closely with the desired HSI. A series of comprehensive experiments were carried out on four common hyperspectral image restoration tasks, including HSI denoising, HSI super-resolution, HSI reconstruction, and HSI inpainting. The results of these experiments highlight the effectiveness of our proposed method, as demonstrated by improvements in both objective metrics and subjective visual quality.

PMID:39383081 | DOI:10.1109/TPAMI.2024.3475249

IEEE Trans Biomed Eng. 2024 Oct 9;PP. doi: 10.1109/TBME.2024.3477275. Online ahead of print.

ABSTRACT

Accurate extraction of heart rate from photoplethysmography (PPG) signals remains challenging due to motion artifacts and signal degradation. Although deep learning methods trained as a data-driven inference problem offer promising solutions, they often underutilize existing knowledge from the medical and signal processing community. In this paper, we address three shortcomings of deep learning models: motion artifact removal, degradation assessment, and physiologically plausible analysis of the PPG signal. We propose KID-PPG, a knowledge-informed deep learning model that integrates expert knowledge through adaptive linear filtering, deep probabilistic inference, and data augmentation. We evaluate KID-PPG on the PPGDalia dataset, achieving an average mean absolute error of 2.85 beats per minute, surpassing existing reproducible methods. Our results demonstrate a significant performance improvement in heart rate tracking through the incorporation of prior knowledge into deep learning models. This approach shows promise in enhancing various biomedical applications by incorporating existing expert knowledge in deep learning models.

PMID:39383068 | DOI:10.1109/TBME.2024.3477275

J Perinat Med. 2024 Oct 10. doi: 10.1515/jpm-2024-0347. Online ahead of print.

ABSTRACT

Artificial intelligence has emerged as a transformative technology in the field of healthcare, offering significant advancements in various medical disciplines, including obstetrics. The integration of artificial intelligence into 3D/4D ultrasound analysis of fetal facial profiles presents numerous benefits. By leveraging machine learning and deep learning algorithms, AI can assist in the accurate and efficient interpretation of complex 3D/4D ultrasound data, enabling healthcare providers to make more informed decisions and deliver better prenatal care. One such innovation that has significantly improved the analysis of fetal facial profiles is the integration of artificial intelligence (AI) in 3D/4D ultrasound imaging. In conclusion, the integration of artificial intelligence in the analysis of 3D/4D ultrasound data for fetal facial profiles offers numerous benefits, including improved accuracy, consistency, and efficiency in prenatal diagnosis and care.

PMID:39383043 | DOI:10.1515/jpm-2024-0347

J Med Internet Res. 2024 Oct 9;26:e56851. doi: 10.2196/56851.

ABSTRACT

BACKGROUND: As part of the TNM (tumor-node-metastasis) staging system, T staging based on tumor depth is crucial for developing treatment plans. Previous studies have constructed a deep learning model based on computed tomographic (CT) radiomic signatures to predict the number of lymph node metastases and survival in patients with resected gastric cancer (GC). However, few studies have reported the combination of deep learning and radiomics in predicting T staging in GC.

OBJECTIVE: This study aimed to develop a CT-based model for automatic prediction of the T stage of GC via radiomics and deep learning.

METHODS: A total of 771 GC patients from 3 centers were retrospectively enrolled and divided into training, validation, and testing cohorts. Patients with GC were classified into mild (stage T1 and T2), moderate (stage T3), and severe (stage T4) groups. Three predictive models based on the labeled CT images were constructed using the radiomics features (radiomics model), deep features (deep learning model), and a combination of both (hybrid model).

RESULTS: The overall classification accuracy of the radiomics model was 64.3% in the internal testing data set. The deep learning model and hybrid model showed better performance than the radiomics model, with overall classification accuracies of 75.7% (P=.04) and 81.4% (P=.001), respectively. On the subtasks of binary classification of tumor severity, the areas under the curve of the radiomics, deep learning, and hybrid models were 0.875, 0.866, and 0.886 in the internal testing data set and 0.820, 0.818, and 0.972 in the external testing data set, respectively, for differentiating mild (stage T1~T2) from nonmild (stage T3~T4) patients, and were 0.815, 0.892, and 0.894 in the internal testing data set and 0.685, 0.808, and 0.897 in the external testing data set, respectively, for differentiating nonsevere (stage T1~T3) from severe (stage T4) patients.

CONCLUSIONS: The hybrid model integrating radiomics features and deep features showed favorable performance in diagnosing the pathological stage of GC.

PMID:39382960 | DOI:10.2196/56851

JAMA Surg. 2024 Oct 9. doi: 10.1001/jamasurg.2024.4299. Online ahead of print.

ABSTRACT

IMPORTANCE: Machine learning tools are increasingly deployed for risk prediction and clinical decision support in surgery. Class imbalance adversely impacts predictive performance, especially for low-incidence complications.

OBJECTIVE: To evaluate risk-prediction model performance when trained on risk-specific cohorts.

DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional study performed from February 2024 to July 2024 deployed a deep learning model, which generated risk scores for common postoperative complications. A total of 109 445 inpatient operations performed at 2 University of Florida Health hospitals from June 1, 2014, to May 5, 2021 were examined.

EXPOSURES: The model was trained de novo on separate cohorts for high-risk, medium-risk, and low-risk Common Procedure Terminology codes defined empirically by incidence of 5 postoperative complications: (1) in-hospital mortality; (2) prolonged intensive care unit (ICU) stay (≥48 hours); (3) prolonged mechanical ventilation (≥48 hours); (4) sepsis; and (5) acute kidney injury (AKI). Low-risk and high-risk cutoffs for complications were defined by the lower-third and upper-third prevalence in the dataset, except for mortality, cutoffs for which were set at 1% or less and greater than 3%, respectively.

MAIN OUTCOMES AND MEASURES: Model performance metrics were assessed for each risk-specific cohort alongside the baseline model. Metrics included area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), F1 scores, and accuracy for each model.

RESULTS: A total of 109 445 inpatient operations were examined among patients treated at 2 University of Florida Health hospitals in Gainesville (77 921 procedures [71.2%]) and Jacksonville (31 524 procedures [28.8%]). Median (IQR) patient age was 58 (43-68) years, and median (IQR) Charlson Comorbidity Index score was 2 (0-4). Among 109 445 operations, 55 646 patients were male (50.8%), and 66 495 patients (60.8%) underwent a nonemergent, inpatient operation. Training on the high-risk cohort had variable impact on AUROC, but significantly improved AUPRC (as assessed by nonoverlapping 95% confidence intervals) for predicting mortality (0.53; 95% CI, 0.43-0.64), AKI (0.61; 95% CI, 0.58-0.65), and prolonged ICU stay (0.91; 95% CI, 0.89-0.92). It also significantly improved F1 score for mortality (0.42; 95% CI, 0.36-0.49), prolonged mechanical ventilation (0.55; 95% CI, 0.52-0.58), sepsis (0.46; 95% CI, 0.43-0.49), and AKI (0.57; 95% CI, 0.54-0.59). After controlling for baseline model performance on high-risk cohorts, AUPRC increased significantly for in-hospital mortality only (0.53; 95% CI, 0.42-0.65 vs 0.29; 95% CI, 0.21-0.40).

CONCLUSION AND RELEVANCE: In this cross-sectional study, by training separate models using a priori knowledge for procedure-specific risk classes, improved performance in standard evaluation metrics was observed, especially for low-prevalence complications like in-hospital mortality. Used cautiously, this approach may represent an optimal training strategy for surgical risk-prediction models.

PMID:39382865 | DOI:10.1001/jamasurg.2024.4299

Eur Radiol Exp. 2024 Oct 9;8(1):111. doi: 10.1186/s41747-024-00510-9.

ABSTRACT

The growing use of artificial neural network (ANN) tools for computed tomography angiography (CTA) data analysis underscores the necessity for elevated data protection measures. We aimed to establish an automated defacing pipeline for CTA data. In this retrospective study, CTA data from multi-institutional cohorts were utilized to annotate facemasks (n = 100) and train an ANN model, subsequently tested on an external institution's dataset (n = 50) and compared to a publicly available defacing algorithm. Face detection (MTCNN) and verification (FaceNet) networks were applied to measure the similarity between the original and defaced CTA images. Dice similarity coefficient (DSC), face detection probability, and face similarity measures were calculated to evaluate model performance. The CTA-DEFACE model effectively segmented soft face tissue in CTA data achieving a DSC of 0.94 ± 0.02 (mean ± standard deviation) on the test set. Our model was benchmarked against a publicly available defacing algorithm. After applying face detection and verification networks, our model showed substantially reduced face detection probability (p < 0.001) and similarity to the original CTA image (p < 0.001). The CTA-DEFACE model enabled robust and precise defacing of CTA data. The trained network is publicly accessible at www.github.com/neuroAI-HD/CTA-DEFACE . RELEVANCE STATEMENT: The ANN model CTA-DEFACE, developed for automatic defacing of CT angiography images, achieves significantly lower face detection probabilities and greater dissimilarity from the original images compared to a publicly available model. The algorithm has been externally validated and is publicly accessible. KEY POINTS: The developed ANN model (CTA-DEFACE) automatically generates facemasks for CT angiography images. CTA-DEFACE offers superior deidentification capabilities compared to a publicly available model. By means of graphics processing unit optimization, our model ensures rapid processing of medical images. Our model underwent external validation, underscoring its reliability for real-world application.

PMID:39382818 | DOI:10.1186/s41747-024-00510-9

MAGMA. 2024 Oct 9. doi: 10.1007/s10334-024-01206-2. Online ahead of print.

ABSTRACT

Deep-learning-based MR image reconstruction in settings where large fully sampled dataset collection is infeasible requires methods that effectively use both under-sampled and fully sampled datasets. This paper evaluates a weakly supervised, multi-coil, physics-guided approach to MR image reconstruction, leveraging both dataset types, to improve both the quality and robustness of reconstruction. A physics-guided end-to-end variational network (VarNet) is pretrained in a self-supervised manner using a 4 × under-sampled dataset following the self-supervised learning via data undersampling (SSDU) methodology. The pre-trained weights are transferred to another VarNet, which is fine-tuned using a smaller, fully sampled dataset by optimizing multi-scale structural similarity (MS-SSIM) loss in image space. The proposed methodology is compared with fully self-supervised and fully supervised training. Reconstruction quality improvements in SSIM, PSNR, and NRMSE when abundant training data is available (the high-data regime), and enhanced robustness when training data is scarce (the low-data regime) are demonstrated using weak supervision for knee and brain MR image reconstructions at 8 × and 10 × acceleration, respectively. Multi-coil physics-guided MR image reconstruction using both under-sampled and fully sampled datasets is achievable with transfer learning and fine-tuning. This methodology can provide improved reconstruction quality in the high-data regime and improved robustness in the low-data regime at high acceleration rates.

PMID:39382814 | DOI:10.1007/s10334-024-01206-2

Eur Radiol Exp. 2024 Oct 9;8(1):110. doi: 10.1186/s41747-024-00507-4.

ABSTRACT

BACKGROUND: Renal quantitative measurements are important descriptors for assessing kidney function. We developed a deep learning-based method for automated kidney measurements from computed tomography (CT) images.

METHODS: The study datasets comprised potential kidney donors (n = 88), both contrast-enhanced (Dataset 1 CE) and noncontrast (Dataset 1 NC) CT scans, and test sets of contrast-enhanced cases (Test set 2, n = 18), cases from a photon-counting (PC)CT scanner reconstructed at 60 and 190 keV (Test set 3 PCCT, n = 15), and low-dose cases (Test set 4, n = 8), which were retrospectively analyzed to train, validate, and test two networks for kidney segmentation and subsequent measurements. Segmentation performance was evaluated using the Dice similarity coefficient (DSC). The quantitative measurements' effectiveness was compared to manual annotations using the intraclass correlation coefficient (ICC).

RESULTS: The contrast-enhanced and noncontrast models demonstrated excellent reliability in renal segmentation with DSC of 0.95 (Test set 1 CE), 0.94 (Test set 2), 0.92 (Test set 3 PCCT) and 0.94 (Test set 1 NC), 0.92 (Test set 3 PCCT), and 0.93 (Test set 4). Volume estimation was accurate with mean volume errors of 4%, 3%, 6% mL (contrast test sets) and 4%, 5%, 7% mL (noncontrast test sets). Renal axes measurements (length, width, and thickness) had ICC values greater than 0.90 (p < 0.001) for all test sets, supported by narrow 95% confidence intervals.

CONCLUSION: Two deep learning networks were shown to derive quantitative measurements from contrast-enhanced and noncontrast renal CT imaging at the human performance level.

RELEVANCE STATEMENT: Deep learning-based networks can automatically obtain renal clinical descriptors from both noncontrast and contrast-enhanced CT images. When healthy subjects comprise the training cohort, careful consideration is required during model adaptation, especially in scenarios involving unhealthy kidneys. This creates an opportunity for improved clinical decision-making without labor-intensive manual effort.

KEY POINTS: Trained 3D UNet models quantify renal measurements from contrast and noncontrast CT. The models performed interchangeably to the manual annotator and to each other. The models can provide expert-level, quantitative, accurate, and rapid renal measurements.

PMID:39382755 | DOI:10.1186/s41747-024-00507-4

J Cancer Res Clin Oncol. 2024 Oct 9;150(10):452. doi: 10.1007/s00432-024-05905-0.

ABSTRACT

PURPOSE: We sought to develop an effective combined model for predicting the survival of patients with diffuse large B-cell lymphoma (DLBCL) based on the multimodal PET-CT deep features radiomics signature (DFR-signature).

METHODS: 369 DLBCL patients from two medical centers were included in this study. Their PET and CT images were fused to construct the multimodal PET-CT images using a deep learning fusion network. Then the deep features were extracted from those fused PET-CT images, and the DFR-signature was constructed through an Automated machine learning (AutoML) model. Combined with clinical indexes from the Cox regression analysis, we constructed a combined model to predict the progression-free survival (PFS) and the overall survival (OS) of patients. In addition, the combined model was evaluated in the concordance index (C-index) and the time-dependent area under the ROC curve (tdAUC).

RESULTS: A total of 1000 deep features were extracted to build a DFR-signature. Besides the DFR-signature, the combined model integrating metabolic and clinical factors performed best in terms of PFS and OS. For PFS, the C-indices are 0.784 and 0.739 in the training cohort and internal validation cohort, respectively. For OS, the C-indices are 0.831 and 0.782 in the training cohort and internal validation cohort.

CONCLUSIONS: DFR-signature constructed from multimodal images improved the classification accuracy of prognosis for DLBCL patients. Moreover, the constructed DFR-signature combined with NCCN-IPI exhibited excellent potential for risk stratification of DLBCL patients.

PMID:39382750 | DOI:10.1007/s00432-024-05905-0

Eur J Nucl Med Mol Imaging. 2024 Oct 9. doi: 10.1007/s00259-024-06938-w. Online ahead of print.

ABSTRACT

PURPOSE: Metabolism and bioenergetics in the central nervous system play important roles in the pathophysiology of Parkinson's disease (PD). Here, we employed a multimodal imaging approach to assess oxygenation changes in the spinal cord of the transgenic M83 murine model of PD overexpressing the mutated A53T alpha-synuclein form in comparison with non-transgenic littermates.

METHODS: In vivo spiral volumetric optoacoustic tomography (SVOT) was performed to assess oxygen saturation (sO2) in the spinal cords of M83 mice and non-transgenic littermates. Ex vivo high-field T1-weighted (T1w) magnetic resonance imaging (MRI) at 9.4T was used to assess volumetric alterations in the spinal cord. 3D SVOT analysis and deep learning-based automatic segmentation of T1w MRI data for the mouse spinal cord were developed for quantification. Immunostaining for phosphorylated alpha-synuclein (pS129 α-syn), as well as vascular organization (CD31 and GLUT1), was performed after MRI scan.

RESULTS: In vivo SVOT imaging revealed a lower sO2SVOT in the spinal cord of M83 mice compared to non-transgenic littermates at sub-100 μm spatial resolution. Ex vivo MRI-assisted by in-house developed deep learning-based automatic segmentation (validated by manual analysis) revealed no volumetric atrophy in the spinal cord of M83 mice compared to non-transgenic littermates at 50 μm spatial resolution. The vascular network was not impaired in the spinal cord of M83 mice in the presence of pS129 α-syn accumulation.

CONCLUSION: We developed tools for deep-learning-based analysis for the segmentation of mouse spinal cord structural MRI data, and volumetric analysis of sO2SVOT data. We demonstrated non-invasive high-resolution imaging of reduced sO2SVOT in the absence of volumetric structural changes in the spinal cord of PD M83 mouse model.

PMID:39382580 | DOI:10.1007/s00259-024-06938-w

Biol Cybern. 2024 Oct 9. doi: 10.1007/s00422-024-00998-9. Online ahead of print.

ABSTRACT

The development of biologically-inspired computational models has been the focus of study ever since the artificial neuron was introduced by McCulloch and Pitts in 1943. However, a scrutiny of literature reveals that most attempts to replicate the highly efficient and complex biological visual system have been futile or have met with limited success. The recent state-of the-art computer vision models, such as pre-trained deep neural networks and vision transformers, may not be biologically inspired per se. Nevertheless, certain aspects of biological vision are still found embedded, knowingly or unknowingly, in the architecture and functioning of these models. This paper explores several principles related to visual neuroscience and the biological visual pathway that resonate, in some manner, in the architectural design and functioning of contemporary computer vision models. The findings of this survey can provide useful insights for building futuristic bio-inspired computer vision models. The survey is conducted from a historical perspective, tracing the biological connections of computer vision models starting with the basic artificial neuron to modern technologies such as deep convolutional neural network (CNN) and spiking neural networks (SNN). One spotlight of the survey is a discussion on biologically plausible neural networks and bio-inspired unsupervised learning mechanisms adapted for computer vision tasks in recent times.

PMID:39382577 | DOI:10.1007/s00422-024-00998-9

JMIR Aging. 2024 Oct 9;7:e59810. doi: 10.2196/59810.

ABSTRACT

BACKGROUND: Visual impairment (VI) is a prevalent global health issue, affecting over 2.2 billion people worldwide, with nearly half of the Chinese population aged 60 years and older being affected. Early detection of high-risk VI is essential for preventing irreversible vision loss among Chinese middle-aged and older adults. While machine learning (ML) algorithms exhibit significant predictive advantages, their application in predicting VI risk among the general middle-aged and older adult population in China remains limited.

OBJECTIVE: This study aimed to predict VI and identify its determinants using ML algorithms.

METHODS: We used 19,047 participants from 4 waves of the China Health and Retirement Longitudinal Study (CHARLS) that were conducted between 2011 and 2018. To envisage the prevalence of VI, we generated a geographical distribution map. Additionally, we constructed a model using indicators of a self-reported questionnaire, a physical examination, and blood biomarkers as predictors. Multiple ML algorithms, including gradient boosting machine, distributed random forest, the generalized linear model, deep learning, and stacked ensemble, were used for prediction. We plotted receiver operating characteristic and calibration curves to assess the predictive performance. Variable importance analysis was used to identify key predictors.

RESULTS: Among all participants, 33.9% (6449/19,047) had VI. Qinghai, Chongqing, Anhui, and Sichuan showed the highest VI rates, while Beijing and Xinjiang had the lowest. The generalized linear model, gradient boosting machine, and stacked ensemble achieved acceptable area under curve values of 0.706, 0.710, and 0.715, respectively, with the stacked ensemble performing best. Key predictors included hearing impairment, self-expectation of health status, pain, age, hand grip strength, depression, night sleep duration, high-density lipoprotein cholesterol, and arthritis or rheumatism.

CONCLUSIONS: Nearly one-third of middle-aged and older adults in China had VI. The prevalence of VI shows regional variations, but there are no distinct east-west or north-south distribution differences. ML algorithms demonstrate accurate predictive capabilities for VI. The combination of prediction models and variable importance analysis provides valuable insights for the early identification and intervention of VI among Chinese middle-aged and older adults.

PMID:39382570 | DOI:10.2196/59810

J Am Chem Soc. 2024 Oct 9. doi: 10.1021/jacs.4c11674. Online ahead of print.

ABSTRACT

Scanning tunneling microscopy (STM) is a powerful technique that provides the ability to manipulate and characterize individual atoms and molecules with atomic-level precision. However, the processes of scanning samples, operating the probe, and analyzing data are typically labor-intensive and subjective. Deep learning (DL) techniques have shown immense potential in automating complex tasks and solving high-dimensional problems. In this study, we developed an autonomous STM framework powered by DL to enable autonomous operations of the STM without human interventions. Our framework employs a convolutional neural network (CNN) for real-time evaluation of STM image quality, a U-net model for identifying bare surfaces, and a deep Q-learning network (DQN) agent for autonomous probe conditioning. Additionally, we integrated an object recognition model for the automated recognition of different adsorbates. This autonomous framework enables the acquisition of space-averaging information using STM techniques without compromising the high-resolution molecular imaging. We achieved measuring an area of approximately 1.9 μm2 within 48 h of continuous measurement and automatedly generated the statistics on the molecular species present within the mesoscopic area. We demonstrate the high robustness of the framework by conducting measurements at the liquid nitrogen temperature (∼78 K). We envision that the integration of DL techniques and high-resolution microscopy will not only extend the functionality and capability of scanning probe microscopes but also accelerate the understanding and discovery of new materials.

PMID:39382312 | DOI:10.1021/jacs.4c11674

MethodsX. 2024 Sep 19;13:102965. doi: 10.1016/j.mex.2024.102965. eCollection 2024 Dec.

ABSTRACT

Milling tool availability and its useful life estimation is essential for optimisation, reliability and cost reduction in milling operations. This work presents DeepTool, a deep learning-based system that predicts the service life of the tool and detects the onset of its wear. DeepTool showcases a comprehensive feature extraction process, and a self-collected dataset of sensor data from milling tests carried out under different cutting settings to extract relevant information from the sensor signals. The main contributions of this study are:•Self-Collected Dataset: Makes use of an extensive, self-collected dataset to record precise sensor signals during milling.•Advanced Predictive Modeling: Employs hybrid autoencoder-LSTM and encoder-decoder LSTM models to estimate tool wear onset and predict its remaining useful life with over 95 % R2 accuracy score.•Comprehensive Feature Extraction: Employs an efficient feature extraction technique from the gathered sensor data, emphasising both time-domain and frequency-domain aspects associated with tool wear.

PMID:39381346 | PMC:PMC11460470 | DOI:10.1016/j.mex.2024.102965

Digit Health. 2024 Oct 7;10:20552076241284349. doi: 10.1177/20552076241284349. eCollection 2024 Jan-Dec.

ABSTRACT

OBJECTIVE: The proportion of older people will soon include nearly a quarter of the world population. This leads to an increased prevalence of non-communicable diseases such as Alzheimer's disease (AD), a progressive neurodegenerative disorder and the most common dementia. mild cognitive impairment (MCI) can be considered its prodromal stage. The early diagnosis of AD is a huge issue. We face it by solving these classification tasks: MCI-AD and cognitively normal (CN)-MCI-AD.

METHODS: An intelligent computing system has been developed and implemented to face both challenges. A non-neural preprocessing module was followed by a processing one based on a hybrid and ontogenetic neural architecture, the modular hybrid growing neural gas (MyGNG). The MyGNG is hierarchically organized, with a growing neural gas (GNG) for clustering followed by a perceptron for labeling. For each task, 495 and 819 patients from the Alzheimer's disease neuroimaging initiative (ADNI) database were used, respectively, each with 211 characteristics.

RESULTS: Encouraging results have been obtained in the MCI-AD classification task, reaching values of area under the curve (AUC) of 0.96 and sensitivity of 0.91, whereas 0.86 and 0.9 in CN-MCI-AD. Furthermore, a comparative study with popular machine learning (ML) models was also performed for each of these tasks.

CONCLUSIONS: The MyGNG proved to be a better computational solution than the other ML methods analyzed. Also, it had a similar performance to other deep learning schemes with neuroimaging. Our findings suggest that our proposal may be an interesting computing solution for the early diagnosis of AD.

PMID:39381826 | PMC:PMC11459500 | DOI:10.1177/20552076241284349

Digit Health. 2024 Oct 7;10:20552076241286140. doi: 10.1177/20552076241286140. eCollection 2024 Jan-Dec.

ABSTRACT

OBJECTIVE: Brain tumors are a leading global cause of mortality, often leading to reduced life expectancy and challenging recovery. Early detection significantly improves survival rates. This paper introduces an efficient deep learning model to expedite brain tumor detection through timely and accurate identification using magnetic resonance imaging images.

METHODS: Our approach leverages deep transfer learning with six transfer learning algorithms: VGG16, ResNet50, MobileNetV2, DenseNet201, EfficientNetB3, and InceptionV3. We optimize data preprocessing, upsample data through augmentation, and train the models using two optimizers: Adam and AdaMax. We perform three experiments with binary and multi-class datasets, fine-tuning parameters to reduce overfitting. Model effectiveness is analyzed using various performance scores with and without cross-validation.

RESULTS: With smaller datasets, the models achieve 100% accuracy in both training and testing without cross-validation. After applying cross-validation, the framework records an outstanding accuracy of 99.96% with a receiver operating characteristic of 100% on average across five tests. For larger datasets, accuracy ranges from 96.34% to 98.20% across different models. The methodology also demonstrates a small computation time, contributing to its reliability and speed.

CONCLUSION: The study establishes a new standard for brain tumor classification, surpassing existing methods in accuracy and efficiency. Our deep learning approach, incorporating advanced transfer learning algorithms and optimized data processing, provides a robust and rapid solution for brain tumor detection.

PMID:39381813 | PMC:PMC11459499 | DOI:10.1177/20552076241286140

Digit Health. 2024 Oct 7;10:20552076241287356. doi: 10.1177/20552076241287356. eCollection 2024 Jan-Dec.

ABSTRACT

OBJECTIVE: Scalp electroencephalograms (EEGs) are critical for neurological evaluations, particularly in epilepsy, yet they demand specialized expertise that is often lacking in many regions. Artificial intelligence (AI) offers potential solutions to this gap. While existing AI models address certain aspects of EEG analysis, a fully automated system for routine EEG interpretation is required for effective epilepsy management and healthcare professionals' decision-making. This study aims to develop an AI-augmented model for automating EEG seizure tracking, thereby supporting a sustainable digital care pathway for epilepsy (DCPE). The goal is to improve patient monitoring, facilitate collaborative decision-making, ensure timely medication adherence, and promote patient compliance.

METHOD: The study proposes an AI-augmented framework using machine learning, focusing on quantitative analysis of EEG data to automate DCPE. A focus group discussion was conducted with healthcare professionals to find the problem of the current digital care pathway and assess the feasibility, usability, and sustainability of the AI-augmented system in the digital care pathway.

RESULTS: The study found that a combination of random forest with principal component analysis and support vector machines with KBest feature selection achieved high accuracy rates of 96.52% and 95.28%, respectively. Additionally, the convolutional neural networks model outperformed other deep learning algorithms with an accuracy of 97.65%. The focus group discussion revealed that automating the diagnostic process in digital care pathway could reduce the time needed to diagnose epilepsy. However, the sustainability of the AI-integrated framework depends on factors such as technological infrastructure, skilled personnel, training programs, patient digital literacy, financial resources, and regulatory compliance.

CONCLUSION: The proposed AI-augmented system could enhance epilepsy management by optimizing seizure tracking accuracy, improving monitoring and timely interventions, facilitating collaborative decision-making, and promoting patient-centered care, thereby making the digital care pathway more sustainable.

PMID:39381810 | PMC:PMC11459578 | DOI:10.1177/20552076241287356

Digit Health. 2024 Oct 7;10:20552076241284773. doi: 10.1177/20552076241284773. eCollection 2024 Jan-Dec.

ABSTRACT

OBJECTIVE: To address the complexities of distinguishing truth from falsehood in the context of the COVID-19 infodemic, this paper focuses on utilizing deep learning models for infodemic ternary classification detection.

METHODS: Eight commonly used deep learning models are employed to categorize collected records as true, false, or uncertain. These models include fastText, three models based on recurrent neural networks, two models based on convolutional neural networks, and two transformer-based models.

RESULTS: Precision, recall, and F1-score metrics for each category, along with overall accuracy, are presented to establish benchmark results. Additionally, a comprehensive analysis of the confusion matrix is conducted to provide insights into the models' performance.

CONCLUSION: Given the limited availability of infodemic records and the relatively modest size of the two tested data sets, models with pretrained embeddings or simpler architectures tend to outperform their more complex counterparts. This highlights the potential efficiency of pretrained or simpler models for ternary classification in COVID-19 infodemic detection and underscores the need for further research in this area.

PMID:39381806 | PMC:PMC11459571 | DOI:10.1177/20552076241284773

Clin Transl Radiat Oncol. 2024 Sep 22;49:100865. doi: 10.1016/j.ctro.2024.100865. eCollection 2024 Nov.

ABSTRACT

This review explores the integration of artificial intelligence (AI) in interventional radiotherapy (IRT), emphasizing its potential to streamline workflows and enhance patient care. Through a systematic analysis of 78 relevant papers spanning from 2002 to 2024, we identified significant advancements in contouring, treatment planning, outcome prediction, and quality assurance. AI-driven approaches offer promise in reducing procedural times, personalizing treatments, and improving treatment outcomes for oncological patients. However, challenges such as clinical validation and quality assurance protocols persist. Nonetheless, AI presents a transformative opportunity to optimize IRT and meet evolving patient needs.

PMID:39381628 | PMC:PMC11459626 | DOI:10.1016/j.ctro.2024.100865

Phys Imaging Radiat Oncol. 2024 Sep 12;32:100644. doi: 10.1016/j.phro.2024.100644. eCollection 2024 Oct.

ABSTRACT

BACKGROUND AND PURPOSE: In radiotherapy, precise comparison of fan-beam computed tomography (CT) and cone-beam CT (CBCT) arises as a commonplace, yet intricate task. This paper proposes a publicly available end-to-end pipeline featuring an intrinsic deep-learning-based speedup technique for generating virtual 3D and 4D CBCT from CT images.

MATERIALS AND METHODS: Physical properties, derived from CT intensity information, are obtained through automated whole-body segmentation of organs and tissues. Subsequently, Monte Carlo (MC) simulations generate CBCT X-ray projections for a full circular arc around the patient employing acquisition settings matched with a clinical CBCT scanner (modeled according to Varian TrueBeam specifications). In addition to 3D CBCT reconstruction, a 4D CBCT can be simulated with a fully time-resolved MC simulation by incorporating respiratory correspondence modeling. To address the computational complexity of MC simulations, a deep-learning-based speedup technique is developed and integrated that uses projection data simulated with a reduced number of photon histories to predict a projection that matches the image characteristics and signal-to-noise ratio of the reference simulation.

RESULTS: MC simulations with default parameter setting yield CBCT images with high agreement to ground truth data acquired by a clinical CBCT scanner. Furthermore, the proposed speedup technique achieves up to 20-fold speedup while preserving image features and resolution compared to the reference simulation.

CONCLUSION: The presented MC pipeline and speedup approach provide an openly accessible end-to-end framework for researchers and clinicians to investigate limitations of image-guided radiation therapy workflows built on both (4D) CT and CBCT images.

PMID:39381614 | PMC:PMC11458955 | DOI:10.1016/j.phro.2024.100644