J Endourol. 2024 May 30. doi: 10.1089/end.2023.0413. Online ahead of print.

ABSTRACT

Background/Aim: To evaluate the performance of Chat Generative Pre-trained Transformer (ChatGPT), a large language model trained by Open artificial intelligence. Materials and Methods: This study has three main steps to evaluate the effectiveness of ChatGPT in the urologic field. The first step involved 35 questions from our institution's experts, who have at least 10 years of experience in their fields. The responses of ChatGPT versions were qualitatively compared with the responses of urology residents to the same questions. The second step assesses the reliability of ChatGPT versions in answering current debate topics. The third step was to assess the reliability of ChatGPT versions in providing medical recommendations and directives to patients' commonly asked questions during the outpatient and inpatient clinic. Results: In the first step, version 4 provided correct answers to 25 questions out of 35 while version 3.5 provided only 19 (71.4% vs 54%). It was observed that residents in their last year of education in our clinic also provided a mean of 25 correct answers, and 4th year residents provided a mean of 19.3 correct responses. The second step involved evaluating the response of both versions to debate situations in urology, and it was found that both versions provided variable and inappropriate results. In the last step, both versions had a similar success rate in providing recommendations and guidance to patients based on expert ratings. Conclusion: The difference between the two versions of the 35 questions in the first step of the study was thought to be due to the improvement of ChatGPT's literature and data synthesis abilities. It may be a logical approach to use ChatGPT versions to inform the nonhealth care providers' questions with quick and safe answers but should not be used to as a diagnostic tool or make a choice among different treatment modalities.

PMID:38815140 | DOI:10.1089/end.2023.0413

PLoS One. 2024 May 30;19(5):e0301835. doi: 10.1371/journal.pone.0301835. eCollection 2024.

ABSTRACT

In this study, we used unidirectional and bidirectional long short-term memory (LSTM) deep learning networks for Chinese news classification and characterized the effects of contextual information on text classification, achieving a high level of accuracy. A Chinese glossary was created using jieba-a word segmentation tool-stop-word removal, and word frequency analysis. Next, word2vec was used to map the processed words into word vectors, creating a convenient lookup table for word vectors that could be used as feature inputs for the LSTM model. A bidirectional LSTM (BiLSTM) network was used for feature extraction from word vectors to facilitate the transfer of information in both the backward and forward directions to the hidden layer. Subsequently, an LSTM network was used to perform feature integration on all the outputs of the BiLSTM network, with the output from the last layer of the LSTM being treated as the mapping of the text into a feature vector. The output feature vectors were then connected to a fully connected layer to construct a feature classifier using the integrated features, finally classifying the news articles. The hyperparameters of the model were optimized based on the loss between the true and predicted values using the adaptive moment estimation (Adam) optimizer. Additionally, multiple dropout layers were added to the model to reduce overfitting. As text classification models for Chinese news articles, the Bi-LSTM and unidirectional LSTM models obtained f1-scores of 94.15% and 93.16%, respectively, with the former outperforming the latter in terms of feature extraction.

PMID:38814925 | DOI:10.1371/journal.pone.0301835

JNCI Cancer Spectr. 2024 May 30:pkae042. doi: 10.1093/jncics/pkae042. Online ahead of print.

ABSTRACT

Deep learning-based mammographic evaluations could noninvasively assess response to breast cancer (BC) chemoprevention. We evaluated change in a convolutional neural network (CNN)-based BC risk model applied to mammograms among women enrolled in SWOG S0812, which randomized 208 premenopausal high-risk women to receive oral vitamin D3 20,000IU weekly or placebo for 12 months. We applied the CNN model to mammograms collected at baseline (n = 109), 12 months (n = 97) and 24 months (n = 67), and compared changes in CNN risk score between treatment groups. Change in CNN score was neither significantly different between vitamin D and placebo groups at 12 months (0.005 vs. 0.002, p = 0.875) nor at 24 months (0.020 vs. 0.001, p = 0.563). The findings are consistent with the primary analysis of S0812, which did not demonstrate significant changes in MD with vitamin D supplementation compared to placebo. There is an ongoing need to evaluate biomarkers of response to novel BC chemopreventive agents.

PMID:38814817 | DOI:10.1093/jncics/pkae042

Dentomaxillofac Radiol. 2024 May 30:twae022. doi: 10.1093/dmfr/twae022. Online ahead of print.

ABSTRACT

Cystic lesions of the gnathic bones present challenges in differential diagnosis. In recent years, artificial intelligence (AI) represented by deep learning (DL) has rapidly developed and emerged in the field of dental and maxillofacial radiology (DMFR) Dental radiography provides a rich resource for the study of diagnostic analysis methods for cystic lesions of the jaws and has attracted many researchers. The aim of the current study was to investigate the diagnostic performance of DL for cystic lesions of the jaws. Online searches on Google Scholar, PubMed, and IEEE Xplore databases, up to September 2023, with subsequent manual screening for confirmation. The initial search yielded 1862 titles, and 44 studies were ultimately included. All studies used DL methods or tools for the identification of a variable number of maxillofacial cysts. The performance of algorithms with different models varies. Although most of the reviewed stu dies demonstrated that DL methods have better discriminative performance than clinicians, further development is still needed before routine clinical implementation due to several challenges and limitations such as lack of model interpretability, multicenter data validation, etc Considering the current limitations and challenges, future studies for the differential diagnosis of cystic lesions of the jaws should follow actual clinical diagnostic scenarios to coordinate study design and enhance the impact of artificial intelligence in the diagnosis of oral and maxillofacial diseases.

PMID:38814810 | DOI:10.1093/dmfr/twae022

IEEE J Biomed Health Inform. 2024 May 30;PP. doi: 10.1109/JBHI.2024.3407116. Online ahead of print.

ABSTRACT

Positron emission tomography/magnetic resonance imaging (PET/MRI) systems can provide precise anatomical and functional information with exceptional sensitivity and accuracy for neurological disorder detection. Nevertheless, the radiation exposure risks and economic costs of radiopharmaceuticals may pose significant burdens on patients. To mitigate image quality degradation during low-dose PET imaging, we proposed a novel 3D network equipped with a spatial brain transform (SBF) module for low-dose whole-brain PET and MR images to synthesize high-quality PET images. The FreeSurfer toolkit was applied to derive the spatial brain anatomical alignment information, which was then fused with low-dose PET and MR features through the SBF module. Moreover, several deep learning methods were employed as comparison measures to evaluate the model performance, with the peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and Pearson correlation coefficient (PCC) serving as quantitative metrics. Both the visual results and quantitative results illustrated the effectiveness of our approach. The obtained PSNR and SSIM were 41.96 ±4.91 dB (p<0.01) and 0.9654 ±0.0215 (p<0.01), which achieved a 19% and 20% improvement, respectively, compared to the original low-dose brain PET images. The volume of interest (VOI) analysis of brain regions such as the left thalamus (PCC = 0.959) also showed that the proposed method could achieve a more accurate standardized uptake value (SUV) distribution while preserving the details of brain structures. In future works, we hope to apply our method to other multimodal systems, such as PET/CT, to assist clinical brain disease diagnosis and treatment.

PMID:38814764 | DOI:10.1109/JBHI.2024.3407116

IEEE Trans Biomed Eng. 2024 May 30;PP. doi: 10.1109/TBME.2024.3407092. Online ahead of print.

ABSTRACT

OBJECTIVE: Chemical exchange saturation transfer (CEST) is a promising magnetic resonance imaging (MRI) technique. CEST imaging usually requires a long scan time, and reducing acquisition time is highly desirable for clinical applications.

METHODS: A novel scan-specific unsupervised deep learning algorithm is proposed to accelerate steady-state pulsed CEST imaging with golden-angle stack-of-stars trajectory using hybrid-feature hash encoding implicit neural representation. Additionally, imaging quality is further improved by using the explicit prior knowledge of low rank and weighted joint sparsity in the spatial and Z-spectral domain of CEST data.

RESULTS: In the retrospective acceleration experiment, the proposed method outperforms other state-of-the-art algorithms (TDDIP, LRTES, kt-SLR, NeRP, CRNN, and PBCS) for the in vivo human brain dataset under various acceleration rates. In the prospective acceleration experiment, the proposed algorithm can still obtain results close to the fully-sampled images.

CONCLUSION AND SIGNIFICANCE: The hybrid-feature hash encoding implicit neural representation combined with explicit sparse prior (INRESP) can efficiently accelerate CEST imaging. The proposed algorithm achieves reduced error and improved image quality compared to several state-of-the-art algorithms at relatively high acceleration factors. The superior performance and the training database-free characteristic make the proposed algorithm promising for accelerating CEST imaging in various applications.

PMID:38814759 | DOI:10.1109/TBME.2024.3407092

Curr Opin Allergy Clin Immunol. 2024 May 23. doi: 10.1097/ACI.0000000000001002. Online ahead of print.

ABSTRACT

PURPOSE OF REVIEW: Drug allergy is responsible for a huge burden on public healthcare systems, representing in some instances a threat for patient's life. Diagnosis is complex due to the heterogeneity of clinical phenotypes and mechanisms involved, the limitations of in vitro tests, and the associated risk to in vivo tests. Predictive models, including those using recent advances in artificial intelligence, may circumvent these drawbacks, leading to an appropriate classification of patients and improving their management in clinical settings.

RECENT FINDINGS: Scores and predictive models to assess drug allergy development, including patient risk stratification, are scarce and usually apply logistic regression analysis. Over recent years, different methods encompassed under the general umbrella of artificial intelligence, including machine and deep learning, and artificial neural networks, are emerging as powerful tools to provide reliable and optimal models for clinical diagnosis, prediction, and precision medicine in different types of drug allergy.

SUMMARY: This review provides general concepts and current evidence supporting the potential utility of predictive models and artificial intelligence branches in drug allergy diagnosis.

PMID:38814733 | DOI:10.1097/ACI.0000000000001002

Neurol Ther. 2024 May 30. doi: 10.1007/s40120-024-00625-6. Online ahead of print.

ABSTRACT

INTRODUCTION: Traditional methods for assessing movement quality rely on subjective standardized scales and clinical expertise. This limitation creates challenges for assessing patients with spinocerebellar ataxia (SCA), in whom changes in mobility can be subtle and varied. We hypothesized that a machine learning analytic system might complement traditional clinician-rated measures of gait. Our objective was to use a video-based assessment of gait dispersion to compare the effects of troriluzole with placebo on gait quality in adults with SCA.

METHODS: Participants with SCA underwent gait assessment in a phase 3, double-blind, placebo-controlled trial of troriluzole (NCT03701399). Videos were processed through a deep learning pose extraction algorithm, followed by the estimation of a novel gait stability measure, the Pose Dispersion Index, quantifying the frame-by-frame symmetry, balance, and stability during natural and tandem walk tasks. The effects of troriluzole treatment were assessed in mixed linear models, participant-level grouping, and treatment group-by-visit week interaction adjusted for age, sex, baseline modified Functional Scale for the Assessment and Rating of Ataxia (f-SARA), and time since diagnosis.

RESULTS: From 218 randomized participants, 67 and 56 participants had interpretable videos of a tandem and natural walk attempt, respectively. At Week 48, individuals assigned to troriluzole exhibited significant (p = 0.010) improvement in tandem walk Pose Dispersion Index versus placebo {adjusted interaction coefficient: 0.584 [95% confidence interval (CI) 0.137 to 1.031]}. A similar, nonsignificant trend was observed in the natural walk assessment [coefficient: 1.198 (95% CI - 1.067 to 3.462)]. Further, lower baseline Pose Dispersion Index during the natural walk was significantly (p = 0.041) associated with a higher risk of subsequent falls [adjusted Poisson coefficient: - 0.356 [95% CI - 0.697 to - 0.014)].

CONCLUSION: Using this novel approach, troriluzole-treated subjects demonstrated improvement in gait as compared to placebo for the tandem walk. Machine learning applied to video-captured gait parameters can complement clinician-reported motor assessment in adults with SCA. The Pose Dispersion Index may enhance assessment in future research. TRIAL REGISTRATION-CLINICALTRIALS.

GOV IDENTIFIER: NCT03701399.

PMID:38814532 | DOI:10.1007/s40120-024-00625-6

Int J Comput Assist Radiol Surg. 2024 May 30. doi: 10.1007/s11548-024-03182-3. Online ahead of print.

ABSTRACT

PURPOSE: The segmentation of the heart and great vessels in CT images of congenital heart disease (CHD) is critical for the clinical assessment of cardiac anomalies and the diagnosis of CHD. However, the diverse types and abnormalities inherent in CHD present significant challenges to comprehensive heart segmentation.

METHODS: We proposed a novel two-stage segmentation approach, integrating a Convolutional Neural Network (CNN) with a postprocessing method with conditioned energy function for pulmonary and aorta. The initial stage employs a CNN enhanced by a gated self-attention mechanism for the segmentation of five primary heart structures and two major vessels. Subsequently, the second stage utilizes a conditioned energy function specifically tailored to refine the segmentation of the pulmonary artery and aorta, ensuring vascular continuity.

RESULTS: Our method was evaluated on a public dataset including 110 3D CT volumes, encompassing 16 CHD variants. Compared to prevailing segmentation techniques (U-Net, V-Net, Unetr, dynUnet), our approach demonstrated improvements of 1.02, 1.04, and 1.41% in Dice Coefficient (DSC), Intersection over Union (IOU), and the 95th percentile Hausdorff Distance (HD95), respectively, for heart structure segmentation. For the two great vessels, the enhancements were 1.05, 1.07, and 1.42% in these metrics.

CONCLUSION: The outcomes on the public dataset affirm the efficacy of our proposed segmentation method. Precise segmentation of the entire heart and great vessels can significantly aid in the diagnosis and treatment of CHD, underscoring the clinical relevance of our findings.

PMID:38814529 | DOI:10.1007/s11548-024-03182-3

Mem Cognit. 2024 May 30. doi: 10.3758/s13421-024-01580-1. Online ahead of print.

ABSTRACT

Early in life and without special training, human beings discern resemblance between abstract visual stimuli, such as drawings, and the real-world objects they represent. We used this capacity for visual abstraction as a tool for evaluating deep neural networks (DNNs) as models of human visual perception. Contrasting five contemporary DNNs, we evaluated how well each explains human similarity judgments among line drawings of recognizable and novel objects. For object sketches, human judgments were dominated by semantic category information; DNN representations contributed little additional information. In contrast, such features explained significant unique variance perceived similarity of abstract drawings. In both cases, a vision transformer trained to blend representations of images and their natural language descriptions showed the greatest ability to explain human perceptual similarity-an observation consistent with contemporary views of semantic representation and processing in the human mind and brain. Together, the results suggest that the building blocks of visual similarity may arise within systems that learn to use visual information, not for specific classification, but in service of generating semantic representations of objects.

PMID:38814385 | DOI:10.3758/s13421-024-01580-1

Int Urol Nephrol. 2024 May 30. doi: 10.1007/s11255-024-04082-w. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Rapid advances in computer vision (CV) have the potential to facilitate the examination, diagnosis, and treatment of diseases of the kidney. The bibliometric study aims to explore the research landscape and evolving research focus of the application of CV in kidney medicine research.

METHODS: The Web of Science Core Collection was utilized to identify publications related to the research or applications of CV technology in the field of kidney medicine from January 1, 1900, to December 31, 2022. We analyzed emerging research trends, highly influential publications and journals, prolific researchers, countries/regions, research institutions, co-authorship networks, and co-occurrence networks. Bibliographic information was analyzed and visualized using Python, Matplotlib, Seaborn, HistCite, and Vosviewer.

RESULTS: There was an increasing trend in the number of publications on CV-based kidney medicine research. These publications mainly focused on medical image processing, surgical procedures, medical image analysis/diagnosis, as well as the application and innovation of CV technology in medical imaging. The United States is currently the leading country in terms of the quantities of published articles and international collaborations, followed by China. Deep learning-based segmentation and machine learning-based texture analysis are the most commonly used techniques in this field. Regarding research hotspot trends, CV algorithms are shifting toward artificial intelligence, and research objects are expanding to encompass a wider range of kidney-related objects, with data dimensions used in research transitioning from 2D to 3D while simultaneously incorporating more diverse data modalities.

CONCLUSION: The present study provides a scientometric overview of the current progress in the research and application of CV technology in kidney medicine research. Through the use of bibliometric analysis and network visualization, we elucidate emerging trends, key sources, leading institutions, and popular topics. Our findings and analysis are expected to provide valuable insights for future research on the use of CV in kidney medicine research.

PMID:38814370 | DOI:10.1007/s11255-024-04082-w

Int J Surg. 2024 May 29. doi: 10.1097/JS9.0000000000001718. Online ahead of print.

NO ABSTRACT

PMID:38814316 | DOI:10.1097/JS9.0000000000001718

Med Phys. 2024 May 30. doi: 10.1002/mp.17230. Online ahead of print.

ABSTRACT

BACKGROUND: 3D neural network dose predictions are useful for automating brachytherapy (BT) treatment planning for cervical cancer. Cervical BT can be delivered with numerous applicators, which necessitates developing models that generalize to multiple applicator types. The variability and scarcity of data for any given applicator type poses challenges for deep learning.

PURPOSE: The goal of this work was to compare three methods of neural network training-a single model trained on all applicator data, fine-tuning the combined model to each applicator, and individual (IDV) applicator models-to determine the optimal method for dose prediction.

METHODS: Models were produced for four applicator types-tandem-and-ovoid (T&O), T&O with 1-7 needles (T&ON), tandem-and-ring (T&R) and T&R with 1-4 needles (T&RN). First, the combined model was trained on 859 treatment plans from 266 cervical cancer patients treated from 2010 onwards. The train/validation/test split was 70%/16%/14%, with approximately 49%/10%/19%/22% T&O/T&ON/T&R/T&RN in each dataset. Inputs included four channels for anatomical masks (high-risk clinical target volume [HRCTV], bladder, rectum, and sigmoid), a mask indicating dwell position locations, and applicator channels for each applicator component. Applicator channels were created by mapping the 3D dose for a single dwell position to each dwell position and summing over each applicator component with uniform dwell time weighting. A 3D Cascade U-Net, which consists of two U-Nets in sequence, and mean squared error loss function were used. The combined model was then fine-tuned to produce four applicator-specific models by freezing the first U-Net and encoding layers of the second and resuming training on applicator-specific data. Finally, four IDV models were trained using only data from each applicator type. Performance of these three model types was compared using the following metrics for the test set: mean error (ME, representing model bias) and mean absolute error (MAE) over all dose voxels and ME of clinical metrics (HRCTV D90% and D2cc of bladder, rectum, and sigmoid), averaged over all patients. A positive ME indicates the clinical dose was higher than predicted. 3D global gamma analysis with the prescription dose as reference value was performed. Dice similarity coefficients (DSC) were computed for each isodose volume.

RESULTS: Fine-tuned and combined models showed better performance than IDV applicator training. Fine-tuning resulted in modest improvements in about half the metrics, compared to the combined model, while the remainder were mostly unchanged. Fine-tuned MAE = 3.98%/2.69%/5.36%/3.80% for T&O/T&R/T&ON/T&RN, and ME over all voxels = -0.08%/-0.89%/-0.59%/1.42%. ME D2cc were bladder = -0.77%/1.00%/-0.66%/-1.53%, rectum = 1.11%/-0.22%/-0.29%/-3.37%, sigmoid = -0.47%/-0.06%/-2.37%/-1.40%, and ME D90 = 2.6%/-4.4%/4.8%/0.0%. Gamma pass rates (3%/3 mm) were 86%/91%/83%/89%. Mean DSCs were 0.92%/0.92%/0.88%/0.91% for isodoses ≤ 150% of prescription.

CONCLUSIONS: 3D BT dose was accurately predicted for all applicator types, as indicated by the low MAE and MEs, high gamma scores and high DSCs. Training on all treatment data overcomes challenges with data scarcity in each applicator type, resulting in superior performance than can be achieved by training on IDV applicators alone. This could presumably be explained by the fact that the larger, more diverse dataset allows the neural network to learn underlying trends and characteristics in dose that are common to all treatment applicators. Accurate, applicator-specific dose predictions could enable automated, knowledge-based planning for any cervical brachytherapy treatment.

PMID:38814165 | DOI:10.1002/mp.17230

J Am Med Inform Assoc. 2024 May 30:ocae108. doi: 10.1093/jamia/ocae108. Online ahead of print.

ABSTRACT

OBJECTIVES: Medical research faces substantial challenges from noisy labels attributed to factors like inter-expert variability and machine-extracted labels. Despite this, the adoption of label noise management remains limited, and label noise is largely ignored. To this end, there is a critical need to conduct a scoping review focusing on the problem space. This scoping review aims to comprehensively review label noise management in deep learning-based medical prediction problems, which includes label noise detection, label noise handling, and evaluation. Research involving label uncertainty is also included.

METHODS: Our scoping review follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We searched 4 databases, including PubMed, IEEE Xplore, Google Scholar, and Semantic Scholar. Our search terms include "noisy label AND medical/healthcare/clinical," "uncertainty AND medical/healthcare/clinical," and "noise AND medical/healthcare/clinical."

RESULTS: A total of 60 papers met inclusion criteria between 2016 and 2023. A series of practical questions in medical research are investigated. These include the sources of label noise, the impact of label noise, the detection of label noise, label noise handling techniques, and their evaluation. Categorization of both label noise detection methods and handling techniques are provided.

DISCUSSION: From a methodological perspective, we observe that the medical community has been up to date with the broader deep-learning community, given that most techniques have been evaluated on medical data. We recommend considering label noise as a standard element in medical research, even if it is not dedicated to handling noisy labels. Initial experiments can start with easy-to-implement methods, such as noise-robust loss functions, weighting, and curriculum learning.

PMID:38814164 | DOI:10.1093/jamia/ocae108

J Phys Chem Lett. 2024 May 30:5978-5984. doi: 10.1021/acs.jpclett.4c01111. Online ahead of print.

ABSTRACT

Recent decades have witnessed the rapid development of autonomous laboratories and artificial intelligence, where experiments can be automatically run and optimized. Although human work is reduced, the total time of experimental optimization is still consuming due to limitations of the current ab metaverse framework, which accurately predicts the future state of the system by receiving and analyzing in situ experimental data. To substitute for traditional simulation methods, we designed a physically endorsed deep learning model to predict the future system picture ranging from atomic image to bulk appearance, intensively using the correlations between properties of the system. Through this framework, we studied the general aqueous system, covering 100+ common ionic solutions. We can accurately simulate properties for a general aqueous system as well as predict the time of solvation of ionic compounds ahead of real experiments. In this way, the experiments can be optimized more efficiently without waiting for the end of a bad iteration. We hope our work offers a fresh direction for the digitization of chemical information, enhancing access to and use of experimental data in advancing the field of physical chemistry.

PMID:38814104 | DOI:10.1021/acs.jpclett.4c01111

Front Aging Neurosci. 2024 May 15;16:1356745. doi: 10.3389/fnagi.2024.1356745. eCollection 2024.

ABSTRACT

OBJECTIVES: Accurately predicting when patients with mild cognitive impairment (MCI) will progress to dementia is a formidable challenge. This work aims to develop a predictive deep learning model to accurately predict future cognitive decline and magnetic resonance imaging (MRI) marker changes over time at the individual level for patients with MCI.

METHODS: We recruited 657 amnestic patients with MCI from the Samsung Medical Center who underwent cognitive tests, brain MRI scans, and amyloid-β (Aβ) positron emission tomography (PET) scans. We devised a novel deep learning architecture by leveraging an attention mechanism in a recurrent neural network. We trained a predictive model by inputting age, gender, education, apolipoprotein E genotype, neuropsychological test scores, and brain MRI and amyloid PET features. Cognitive outcomes and MRI features of an MCI subject were predicted using the proposed network.

RESULTS: The proposed predictive model demonstrated good prediction performance (AUC = 0.814 ± 0.035) in five-fold cross-validation, along with reliable prediction in cognitive decline and MRI markers over time. Faster cognitive decline and brain atrophy in larger regions were forecasted in patients with Aβ (+) than with Aβ (-).

CONCLUSION: The proposed method provides effective and accurate means for predicting the progression of individuals within a specific period. This model could assist clinicians in identifying subjects at a higher risk of rapid cognitive decline by predicting future cognitive decline and MRI marker changes over time for patients with MCI. Future studies should validate and refine the proposed predictive model further to improve clinical decision-making.

PMID:38813529 | PMC:PMC11135285 | DOI:10.3389/fnagi.2024.1356745

Front Med (Lausanne). 2024 May 14;11:1421603. doi: 10.3389/fmed.2024.1421603. eCollection 2024.

ABSTRACT

[This corrects the article DOI: 10.3389/fmed.2023.1217037.].

PMID:38813378 | PMC:PMC11135626 | DOI:10.3389/fmed.2024.1421603

Heliyon. 2024 May 16;10(10):e30958. doi: 10.1016/j.heliyon.2024.e30958. eCollection 2024 May 30.

ABSTRACT

In this work, we present a method for optical frequency multiplication utilizing a hybrid deep learning approach that integrates the Residual Network (ResNet) with the Random Forest Regression (RFR) algorithm. Three different frequency multiplication modulation schemes are adopted to illustrate the method, which can obtain suitable parameters for these schemes. Based on the parameters predicted by the algorithm, the 8-tupling, 12-tupling, and 16-tupling mm-wave signals are generated by numerical simulation. The simulation results show that for 8-tupling frequency multiplication, an OSSR (optical sideband suppression ratio) is 30.73 dB and an RFSSR (radio frequency spurious suppression ratio) of 80 GHz is 42.29 dB. For 12-tupling frequency multiplication, the OSSR is 30.09 dB, and the RFSSR of the 120 GHz mm wave is 36.21 dB. For generating 16-tupling frequency mm-wave, an OSSR of 29.86 dB and an RFSSR of 34.52 dB are obtained. In addition, the impact of amplitude fluctuation and bias voltage drift on the quality of mm-wave signals is also studied.

PMID:38813222 | PMC:PMC11133761 | DOI:10.1016/j.heliyon.2024.e30958

Front Bioeng Biotechnol. 2024 May 14;12:1397003. doi: 10.3389/fbioe.2024.1397003. eCollection 2024.

ABSTRACT

BACKGROUND: Digital radiography (DR) is a common and widely available examination. However, spinal DR cannot detect bone marrow edema, therefore, determining vertebral compression fractures (VCFs), especially fresh VCFs, remains challenging for clinicians.

METHODS: We trained, validated, and externally tested the deep residual network (DRN) model that automated the detection and identification of fresh VCFs from spinal DR images. A total of 1,747 participants from five institutions were enrolled in this study and divided into the training cohort, validation cohort and external test cohorts (YHDH and BMUH cohorts). We evaluated the performance of DRN model based on the area under the receiver operating characteristic curve (AUC), feature attention maps, sensitivity, specificity, and accuracy. We compared it with five other deep learning models and validated and tested the model internally and externally and explored whether it remains highly accurate for an external test cohort. In addition, the influence of old VCFs on the performance of the DRN model was assessed.

RESULTS: The AUC was 0.99, 0.89, and 0.88 in the validation, YHDH, and BMUH cohorts, respectively, for the DRN model for detecting and discriminating fresh VCFs. The accuracies were 81.45% and 72.90%, sensitivities were 84.75% and 91.43%, and specificities were 80.25% and 63.89% in the YHDH and BMUH cohorts, respectively. The DRN model generated correct activation on the fresh VCFs and accurate peak responses on the area of the target vertebral body parts and demonstrated better feature representation learning and classification performance. The AUC was 0.90 (95% confidence interval [CI] 0.84-0.95) and 0.84 (95% CI 0.72-0.93) in the non-old VCFs and old VCFs groups, respectively, in the YHDH cohort (p = 0.067). The AUC was 0.89 (95% CI 0.84-0.94) and 0.85 (95% CI 0.72-0.95) in the non-old VCFs and old VCFs groups, respectively, in the BMUH cohort (p = 0.051).

CONCLUSION: In present study, we developed the DRN model for automated diagnosis and identification of fresh VCFs from spinal DR images. The DRN model can provide interpretable attention maps to support the excellent prediction results, which is the key that most clinicians care about when using the model to assist decision-making.

PMID:38812917 | PMC:PMC11135169 | DOI:10.3389/fbioe.2024.1397003

Digit Health. 2024 May 27;10:20552076241258079. doi: 10.1177/20552076241258079. eCollection 2024 Jan-Dec.

ABSTRACT

OBJECTIVE: Acute leukemia (AL) is a life-threatening malignant disease that occurs in the bone marrow and blood, and is classified as either acute myeloid leukemia (AML) or acute lymphoblastic leukemia (ALL). Diagnosing AL warrants testing methods, such as flow cytometry, which require trained professionals, time, and money. We aimed to develop a model that can classify peripheral blood images of 12 cell types, including pathological cells associated with AL, using artificial intelligence.

METHODS: We acquired 42,386 single-cell images of peripheral blood slides from 282 patients (82 with AML, 40 with ALL, and 160 with immature granulocytes).

RESULTS: The performance of EfficientNet-V2 (B2) using the original image size exhibited the greatest accuracy (accuracy, 0.8779; precision, 0.7221; recall, 0.7225; and F1 score, 0.7210). The next-best accuracy was achieved by EfficientNet-V1 (B1), with a 256 × 256 pixels image. F1 score was the greatest for EfficientNet-V1 (B1) with the original image size. EfficientNet-V1 (B1) and EfficientNet-V2 (B2) were used to develop an ensemble model, and the accuracy (0.8858) and F1 score (0.7361) were improved. The classification performance of the developed ensemble model for the 12 cell types was good, with an area under the receiver operating characteristic curve above 0.9, and F1 scores for myeloblasts and lymphoblasts of 0.8873 and 0.8006, respectively.

CONCLUSIONS: The performance of the developed ensemble model for the 12 cell classifications was satisfactory, particularly for myeloblasts and lymphoblasts. We believe that the application of our model will benefit healthcare settings where the rapid and accurate diagnosis of AL is difficult.

PMID:38812848 | PMC:PMC11135107 | DOI:10.1177/20552076241258079