Acta Radiol Open. 2024 Nov 30;13(11):20584601241297530. doi: 10.1177/20584601241297530. eCollection 2024 Nov.

ABSTRACT

BACKGROUND: Extensor Carpi Ulnaris (ECU) tendinosis, a frequent cause of chronic wrist pain, requires prompt diagnosis to prevent disability. This study demonstrates the use of convolutional neural networks (CNNs) for automated detection and segmentation of the ECU tendon and tendinosis in 2D axial wrist MRI.

PURPOSE: To develop a CNN for the automated detection of ECU tendon and automatic delineation of tendinosis in 2D wrist MRI. The study serves as a proof-of-concept, demonstrating the feasibility of automating the segmentation of musculoskeletal structures in wrist MRI and offering an efficient solution for detecting tendinosis.

MATERIAL AND METHODS: In a retrospective analysis of 1081 patients undergoing wrist MRI imaging, 46 patients exhibited tendinosis. Two deep learning-based methods for segmenting the ECU tendon and T2 hyperintense lesions indicative of tendinosis from 2D axial wrist MRI series were developed and compared in this study. Both methods were trained and evaluated over all 46 patients using Dice score as the main evaluation metric.

RESULTS: The mean ECU tendon segmentation Dice score ranged from 0.61 to 0.64 (± 0.27 to 0.31). Tendinosis detection yielded a Dice score of 0.38 for both the threshold method (±0.19) and the CNN (±0.22). A Dice score > 0.50 indicated successful detection, with our methods achieving a detection rate of 72-76%.

CONCLUSION: The developed CNN effectively detected and segmented the ECU tendon in 2D MRI series. Tendinosis was detected with comparable accuracy using both signal intensity thresholding and the trained CNN method.

PMID:39624259 | PMC:PMC11608437 | DOI:10.1177/20584601241297530

Comput Struct Biotechnol J. 2024 Nov 14;23:4124-4130. doi: 10.1016/j.csbj.2024.11.028. eCollection 2024 Dec.

ABSTRACT

Although over 300 million protein sequences are registered in a reference sequence database, only 0.2 % have experimentally determined functions. This suggests that many valuable proteins, potentially catalyzing novel enzymatic reactions, remain undiscovered among the vast number of function-unknown proteins. In this study, we developed a method to predict whether two proteins catalyze the same enzymatic reaction by analyzing sequence and structural similarities, utilizing structural models predicted by AlphaFold2. We performed pocket detection and domain decomposition for each structural model. The similarity between protein pairs was assessed using features such as full-length sequence similarity, domain structural similarity, and pocket similarity. We developed several models using conventional machine learning algorithms and found that the LightGBM-based model outperformed the models. Our method also surpassed existing approaches, including those based solely on full-length sequence similarity and state-of-the-art deep learning models. Feature importance analysis revealed that domain sequence identity, calculated through structural alignment, had the greatest influence on the prediction. Therefore, our findings demonstrate that integrating sequence and structural information improves the accuracy of protein function prediction.

PMID:39624166 | PMC:PMC11609699 | DOI:10.1016/j.csbj.2024.11.028

Genome Res. 2024 Dec 2:gr.278812.123. doi: 10.1101/gr.278812.123. Online ahead of print.

ABSTRACT

Application of single-cell/nucleus genomic sequencing to patient-derived tissues offers potential solutions to delineate disease mechanisms in human. However, individual cells in patient-derived tissues are in different pathological stages, and hence such cellular variability impedes subsequent differential gene expression analyses. To overcome such heterogeneity issue, we present a novel deep learning approach, scIDST, that infers disease progressive levels of individual cells with weak supervision framework. The inferred disease progressive cells displayed significant differential expression of disease-relevant genes, which could not be detected by comparative analysis between patients and healthy donors. In addition, we demonstrated that pretrained models by scIDST are applicable to multiple independent data resources, and advantageous to infer cells related to certain disease risks and comorbidities. Taken together, scIDST offers a new strategy of single-cell sequencing analysis to identify bona fide disease-associated molecular features.

PMID:39622637 | DOI:10.1101/gr.278812.123

BMJ Open. 2024 Dec 2;14(12):e086896. doi: 10.1136/bmjopen-2024-086896.

ABSTRACT

OBJECTIVES: To assess the current state-of-the-art in deep learning methods applied to pre-operative radiologic staging of colorectal cancer lymph node metastasis. Specifically, by evaluating the data, methodology and validation of existing work, as well as the current use of explainable AI in this fast-moving domain.

DESIGN: Scoping review.

DATA SOURCES: Academic databases MEDLINE, Embase, Scopus, IEEE Xplore, Web of Science and Google Scholar were searched with a date range of 1 January 2018 to 1 February 2024.

ELIGIBILITY CRITERIA: Includes any English language research articles or conference papers published since 2018 which have applied deep learning methods for feature extraction and classification of colorectal cancer lymph nodes on pre-operative radiologic imaging.

DATA EXTRACTION AND SYNTHESIS: Key results and characteristics for each included study were extracted using a shared template. A narrative synthesis was then conducted to qualitatively integrate and interpret these findings.

RESULTS: This scoping review covers 13 studies which met the inclusion criteria. The deep learning methods had an area under the curve score of 0.856 (0.796 to 0.916) for patient-level lymph node diagnosis and 0.904 (0.841 to 0.967) for individual lymph node assessment, given with a 95% confidence interval. Most studies have fundamental limitations including unrepresentative data, inadequate methodology, poor model validation and limited explainability techniques.

CONCLUSIONS: Deep learning methods have demonstrated the potential for accurately diagnosing colorectal cancer lymph nodes using pre-operative radiologic imaging. However, several methodological and validation flaws such as selection bias and lack of external validation make it difficult to trust the results. This review has uncovered a research gap for robust, representative and explainable deep learning methods that are end-to-end from automatic lymph node detection to the diagnosis of lymph node metastasis.

PMID:39622569 | DOI:10.1136/bmjopen-2024-086896

Clin Res Hepatol Gastroenterol. 2024 Nov 30:102509. doi: 10.1016/j.clinre.2024.102509. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVES: Deep learning (DL) algorithms demonstrate excellent diagnostic performance for the detection of vascular lesions via small bowel (SB) capsule endoscopy (CE), including vascular abnormalities with high (P2), intermediate (P1) or low (P0) bleeding potential, while dramatically decreasing the reading time. We aimed to improve the performance of a DL algorithm by characterizing vascular abnormalities using a machine learning (ML) classifier, and selecting the most relevant images for insertion into reports.

MATERIALS AND METHODS: A training dataset of 75 SB CE videos was created, containing 401 sequences of interest that encompassed 1,525 images of various vascular lesions. Several image classification algorithms were tested, to discriminate "typical angiodysplasia" (P2/P1) and "other vascular lesion" (P0) and to select the most relevant image within sequences with repetitive images. The performances of the best-fitting algorithms were subsequently assessed on an independent test dataset of 73 full-length SB CE video recordings.

RESULTS: Following DL detection, a random forest (RF) method demonstrated a specificity of 91.1%, an area under the receiving operating characteristic curve of 0.873, and an accuracy of 84.2% for discriminating P2/P1 from P0 lesions while allowing an 83.2% reduction in the number of reported images. In the independent testing database, after RF was applied, the output number decreased by 91.6%, from 216 (IQR 108-432) to 12 (IQR 5-33). The RF algorithm achieved 98% agreement with initial, conventional (human) reporting. Following DL detection, the RF method allowed better characterization and accurate selection of images of relevant (P2/P1) SB vascular abnormalities for CE reporting without impairing diagnostic accuracy. These findings pave the way for automated SB CE reporting.

PMID:39622290 | DOI:10.1016/j.clinre.2024.102509

EBioMedicine. 2024 Dec 1;110:105467. doi: 10.1016/j.ebiom.2024.105467. Online ahead of print.

ABSTRACT

BACKGROUND: Manually extracted imaging-based body composition measures from a single-slice area (A) have shown associations with clinical outcomes in patients with cardiometabolic disease and cancer. With advances in artificial intelligence, fully automated volumetric (V) segmentation approaches are now possible, but it is unknown whether these measures carry prognostic value to predict mortality in the general population. Here, we developed and tested a deep learning framework to automatically quantify volumetric body composition measures from whole-body magnetic resonance imaging (MRI) and investigated their prognostic value to predict mortality in a large Western population.

METHODS: The framework was developed using data from two large Western European population-based cohort studies, the UK Biobank (UKBB) and the German National Cohort (NAKO). Body composition was defined as (i) subcutaneous adipose tissue (SAT), (ii) visceral adipose tissue (VAT), (iii) skeletal muscle (SM), SM fat fraction (SMFF), and (iv) intramuscular adipose tissue (IMAT). The prognostic value of the body composition measures was assessed in the UKBB using Cox regression analysis. Additionally, we extracted body composition areas for every level of the thoracic and lumbar spine (i) to compare the proposed volumetric whole-body approach to the currently established single-slice area approach on the height of the L3 vertebra and (ii) to investigate the correlation between volumetric and single slice area body composition measures on the level of each vertebral body.

FINDINGS: In 36,317 UKBB participants (mean age 65.1 ± 7.8 years, age range 45-84 years; 51.7% female; 1.7% [634/36,471] all-cause deaths; median follow-up 4.8 years), Cox regression revealed an independent association between VSM (adjusted hazard ratio [aHR]: 0.88, 95% confidence interval [CI] [0.81-0.91], p = 0.00023), VSMFF (aHR: 1.06, 95% CI [1.02-1.10], p = 0.0043), and VIMAT (aHR: 1.19, 95% CI [1.05-1.35], p = 0.0056) and mortality after adjustment for demographics (age, sex, BMI, race) and cardiometabolic risk factors (alcohol consumption, smoking status, hypertension, diabetes, history of cancer, blood serum markers). This association was attenuated when using traditional single-slice area measures. Highest correlation coefficients (R) between volumetric and single-slice area body composition measures were located at vertebra L5 for SAT (R = 0.820) and SMFF (R = 0.947), at L3 for VAT (R = 0.892), SM (R = 0.944), and at L4 for IMAT (R = 0.546) (all p < 0.0001). A similar pattern was found in 23,725 NAKO participants (mean age 53.9 ± 8.3 years, age range 40-75; 44.9% female).

INTERPRETATION: Automated volumetric body composition assessment from whole-body MRI predicted mortality in a large Western population beyond traditional clinical risk factors. Single slice areas were highly correlated with volumetric body composition measures but their association with mortality attenuated after multivariable adjustment. As volumetric body composition measures are increasingly accessible using automated techniques, identifying high-risk individuals may help to improve personalised prevention and lifestyle interventions.

FUNDING: This project was conducted using data from the German National Cohort (NAKO) (www.nako.de). The NAKO is funded by the Federal Ministry of Education and Research (BMBF) [project funding reference numbers: 01ER1301A/B/C, 01ER1511D, and 01ER1801A/B/C/D], federal states of Germany and the Helmholtz Association, the participating universities and the institutes of the Leibniz Association. This research has been conducted using the UK Biobank Resource under Application Number 80337. MJ was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)-518480401. VKR was funded by American Heart Association Career Development Award 935176 and National Heart, Lung, and Blood Institute-K01HL168231.

PMID:39622188 | DOI:10.1016/j.ebiom.2024.105467

J Transl Med. 2024 Dec 2;22(1):1090. doi: 10.1186/s12967-024-05818-z.

ABSTRACT

BACKGROUND: Tumor Budding (TB) and Immunoscore are independent prognostic markers in colon cancer (CC). Given their respective representation of tumor aggressiveness and immune response, we examined their combination in association with patient disease-free survival (DFS) in pTNM stage I-III CC.

METHODS: In a series of pTNM stage I-III CCs (n = 654), the Immunoscore was computed and TB detected automatically using a deep learning network. Two-tiered systems for both biomarkers were used with cut-offs of 25% and ten buds for Immunoscore and TB according to clinical guidelines, respectively. Associations of Immunoscore with TB with 5-year DFS were examined using Kaplan-Meier survival analysis in addition to multivariable modeling and relative contribution analysis using Cox regression.

RESULTS: Immunoscore and TB independently are prognostic with hazard ratio (HR) = 2.0, 95% confidence interval (CI) 1.4-2.8 and HR 2.5, with 95% CI 1.4-4.5, respectively; P value < 0.0001. By combining Immunoscore with TB, patients with Immunoscore Low, TB High tumors had a significantly poorer DFS (HR 5.6, 95% CI 2.6-12.0; P value < 0.0001) than those with Immunoscore High, TB Low tumors. The combined Immunoscore with TB score was independently prognostic (P value = 0.009) in comparison to N-stage, T-stage, and MSI. Immunoscore with TB had the highest relative contribution (35%) to DFS in pTNM stage I-II CCs.

CONCLUSIONS: The association of Immunoscore and TB with patient survival suggests that both biomarkers are complementary and should be interpreted in combination to identify high-risk Stage I-II patients who should be considered for adjuvant therapy or further diagnostic testing.

PMID:39623479 | DOI:10.1186/s12967-024-05818-z

Surg Endosc. 2024 Dec 2. doi: 10.1007/s00464-024-11426-1. Online ahead of print.

ABSTRACT

BACKGROUND: Deficient mismatch repair or microsatellite instability is a major predictive biomarker for the efficacy of immune checkpoint inhibitors of colorectal cancer. However, routine testing has not been uniformly implemented due to cost and resource constraints.

METHODS: We developed and validated a deep learning-based classifiers to detect mismatch repair-deficient status from routine colonoscopy images. We obtained the colonoscopy images from the imaging database at Endoscopic Center of the Sixth Affiliated Hospital, Sun Yat-sen University. Colonoscopy images from a prospective trial (Neoadjuvant PD-1 blockade by toripalimab with or without celecoxib in mismatch repair-deficient or microsatellite instability-high locally advanced colorectal cancer) were used to test the model.

RESULTS: A total of 5226 eligible images from 892 tumors from the consecutive patients were utilized to develop and validate the deep learning model. 2105 colorectal cancer images from 306 tumors were randomly selected to form model development dataset with a class-balanced approach. 3121 images of 488 proficient mismatch repair tumors and 98 deficient mismatch repair tumors were used to form the independent dataset. The model achieved an AUROC of 0.948 (95% CI 0.919-0.977) on the test dataset. On the independent validation dataset, the AUROC was 0.807 (0.760-0.854), and the NPV in was 94.2% (95% CI 0.918-0.967). On the prospective trial dataset, the model identified 29 tumors among the 33 deficient mismatch repair tumors (87.88%).

CONCLUSIONS: The model achieved a high NPV in detecting deficient mismatch repair colorectal cancers. This model might serve as an automatic screening tool.

PMID:39623175 | DOI:10.1007/s00464-024-11426-1

Sci Rep. 2024 Dec 2;14(1):29888. doi: 10.1038/s41598-024-81587-5.

ABSTRACT

Timely and accurate detection of rice pests is highly important for pest control, as well as for improving rice yield and quality. However, owing to the high interclass similarity, significant intraclass age differences, and complex backgrounds among different pests, accurately and rapidly identifying a variety of rice pests via deep neural network models poses a significant challenge. To address this issue, this paper presents a fast and accurate method for rice pest detection and identification named Rice-YOLO (You Only Look Once). This model is based on YOLOv8-N and incorporates an efficient detection head designed for the complex characteristics of pests. Additionally, deep supervision layers were introduced into the network, along with the incorporation and improvement of the dynamic upsampling module. The experimental data included the large-scale pest public dataset IP102 and the sixteen-class rice pest dataset R2000. The experimental results demonstrated that Rice-YOLO outperformed previous object detection algorithms, with 78.1% mAP@0.5, 62.9% mAP@0.5:0.95, and 74.3% F1 scores.

PMID:39623058 | DOI:10.1038/s41598-024-81587-5

Sci Rep. 2024 Dec 2;14(1):29966. doi: 10.1038/s41598-024-81377-z.

ABSTRACT

The extension of human spaceflight across an ever-expanding domain, in conjunction with intricate mission architectures demands a paradigm shift in autonomous navigation algorithms, especially for the powered descent phase of planetary landing. Deep learning architectures have previously been explored to perform low-dimensional localization with limited success. Due to the expectations regarding novel algorithms in the context of real missions, the proposed approaches must be rigorously evaluated in extraneous scenarios and demonstrate sufficient robustness. In the current work, a novel formulation is proposed to train CNN-based Deep Learning (DL) models in a multi-layer cascading architecture and utilize the resulting classification probabilities as regression weights to estimate the position of the lander spacecraft. The approach leverages image intensity and depth data provided by multiple sensors on board to accurately determine the spacecraft's location relative to the observed terrain at a specific altitude. Navigation performance is validated through Monte Carlo analysis, demonstrating the efficacy of the proposed DL architecture and the subsequent state-estimation framework across several simulated scenarios. It shows tremendous promise in extending the multi-modal feature learning approach to realistic missions.

PMID:39623052 | DOI:10.1038/s41598-024-81377-z

NPJ Precis Oncol. 2024 Dec 2;8(1):276. doi: 10.1038/s41698-024-00775-8.

ABSTRACT

Nuclear atypia is a hallmark of cancer. A recent model posits that excess surface area, visible as folds/wrinkles in the lamina of a rounded nucleus, allows the nucleus to take on diverse shapes with little mechanical resistance. Whether this model is applicable to normal and cancer nuclei in human tissues is unclear. We image nuclear lamins in patient tissues and find: (a) nuclear laminar wrinkles are present in control and cancer tissue but are obscured in hematoxylin and eosin (H&E) images, (b) nuclei rarely have a smooth lamina, and (c) wrinkled nuclei assume diverse shapes. Deep learning reveals the presence of extreme nuclear laminar wrinkling in cancer tissues, which is confirmed by Fourier analysis. These data support a model in which excess surface area in the nuclear lamina enables nuclear shape diversity in vivo. Extreme laminar wrinkling is a marker of cancer, and imaging the lamina may benefit cancer diagnosis.

PMID:39623008 | DOI:10.1038/s41698-024-00775-8

Sci Rep. 2024 Dec 2;14(1):29898. doi: 10.1038/s41598-024-81868-z.

ABSTRACT

This study aims to utilize deep learning technology to optimize rural tourism image, enhance visitor experience, and promote sustainable development. By deploying sensors for real-time monitoring of the environment and visitor flow in rural scenic areas, combined with a Dense Convolutional Neural Network (DenseNet), automatic identification and analysis of rural landscapes are achieved. Using rural tourism along the Yellow River as a case study, this study constructs a tourism image evaluation and optimization model based on big data. The results indicate that the model performs excellently in terms of accuracy and robustness, significantly improving the presentation of rural tourism images. The study shows that realism and service facilities have the greatest impact on rural tourism image, underscoring the value of technological means in optimizing the rural tourism image.

PMID:39622993 | DOI:10.1038/s41598-024-81868-z

Sci Rep. 2024 Dec 2;14(1):29875. doi: 10.1038/s41598-024-81506-8.

ABSTRACT

The latest advancements of deep learning have resulted in a new era of natural language processing. The machines now possess an unparallel ability to interpret and engage with various tasks such as text classification, content generation and natural language understanding. This development extended to the analysis of human behavior, where deep learning models are used to decode human personality. Due to the rise of social media, generating huge amounts of textual data that reshaped communication patterns. Understanding personality traits is a challenging topic which helps us to explore the patterns of thoughts, feelings and behaviors which are helpful for recruitment, career counselling and consumers' behavior for marketing, etc. In this research study, the main aim is to predict the human personality trait of agreeableness showing whether a person is emotional who feels a lot or thinker who is logical and has rational thinking. This behavior leads to analyzing them as cooperative, friendly and respecting difference of views. For comprehensive empirical analysis, shallow machine learning models, ensemble models, and deep learning technique including state of the art transformer-based models are applied on real-world dataset of MBTI. For feature engineering, textual features of TF-IDF and POS tagging and word embeddings such as word2vec, glove and sentence embeddings are explored. The results analysis shows the highest performance 91.57% with sentence embeddings utilizing Bi-LSTM algorithm that highlights the power of this study as compared to existing studies in the relevant literature.

PMID:39622946 | DOI:10.1038/s41598-024-81506-8

Sci Rep. 2024 Dec 2;14(1):29923. doi: 10.1038/s41598-024-78626-6.

ABSTRACT

Pandemics like COVID-19 have a huge impact on human society and the global economy. Vaccines are effective in the fight against these pandemics but often in limited supplies, particularly in the early stages. Thus, it is imperative to distribute such crucial public goods efficiently. Identifying and vaccinating key spreaders (i.e., influential nodes) is an effective approach to break down the virus transmission network, thereby inhibiting the spread of the virus. Previous methods for identifying influential nodes in networks lack consistency in terms of effectiveness and precision. Their applicability also depends on the unique characteristics of each network. Furthermore, most of them rank nodes by their individual influence in the network without considering mutual effects among them. However, in many practical settings like vaccine distribution, the challenge is how to select a group of influential nodes. This task is more complex due to the interactions and collective influence of these nodes together. This paper introduces a new framework integrating Graph Neural Network (GNN) and Deep Reinforcement Learning (DRL) for vaccination distribution. This approach combines network structural learning with strategic decision-making. It aims to efficiently disrupt the network structure and stop disease spread through targeting and removing influential nodes. This method is particularly effective in complex environments, where traditional strategies might not be efficient or scalable. Its effectiveness is tested across various network types including both synthetic and real-world datasets, demonstrting a potential for real-world applications in fields like epidemiology and cybersecurity. This interdisciplinary approach shows the capabilities of deep learning in understanding and manipulating complex network systems.

PMID:39622907 | DOI:10.1038/s41598-024-78626-6

Sci Rep. 2024 Dec 2;14(1):29877. doi: 10.1038/s41598-024-80691-w.

ABSTRACT

Diabetes foot ulcer (DFU) is one of the common complications of diabetes patients, which may lead to infection, necrosis and even amputation. Therefore, early diagnosis, classification of severity and related treatment are crucial for the patients. Current DFU classification methods often require experienced doctors to manually classify the severity, which is time-consuming and low accuracy. The objective of the study is to propose a few-shot DFU image classification method based on deep residual neural network and transfer learning. Considering the difficulty in obtaining clinical DFU images, it is a few-shot problem. Therefore, the methods include: (1) Data augmentation of the original DFU images by using geometric transformations and random noise; (2) Deep ResNet models selection based on different convolutional layers comparative experiments; (3) DFU classification model training with transfer learning by using the selected pre-trained ResNet model and fine tuning. To verify the proposed classification method, the experiments were performed with the original and augmented datasets by separating three classifications: zero grade, mild grade, severe grade. (1) The datasets were augmented from the original 146 to 3000 image datasets and the corresponding DFU classification's average accuracy from 0.9167 to 0.9867; (2) Comparative experiments were conducted with ResNet18, ResNet34, ResNet50, ResNet101, ResNet152 by using 3000 image datasets, and the average accuracy/loss is 0.9325/0.2927, 0.9276/0.3234, 0.9901/0.1356, 0.9865/0.1427, 0.9790/0.1583 respectively; (3) Based on the augmented 3000 image datasets, it was achieved 0.9867 average accuracy with the DFU classification model, which was trained by the pre-trained ResNet50 and hyper-parameters. The experimental results indicated that the proposed few-shot DFU image classification method based on deep ResNet and transfer learning got very high accuracy, and it is expected to be suitable for low-cost and low-computational terminal equipment, aiming at helping clinical DFU classification efficiently and auxiliary diagnosis.

PMID:39622873 | DOI:10.1038/s41598-024-80691-w

JMIR Med Inform. 2024 Nov 21;12:e60334. doi: 10.2196/60334.

ABSTRACT

BACKGROUND: Clinical named entity recognition (CNER) is a fundamental task in natural language processing used to extract named entities from electronic medical record texts. In recent years, with the continuous development of machine learning, deep learning models have replaced traditional machine learning and template-based methods, becoming widely applied in the CNER field. However, due to the complexity of clinical texts, the diversity and large quantity of named entity types, and the unclear boundaries between different entities, existing advanced methods rely to some extent on annotated databases and the scale of embedded dictionaries.

OBJECTIVE: This study aims to address the issues of data scarcity and labeling difficulties in CNER tasks by proposing a dataset augmentation algorithm based on proximity word calculation.

METHODS: We propose a Segmentation Synonym Sentence Synthesis (SSSS) algorithm based on neighboring vocabulary, which leverages existing public knowledge without the need for manual expansion of specialized domain dictionaries. Through lexical segmentation, the algorithm replaces new synonymous vocabulary by recombining from vast natural language data, achieving nearby expansion expressions of the dataset. We applied the SSSS algorithm to the Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach (RoBERTa) + conditional random field (CRF) and RoBERTa + Bidirectional Long Short-Term Memory (BiLSTM) + CRF models and evaluated our models (SSSS + RoBERTa + CRF; SSSS + RoBERTa + BiLSTM + CRF) on the China Conference on Knowledge Graph and Semantic Computing (CCKS) 2017 and 2019 datasets.

RESULTS: Our experiments demonstrated that the models SSSS + RoBERTa + CRF and SSSS + RoBERTa + BiLSTM + CRF achieved F1-scores of 91.30% and 91.35% on the CCKS-2017 dataset, respectively. They also achieved F1-scores of 83.21% and 83.01% on the CCKS-2019 dataset, respectively.

CONCLUSIONS: The experimental results indicated that our proposed method successfully expanded the dataset and remarkably improved the performance of the model, effectively addressing the challenges of data acquisition, annotation difficulties, and insufficient model generalization performance.

PMID:39622697 | DOI:10.2196/60334

Biomed Phys Eng Express. 2024 Dec 2. doi: 10.1088/2057-1976/ad992c. Online ahead of print.

ABSTRACT

The prediction of epileptic seizures is a classical research problem, representing one of the most challenging tasks in the analysis of brain disorders. There is active research into digital twins (DT) for various healthcare applications, as they can transform research into customized and personalized healthcare. The widespread adoption of DT technology relies on ample patient data to ensure precise monitoring and decision-making, leveraging Machine Learning (ML) and Deep Learning (DL) algorithms. Given the non-stationarity of EEG recordings, characterized by substantial frequency variations over time, there is a notable preference for advanced time-frequency methods in seizure prediction. This research proposes a DT-based seizure prediction system by applying an advanced time-frequency analysis approach known as Time-Reassigned MultiSynchroSqueezing Transform (TMSST) to EEG data to extract patient-specific impulse features and subsequently, a Deep Learning strategy, CNN-BiLSTM-Attention mechanism model is utilized in learning and classifying features for seizure prediction. The proposed architecture is named as "Digital Twin-Net". By estimating the group delay in the time direction, TMSST produces the frequency components that are responsible for the EEG signal's temporal behavior and those time-frequency signatures are learned by the developed CNN-BiLSTM-Attention mechanism model. Thus the combination acts as a digital twin of a patient for the prediction of epileptic seizures. The experimental results showed that the suggested approach achieved an accuracy of 99.70% when tested on 23 patients from the publicly accessible CHB-MIT dataset. The proposed method surpasses previous solutions in terms of overall performance. Consequently, the suggested method can be regarded as an efficient approach to EEG seizure prediction.&#xD.

PMID:39622083 | DOI:10.1088/2057-1976/ad992c

Biomed Phys Eng Express. 2024 Dec 2. doi: 10.1088/2057-1976/ad992d. Online ahead of print.

ABSTRACT

Smartphone-assisted urine analyzers estimate the urinary albumin by quantifying color changes at sensor pad of test strips. These strips yield color variations due to the total protein present in the sample, making it difficult to relate to color changes due to specific analyte. We have addressed it using a Lateral Flow Assay (LFA) device for automatic detection and quantification of urinary albumin. LFAs are specific to individual analytes, allowing color changes to be linked to the specific analyte, minimizing the interference. The proposed reader performs automatic segmentation of the region of interest (ROI) using YOLOv5, a deep learning-based model. Concentrations of urinary albumin in clinical samples were classified using customized machine learning algorithms. An accuracy of 96% was achieved on the test data using the k-Nearest Neighbour (k-NN) algorithm. Performance of the model was also evaluated under different illumination conditions and with different smartphone cameras, and validated using standard nephelometer.

PMID:39622082 | DOI:10.1088/2057-1976/ad992d

Chaos. 2024 Dec 1;34(12):120401. doi: 10.1063/5.0247498.

ABSTRACT

Regime switching, the process where complex systems undergo transitions between qualitatively different dynamical states due to changes in their conditions, is a widespread phenomenon, from climate and ocean circulation, to ecosystems, power grids, and the brain. Capturing the mechanisms that give rise to isolated or sequential switching dynamics, as well as developing generic and robust methods for forecasting, detecting, and controlling them is essential for maintaining optimal performance and preventing dysfunctions or even collapses in complex systems. This Focus Issue provides new insights into regime switching, covering the recent advances in theoretical analysis harnessing the reduction approaches, as well as data-driven detection methods and non-feedback control strategies. Some of the key challenges addressed include the development of reduction techniques for coupled stochastic and adaptive systems, the influence of multiple timescale dynamics on chaotic structures and cyclic patterns in forced systems, and the role of chaotic saddles and heteroclinic cycles in pattern switching in coupled oscillators. The contributions further highlight deep learning applications for predicting power grid failures, the use of blinking networks to enhance synchronization, creating adaptive strategies to control epidemic spreading, and non-feedback control strategies to suppress epileptic seizures. These developments are intended to catalyze further dialog between the different branches of complexity.

PMID:39621472 | DOI:10.1063/5.0247498

J Imaging Inform Med. 2024 Dec 2. doi: 10.1007/s10278-024-01337-x. Online ahead of print.

ABSTRACT

Small cohorts of certain disease states are common especially in medical imaging. Despite the growing culture of data sharing, information safety often precludes open sharing of these datasets for creating generalizable machine learning models. To overcome this barrier and maintain proper health information protection, foundational models are rapidly evolving to provide deep learning solutions that have been pretrained on the native feature spaces of the data. Although this has been optimized in Large Language Models (LLMs), there is still a sparsity of foundational models for computer vision tasks. It is in this space that we provide an investigation into pretraining Visual Geometry Group (VGG)-16, Residual Network (ResNet)-50, and Dense Network (DenseNet)-121 on an unrelated dataset of 8500 chest CTs which was subsequently fine-tuned to classify bone mineral density (BMD) in 199 breast cancer patients using the L1 vertebra on CT. These semi-foundational models showed significant improved ternary classification into mild, moderate, and severe demineralization in comparison to ground truth Hounsfield Unit (HU) measurements in trabecular bone with the semi-foundational ResNet50 architecture demonstrating the best relative performance. Specifically, the holdout testing AUC was 0.99 (p-value < 0.05, ANOVA versus no pretraining versus ImageNet transfer learning) and F1-score 0.99 (p-value < 0.05) for the holdout testing set. In this study, the use of a semi-foundational model trained on the native feature space of CT provided improved classification in a completely disparate disease state with different window levels. Future implementation with these models may provide better generalization despite smaller numbers of a disease state to be classified.

PMID:39621209 | DOI:10.1007/s10278-024-01337-x