J Dent Res. 2024 May 31:220345241255593. doi: 10.1177/00220345241255593. Online ahead of print.

ABSTRACT

Endodontics is the dental specialty foremost concerned with diseases of the pulp and periradicular tissues. Clinicians often face patients with varying symptoms, must critically assess radiographic images in 2 and 3 dimensions, derive complex diagnoses and decision making, and deliver sophisticated treatment. Paired with low intra- and interobserver agreement for radiographic interpretation and variations in treatment outcome resulting from nonstandardized clinical techniques, there exists an unmet need for support in the form of artificial intelligence (AI), providing automated biomedical image analysis, decision support, and assistance during treatment. In the past decade, there has been a steady increase in AI studies in endodontics but limited clinical application. This review focuses on critically assessing the recent advancements in endodontic AI research for clinical applications, including the detection and diagnosis of endodontic pathologies such as periapical lesions, fractures and resorptions, as well as clinical treatment outcome predictions. It discusses the benefits of AI-assisted diagnosis, treatment planning and execution, and future directions including augmented reality and robotics. It critically reviews the limitations and challenges imposed by the nature of endodontic data sets, AI transparency and generalization, and potential ethical dilemmas. In the near future, AI will significantly affect the everyday endodontic workflow, education, and continuous learning.

PMID:38822561 | DOI:10.1177/00220345241255593

Plant Methods. 2024 May 31;20(1):81. doi: 10.1186/s13007-024-01202-6.

ABSTRACT

BACKGROUND: Traditional Chinese Medicinal Plants (CMPs) hold a significant and core status for the healthcare system and cultural heritage in China. It has been practiced and refined with a history of exceeding thousands of years for health-protective affection and clinical treatment in China. It plays an indispensable role in the traditional health landscape and modern medical care. It is important to accurately identify CMPs for avoiding the affected clinical safety and medication efficacy by the different processed conditions and cultivation environment confusion.

RESULTS: In this study, we utilize a self-developed device to obtain high-resolution data. Furthermore, we constructed a visual multi-varieties CMPs image dataset. Firstly, a random local data enhancement preprocessing method is proposed to enrich the feature representation for imbalanced data by random cropping and random shadowing. Then, a novel hybrid supervised pre-training network is proposed to expand the integration of global features within Masked Autoencoders (MAE) by incorporating a parallel classification branch. It can effectively enhance the feature capture capabilities by integrating global features and local details. Besides, the newly designed losses are proposed to strengthen the training efficiency and improve the learning capacity, based on reconstruction loss and classification loss.

CONCLUSIONS: Extensive experiments are performed on our dataset as well as the public dataset. Experimental results demonstrate that our method achieves the best performance among the state-of-the-art methods, highlighting the advantages of efficient implementation of plant technology and having good prospects for real-world applications.

PMID:38822406 | DOI:10.1186/s13007-024-01202-6

J Orthop Surg Res. 2024 May 31;19(1):324. doi: 10.1186/s13018-024-04809-6.

ABSTRACT

BACKGROUND: The patellar height index is important; however, the measurement procedures are time-consuming and prone to significant variability among and within observers. We developed a deep learning-based automatic measurement system for the patellar height and evaluated its performance and generalization ability to accurately measure the patellar height index.

METHODS: We developed a dataset containing 3,923 lateral knee X-ray images. Notably, all X-ray images were from three tertiary level A hospitals, and 2,341 cases were included in the analysis after screening. By manually labeling key points, the model was trained using the residual network (ResNet) and high-resolution network (HRNet) for human pose estimation architectures to measure the patellar height index. Various data enhancement techniques were used to enhance the robustness of the model. The root mean square error (RMSE), object keypoint similarity (OKS), and percentage of correct keypoint (PCK) metrics were used to evaluate the training results. In addition, we used the intraclass correlation coefficient (ICC) to assess the consistency between manual and automatic measurements.

RESULTS: The HRNet model performed excellently in keypoint detection tasks by comparing different deep learning models. Furthermore, the pose_hrnet_w48 model was particularly outstanding in the RMSE, OKS, and PCK metrics, and the Insall-Salvati index (ISI) automatically calculated by this model was also highly consistent with the manual measurements (intraclass correlation coefficient [ICC], 0.809-0.885). This evidence demonstrates the accuracy and generalizability of this deep learning system in practical applications.

CONCLUSION: We successfully developed a deep learning-based automatic measurement system for the patellar height. The system demonstrated accuracy comparable to that of experienced radiologists and a strong generalizability across different datasets. It provides an essential tool for assessing and treating knee diseases early and monitoring and rehabilitation after knee surgery. Due to the potential bias in the selection of datasets in this study, different datasets should be examined in the future to optimize the model so that it can be reliably applied in clinical practice.

TRIAL REGISTRATION: The study was registered at the Medical Research Registration and Filing Information System (medicalresearch.org.cn) MR-61-23-013065. Date of registration: May 04, 2023 (retrospectively registered).

PMID:38822361 | DOI:10.1186/s13018-024-04809-6

BMC Med Inform Decis Mak. 2024 May 31;24(1):149. doi: 10.1186/s12911-024-02552-w.

ABSTRACT

BACKGROUND: Epilepsy, a chronic brain disorder characterized by abnormal brain activity that causes seizures and other symptoms, is typically treated using anti-epileptic drugs (AEDs) as the first-line therapy. However, due to the variations in their modes of action, identification of effective AEDs often relies on ad hoc trials, which is particularly challenging for pediatric patients. Thus, there is significant value in computational methods capable of assisting in the selection of AEDs, aiming to minimize unnecessary medication and improve treatment efficacy.

RESULTS: In this study, we collected 7,507 medical records from 1,000 pediatric epilepsy patients and developed a computational clinical decision-supporting system for AED selection. This system leverages three multi-channel convolutional neural network (CNN) models tailored to three specific AEDs (vigabatrin, prednisolone, and clobazam). Each CNN model predicts whether a respective AED is effective on a given patient or not. The CNN models showed AUROCs of 0.90, 0.80, and 0.92 in 10-fold cross-validation, respectively. Evaluation on a hold-out test dataset further revealed positive predictive values (PPVs) of 0.92, 0.97, and 0.91 for the three respective CNN models, representing that suggested AEDs by our models would be effective in controlling epilepsy with a high accuracy and thereby reducing unnecessary medications for pediatric patients.

CONCLUSION: Our CNN models in the system demonstrated high PPVs for the three AEDs, which signifies the potential of our approach to support the clinical decision-making by assisting doctors in recommending effective AEDs within the three AEDs for patients based on their medical history. This would result in a reduction in the number of unnecessary ad hoc attempts to find an effective AED for pediatric epilepsy patients.

PMID:38822293 | DOI:10.1186/s12911-024-02552-w

BMC Med Imaging. 2024 May 31;24(1):129. doi: 10.1186/s12880-024-01309-1.

ABSTRACT

BACKGROUND: Segmenting liver vessels from contrast-enhanced computed tomography images is essential for diagnosing liver diseases, planning surgeries and delivering radiotherapy. Nevertheless, identifying vessels is a challenging task due to the tiny cross-sectional areas occupied by vessels, which has posed great challenges for vessel segmentation, such as limited features to be learned and difficult to construct high-quality as well as large-volume data.

METHODS: We present an approach that only requires a few labeled vessels but delivers significantly improved results. Our model starts with vessel enhancement by fading out liver intensity and generates candidate vessels by a classifier fed with a large number of image filters. Afterwards, the initial segmentation is refined using Markov random fields.

RESULTS: In experiments on the well-known dataset 3D-IRCADb, the averaged Dice coefficient is lifted to 0.63, and the mean sensitivity is increased to 0.71. These results are significantly better than those obtained from existing machine-learning approaches and comparable to those generated from deep-learning models.

CONCLUSION: Sophisticated integration of a large number of filters is able to pinpoint effective features from liver images that are sufficient to distinguish vessels from other liver tissues under a scarcity of large-volume labeled data. The study can shed light on medical image segmentation, especially for those without sufficient data.

PMID:38822274 | DOI:10.1186/s12880-024-01309-1

BMC Med Imaging. 2024 May 31;24(1):127. doi: 10.1186/s12880-024-01308-2.

ABSTRACT

BACKGROUND: The presence of infarction in patients with unrecognized myocardial infarction (UMI) is a critical feature in predicting adverse cardiac events. This study aimed to compare the detection rate of UMI using conventional and deep learning reconstruction (DLR)-based late gadolinium enhancement (LGEO and LGEDL, respectively) and evaluate optimal quantification parameters to enhance diagnosis and management of suspected patients with UMI.

METHODS: This prospective study included 98 patients (68 men; mean age: 55.8 ± 8.1 years) with suspected UMI treated at our hospital from April 2022 to August 2023. LGEO and LGEDL images were obtained using conventional and commercially available inline DLR algorithms. The myocardial signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and percentage of enhanced area (Parea) employing the signal threshold versus reference mean (STRM) approach, which correlates the signal intensity (SI) within areas of interest with the average SI of normal regions, were analyzed. Analysis was performed using the standard deviation (SD) threshold approach (2SD-5SD) and full width at half maximum (FWHM) method. The diagnostic efficacies based on LGEDL and LGEO images were calculated.

RESULTS: The SNRDL and CNRDL were two times better than the SNRO and CNRO, respectively (P < 0.05). Parea-DL was elevated compared to Parea-O using the threshold methods (P < 0.05); however, no intergroup difference was found based on the FWHM method (P > 0.05). The Parea-DL and Parea-O also differed except between the 2SD and 3SD and the 4SD/5SD and FWHM methods (P < 0.05). The receiver operating characteristic curve analysis revealed that each SD method exhibited good diagnostic efficacy for detecting UMI, with the Parea-DL having the best diagnostic efficacy based on the 5SD method (P < 0.05). Overall, the LGEDL images had better image quality. Strong diagnostic efficacy for UMI identification was achieved when the STRM was ≥ 4SD and ≥ 3SD for the LGEDL and LGEO, respectively.

CONCLUSIONS: STRM selection for LGEDL magnetic resonance images helps improve clinical decision-making in patients with UMI. This study underscored the importance of STRM selection for analyzing LGEDL images to enhance diagnostic accuracy and clinical decision-making for patients with UMI, further providing better cardiovascular care.

PMID:38822240 | DOI:10.1186/s12880-024-01308-2

J Ultrasound Med. 2024 May 31. doi: 10.1002/jum.16489. Online ahead of print.

ABSTRACT

PURPOSE: To develop a deep neural network system for the automatic segmentation and risk stratification prediction of gastrointestinal stromal tumors (GISTs).

METHODS: A total of 980 ultrasound (US) images from 245 GIST patients were retrospectively collected. These images were randomly divided (6:2:2) into a training set, a validation set, and an internal test set. Additionally, 188 US images from 47 prospective GIST patients were collected to evaluate the segmentation and diagnostic performance of the model. Five deep learning-based segmentation networks, namely, UNet, FCN, DeepLabV3+, Swin Transformer, and SegNeXt, were employed, along with the ResNet 18 classification network, to select the most suitable network combination. The performance of the segmentation models was evaluated using metrics such as the intersection over union (IoU), Dice similarity coefficient (DSC), recall, and precision. The classification performance was assessed based on accuracy and the area under the receiver operating characteristic curve (AUROC).

RESULTS: Among the compared models, SegNeXt-ResNet18 exhibited the best segmentation and classification performance. On the internal test set, the proposed model achieved IoU, DSC, precision, and recall values of 82.1, 90.2, 91.7, and 88.8%, respectively. The accuracy and AUC for GIST risk prediction were 87.4 and 92.0%, respectively. On the external test set, the segmentation models exhibited IoU, DSC, precision, and recall values of 81.0, 89.5, 92.8, and 86.4%, respectively. The accuracy and AUC for GIST risk prediction were 86.7 and 92.5%, respectively.

CONCLUSION: This two-stage SegNeXt-ResNet18 model achieves automatic segmentation and risk stratification prediction for GISTs and demonstrates excellent segmentation and classification performance.

PMID:38822195 | DOI:10.1002/jum.16489

Sci Rep. 2024 May 31;14(1):12567. doi: 10.1038/s41598-024-63094-9.

ABSTRACT

In recent years, the growth spurt of medical imaging data has led to the development of various machine learning algorithms for various healthcare applications. The MedMNISTv2 dataset, a comprehensive benchmark for 2D biomedical image classification, encompasses diverse medical imaging modalities such as Fundus Camera, Breast Ultrasound, Colon Pathology, Blood Cell Microscope etc. Highly accurate classifications performed on these datasets is crucial for identification of various diseases and determining the course of treatment. This research paper presents a comprehensive analysis of four subsets within the MedMNISTv2 dataset: BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST. Each of these selected datasets is of diverse data modalities and comes with various sample sizes, and have been selected to analyze the efficiency of the model against diverse data modalities. The study explores the idea of assessing the Vision Transformer Model's ability to capture intricate patterns and features crucial for these medical image classification and thereby transcend the benchmark metrics substantially. The methodology includes pre-processing the input images which is followed by training the ViT-base-patch16-224 model on the mentioned datasets. The performance of the model is assessed using key metrices and by comparing the classification accuracies achieved with the benchmark accuracies. With the assistance of ViT, the new benchmarks achieved for BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST are 97.90%, 90.38%, 94.62% and 57%, respectively. The study highlights the promise of Vision transformer models in medical image analysis, preparing the way for their adoption and further exploration in healthcare applications, aiming to enhance diagnostic accuracy and assist medical professionals in clinical decision-making.

PMID:38821977 | DOI:10.1038/s41598-024-63094-9

Nat Commun. 2024 May 31;15(1):4631. doi: 10.1038/s41467-024-49060-z.

ABSTRACT

Although long-read sequencing enables the generation of complete genomes for unculturable microbes, its high cost limits the widespread adoption of long-read sequencing in large-scale metagenomic studies. An alternative method is to assemble short-reads with long-range connectivity, which can be a cost-effective way to generate high-quality microbial genomes. Here, we develop Pangaea, a bioinformatic approach designed to enhance metagenome assembly using short-reads with long-range connectivity. Pangaea leverages connectivity derived from physical barcodes of linked-reads or virtual barcodes by aligning short-reads to long-reads. Pangaea utilizes a deep learning-based read binning algorithm to assemble co-barcoded reads exhibiting similar sequence contexts and abundances, thereby improving the assembly of high- and medium-abundance microbial genomes. Pangaea also leverages a multi-thresholding algorithm strategy to refine assembly for low-abundance microbes. We benchmark Pangaea on linked-reads and a combination of short- and long-reads from simulation data, mock communities and human gut metagenomes. Pangaea achieves significantly higher contig continuity as well as more near-complete metagenome-assembled genomes (NCMAGs) than the existing assemblers. Pangaea also generates three complete and circular NCMAGs on the human gut microbiomes.

PMID:38821971 | DOI:10.1038/s41467-024-49060-z

Otolaryngol Clin North Am. 2024 May 30:S0030-6665(24)00068-9. doi: 10.1016/j.otc.2024.04.010. Online ahead of print.

ABSTRACT

Rhinology, allergy, and skull base surgery are fields primed for the integration and implementation of artificial intelligence (AI). The heterogeneity of the disease processes within these fields highlights the opportunity for AI to augment clinical care and promote personalized medicine. Numerous research studies have been published demonstrating the development and clinical potential of AI models within the field. Most describe in silico evaluation models without direct clinical implementation. The major themes of existing studies include diagnostic or clinical decisions support, clustering patients into specific phenotypes or endotypes, predicting post-treatment outcomes, and surgical planning.

PMID:38821734 | DOI:10.1016/j.otc.2024.04.010

Int J Oral Maxillofac Surg. 2024 May 30:S0901-5027(24)00148-6. doi: 10.1016/j.ijom.2024.05.003. Online ahead of print.

ABSTRACT

The surgery-first approach (SFA) orthognathic surgery can be beneficial due to reduced overall treatment time and earlier profile improvement. The objective of this study was to utilize deep learning to predict the treatment modality of SFA or the orthodontics-first approach (OFA) in orthognathic surgery patients and assess its clinical accuracy. A supervised deep learning model using three convolutional neural networks (CNNs) was trained based on lateral cephalograms and occlusal views of 3D dental model scans from 228 skeletal Class III malocclusion patients (114 treated by SFA and 114 by OFA). An ablation study of five groups (lateral cephalogram only, mandible image only, maxilla image only, maxilla and mandible images, and all data combined) was conducted to assess the influence of each input type. The results showed the average validation accuracy, precision, recall, F1 score, and AUROC for the five folds were 0.978, 0.980, 0.980, 0.980, and 0.998 ; the average testing results for the five folds were 0.906, 0.986, 0.828, 0.892, and 0.952. The lateral cephalogram only group had the least accuracy, while the maxilla image only group had the best accuracy. Deep learning provides a novel method for an accelerated workflow, automated assisted decision-making, and personalized treatment planning.

PMID:38821731 | DOI:10.1016/j.ijom.2024.05.003

J Dent. 2024 May 29:105105. doi: 10.1016/j.jdent.2024.105105. Online ahead of print.

ABSTRACT

OBJECTIVES: This study aimed to assess the reliability of AI-based Diagnocat system that assists the healthcare processes in the diagnosis of caries on intraoral radiographs.

METHODS: The proximal surfaces of the 323 selected teeth on the intraoral radiographs were evaluated by two independent observers using the AI-based Diagnocat system. The presence or absence of carious lesions was recorded during Phase 1. After 4 months, the AI-aided human observers evaluated the same radiographs (Phase 2), and the advanced convolutional neural network (CNN) reassessed the radiographic data (Phase 3). Subsequently, data reflecting human disagreements were excluded (Phase 4). For each phase, the Cohen and Fleiss kappa values, as well as the sensitivity, specificity, positive and negative predictive values, and diagnostic accuracy ​​of Diagnocat, were calculated.

RESULTS: During the four phases, the range of Cohen kappa values between the human observers and Diagnocat were κ=0.66-1, κ=0.58-0.7, and κ=0.49-0.7. The Fleiss kappa values were κ=0.57-0.8. The sensitivity, specificity and diagnostic accuracy values ranged between 0.51-0.76, 0.88-0.97 and 0.76-0.86, respectively.

CONCLUSIONS: The Diagnocat CNN supports the evaluation of intraoral radiographs for caries diagnosis, as determined by consensus between human and AI system observers.

CLINICAL SIGNIFICANCE: Our study may aid in the understanding of deep learning-based systems developed for dental imaging modalities for dentists and contribute to expanding the body of results in the field of AI-supported dental radiology, as concluded by other scientific publications.

PMID:38821394 | DOI:10.1016/j.jdent.2024.105105

Food Chem. 2024 May 30;454:139705. doi: 10.1016/j.foodchem.2024.139705. Online ahead of print.

ABSTRACT

The overuse and misuse of tetracycline (TCs) antibiotics, including tetracycline (TTC), oxytetracycline (OTC), doxycycline (DC), and chlortetracycline (CTC), pose a serious threat to human health. However, current rapid sensing platforms for tetracyclines can only quantify the total amount of TCs mixture, lacking real-time identification of individual components. To address this challenge, we integrated a deep learning strategy with fluorescence and colorimetry-based multi-mode logic gates in our self-designed smartphone-integrated toolbox for the real-time identification of natural TCs. Our ratiometric fluorescent probe (CD-Au NCs@ZIF-8) encapsulated carbon dots and Au NCs in ZIF-8 to prevent false negative or positive results. Additionally, our independently developed WeChat app enabled linear quantification of the four natural TCs using the fluorescence channels. The colorimetric channels were also utilized as outputs of logic gates to achieve real-time identification of the four individual natural tetracyclines. We anticipate this strategy could provide a new perspective for effective control of antibiotics.

PMID:38820637 | DOI:10.1016/j.foodchem.2024.139705

PLoS One. 2024 May 31;19(5):e0304419. doi: 10.1371/journal.pone.0304419. eCollection 2024.

ABSTRACT

In recent years, various data-driven algorithms have been applied to the classification and staging of brain glioma MRI detection. However, the restricted availability of brain glioma MRI data in purely data-driven deep learning algorithms has presented challenges in extracting high-quality features and capturing their complex patterns. Moreover, the analysis methods designed for 2D data necessitate the selection of ideal tumor image slices, which does not align with practical clinical scenarios. Our research proposes an novel brain glioma staging model, Medical Cognition Embedded (MCE) model for 3D data. This model embeds knowledge characteristics into data-driven approaches to enhance the quality of feature extraction. Approach includes the following key components: (1) Deep feature extraction, drawing upon the imaging technical characteristics of different MRI sequences, has led to the design of two methods at both the algorithmic and strategic levels to mimic the learning process of real image interpretation by medical professionals during film reading; (2) We conduct an extensive Radiomics feature extraction, capturing relevant features such as texture, morphology, and grayscale distribution; (3) By referencing key points in radiological diagnosis, Radiomics feature experimental results, and the imaging characteristics of various MRI sequences, we manually create diagnostic features (Diag-Features). The efficacy of proposed methodology is rigorously evaluated on the publicly available BraTS2018 and BraTS2020 datasets. Comparing it to most well-known purely data-driven models, our method achieved higher accuracy, recall, and precision, reaching 96.14%, 93.4%, 97.06%, and 97.57%, 92.80%, 95.96%, respectively.

PMID:38820482 | DOI:10.1371/journal.pone.0304419

PLoS One. 2024 May 31;19(5):e0303670. doi: 10.1371/journal.pone.0303670. eCollection 2024.

ABSTRACT

Breast cancer remains a critical global concern, underscoring the urgent need for early detection and accurate diagnosis to improve survival rates among women. Recent developments in deep learning have shown promising potential for computer-aided detection (CAD) systems to address this challenge. In this study, a novel segmentation method based on deep learning is designed to detect tumors in breast ultrasound images. Our proposed approach combines two powerful attention mechanisms: the novel Positional Convolutional Block Attention Module (PCBAM) and Shifted Window Attention (SWA), integrated into a Residual U-Net model. The PCBAM enhances the Convolutional Block Attention Module (CBAM) by incorporating the Positional Attention Module (PAM), thereby improving the contextual information captured by CBAM and enhancing the model's ability to capture spatial relationships within local features. Additionally, we employ SWA within the bottleneck layer of the Residual U-Net to further enhance the model's performance. To evaluate our approach, we perform experiments using two widely used datasets of breast ultrasound images and the obtained results demonstrate its capability in accurately detecting tumors. Our approach achieves state-of-the-art performance with dice score of 74.23% and 78.58% on BUSI and UDIAT datasets, respectively in segmenting the breast tumor region, showcasing its potential to help with precise tumor detection. By leveraging the power of deep learning and integrating innovative attention mechanisms, our study contributes to the ongoing efforts to improve breast cancer detection and ultimately enhance women's survival rates. The source code of our work can be found here: https://github.com/AyushRoy2001/DAUNet.

PMID:38820462 | DOI:10.1371/journal.pone.0303670

PLoS One. 2024 May 31;19(5):e0304469. doi: 10.1371/journal.pone.0304469. eCollection 2024.

ABSTRACT

In recent years, the advancement of hyperspectral remote sensing technology has greatly enhanced the detailed mapping of tree species. Nevertheless, delving deep into the significance of hyperspectral remote sensing data features for tree species recognition remains a challenging endeavor. The method of Hybrid-CS was proposed to addresses this challenge by synergizing the strengths of both deep learning and traditional learning techniques. Initially, we extract comprehensive correlation structures and spectral features. Subsequently, a hybrid approach, combining correlation-based feature selection with an optimized recursive feature elimination algorithm, identifies the most valuable feature set. We leverage the Support Vector Machine algorithm to evaluate feature importance and perform classification. Through rigorous experimentation, we evaluate the robustness of hyperspectral image-derived features and compare our method with other state-of-the-art classification methods. The results demonstrate: (1) Superior classification accuracy compared to traditional machine learning methods (e.g., SVM, RF) and advanced deep learning approaches on the tree species dataset. (2) Enhanced classification accuracy achieved by incorporating SVM and CNN information, particularly with the integration of attention mechanisms into the network architecture. Additionally, the classification performance of a two-branch network surpasses that of a single-branch network. (3) Consistent high accuracy across different proportions of training samples, indicating the stability and robustness of the method. This study underscores the potential of hyperspectral images and our proposed methodology for achieving precise tree species classification, thus holding significant promise for applications in forest resource management and monitoring.

PMID:38820430 | DOI:10.1371/journal.pone.0304469

Med Phys. 2024 May 31. doi: 10.1002/mp.17237. Online ahead of print.

ABSTRACT

BACKGROUND: Chronic cerebral hypoperfusion (CCH) is a frequently encountered clinical condition that poses a diagnostic challenge due to its nonspecific symptoms.

PURPOSE: To enhance the diagnosis of CCH and non-CCH through Magnetic Resonance Imaging (MRI), offering support in clinical decision-making and recommendations to ultimately elevate diagnostic accuracy and optimize patient treatment outcomes.

METHODS: In the retrospective research, we collected 204 routine brain magnetic resonance imaging (MRI) from March 1 to September 10 2022, as training and testing cohorts. And a validation cohort with 108 samples was collected from November 14 2022 to August 4 2023. MRI sequences were processed to obtain T1-weighted (T1WI) and T2-weighted (T2WI) sequence images for each patient. We propose CCH-Network (CCHNet), an end-to-end deep learning model, integrating convolution and Transformer modules to capture local and global structural information. Our novel adversarial training method improves feature knowledge capture, enhancing both generalization ability and efficiency in predicting CCH risk. We assessed the classification performance of the proposed model CCHNet by comparing it with existing state-of-the-art deep learning algorithms, including ResNet34, DenseNet121, VGG16, Convnext, ViT, Coat, and TransFG. To better validate model performance, we compared the results of the proposed model with eight neurologists to evaluate their consistency.

RESULTS: CCHNet achieved an AUC of 91.6% (95% CI: 86.8-99.1), with an accuracy (ACC) of 85.0% (95% CI: 75.6-95.2). It demonstrated a sensitivity (SE) of 80.0% (95% CI: 71.6-95.6) and a specificity (SP) of 90.0% (95% CI: 82.3-97.8) in the testing cohort. In the validation cohort, the model demonstrated an AUC of 86.0% (95% CI: 80.3-93.0), an ACC of 84.2% (95% CI: 70.2-93.6), a SE of 83.3% (95% CI: 68.3-95.5), and a SP of 84.7% (95% CI: 70.3-96.8).

CONCLUSIONS: The model improved the diagnostic performance of MRI with high SE and SP, providing a promising method for the diagnosis of CCH.

PMID:38820428 | DOI:10.1002/mp.17237

PLoS One. 2024 May 31;19(5):e0301275. doi: 10.1371/journal.pone.0301275. eCollection 2024.

ABSTRACT

Skin cancer has a significant impact on the lives of many individuals annually and is recognized as the most prevalent type of cancer. In the United States, an estimated annual incidence of approximately 3.5 million people receiving a diagnosis of skin cancer underscores its widespread prevalence. Furthermore, the prognosis for individuals afflicted with advancing stages of skin cancer experiences a substantial decline in survival rates. This paper is dedicated to aiding healthcare experts in distinguishing between benign and malignant skin cancer cases by employing a range of machine learning and deep learning techniques and different feature extractors and feature selectors to enhance the evaluation metrics. In this paper, different transfer learning models are employed as feature extractors, and to enhance the evaluation metrics, a feature selection layer is designed, which includes diverse techniques such as Univariate, Mutual Information, ANOVA, PCA, XGB, Lasso, Random Forest, and Variance. Among transfer models, DenseNet-201 was selected as the primary feature extractor to identify features from data. Subsequently, the Lasso method was applied for feature selection, utilizing diverse machine learning approaches such as MLP, XGB, RF, and NB. To optimize accuracy and precision, ensemble methods were employed to identify and enhance the best-performing models. The study provides accuracy and sensitivity rates of 87.72% and 92.15%, respectively.

PMID:38820401 | DOI:10.1371/journal.pone.0301275

PLoS One. 2024 May 31;19(5):e0302664. doi: 10.1371/journal.pone.0302664. eCollection 2024.

ABSTRACT

The ever-increasing demand for electricity has presented a grave threat to traditional energy sources, which are finite, rapidly depleting, and have a detrimental environmental impact. These shortcomings of conventional energy resources have caused the globe to switch from traditional to renewable energy sources. Wind power significantly contributes to carbon-free energy because it is widely accessible, inexpensive, and produces no harmful emissions. Better and more efficient renewable wind power production relies on accurate wind speed predictions. Accurate short-term wind speed forecasting is essential for effectively handling unsteady wind power generation and ensuring that wind turbines operate safely. The significant stochastic nature of the wind speed and its dynamic unpredictability makes it difficult to forecast. This paper develops a hybrid model, L-LG-S, for precise short-term wind speed forecasting to address problems in wind speed forecasting. In this research, state-of-the-art machine learning and deep learning algorithms employed in wind speed forecasting are compared with the proposed approach. The effectiveness of the proposed hybrid model is tested using real-world wind speed data from a wind turbine located in the city of Karachi, Pakistan. Moreover, the mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) are used as accuracy evaluation indices. Experimental results show that the proposed model outperforms the state-of-the-art legacy models in terms of accuracy for short-term wind speed in training, validation and test predictions by 98% respectively.

PMID:38820359 | DOI:10.1371/journal.pone.0302664

PLoS One. 2024 May 31;19(5):e0304709. doi: 10.1371/journal.pone.0304709. eCollection 2024.

ABSTRACT

Imaging mass spectrometry (IMS) provides promising avenues to augment histopathological investigation with rich spatio-molecular information. We have previously developed a classification model to differentiate melanoma from nevi lesions based on IMS protein data, a task that is challenging solely by histopathologic evaluation. Most IMS-focused studies collect microscopy in tandem with IMS data, but this microscopy data is generally omitted in downstream data analysis. Microscopy, nevertheless, forms the basis for traditional histopathology and thus contains invaluable morphological information. In this work, we developed a multimodal classification pipeline that uses deep learning, in the form of a pre-trained artificial neural network, to extract the meaningful morphological features from histopathological images, and combine it with the IMS data. To test whether this deep learning-based classification strategy can improve on our previous results in classification of melanocytic neoplasia, we utilized MALDI IMS data with collected serial H&E stained sections for 331 patients, and compared this multimodal classification pipeline to classifiers using either exclusively microscopy or IMS data. The multimodal pipeline achieved the best performance, with ROC-AUCs of 0.968 vs. 0.938 vs. 0.931 for the multimodal, unimodal microscopy and unimodal IMS pipelines respectively. Due to the use of a pre-trained network to perform the morphological feature extraction, this pipeline does not require any training on large amounts of microscopy data. As such, this framework can be readily applied to improve classification performance in other experimental settings where microscopy data is acquired in tandem with IMS experiments.

PMID:38820337 | DOI:10.1371/journal.pone.0304709