J Microsc. 2024 Dec 9. doi: 10.1111/jmi.13376. Online ahead of print.

ABSTRACT

Conventional optical microscopy imaging of obligate intracellular bacteria is hampered by the small size of bacterial cells, tight clustering exhibited by some bacterial species and challenges relating to labelling such as background from host cells, a lack of validated reagents, and a lack of tools for genetic manipulation. In this study, we imaged intracellular bacteria from the species Orientia tsutsugamushi (Ot) using five different fluorescence microscopy techniques: standard confocal, Airyscan confocal, instant Structured Illumination Microscopy (iSIM), three-dimensional Structured Illumination Microscopy (3D-SIM) and Stimulated Emission Depletion Microscopy (STED). We compared the ability of each to resolve bacterial cells in intracellular clumps in the lateral (xy) axis, using full width half-maximum (FWHM) measurements of a labelled outer membrane protein (ScaA) and the ability to detect small, outer membrane vesicles external to the cells. Comparing the techniques readily available to us (above), 3D-SIM microscopy, in combination with the shortest-wavelength dyes, was found overall to give the best lateral resolution. We next compared the ability of each technique to sufficiently resolve bacteria in the axial (z) direction and found 3D-STED to be the most successful method for this. We then combined this 3D-STED approach with a custom 3D cell segmentation and analysis pipeline using the open-source, deep learning software, Cellpose to segment the cells and subsequently the commercial software Imaris to analyse their 3D shape and size. Using this combination, we demonstrated differences in bacterial shape, but not their size, when grown in different mammalian cell lines. Overall, we compare the advantages and disadvantages of different super-resolution microscopy techniques for imaging this cytoplasmic obligate intracellular bacterium based on the specific research question being addressed.

PMID:39651611 | DOI:10.1111/jmi.13376

Big Data. 2024 Dec 9. doi: 10.1089/big.2024.0071. Online ahead of print.

ABSTRACT

Liver cirrhosis stands as a prominent contributor to mortality, impacting millions across the United States. Enabling health care providers to predict early mortality among patients with cirrhosis holds the potential to enhance treatment efficacy significantly. Our hypothesis centers on the correlation between mortality and laboratory test results along with relevant diagnoses in this patient cohort. Additionally, we posit that a deep learning model could surpass the predictive capabilities of the existing Model for End-Stage Liver Disease score. This research seeks to advance prognostic accuracy and refine approaches to address the critical challenges posed by cirrhosis-related mortality. This study evaluates the performance of an artificial neural network model for liver disease classification using various training dataset sizes. Through meticulous experimentation, three distinct training proportions were analyzed: 70%, 80%, and 90%. The model's efficacy was assessed using precision, recall, F1-score, accuracy, and support metrics, alongside receiver operating characteristic (ROC) and precision-recall (PR) curves. The ROC curves were quantified using the area under the curve (AUC) metric. Results indicated that the model's performance improved with an increased size of the training dataset. Specifically, the 80% training data model achieved the highest AUC, suggesting superior classification ability over the models trained with 70% and 90% data. PR analysis revealed a steep trade-off between precision and recall across all datasets, with 80% training data again demonstrating a slightly better balance. This is indicative of the challenges faced in achieving high precision with a concurrently high recall, a common issue in imbalanced datasets such as those found in medical diagnostics.

PMID:39651607 | DOI:10.1089/big.2024.0071

Curr Eye Res. 2024 Dec 9:1-6. doi: 10.1080/02713683.2024.2430212. Online ahead of print.

ABSTRACT

PURPOSE: To examine the performance of deep-learning models that predicts the visual acuity after cataract surgery using preoperative clinical information and color fundus photography (CFP).

METHODS: We retrospectively collected the age, sex, and logMAR preoperative best corrected visual acuity (preoperative-BCVA) and CFP from patients who underwent cataract surgeries from 2020 to 2021 at National Taiwan University Hospital. Feature extraction of CFP was performed using a pre-existing image classification model, Xception. The CFP-extracted features and pre-operative clinical information were then fed to a downstream neural network for final prediction. We assessed the model performance by calculating the mean absolute error (MAE) between the predicted and the true logMAR of postoperative BCVA. A nested 10-fold cross-validation was performed for model validation.

RESULTS: A total of 673 fundus images from 446 patients were collected. The mean preoperative BCVA and postoperative BCVA was 0.60 ± 0.39 and 0.14 ± 0.18, respectively. The model using age and sex as predictors achieved an MAE of 0.121 ± 0.016 in postoperative BCVA prediction. The inclusion of CFP as additional predictor in the model (predictors: age, sex and CFP) did not further improve the predictive performance (MAE = 0.120 ± 0.023, p = 0.375), while adding the preoperative BCVA as an additional predictor resulted in a 4.13% improvement (predictors: age, sex and preoperative BCVA, MAE = 0.116 ± 0.016, p = 0.013).

CONCLUSIONS: Our multimodal models including both CFP and clinical information achieved excellent accuracy in predicting BCVA after cataract surgery, while the learning models input with only clinical information performed similarly. Future studies are needed to clarify the effects of multimodal input on this task.

PMID:39651583 | DOI:10.1080/02713683.2024.2430212

Int J Comput Dent. 2024 Dec 9;27(4):401-411. doi: 10.3290/j.ijcd.b5870240.

ABSTRACT

AIM: The objective of the present study was to investigate the clinical understanding and reasoning abilities of large language models (LLMs); namely, ChatGPT, GPT-4, and New Bing, by evaluating their performance in the NDLE (National Dental Licensing Examination) in China.

MATERIALS AND METHODS: Questions from the NDLE from 2020 to 2022 were selected based on subject weightings. Standardized prompts were utilized to regulate the output of LLMs for acquiring more precise answers. The performance of each model across each subject category and for the subjects overall was analyzed employing the McNemar's test.

RESULTS: The percentage scores obtained by ChatGPT, GPT-4, and New Bing were 42.6% (138/324), 63.0% (204/324), and 72.5% (235/324), respectively. Significant variance was seen between the performance of New Bing compared with ChatGPT and GPT-4. GPT-4 and New Bing outperformed ChatGPT across all subjects, with New Bing surpassing GPT-4 in most subjects.

CONCLUSION: GPT-4 and New Bing exhibited promising capabilities in the NDLE. However, their performance in specific subjects such as prosthodontics and oral and maxillofacial surgery requires improvement. This performance gap can be attributed to limited dental training data and the inherent complexity of these subjects.

PMID:39651568 | DOI:10.3290/j.ijcd.b5870240

Interface Focus. 2024 Dec 6;14(6):20240024. doi: 10.1098/rsfs.2024.0024. eCollection 2024 Dec 6.

ABSTRACT

Functional magnetic resonance imaging (fMRI) captures rich physiological and neuronal information, offering insight into neurofluid dynamics, vascular health and waste clearance. Accurate cerebral vessel segmentation could greatly facilitate fluid dynamics research in fMRI. However, existing vessel identification methods, such as magnetic resonance angiography or deep-learning-based segmentation on structural MRI, cannot reliably locate cerebral vessels in fMRI space due to misregistration from inherent fMRI distortions. To address this challenge, we developed a data-driven, automatic segmentation of cerebral vessels directly within fMRI space. This approach identified large cerebral arteries and the superior sagittal sinus (SSS) by leveraging these vessels' distinct pulsatile signal patterns during the cardiac cycle. The method was validated in a local dataset by comparing it to ground truth cerebral artery and SSS segmentations. Using the Human Connectome Project (HCP) ageing dataset, the method's reproducibility was tested on 422 participants aged 36-90, each with four repeated fMRI scans. The method demonstrated high reproducibility, with an intraclass correlation coefficient > 0.7 in both cerebral artery and SSS segmentation volumes. This study demonstrates that large cerebral arteries and SSS can be reproducibly and automatically segmented in fMRI datasets, facilitating reliable fluid dynamics investigation in these regions.

PMID:39649451 | PMC:PMC11620823 | DOI:10.1098/rsfs.2024.0024

Npj Imaging. 2024;2(1):51. doi: 10.1038/s44303-024-00055-x. Epub 2024 Dec 4.

ABSTRACT

Voltage imaging is a powerful technique for studying neuronal activity, but its effectiveness is often constrained by low signal-to-noise ratios (SNR). Traditional denoising methods, such as matrix factorization, impose rigid assumptions about noise and signal structures, while existing deep learning approaches fail to fully capture the rapid dynamics and complex dependencies inherent in voltage imaging data. Here, we introduce CellMincer, a novel self-supervised deep learning method specifically developed for denoising voltage imaging datasets. CellMincer operates by masking and predicting sparse pixel sets across short temporal windows and conditions the denoiser on precomputed spatiotemporal auto-correlations to effectively model long-range dependencies without large temporal contexts. We developed and utilized a physics-based simulation framework to generate realistic synthetic datasets, enabling rigorous hyperparameter optimization and ablation studies. This approach highlighted the critical role of conditioning on spatiotemporal auto-correlations, resulting in an additional 3-fold SNR gain. Comprehensive benchmarking on both simulated and real datasets, including those validated with patch-clamp electrophysiology (EP), demonstrates CellMincer's state-of-the-art performance, with substantial noise reduction across the frequency spectrum, enhanced subthreshold event detection, and high-fidelity recovery of EP signals. CellMincer consistently outperforms existing methods in SNR gain (0.5-2.9 dB) and reduces SNR variability by 17-55%. Incorporating CellMincer into standard workflows significantly improves neuronal segmentation, peak detection, and functional phenotype identification, consistently surpassing current methods in both SNR gain and consistency.

PMID:39649342 | PMC:PMC11618097 | DOI:10.1038/s44303-024-00055-x

Phys Imaging Radiat Oncol. 2024 Nov 16;32:100676. doi: 10.1016/j.phro.2024.100676. eCollection 2024 Oct.

ABSTRACT

BACKGROUND AND PURPOSE: This study aimed at investigating the dosimetric impact on organs at risk, when the left-sided internal mammary lymph nodes (IMN) were delineated with two interpretations of the same guideline.

MATERIALS AND METHODS: The cohort consisted of 95 left-sided breast cancer patients with indication for irradiation of the CTVn_IMN treated at the Netherlands Cancer Institute (NKI). The NKI interpretation of the ESTRO guidelines was in the clinical structure sets (CTVn_IMN_NKI). A deep learning model was used as second interpretation of the guideline, based on a Danish consensus interpretation (CTVn_IMN_DK). The geometrical similarity was evaluated with the Dice Similarity Coefficient (DSC), volume, width, distance to sternal bone (SB) and maximum distance between the interpretations in the medial direction. Treatment plans were generated for both CTVn_IMNs. Mean heart dose (MHD) was correlated with the geometrical metrics.

RESULTS: 62 patients were eligible for analysis. The geometric comparison showed a median volume of 9.59 ml/7.19 ml for the CTVN_IMN_NKI/CTVn_IMN_DK along with a median DSC of 0.63. The width and distance from SB were significantly different, with a median width of 18.2 mm/14.7 mm and distance to SB of 3.4 mm/5.1 mm for CTVn_IMN_NKI/CTVn_IMN_DK. The MHD was significantly higher with the CTVn_IMN_NKI. The strongest correlation was found between MHD and maximum medial difference between the CTVn_IMN in slices where the heart was present.

CONCLUSIONS: Differences in interpretations of the CTVn_IMN delineation guidelines were found, resulting in significant differences in MHD. For the individual patients, the dosimetric differences may impact treatment decisions, underscoring the need for strong consensus across borders.

PMID:39649154 | PMC:PMC11625340 | DOI:10.1016/j.phro.2024.100676

Rev Bras Ortop (Sao Paulo). 2024 Dec 7;59(5):e689-e695. doi: 10.1055/s-0044-1779317. eCollection 2024 Oct.

ABSTRACT

Objective Artificial intelligence technologies have been used increasingly in spine surgery as a diagnostic tool. The aim of the present study was to evaluate the effectiveness of the convolutional neural networks in the diagnosis of cervical myelopathy (CM) compared with conventional cervical magnetic resonance imaging (MRI). Materials and Methods This was a cross-sectional descriptive analytical study. A total of 125 participants with clinical and radiological diagnosis of CM were included in the study. Sagittal and axial MRI images in the T2 sequence of the cervical spine were used. All image parts were obtained as 8 bytes/pixel in 2 different categories, CM and normal, both in axial and sagittal views. Results Triple cross validation was performed to prevent overfitting during the training process. A total of 242 sample images were used for training and testing the model created for axial views. In the axial view, the calculated values are 97.44% for sensitivity and 97.56% for specificity. A total of 249 sample images were used for training and testing the model created for sagittal views. The calculated values are 97.50% for sensitivity and 97.67% for specificity. After the training, the average accuracy value was 96.7% (±1.53) for the axial view and 97.19% (±1.2) for the sagittal view. Conclusion Deep learning (DL) has shown a great improvement especially in spine surgery. We found that DL technology works with a higher accuracy than other studies in the literature for the diagnosis of CM.

PMID:39649041 | PMC:PMC11624937 | DOI:10.1055/s-0044-1779317

J Med Eng Technol. 2024 Dec 9:1-10. doi: 10.1080/03091902.2024.2438158. Online ahead of print.

ABSTRACT

The conventional detection of COVID-19 by evaluating the CT scan images is tiresome, often experiences high inter-observer variability and uncertainty issues. This work proposes the automatic detection and classification of COVID-19 by analysing the chest X-ray images (CXR) with the deep convolutional neural network (DCNN) models through a fine-tuning and pre-training approach. CXR images pertaining to four health scenarios, namely, healthy, COVID-19, bacterial pneumonia and viral pneumonia, are considered and subjected to data augmentation. Two types of input datasets are prepared; in which dataset I contains the original image dataset categorised under four classes, whereas the original CXR images are subjected to image pre-processing via Contrast Limited Adaptive Histogram Equalisation (CLAHE) algorithm and Blackhat Morphological Operation (BMO) for devising the input dataset II. Both datasets are supplied as input to various DCNN models such as DenseNet, MobileNet, ResNet, VGG16, and Xception for achieving multi-class classification. It is observed that the classification accuracies are improved, and the classification errors are reduced with the image pre-processing. Overall, the VGG16 model resulted in better classification accuracies and reduced classification errors while accomplishing multi-class classification. Thus, the proposed work would assist the clinical diagnosis, and reduce the workload of the front-line healthcare workforce and medical professionals.

PMID:39648993 | DOI:10.1080/03091902.2024.2438158

Diagn Interv Radiol. 2024 Dec 9. doi: 10.4274/dir.2024.242923. Online ahead of print.

ABSTRACT

PURPOSE: The purpose of this study was to propose a new computer-assisted two-staged diagnosis system that combines a modified deep learning (DL) architecture (VGG19) for the classification of digital breast tomosynthesis (DBT) images with the detection of tumors as benign or cancerous using the You Only Look Once version 5 (YOLOv5) model combined with the convolutional block attention module (CBAM) (known as YOLOv5-CBAM).

METHODS: In the modified version of VGG19, eight additional layers were integrated, comprising four batch normalization layers and four additional pooling layers (two max pooling and two average pooling). The CBAM was incorporated into the YOLOv5 model structure after each feature fusion. The experiment was carried out using a sizable benchmark dataset of breast tomography images. A total of 22,032 DBT examinations from 5,060 patients were included in the data.

RESULTS: Test accuracy, training loss, and training accuracy showed better performance with our proposed architecture than with previous models. Hence, the modified VGG19 classified DBT images more accurately than previously possible using pre-trained model-based architectures. Furthermore, a YOLOv5-based CBAM precisely discriminated between benign lesions and those that were malignant.

CONCLUSION: DBT images can be classified using modified VGG19 with accuracy greater than the previously available pre-trained models-based architectures. Furthermore, a YOLOv5-based CBAM can precisely distinguish between benign and cancerous lesions.

CLINICAL SIGNIFICANCE: The proposed two-tier DL algorithm, combining a modified VGG19 model for image classification and YOLOv5-CBAM for lesion detection, can improve the accuracy, efficiency, and reliability of breast cancer screening and diagnosis through innovative artificial intelligence-driven methodologies.

PMID:39648903 | DOI:10.4274/dir.2024.242923

Adv Mater. 2024 Dec 8:e2407613. doi: 10.1002/adma.202407613. Online ahead of print.

ABSTRACT

Designing donor (D) and acceptor (A) structures and discovering promising D-A combinations can effectively improve organic photovoltaic (OPV) device performance. However, to obtain excellent power conversion efficiency (PCE), the trial-and-error structural design in the infinite chemical space is time-consuming and costly. Herein, a deep learning (DL)-assisted design framework for OPV materials is proposed. To effectively digitally represent the D and A structures, a structure representation method, polymer fingerprints, is developed, and a database of OPV materials is constructed. By applying an end-to-end graph neural network modeling method, high-precision DL models for predicting OPV performance are established. After combining the existing structures, ≈0.6 million virtual D-A combinations are generated. Then, the OPV performance of these candidate combinations is predicted by the well-trained models, and numbers of novel D-A combinations with high efficiency are identified. Experimental validations confirm that the prediction accuracy is greater than 93% and one of the screened combinations (i.e., D18:BTP-S11) exhibits an efficiency above 19.3% in single-junction organic solar cells. Finally, based on the structural gene analysis, the design rules to guide experimental explorations are suggested. The developed DL-assisted approach can accelerate the design of D-A combinations with ultrahigh efficiency and bring property breakthroughs for OPV devices.

PMID:39648547 | DOI:10.1002/adma.202407613

Mol Divers. 2024 Dec 8. doi: 10.1007/s11030-024-11055-9. Online ahead of print.

ABSTRACT

Triple-negative breast cancer (TNBC) lacks estrogen, progesterone, and HER2 expression, accounting for 15-20% of breast cancer cases. It is challenging due to low therapeutic response, heterogeneity, and aggressiveness. The PI3Ka isoform is a promising therapeutic target, often hyperactivated in TNBC, contributing to uncontrolled growth and cancer cell formation. We have proposed an interpretable deep convolutional neural network prediction (iDCNNPred) system using 2D molecular images to classify bioactivity and identify potential PI3Ka inhibitors. We built Custom-DCNN models and pre-trained models such as AlexNet, SqueezeNet, and VGG19 by using the Bayesian optimization algorithm, and found that our Custom-DCNN model performed better than a pre-trained model with lower complexity and memory usage. All top-performed models were screened with the Maybridge Chemical library to find predictive hit molecules. The screened molecules were further evaluated for protein-ligand interaction with molecular docking and finally 12 promising hits were shortlisted for biological validation using in-vitro PI3K inhibition studies. After biological evaluation, 4 potent molecules with different structural moieties were identified, and these molecules present new starting scaffolds for further improvement in terms of their potency and selectivity as PI3K inhibitors with the help of medicinal chemistry efforts. Furthermore, we also showed the significance of the interpretation and visualization of the model's predictions by the Grad-CAM technique, enhancing the robustness, transparency, and interpretability of the model's predictions. The data and script files and prediction run of models used for this study to reproduce the experiment are available in the GitHub repository at https://github.com/ravishankar1307/iDCNNPred.git .

PMID:39648257 | DOI:10.1007/s11030-024-11055-9

Biosci Trends. 2024 Dec 8. doi: 10.5582/bst.2024.01342. Online ahead of print.

ABSTRACT

In recent years, machine learning, and particularly deep learning, has shown remarkable potential in various fields, including medicine. Advanced techniques like convolutional neural networks and transformers have enabled high-performance predictions for complex problems, making machine learning a valuable tool in medical decision-making. From predicting postoperative complications to assessing disease risk, machine learning has been actively used to analyze patient data and assist healthcare professionals. However, the "black box" problem, wherein the internal workings of machine learning models are opaque and difficult to interpret, poses a significant challenge in medical applications. The lack of transparency may hinder trust and acceptance by clinicians and patients, making the development of explainable AI (XAI) techniques essential. XAI aims to provide both global and local explanations for machine learning models, offering insights into how predictions are made and which factors influence these outcomes. In this article, we explore various applications of machine learning in medicine, describe commonly used algorithms, and discuss explainable AI as a promising solution to enhance the interpretability of these models. By integrating explainability into machine learning, we aim to ensure its ethical and practical application in healthcare, ultimately improving patient outcomes and supporting personalized treatment strategies.

PMID:39647859 | DOI:10.5582/bst.2024.01342

Radiother Oncol. 2024 Dec 6:110662. doi: 10.1016/j.radonc.2024.110662. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: Fast, high-quality deep learning (DL) prediction of patient-specific 3D dose distributions can enable instantaneous treatment planning (IP), in which the treating physician can evaluate the dose and approve the plan immediately after contouring, rather than days later. This would greatly benefit clinical workload, patient waiting times and treatment quality. IP requires that predicted dose distributions closely match the ground truth. This study examines how training dataset size and model size affect dose prediction accuracy for Erasmus-iCycle GT plans to enable IP.

MATERIALS AND METHODS: For 1250 prostate patients, dose distributions were automatically generated using Erasmus-iCycle. Hierarchically Densely Connected U-Nets with 2/3/4/5/6 pooling layers were trained with datasets of 50/100/250/500/1000 patients, using a validation set of 100 patients. A fixed test set of 150 patients was used for evaluations.

RESULTS: For all model sizes, prediction accuracy increased with the number of training patients, without levelling off at 1000 patients. For 4-6 level models with 1000 training patients, prediction accuracies were high and comparable. For 6 levels and 1000 training patients, the median prediction errors and interquartile ranges for PTV V95%, rectum V75Gy and bladder V65Gy were 0.01 [-0.06,0.15], 0.01 [-0.20,0.29] and -0.02 [-0.27,0.27] %-point. Dose prediction times were around 1.2 s.

CONCLUSION: Although even for 1000 training patients there was no convergence in obtained prediction accuracy yet, the accuracy for the 6-level model with 1000 training patients may be adequate for the pursued instantaneous planning, which is subject of further research.

PMID:39647528 | DOI:10.1016/j.radonc.2024.110662

J Magn Reson. 2024 Nov 29;370:107812. doi: 10.1016/j.jmr.2024.107812. Online ahead of print.

ABSTRACT

In this study, we introduce a denoising method aimed at improving the contrast ratio in low-field MRI (LFMRI) using an advanced 3D deep convolutional residual network model. Our approach employs synthetic brain imaging datasets that closely mimic the contrast and noise characteristics of LFMRI scans, addressing the limitation of available in-vivo LFMRI datasets for training deep learning models. In the simulation data, the Relative Contrast Ratio (RCR) increased, and similar improvements were observed in the in-vivo data across different imaging conditions. Comparative evaluations demonstrate that our model performs better than the widely used non-deep learning method, BM4D, in enhancing RCR and maintaining high spatial frequency components in in-vivo data.

PMID:39647413 | DOI:10.1016/j.jmr.2024.107812

Comput Methods Programs Biomed. 2024 Dec 4;260:108540. doi: 10.1016/j.cmpb.2024.108540. Online ahead of print.

ABSTRACT

BACKGROUND: Ultrasound (US) is a medical imaging modality that plays a crucial role in the early detection of breast cancer. The emergence of numerous deep learning systems has offered promising avenues for the segmentation and classification of breast cancer tumors in US images. However, challenges such as the absence of data standardization, the exclusion of non-tumor images during training, and the narrow view of single-task methodologies have hindered the practical applicability of these systems, often resulting in biased outcomes. This study aims to explore the potential of multi-task systems in enhancing the detection of breast cancer lesions.

METHODS: To address these limitations, our research introduces an end-to-end multi-task framework designed to leverage the inherent correlations between breast cancer lesion classification and segmentation tasks. Additionally, a comprehensive analysis of a widely utilized public breast cancer ultrasound dataset named BUSI was carried out, identifying its irregularities and devising an algorithm tailored for detecting duplicated images in it.

RESULTS: Experiments are conducted utilizing the curated dataset to minimize potential biases in outcomes. Our multi-task framework exhibits superior performance in breast cancer respecting single-task approaches, achieving improvements close to 15% in segmentation and classification. Moreover, a comparative analysis against the state-of-the-art reveals statistically significant enhancements across both tasks.

CONCLUSION: The experimental findings underscore the efficacy of multi-task techniques, showcasing better generalization capabilities when considering all image types: benign, malignant, and non-tumor images. Consequently, our methodology represents an advance towards more general architectures with real clinical applications in the breast cancer field.

PMID:39647406 | DOI:10.1016/j.cmpb.2024.108540

Food Chem. 2024 Nov 12;467:141999. doi: 10.1016/j.foodchem.2024.141999. Online ahead of print.

ABSTRACT

Timely and effective detection of quality attributes during drying control is essential for enhancing the quality of fruit processing. Consequently, this study aims to employ hyperspectral imaging technology for the non-destructive monitoring of soluble solids content (SSC), titratable acidity (TA), moisture, and hardness in jujubes during hot air drying. Quality parameters were measured at drying temperatures of 55 °C, 60 °C, and 65 °C. A deep learning model (CNN_BiLSTM_SE) was developed, incorporating a convolutioyounal neural network (CNN), bidirectional long short-term memory (BiLSTM), and a squeeze-and-excitation (SE) attention mechanism. The performance of PLSR, SVR, and CNN_BiLSTM_SE was compared using different preprocessing methods (MSC, Baseline, and MSC_1st). The CNN_BiLSTM_SE model, optimized for hyperparameters, outperforms PLSR and SVR in predicting jujube quality attributes. Subsequently, these best prediction models were used to predict quality attributes at the pixel level for jujube, enabling the visualization of the Spatio-temporal distribution of these parameters at different drying stages.

PMID:39647380 | DOI:10.1016/j.foodchem.2024.141999

Comput Biol Med. 2024 Dec 7;185:109503. doi: 10.1016/j.compbiomed.2024.109503. Online ahead of print.

ABSTRACT

GI abnormalities significantly increase mortality rates and impose considerable strain on healthcare systems, underscoring the essential requirement for rapid detection, precise diagnosis, and efficient strategic treatment. To develop a CAD system, this study aims to automatically classify GI disorders utilizing various deep learning methodologies. The proposed system features a three-stage lightweight architecture, consisting of a feature extractor using PSE-CNN, a feature selector employing PCA, and a classifier based on DELM. The framework, designed with only 24 layers and 1.25 million parameters, is employed on the largest dataset, GastroVision, containing 8000 images of 27 GI disorders. To improve visual clarity, a sequential preprocessing strategy is implemented. The model's robustness is evaluated through 5-fold cross-validation. Additionally, several XAI methods, namely Grad-CAM, heatmaps, saliency maps, SHAP, and activation feature maps, are used to explore the model's interpretability. Statistical significance is ensured by calculating the p-value, demonstrating the framework's reliability. The proposed model PSE-CNN-PCA-DELM has achieved outstanding results in the first stage, categorizing the diseases' positions into three primary classes, with average accuracy (97.24 %), precision (97.33 ± 0.01 %), recall (97.24 ± 0.01 %), F1-score (97.33 ± 0.01 %), ROC-AUC (99.38 %), and AUC-PR (98.94 %). In the second stage, the dataset is further divided into nine separate classes, considering the overall disease characteristics, and achieves excellent outcomes with average performance rates of 90.00 %, 89.71 ± 0.11 %, 89.59 ± 0.14 %, 89.51 ± 0.12 %, 98.49 %, and 94.63 %, respectively. The third stage involves a more detailed classification into twenty-seven classes, maintaining strong performance with scores of 93.00 %, 82.69 ± 0.37 %, 83.00 ± 0.38 %, 81.54 ± 0.35 %, 97.38 %, and 88.03 %, respectively. The framework's compact size of 14.88 megabytes and average testing time of 59.17 milliseconds make it highly efficient. Its effectiveness is further validated through comparisons with several TL approaches. Practically, the framework is extremely resilient for clinical implementation.

PMID:39647242 | DOI:10.1016/j.compbiomed.2024.109503

Mol Pharm. 2024 Dec 8. doi: 10.1021/acs.molpharmaceut.4c00946. Online ahead of print.

ABSTRACT

The Biopharmaceutics Classification System (BCS) has facilitated biowaivers and played a significant role in enhancing drug regulation and development efficiency. However, the productivity of measuring the key discriminative properties of BCS, solubility and permeability, still requires improvement, limiting high-throughput applications of BCS, which is essential for evaluating drug candidate developability and guiding formulation decisions in the early stages of drug development. In recent years, advancements in machine learning (ML) and molecular characterization have revealed the potential of quantitative structure-performance relationships (QSPR) for rapid and accurate in silico BCS classification. The present study aims to develop a web platform for high-throughput BCS classification based on high-performance ML models. Initially, four data sets of BCS-related molecular properties: log S, log P, log D, and log Papp were curated. Subsequently, 6 ML algorithms or deep learning frameworks were employed to construct models, with diverse molecular representations ranging from one-dimensional molecular fingerprints, descriptors, and molecular graphs to three-dimensional molecular spatial coordinates. By comparing different combinations of molecular representations and learning algorithms, LightGBM exhibited excellent performance in solubility prediction, with an R2 of 0.84; AttentiveFP outperformed others in permeability prediction, with R2 values of 0.96 and 0.76 for log P and log D, respectively; and XGBoost was the most accurate for log Papp prediction, with an R2 of 0.71. When externally validated on a marketed drug BCS category data set, the best-performing models achieved classification accuracies of over 77 and 73% for solubility and permeability, respectively. Finally, the well-trained models were embedded into the first ML-based BCS class prediction web platform (x f), enabling pharmaceutical scientists to quickly determine the BCS category of candidate drugs, which will aid in the high-throughput BCS assessment for candidate drugs during the preformulation stage, thereby promoting reduced risk and enhanced efficiency in drug development and regulation.

PMID:39647169 | DOI:10.1021/acs.molpharmaceut.4c00946

J Eval Clin Pract. 2025 Feb;31(1):e14253. doi: 10.1111/jep.14253.

ABSTRACT

INTRODUCTION: Understanding students' learning approach, modifying teaching methods, curriculum and material accordingly is essential to deliver quality education. Knowing more about the learning approaches assists in upgrading the profession's quality for continuous professional development.

METHODS: The cross-sectional study was carried out among physiotherapy students studying in physiotherapy colleges affiliated with the same university. The Approaches and Study Skills Inventory for Students questionnaire was used to evaluate learning approaches in both preclinical and clinical students. Data were analysed using the IBM Statistical Package SPSS 27. Statistical significance was set at p < 0.05.

RESULTS: A total of 250 participants with a mean age of 21.09 + 1.93 years, 129 (51.6%) in the preclinical group and 121 (48.4%) in the clinical group participated in the study. 67 (26.7%) of the students were male, while 183 (72.9%) were females. The vast majority of participants (97.6%) adopt a deep approach to learning, while only a small fraction (2.0%) use a surface approach, with the strategic approach being rarely used (0.4%). No significant difference was observed between the males and females, and students of different colleges under the same university.

CONCLUSION: The predominant approach is the deep learning approach reflecting active learning. This may indicate that curriculum and strategies of teaching are employed over physiotherapy students to promote quality learning. Also, the teaching preferences varies between two group of physiotherapy students. Thus, this will also assist physiotherapy educators in planning and delivering learning activities according to learners by knowing their preferences.

PMID:39644511 | DOI:10.1111/jep.14253