IEEE Trans Med Imaging. 2024 Apr 11;PP. doi: 10.1109/TMI.2024.3387830. Online ahead of print.

ABSTRACT

Image-guided interventional oncology procedures can greatly enhance the outcome of cancer treatment. As an enhancing procedure, oncology smart material delivery can increase cancer therapy's quality, effectiveness, and safety. However, the effectiveness of enhancing procedures highly depends on the accuracy of smart material placement procedures. Inaccurate placement of smart materials can lead to adverse side effects and health hazards. Image guidance can considerably improve the safety and robustness of smart material delivery. In this study, we developed a novel generative deep-learning platform that highly prioritizes clinical practicality and provides the most informative intra-operative feedback for image-guided smart material delivery. XIOSIS generates a patient-specific 3D volumetric computed tomography (CT) from three intraoperative radiographs (X-ray images) acquired by a mobile C-arm during the operation. As the first of its kind, XIOSIS (i) synthesizes the CT from small field-of-view radiographs;(ii) reconstructs the intra-operative spacer distribution; (iii) is robust; and (iv) is equipped with a novel soft-contrast cost function. To demonstrate the effectiveness of XIOSIS in providing intra-operative image guidance, we applied XIOSIS to the duodenal hydrogel spacer placement procedure. We evaluated XIOSIS performance in an image-guided virtual spacer placement and actual spacer placement in two cadaver specimens. XIOSIS showed a clinically acceptable performance, reconstructed the 3D intra-operative hydrogel spacer distribution with an average structural similarity of 0.88 and Dice coefficient of 0.63 and with less than 1 cm difference in spacer location relative to the spinal cord.

PMID:38602853 | DOI:10.1109/TMI.2024.3387830

Cereb Cortex. 2024 Apr 1;34(4):bhae146. doi: 10.1093/cercor/bhae146.

ABSTRACT

The gyrus, a pivotal cortical folding pattern, is essential for integrating brain structure-function. This study focuses on 2-Hinge and 3-Hinge folds, characterized by the gyral convergence from various directions. Existing voxel-level studies may not adequately capture the precise spatial relationships within cortical folding patterns, especially when relying solely on local cortical characteristics due to their variable shapes and homogeneous frequency-specific features. To overcome these challenges, we introduced a novel model that combines spatial distribution, morphological structure, and functional magnetic resonance imaging data. We utilized spatio-morphological residual representations to enhance and extract subtle variations in cortical spatial distribution and morphological structure during blood oxygenation, integrating these with functional magnetic resonance imaging embeddings using self-attention for spatio-morphological-temporal representations. Testing these representations for identifying cortical folding patterns, including sulci, gyri, 2-Hinge, and 2-Hinge folds, and evaluating the impact of phenotypic data (e.g. stimulus) on recognition, our experimental results demonstrate the model's superior performance, revealing significant differences in cortical folding patterns under various stimulus. These differences are also evident in the characteristics of sulci and gyri folds between genders, with 3-Hinge showing more variations. Our findings indicate that our representations of cortical folding patterns could serve as biomarkers for understanding brain structure-function correlations.

PMID:38602743 | DOI:10.1093/cercor/bhae146

J Chem Theory Comput. 2024 Apr 11. doi: 10.1021/acs.jctc.3c01145. Online ahead of print.

ABSTRACT

The Protein Structure Transformer (PeSTo), a geometric transformer, has exhibited exceptional performance in predicting protein-protein binding interfaces and distinguishing interfaces with nucleic acids, lipids, small molecules, and ions. In this study, we introduce PeSTo-Carbs, an extension of PeSTo specifically engineered to predict protein-carbohydrate binding interfaces. We evaluate the performance of this approach using independent test sets and compare them with those of previous methods. Furthermore, we highlight the model's capability to specialize in predicting interfaces involving cyclodextrins, a biologically and pharmaceutically significant class of carbohydrates. Our method consistently achieves remarkable accuracy despite the scarcity of available structural data for cyclodextrins.

PMID:38602504 | DOI:10.1021/acs.jctc.3c01145

Anal Chem. 2024 Apr 11. doi: 10.1021/acs.analchem.3c04930. Online ahead of print.

ABSTRACT

Raman spectroscopy has been widely used for label-free biomolecular analysis of cells and tissues for pathological diagnosis in vitro and in vivo. AI technology facilitates disease diagnosis based on Raman spectroscopy, including machine learning (PCA and SVM), manifold learning (UMAP), and deep learning (ResNet and AlexNet). However, it is not clear how to optimize the appropriate AI classification model for different types of Raman spectral data. Here, we selected five representative Raman spectral data sets, including endometrial carcinoma, hepatoma extracellular vesicles, bacteria, melanoma cell, diabetic skin, with different characteristics regarding sample size, spectral data size, Raman shift range, tissue sites, Kullback-Leibler (KL) divergence, and significant Raman shifts (i.e., wavenumbers with significant differences between groups), to explore the performance of different AI models (e.g., PCA-SVM, SVM, UMAP-SVM, ResNet or AlexNet). For data set of large spectral data size, Resnet performed better than PCA-SVM and UMAP. By building data characteristic-assisted AI classification model, we optimized the network parameters (e.g., principal components, activation function, and loss function) of AI model based on data size and KL divergence etc. The accuracy improved from 85.1 to 94.6% for endometrial carcinoma grading, from 77.1 to 90.7% for hepatoma extracellular vesicles detection, from 89.3 to 99.7% for melanoma cell detection, from 88.1 to 97.9% for bacterial identification, from 53.7 to 85.5% for diabetic skin screening, and mean time expense of 5 s.

PMID:38602477 | DOI:10.1021/acs.analchem.3c04930

Adv Physiol Educ. 2024 Apr 11. doi: 10.1152/advan.00196.2023. Online ahead of print.

ABSTRACT

This study aimed to compare the impact of the partially flipped physiology classroom (PFC) and the traditional lecture-based classroom (TLC) on students' learning approaches. The study was conducted over five months at Xiangya School of Medicine from February to July 2022 and comprised 71 students majoring in clinical medicine. The experimental group (n = 32) received PFC teaching, while the control group (n = 39) received TLC. The Revised Two-Factor Study Process Questionnaire (R-SPQ-2F) was used to assess the impact of different teaching methods on students' learning approaches. After the PFC, students got significantly higher scores on deep learning approach (Z=-3.133, P<0.05). Conversely, after the TLC, students showed significantly higher scores on surface learning approach (Z=-2.259, P<0.05). After the course, students in the PFC group scored significantly higher in deep learning strategy than those in the TLC group (Z=-2.196, P<0.05). The PFC model had a positive impact on the deep learning motive and strategy, leading to an improvement in the deep approach, which is beneficial for the long-term development of students. In contrast, the TLC model only improved the surface learning approach. The study implies that educators should consider implementing PFC to enhance students' learning approaches.

PMID:38602011 | DOI:10.1152/advan.00196.2023

Food Technol Biotechnol. 2024 Mar;62(1):102-109. doi: 10.17113/ftb.62.01.24.8301.

ABSTRACT

RESEARCH BACKGROUND: The aim of this study is to emphasize the importance of artificial intelligence (AI) and causality modelling of food quality and analysis with 'big data'. AI with structural causal modelling (SCM), based on Bayesian networks and deep learning, enables the integration of theoretical field knowledge in food technology with process production, physicochemical analytics and consumer organoleptic assessments. Food products have complex nature and data are highly dimensional, with intricate interrelations (correlations) that are difficult to relate to consumer sensory perception of food quality. Standard regression modelling techniques such as multiple ordinary least squares (OLS) and partial least squares (PLS) are effectively applied for the prediction by linear interpolations of observed data under cross-sectional stationary conditions. Upgrading linear regression models by machine learning (ML) accounts for nonlinear relations and reveals functional patterns, but is prone to confounding and failed predictions under unobserved nonstationary conditions. Confounding of data variables is the main obstacle to applications of the regression models in food innovations under previously untrained conditions. Hence, this manuscript focuses on applying causal graphical models with Bayesian networks to infer causal relationships and intervention effects between process variables and consumer sensory assessment of food quality.

EXPERIMENTAL APPROACH: This study is based on the data available in the literature on the process of wheat bread baking quality, consumer sensory quality assessments of fermented milk products, and professional wine tasting data. The data for wheat baking quality were regularized by the least absolute shrinkage and selection operator (LASSO elastic net). Bayesian statistics was applied for the evaluation of the model joint probability function for inferring the network structure and parameters. The obtained SCMs are presented as directed acyclic graphs (DAG). D-separation criteria were applied to block confounding effects in estimating direct and total causal effects of process variables and consumer perception on food quality. Probability distributions of causal effects of the intervention of individual process variables on quality are presented as partial dependency plots determined by Bayesian neural networks. In the case of wine quality causality, the total causal effects determined by SCMs are positively validated by the double machine learning (DML) algorithm.

RESULTS AND CONCLUSIONS: The data set of 45 continuous variables corresponding to different chemical, physical and biochemical variables of wheat properties from seven Croatian cultivars during two years of controlled cultivation were analysed. LASSO regularization of the data set yielded the ten key predictors, accounting for 98 % variance of the baking quality data. Based on the key variables, the quality predictive random forest model with 75 % cross-validation accuracy was derived. Causal analysis between the quality and key predictors was based on the Bayesian model shown as a DAG graph. Protein content shows the most important direct causal effect with the corresponding path coefficient of 0.71, and THMM (total high-molecular-mass glutenin subunits) content was an indirect cause with a path coefficient of 0.42, and protein total average causal effect (ACE) was 0.65. The large data set of the quality of fermented milk products included binary consumer sensory data (taste, odour, turbidity), continuous physical variables (temperature, fat, pH, colour) and three grade classes of products by consumer quality assessment. A random forest model was derived for the prediction of the quality classification with an out-of-bag (OOB) error of 0.28 %. The Bayesian network model predicts that the direct causes of the taste classification are temperature, colour and fat content, while the direct causes of the quality classification are temperature, turbidity, odour and fat content. The key quality grade ACE of temperature -0.04 grade/°C and 0.3 quality grade/fat content were estimated. The temperature ACE dependency shows a nonlinear type as negative saturation with the 'breaking' point at 60 °C, while for fat ACE had a positive linear trend. Causal quality analysis of red and white wine was based on the large data set of eleven continuous variables of physical and chemical properties and quality assessments classified in ten classes, from 1 to 10. Each classification was obtained in triplicate by a panel of professional wine tasters. A non-structural double machine learning (DML) algorithm was applied for total ACE quality assessment. The alcohol content of red and white wine had the key positive ACE relative factor of 0.35 quality/alcohol, while volatile acidity had the key negative ACE of -0.2 quality/acidity. The obtained ACE predictions by the unstructured DML algorithm are in close agreement with the ACE obtained by the structural SCM.

NOVELTY AND SCIENTIFIC CONTRIBUTION: Novel methodologies and results for the application of causal artificial intelligence models in the analysis of consumer assessment of the quality of food products are presented. The application of Bayesian network structural causal models (SCM) enables the d-separation of pronounced effects of confounding between parameters in noncausal regression models. Based on the SCM, inference of ACE provides substantiated and validated research hypotheses for new products and support for decisions of potential interventions for improvement in product design, new process introduction, process control, management and marketing.

PMID:38601958 | PMC:PMC11002446 | DOI:10.17113/ftb.62.01.24.8301

Front Pain Res (Lausanne). 2024 Mar 27;5:1372814. doi: 10.3389/fpain.2024.1372814. eCollection 2024.

ABSTRACT

Accurate and objective pain evaluation is crucial in developing effective pain management protocols, aiming to alleviate distress and prevent patients from experiencing decreased functionality. A multimodal automatic assessment framework for acute pain utilizing video and heart rate signals is introduced in this study. The proposed framework comprises four pivotal modules: the Spatial Module, responsible for extracting embeddings from videos; the Heart Rate Encoder, tasked with mapping heart rate signals into a higher dimensional space; the AugmNet, designed to create learning-based augmentations in the latent space; and the Temporal Module, which utilizes the extracted video and heart rate embeddings for the final assessment. The Spatial-Module undergoes pre-training on a two-stage strategy: first, with a face recognition objective learning universal facial features, and second, with an emotion recognition objective in a multitask learning approach, enabling the extraction of high-quality embeddings for the automatic pain assessment. Experiments with the facial videos and heart rate extracted from electrocardiograms of the BioVid database, along with a direct comparison to 29 studies, demonstrate state-of-the-art performances in unimodal and multimodal settings, maintaining high efficiency. Within the multimodal context, 82.74% and 39.77% accuracy were achieved for the binary and multi-level pain classification task, respectively, utilizing 9.62 million parameters for the entire framework.

PMID:38601923 | PMC:PMC11004333 | DOI:10.3389/fpain.2024.1372814

Commun Integr Biol. 2024 Apr 8;17(1):2338073. doi: 10.1080/19420889.2024.2338073. eCollection 2024.

ABSTRACT

In this hypothesis, I discuss how laughter from physical play could have evolved to being induced via visual or even verbal stimuli, and serves as a signal to highlight incongruity that could potentially pose a threat to survival. I suggest how laughter's induction could have negated the need for physical contact in play, evolving from its use in tickling, to tickle-misses, and to taunting, and I discuss how the application of deep learning neural networks trained on images of spectra of a variety of laughter types from a variety of individuals or even species, could be used to determine such evolutionary pathways via the use of latent space exploration.

PMID:38601922 | PMC:PMC11005796 | DOI:10.1080/19420889.2024.2338073

Front Radiol. 2024 Mar 27;4:1385742. doi: 10.3389/fradi.2024.1385742. eCollection 2024.

ABSTRACT

The aim of this systematic review is to determine whether Deep Learning (DL) algorithms can provide a clinically feasible alternative to classic algorithms for synthetic Computer Tomography (sCT). The following categories are presented in this study: ∙ MR-based treatment planning and synthetic CT generation techniques. ∙ Generation of synthetic CT images based on Cone Beam CT images. ∙ Low-dose CT to High-dose CT generation. ∙ Attenuation correction for PET images. To perform appropriate database searches, we reviewed journal articles published between January 2018 and June 2023. Current methodology, study strategies, and results with relevant clinical applications were analyzed as we outlined the state-of-the-art of deep learning based approaches to inter-modality and intra-modality image synthesis. This was accomplished by contrasting the provided methodologies with traditional research approaches. The key contributions of each category were highlighted, specific challenges were identified, and accomplishments were summarized. As a final step, the statistics of all the cited works from various aspects were analyzed, which revealed that DL-based sCTs have achieved considerable popularity, while also showing the potential of this technology. In order to assess the clinical readiness of the presented methods, we examined the current status of DL-based sCT generation.

PMID:38601888 | PMC:PMC11004271 | DOI:10.3389/fradi.2024.1385742

PNAS Nexus. 2024 Mar 29;3(4):pgae133. doi: 10.1093/pnasnexus/pgae133. eCollection 2024 Apr.

ABSTRACT

Deep learning algorithms have been widely used in microscopic image translation. The corresponding data-driven models can be trained by supervised or unsupervised learning depending on the availability of paired data. However, general cases are where the data are only roughly paired such that supervised learning could be invalid due to data unalignment, and unsupervised learning would be less ideal as the roughly paired information is not utilized. In this work, we propose a unified framework (U-Frame) that unifies supervised and unsupervised learning by introducing a tolerance size that can be adjusted automatically according to the degree of data misalignment. Together with the implementation of a global sampling rule, we demonstrate that U-Frame consistently outperforms both supervised and unsupervised learning in all levels of data misalignments (even for perfectly aligned image pairs) in a myriad of image translation applications, including pseudo-optical sectioning, virtual histological staining (with clinical evaluations for cancer diagnosis), improvement of signal-to-noise ratio or resolution, and prediction of fluorescent labels, potentially serving as new standard for image translation.

PMID:38601859 | PMC:PMC11004937 | DOI:10.1093/pnasnexus/pgae133

Front Oncol. 2024 Mar 27;14:1363812. doi: 10.3389/fonc.2024.1363812. eCollection 2024.

ABSTRACT

BACKGROUND: Artificial intelligence (AI) models, clinical models (CM), and the integrated model (IM) are utilized to evaluate the response to neoadjuvant chemotherapy (NACT) in patients diagnosed with gastric cancer.

OBJECTIVE: The objective is to identify the diagnostic test of the AI model and to compare the accuracy of AI, CM, and IM through a comprehensive summary of head-to-head comparative studies.

METHODS: PubMed, Web of Science, Cochrane Library, and Embase were systematically searched until September 5, 2023, to compile English language studies without regional restrictions. The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) criteria. Forest plots were utilized to illustrate the findings of diagnostic accuracy, while Hierarchical Summary Receiver Operating Characteristic curves were generated to estimate sensitivity (SEN) and specificity (SPE). Meta-regression was applied to analyze heterogeneity across the studies. To assess the presence of publication bias, Deeks' funnel plot and an asymmetry test were employed.

RESULTS: A total of 9 studies, comprising 3313 patients, were included for the AI model, with 7 head-to-head comparative studies involving 2699 patients. Across the 9 studies, the pooled SEN for the AI model was 0.75 (95% confidence interval (CI): 0.66, 0.82), and SPE was 0.77 (95% CI: 0.69, 0.84). Meta-regression was conducted, revealing that the cut-off value, approach to predicting response, and gold standard might be sources of heterogeneity. In the head-to-head comparative studies, the pooled SEN for AI was 0.77 (95% CI: 0.69, 0.84) with SPE at 0.79 (95% CI: 0.70, 0.85). For CM, the pooled SEN was 0.67 (95% CI: 0.57, 0.77) with SPE at 0.59 (95% CI: 0.54, 0.64), while for IM, the pooled SEN was 0.83 (95% CI: 0.79, 0.86) with SPE at 0.69 (95% CI: 0.56, 0.79). Notably, there was no statistical difference, except that IM exhibited higher SEN than AI, while maintaining a similar level of SPE in pairwise comparisons. In the Receiver Operating Characteristic analysis subgroup, the CT-based Deep Learning (DL) subgroup, and the National Comprehensive Cancer Network (NCCN) guideline subgroup, the AI model exhibited higher SEN but lower SPE compared to the IM. Conversely, in the training cohort subgroup and the internal validation cohort subgroup, the AI model demonstrated lower SEN but higher SPE than the IM. The subgroup analysis underscored that factors such as the number of cohorts, cohort type, cut-off value, approach to predicting response, and choice of gold standard could impact the reliability and robustness of the results.

CONCLUSION: AI has demonstrated its viability as a tool for predicting the response of GC patients to NACT Furthermore, CT-based DL model in AI was sensitive to extract tumor features and predict the response. The results of subgroup analysis also supported the above conclusions. Large-scale rigorously designed diagnostic accuracy studies and head-to-head comparative studies are anticipated.

SYSTEMATIC REVIEW REGISTRATION: PROSPERO, CRD42022377030.

PMID:38601765 | PMC:PMC11004479 | DOI:10.3389/fonc.2024.1363812

Heliyon. 2024 Apr 6;10(7):e29249. doi: 10.1016/j.heliyon.2024.e29249. eCollection 2024 Apr 15.

ABSTRACT

Peritoneal carcinomatosis (PC) is a type of secondary cancer which is not sensitive to conventional intravenous chemotherapy. Treatment strategies for PC are usually palliative rather than curative. Recently, artificial intelligence (AI) has been widely used in the medical field, making the early diagnosis, individualized treatment, and accurate prognostic evaluation of various cancers, including mediastinal malignancies, colorectal cancer, lung cancer more feasible. As a branch of computer science, AI specializes in image recognition, speech recognition, automatic large-scale data extraction and output. AI technologies have also made breakthrough progress in the field of peritoneal carcinomatosis (PC) based on its powerful learning capacity and efficient computational power. AI has been successfully applied in various approaches in PC diagnosis, including imaging, blood tests, proteomics, and pathological diagnosis. Due to the automatic extraction function of the convolutional neural network and the learning model based on machine learning algorithms, AI-assisted diagnosis types are associated with a higher accuracy rate compared to conventional diagnosis methods. In addition, AI is also used in the treatment of peritoneal cancer, including surgical resection, intraperitoneal chemotherapy, systemic chemotherapy, which significantly improves the survival of patients with PC. In particular, the recurrence prediction and emotion evaluation of PC patients are also combined with AI technology, further improving the quality of life of patients. Here we have comprehensively reviewed and summarized the latest developments in the application of AI in PC, helping oncologists to comprehensively diagnose PC and provide more precise treatment strategies for patients with PC.

PMID:38601686 | PMC:PMC11004411 | DOI:10.1016/j.heliyon.2024.e29249

Heliyon. 2024 Mar 24;10(7):e28062. doi: 10.1016/j.heliyon.2024.e28062. eCollection 2024 Apr 15.

ABSTRACT

Brain tumors are abnormal cell masses that can get originated in the brain spread from other organs. They can be categorized as either malignant (cancerous) or benign (noncancerous), and their growth rates and locations can impact the functioning of the nerve system. The timely detection of brain tumors is crucial for effective treatment and prognosis. In this study, a new approach has been proposed for diagnosing brain tumors using deep learning and a meta-heuristic algorithm. The method involves three main steps: (1) extracting features from brain MRI images using AlexNet, (2) reducing the complexity of AlexNet by employing an Extreme Learning Machine (ELM) network as a classification layer, and (3) fine-tuning the parameters of the ELM network using an Amended Grasshopper Optimization Algorithm (AGOA). The performance of the method has been evaluated on a publicly available dataset consisting of 20 patients with newly diagnosed glioblastoma that is compared with several state-of-the-art techniques. Experimental results demonstrate that the method achieves the highest accuracy, precision, specificity, F1-score, sensitivity, and MCC with values of 0.96, 0.94, 0.96, 0.96, 0.94, and 0.90, respectively. Furthermore, the robustness and stability of the method have been illustrated when subjected to different levels of noise and image resolutions. The proposed approach offers a rapid, accurate, and dependable diagnosis of brain tumors and holds potential for application in other medical image analysis tasks.

PMID:38601620 | PMC:PMC11004699 | DOI:10.1016/j.heliyon.2024.e28062

Heliyon. 2024 Mar 29;10(7):e28058. doi: 10.1016/j.heliyon.2024.e28058. eCollection 2024 Apr 15.

ABSTRACT

Skin blemishes can be caused by multiple events or diseases and, in some cases, it is difficult to distinguish where they come from. Therefore, there may be cases with a dangerous origin that go unnoticed or the opposite case (which can lead to overcrowding of health services). To avoid this, the use of artificial intelligence-based classifiers using images taken with mobile devices is proposed; this would help in the initial screening process and provide some information to the patient prior to their final diagnosis. To this end, this work proposes an optimization mechanism based on two phases in which a global search for the best classifiers (from among more than 150 combinations) is carried out, and, in the second phase, the best candidates are subjected to a phase of evaluation of the robustness of the system by applying the cross-validation technique. The results obtained reach 99.95% accuracy for the best case and 99.75% AUC. Comparing the developed classifier with previous works, an improvement in terms of classification rate is appreciated, as well as in the reduction of the classifier complexity, which allows our classifier to be integrated in a specific purpose system with few computational resources.

PMID:38601606 | PMC:PMC11004532 | DOI:10.1016/j.heliyon.2024.e28058

Dent Mater J. 2024 Apr 11. doi: 10.4012/dmj.2023-253. Online ahead of print.

ABSTRACT

The purpose of this study was to construct deep learning models for more efficient and reliable sex estimation. Two deep learning models, VGG16 and DenseNet-121, were used in this retrospective study. In total, 600 lateral cephalograms were analyzed. A saliency map was generated by gradient-weighted class activation mapping for each output. The two deep learning models achieved high values in each performance metric according to accuracy, sensitivity (recall), precision, F1 score, and areas under the receiver operating characteristic curve. Both models showed substantial differences in the positions indicated in saliency maps for male and female images. The positions in saliency maps also differed between VGG16 and DenseNet-121, regardless of sex. This analysis of our proposed system suggested that sex estimation from lateral cephalograms can be achieved with high accuracy using deep learning.

PMID:38599831 | DOI:10.4012/dmj.2023-253

Environ Sci Technol. 2024 Apr 10. doi: 10.1021/acs.est.3c08734. Online ahead of print.

ABSTRACT

Often large quantities of plastics are found in compost, with price look-up stickers being a major but little-explored component in the contamination path. Stickers glued to fruit or vegetable peels usually remain attached to the organic material despite sorting processes in the composting plant. Here, we investigated the effects of industrial composting on the structural alterations of these stickers. Commercial polypropylene (PP) stickers on banana peels were added to a typical organic material mixture for processing in an industrial composting plant and successfully resampled after a prerotting (11 days) and main rotting step (25 days). Afterward, both composted and original stickers were analyzed for surface and structural changes via scanning electron microscopy, Fourier-transform infrared spectroscopy, and micro- and nano-X-ray computed tomography (CT) combined with deep learning approaches. The composting resulted in substantial surface changes and degradation in the form of microbial colonization, deformation, and occurrence of cracks in all stickers. Their pore volumes increased from 16.7% in the original sticker to 26.3% at the end of the compost process. In a similar way, the carbonyl index of the stickers increased. Micro-CT images additionally revealed structural changes in the form of large adhesions that penetrated the surface of the sticker. These changes were accompanied by delamination after 25 days of composting, thus overall hinting at the degradation of the stickers and the subsequent formation of smaller microplastic pieces.

PMID:38599582 | DOI:10.1021/acs.est.3c08734

Int J Biol Macromol. 2024 Apr 8:131311. doi: 10.1016/j.ijbiomac.2024.131311. Online ahead of print.

ABSTRACT

In the rapidly evolving field of computational biology, accurate prediction of protein secondary structures is crucial for understanding protein functions, facilitating drug discovery, and advancing disease diagnostics. In this paper, we propose MFTrans, a deep learning-based multi-feature fusion network aimed at enhancing the precision and efficiency of Protein Secondary Structure Prediction (PSSP). This model employs a Multiple Sequence Alignment (MSA) Transformer in combination with a multi-view deep learning architecture to effectively capture both global and local features of protein sequences. MFTrans integrates diverse features generated by protein sequences, including MSA, sequence information, evolutionary information, and hidden state information, using a multi-feature fusion strategy. The MSA Transformer is utilized to interleave row and column attention across the input MSA, while a Transformer encoder and decoder are introduced to enhance the extracted high-level features. A hybrid network architecture, combining a convolutional neural network with a bidirectional Gated Recurrent Unit (BiGRU) network, is used to further extract high-level features after feature fusion. In independent tests, our experimental results show that MFTrans has superior generalization ability, outperforming other state-of-the-art PSSP models by 3 % on average on public benchmarks including CASP12, CASP13, CASP14, TEST2016, TEST2018, and CB513. Case studies further highlight its advanced performance in predicting mutation sites. MFTrans contributes significantly to the protein science field, opening new avenues for drug discovery, disease diagnosis, and protein.

PMID:38599417 | DOI:10.1016/j.ijbiomac.2024.131311

Physiol Meas. 2024 Apr 10. doi: 10.1088/1361-6579/ad3d28. Online ahead of print.

ABSTRACT

This study aims to automate the segmentation of retinal arterioles and venules (A/V) from digital fundus images (DFI), as changes in the spatial distribution of retinal microvasculature are indicative of cardiovascular diseases, positioning the eyes as windows to cardiovascular health.&#xD;&#xD;Approach: We utilized active learning to create a new DFI dataset with 240 crowd-sourced manual A/V segmentations performed by 15 medical students and reviewed by an ophthalmologist. We then developed LUNet, a novel deep learning architecture optimized for high-resolution A/V segmentation. The LUNet model features a double dilated convolutional block to widen the receptive field and reduce parameter count, alongside a high-resolution tail to refine segmentation details. A custom loss function was designed to prioritize the continuity of blood vessel segmentation.&#xD;&#xD;Main Results: LUNet significantly outperformed three benchmark A/V segmentation algorithms both on a local test set and on four external test sets that simulated variations in ethnicity, comorbidities and annotators.&#xD;&#xD;Significance: The release of the new datasets and the LUNet model (URL upon publication) provides a valuable resource for the advancement of retinal microvasculature analysis. The improvements in A/V segmentation accuracy highlight LUNet's potential as a robust tool for diagnosing and understanding cardiovascular diseases through retinal imaging.

PMID:38599224 | DOI:10.1088/1361-6579/ad3d28

Physiol Meas. 2024 Apr 10. doi: 10.1088/1361-6579/ad3d25. Online ahead of print.

ABSTRACT

OBJECTIVE: &#xD;Myocardial infarction (MI) is a serious cardiovascular disease that can cause irreversible damage to the heart, making early identification and treatment crucial. However, automatic MI detection and localization from an electrocardiogram (ECG) remain challenging. In this study, we propose two models, MFB-SENET and MFB-DMIL, for MI detection and localization, respectively.

APPROACH: The MFB-SENET model is designed to detect MI, while the MFB-DMIL model is designed to localize MI. The MI localization model employs a specialized attention mechanism to integrate multi-instance learning with domain knowledge. This approach incorporates handcrafted features and introduces a new loss function called lead-loss, to improve MI localization. Grad-CAM is employed to visualize the decision-making process.&#xD;Main Results:&#xD;The proposed method was evaluated on the PTB and PTB-XL databases. Under the inter-patient scheme, the accuracy of MI detection and localization on the PTB database reached 93.88% and 67.17%, respectively. The accuracy of MI detection and localization on the PTB-XL database were 94.89% and 85.83%, respectively.

SIGNIFICANCE: Our method achieved comparable or better performance than other state-of-the-art algorithms. The proposed method combined deep learning and medical domain knowledge, demonstrates effectiveness and reliability, holding promise as an efficient MI diagnostic tool to assist physicians in formulating accurate diagnoses.&#xD.

PMID:38599223 | DOI:10.1088/1361-6579/ad3d25

Biomed Phys Eng Express. 2024 Apr 10. doi: 10.1088/2057-1976/ad3cde. Online ahead of print.

ABSTRACT

Prompt diagnosis of epilepsy relies on accurate classification of automated electroencephalogram (EEG) signals. Several approaches have been developed to characterize epileptic EEG data; however, none of them have exploited time-frequency data to evaluate the effect of tweaking parameters in pretrained frameworks for EEG data classification. This study compares the performance of several pretrained convolutional neural networks (CNNs) namely, AlexNet, GoogLeNet, MobileNetV2, ResNet-18 and SqueezeNet for the localization of epilepsy EEG data using various time-frequency data representation algorithms. Continuous wavelet transform (CWT), empirical Fourier decomposition (EFD), empirical mode decomposition (EMD), empirical wavelet transform (EWT), and variational mode decomposition (VMD) were exploited for the acquisition of 2D scalograms from 1D data. The research evaluates the effect of multiple factors, including noisy versus denoised scalograms, different optimizers, learning rates, single versus dual channels, model size, and computational time consumption. The benchmark Bern Barcelona EEG dataset is used for testing purpose. Results obtained show that the combination of MobileNetV2, Continuous Wavelet Transform (CWT) and Adam optimizer at a learning rate of 10^-4, coupled with dual-data channels, provides the best performance metrics. Specifically, these parameters result in optimal sensitivity, specificity, f1-score, and classification accuracy, with respective values of 96.06%, 96.15%, 96.08%, and 96.10%. To further corroborate the efficacy of opted pretrained models on exploited Signal Decomposition (SD) algorithms, the classifiers are also being simulated on Temple University database at pinnacle modeling composition. A similar pattern in the outcome readily validate the findings of our study and robustness of deep learning models on epilepsy EEG scalograms.The conclusions drawn emphasize the potential of pretrained CNN-based models to create a robust, automated system for diagnosing epileptiform. Furthermore, the study offers insights into the effectiveness of varying time-frequency techniques and classifier parameters for classifying epileptic EEG data.

PMID:38599183 | DOI:10.1088/2057-1976/ad3cde