Biol Lett. 2024 May;20(5):20240037. doi: 10.1098/rsbl.2024.0037. Epub 2024 May 29.

ABSTRACT

Animal play encompasses a variety of aspects, with kinematic and social aspects being particularly prevalent in mammalian play behaviour. While the developmental effects of play have been increasingly documented in recent decades, understanding the specific contributions of different play aspects remains crucial to understand the function and evolutionary benefit of animal play. In our study, developing male rats were exposed to rough-and-tumble play selectively reduced in either the kinematic or the social aspect. We then assessed the developmental effects of reduced play on their appraisal of standardized human-rat play ('tickling') by examining their emission of 50 kHz ultrasonic vocalizations (USVs). Using a deep learning framework, we efficiently classified five subtypes of these USVs across six behavioural states. Our results revealed that rats lacking the kinematic aspect in play emitted fewer USVs during tactile contacts by human and generally produced fewer USVs of positive valence compared with control rats. Rats lacking the social aspect did not differ from the control and the kinematically reduced group. These results indicate aspects of play have different developmental effects, underscoring the need for researchers to further disentangle how each aspect affects animals.

PMID:38808945 | DOI:10.1098/rsbl.2024.0037

NMR Biomed. 2024 May 29:e5179. doi: 10.1002/nbm.5179. Online ahead of print.

ABSTRACT

Deep learning presents a generalizable solution for motion correction requiring no pulse sequence modifications or additional hardware, but previous networks have all been applied to coil-combined data. Multichannel MRI data provide a degree of spatial encoding that may be useful for motion correction. We hypothesize that incorporating deep learning for motion correction prior to coil combination will improve results. A conditional generative adversarial network was trained using simulated rigid motion artifacts in brain images acquired at multiple sites with multiple contrasts (not limited to healthy subjects). We compared the performance of deep-learning-based motion correction on individual channel images (single-channel model) with that performed after coil combination (channel-combined model). We also investigate simultaneous motion correction of all channel data from an image volume (multichannel model). The single-channel model significantly (p < 0.0001) improved mean absolute error, with an average 50.9% improvement compared with the uncorrected images. This was significantly (p < 0.0001) better than the 36.3% improvement achieved by the channel-combined model (conventional approach). The multichannel model provided no significant improvement in quantitative measures of image quality compared with the uncorrected images. Results were independent of the presence of pathology, and generalizable to a new center unseen during training. Performing motion correction on single-channel images prior to coil combination provided an improvement in performance compared with conventional deep-learning-based motion correction. Improved deep learning methods for retrospective correction of motion-affected MR images could reduce the need for repeat scans if applied in a clinical setting.

PMID:38808752 | DOI:10.1002/nbm.5179

Network. 2024 May 29:1-30. doi: 10.1080/0954898X.2024.2349275. Online ahead of print.

ABSTRACT

Sentiment Analysis (SA) is a technique for categorizing texts based on the sentimental polarity of people's opinions. This paper introduces a sentiment analysis (SA) model with text and emojis. The two preprocessed data's are data with text and emojis and text without emojis. Feature extraction consists text features and text with emojis features. The text features are features like N-grams, modified Term Frequency-Inverse Document Frequency (TF-IDF), and Bag-of-Words (BoW) features extracted from the text. In classification, CNN (Conventional Neural Network) and MLP (Multi-Layer Perception) use emojis and text-based SA. The CNN weight is optimized by a new Electric fish Customized Shark Smell Optimization (ECSSO) Algorithm. Similarly, the text-based SA is carried out by hybrid Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) classifiers. The bagged data are given as input to the classification process via RNN and LSTM. Here, the weight of LSTM is optimized by the suggested ECSSO algorithm. Then, the mean of LSTM and RNN determines the final output. The specificity of the developed scheme is 29.01%, 42.75%, 23.88%,22.07%, 25.31%, 18.42%, 5.68%, 10.34%, 6.20%, 6.64%, and 6.84% better for 70% than other models. The efficiency of the proposed scheme is computed and evaluated.

PMID:38808648 | DOI:10.1080/0954898X.2024.2349275

J Environ Qual. 2024 May 29. doi: 10.1002/jeq2.20574. Online ahead of print.

ABSTRACT

High rate of aquatic mortality incidents recorded in Taiwan and worldwide is creating an urgent demand for more accurate fish mortality prediction. Present study innovatively integrated air and water quality data to measure water quality degradation, and utilized deep learning methods to predict accidental fish mortality from the data. Keras library was used to build multilayer perceptron and long short-term memory models for training purposes, and the models' accuracies in fish mortality prediction were compared with that of the naïve Bayesian classifier. Environmental data from the 5 days before a fish mortality event proved to be the most important data for effective model training. Multilayer perceptron model reached an accuracy of 93.4%, with a loss function of 0.01, when meteorological and water quality data were jointly considered. It was found that meteorological conditions were not the sole contributors to fish mortality. Predicted fish mortality rate of 4.7% closely corresponded to the true number of fish mortality events during the study period, that is, four. A significant surge in fish mortality, from 20% to 50%, was noted when the river pollution index increased from 5.36 to 6.5. Moreover, the probability of fish mortality increased when the concentration of dissolved oxygen dropped below 2 mg/L. To mitigate fish mortality, ammonia nitrogen concentrations should be capped at 5 mg/L. Dissolved oxygen concentration was found to be the paramount factor influencing fish mortality, followed by the river pollution index and meteorological data. Results of the present study are expected to aid progress toward achieving the Sustainable Development Goals and to increase the profitability of water resources.

PMID:38808585 | DOI:10.1002/jeq2.20574

J Dent Res. 2024 May 29:220345241253186. doi: 10.1177/00220345241253186. Online ahead of print.

ABSTRACT

The increasing application of virtual surgical planning (VSP) in orthognathic surgery implies a critical need for accurate prediction of facial and skeletal shapes. The craniofacial relationship in patients with dentofacial deformities is still not understood, and transformations between facial and skeletal shapes remain a challenging task due to intricate anatomical structures and nonlinear relationships between the facial soft tissue and bones. In this study, a novel bidirectional 3-dimensional (3D) deep learning framework, named P2P-ConvGC, was developed and validated based on a large-scale data set for accurate subject-specific transformations between facial and skeletal shapes. Specifically, the 2-stage point-sampling strategy was used to generate multiple nonoverlapping point subsets to represent high-resolution facial and skeletal shapes. Facial and skeletal point subsets were separately input into the prediction system to predict the corresponding skeletal and facial point subsets via the skeletal prediction subnetwork and facial prediction subnetwork. For quantitative evaluation, the accuracy was calculated with shape errors and landmark errors between the predicted skeleton or face with corresponding ground truths. The shape error was calculated by comparing the predicted point sets with the ground truths, with P2P-ConvGC outperforming existing state-of-the-art algorithms including P2P-Net, P2P-ASNL, and P2P-Conv. The total landmark errors (Euclidean distances of craniomaxillofacial landmarks) of P2P-ConvGC in the upper skull, mandible, and facial soft tissues were 1.964 ± 0.904 mm, 2.398 ± 1.174 mm, and 2.226 ± 0.774 mm, respectively. Furthermore, the clinical feasibility of the bidirectional model was validated using a clinical cohort. The result demonstrated its prediction ability with average surface deviation errors of 0.895 ± 0.175 mm for facial prediction and 0.906 ± 0.082 mm for skeletal prediction. To conclude, our proposed model achieved good performance on the subject-specific prediction of facial and skeletal shapes and showed clinical application potential in postoperative facial prediction and VSP for orthognathic surgery.

PMID:38808566 | DOI:10.1177/00220345241253186

Technol Cancer Res Treat. 2024 Jan-Dec;23:15330338241256594. doi: 10.1177/15330338241256594.

ABSTRACT

Purpose: Intensity-modulated radiotherapy (IMRT) is currently the most important treatment method for nasopharyngeal carcinoma (NPC). This study aimed to enhance prediction accuracy by incorporating dose information into a deep convolutional neural network (CNN) using a multichannel input method. Methods: A target conformal plan (TCP) was created based on the maximum planning target volume (PTV). Input data included TCP dose distribution, images, target structures, and organ-at-risk (OAR) information. The role of target conformal plan dose (TCPD) was assessed by comparing the TCPD-CNN (with dose information) and NonTCPD-CNN models (without dose information) using statistical analyses with the ranked Wilcoxon test (P < .05 considered significant). Results: The TCPD-CNN model showed no statistical differences in predicted target indices, except for PTV60, where differences in the D98% indicator were < 0.5%. For OARs, there were no significant differences in predicted results, except for some small-volume or closely located OARs. On comparing TCPD-CNN and NonTCPD-CNN models, TCPD-CNN's dose-volume histograms closely resembled clinical plans with higher similarity index. Mean dose differences for target structures (predicted TCPD-CNN and NonTCPD-CNN results) were within 3% of the maximum prescription dose for both models. TCPD-CNN and NonTCPD-CNN outcomes were 67.9% and 54.2%, respectively. 3D gamma pass rates of the target structures and the entire body were higher in TCPD-CNN than in the NonTCPD-CNN models (P < .05). Additional evaluation on previously unseen volumetric modulated arc therapy plans revealed that average 3D gamma pass rates of the target structures were larger than 90%. Conclusions: This study presents a novel framework for dose distribution prediction using deep learning and multichannel input, specifically incorporating TCPD information, enhancing prediction accuracy for IMRT in NPC treatment.

PMID:38808514 | DOI:10.1177/15330338241256594

Front Artif Intell. 2024 May 14;7:1403593. doi: 10.3389/frai.2024.1403593. eCollection 2024.

ABSTRACT

Crickets (Gryllus bimaculatus) produce sounds as a natural means to communicate and convey various behaviors and activities, including mating, feeding, aggression, distress, and more. These vocalizations are intricately linked to prevailing environmental conditions such as temperature and humidity. By accurately monitoring, identifying, and appropriately addressing these behaviors and activities, the farming and production of crickets can be enhanced. This research implemented a decision support system that leverages machine learning (ML) algorithms to decode and classify cricket songs, along with their associated key weather variables (temperature and humidity). Videos capturing cricket behavior and weather variables were recorded. From these videos, sound signals were extracted and classified such as calling, aggression, and courtship. Numerical and image features were extracted from the sound signals and combined with the weather variables. The extracted numerical features, i.e., Mel-Frequency Cepstral Coefficients (MFCC), Linear Frequency Cepstral Coefficients, and chroma, were used to train shallow (support vector machine, k-nearest neighbors, and random forest (RF)) ML algorithms. While image features, i.e., spectrograms, were used to train different state-of-the-art deep ML models, i,e., convolutional neural network architectures (ResNet152V2, VGG16, and EfficientNetB4). In the deep ML category, ResNet152V2 had the best accuracy of 99.42%. The RF algorithm had the best accuracy of 95.63% in the shallow ML category when trained with a combination of MFCC+chroma and after feature selection. In descending order of importance, the top 6 ranked features in the RF algorithm were, namely humidity, temperature, C#, mfcc11, mfcc10, and D. From the selected features, it is notable that temperature and humidity are necessary for growth and metabolic activities in insects. Moreover, the songs produced by certain cricket species naturally align to musical tones such as C# and D as ranked by the algorithm. Using this knowledge, a decision support system was built to guide farmers about the optimal temperature and humidity ranges and interpret the songs (calling, aggression, and courtship) in relation to weather variables. With this information, farmers can put in place suitable measures such as temperature regulation, humidity control, addressing aggressors, and other relevant interventions to minimize or eliminate losses and enhance cricket production.

PMID:38808214 | PMC:PMC11130480 | DOI:10.3389/frai.2024.1403593

Comput Struct Biotechnol J. 2024 May 15;23:2116-2121. doi: 10.1016/j.csbj.2024.05.017. eCollection 2024 Dec.

ABSTRACT

De novo drug design aims to rationally discover novel and potent compounds while reducing experimental costs during the drug development stage. Despite the numerous generative models that have been developed, few successful cases of drug design utilizing generative models have been reported. One of the most common challenges is designing compounds that are not synthesizable or realistic. Therefore, methods capable of accurately assessing the chemical structures proposed by generative models for drug design are needed. In this study, we present AnoChem, a computational framework based on deep learning designed to assess the likelihood of a generated molecule being real. AnoChem achieves an area under the receiver operating characteristic curve score of 0.900 for distinguishing between real and generated molecules. We utilized AnoChem to evaluate and compare the performances of several generative models, using other metrics, namely SAscore and Fréschet ChemNet distance (FCD). AnoChem demonstrates a strong correlation with these metrics, validating its effectiveness as a reliable tool for assessing generative models. The source code for AnoChem is available at https://github.com/CSB-L/AnoChem.

PMID:38808129 | PMC:PMC11130677 | DOI:10.1016/j.csbj.2024.05.017

Front Neurosci. 2024 May 14;18:1339075. doi: 10.3389/fnins.2024.1339075. eCollection 2024.

ABSTRACT

AIM: Conventional approaches to diagnosing common eye diseases using B-mode ultrasonography are labor-intensive and time-consuming, must requiring expert intervention for accuracy. This study aims to address these challenges by proposing an intelligence-assisted analysis five-classification model for diagnosing common eye diseases using B-mode ultrasound images.

METHODS: This research utilizes 2064 B-mode ultrasound images of the eye to train a novel model integrating artificial intelligence technology.

RESULTS: The ConvNeXt-L model achieved outstanding performance with an accuracy rate of 84.3% and a Kappa value of 80.3%. Across five classifications (no obvious abnormality, vitreous opacity, posterior vitreous detachment, retinal detachment, and choroidal detachment), the model demonstrated sensitivity values of 93.2%, 67.6%, 86.1%, 89.4%, and 81.4%, respectively, and specificity values ranging from 94.6% to 98.1%. F1 scores ranged from 71% to 92%, while AUC values ranged from 89.7% to 97.8%.

CONCLUSION: Among various models compared, the ConvNeXt-L model exhibited superior performance. It effectively categorizes and visualizes pathological changes, providing essential assisted information for ophthalmologists and enhancing diagnostic accuracy and efficiency.

PMID:38808029 | PMC:PMC11130417 | DOI:10.3389/fnins.2024.1339075

Heliyon. 2024 May 17;10(10):e31395. doi: 10.1016/j.heliyon.2024.e31395. eCollection 2024 May 30.

ABSTRACT

Accurate segmentation is crucial in diagnosing and analyzing skin lesions. However, automatic segmentation of skin lesions is extremely challenging because of their variable sizes, uneven color distributions, irregular shapes, hair occlusions, and blurred boundaries. Owing to the limited range of convolutional networks receptive fields, shallow convolution cannot extract the global features of images and thus has limited segmentation performance. Because medical image datasets are small in scale, the use of excessively deep networks could cause overfitting and increase computational complexity. Although transformer networks can focus on extracting global information, they cannot extract sufficient local information and accurately segment detailed lesion features. In this study, we designed a dual-branch encoder that combines a convolution neural network (CNN) and a transformer. The CNN branch of the encoder comprises four layers, which learn the local features of images through layer-wise downsampling. The transformer branch also comprises four layers, enabling the learning of global image information through attention mechanisms. The feature fusion module in the network integrates local features and global information, emphasizes important channel features through the channel attention mechanism, and filters irrelevant feature expressions. The information exchange between the decoder and encoder is finally achieved through skip connections to supplement the information lost during the sampling process, thereby enhancing segmentation accuracy. The data used in this paper are from four public datasets, including images of melanoma, basal cell tumor, fibroma, and benign nevus. Because of the limited size of the image data, we enhanced them using methods such as random horizontal flipping, random vertical flipping, random brightness enhancement, random contrast enhancement, and rotation. The segmentation accuracy is evaluated through intersection over union and duration, integrity, commitment, and effort indicators, reaching 87.7 % and 93.21 %, 82.05 % and 89.19 %, 86.81 % and 92.72 %, and 92.79 % and 96.21 %, respectively, on the ISIC 2016, ISIC 2017, ISIC 2018, and PH2 datasets, respectively (code: https://github.com/hyjane/CCT-Net).

PMID:38807881 | PMC:PMC11130697 | DOI:10.1016/j.heliyon.2024.e31395

Cureus. 2024 Apr 27;16(4):e59171. doi: 10.7759/cureus.59171. eCollection 2024 Apr.

ABSTRACT

Colorectal carcinoma, a prevalent and deadly malignancy, necessitates precise histopathological assessment for effective diagnosis and prognosis. Artificial intelligence (AI) emerges as a transformative force in this realm, offering innovative solutions to enhance traditional histopathological methods. This narrative review explores AI's pioneering role in colorectal carcinoma histopathology, encompassing its evolution, techniques, and advancements. AI algorithms, notably machine learning and deep learning, have revolutionized image analysis, facilitating accurate diagnosis and prognosis prediction. Furthermore, AI-driven histopathological analysis unveils potential biomarkers and therapeutic targets, heralding personalized treatment approaches. Despite its promise, challenges persist, including data quality, interpretability, and integration. Collaborative efforts among researchers, clinicians, and AI developers are imperative to surmount these hurdles and realize AI's full potential in colorectal carcinoma care. This review underscores AI's transformative impact and implications for future oncology research, clinical practice, and interdisciplinary collaboration.

PMID:38807833 | PMC:PMC11129955 | DOI:10.7759/cureus.59171

J Phys Chem C Nanomater Interfaces. 2024 May 13;128(20):8395-8407. doi: 10.1021/acs.jpcc.4c00323. eCollection 2024 May 23.

ABSTRACT

The pore network architecture of porous heterogeneous catalyst supports has a significant effect on the kinetics of mass transfer occurring within them. Therefore, characterizing and understanding structure-transport relationships is essential to guide new designs of heterogeneous catalysts with higher activity and selectivity and superior resistance to deactivation. This study combines classical characterization via N2 adsorption and desorption and mercury porosimetry with advanced scanning electron microscopy (SEM) imaging and processing approaches to quantify the spatial heterogeneity of γ-alumina (γ-Al2O3), a catalyst support of great industrial relevance. Based on this, a model is proposed for the spatial organization of γ-Al2O3, containing alumina inclusions of different porosities with respect to the alumina matrix. Using original, advanced SEM image analysis techniques, including deep learning semantic segmentation and porosity measurement under gray-level calibration, the inclusion volume fraction and interphase porosity difference were identified and quantified as the key parameters that served as input for effective tortuosity factor predictions using effective medium theory (EMT)-based models. For the studied aluminas, spatial porosity heterogeneity impact on the effective tortuosity factor was found to be negligible, yet it was proven to become significant for an inclusion content of at least 30% and an interphase porosity difference of over 20%. The proposed methodology based on machine-learning-supported image analysis, in conjunction with other analytical techniques, is a general platform that should have a broader impact on porous materials characterization.

PMID:38807629 | PMC:PMC11129297 | DOI:10.1021/acs.jpcc.4c00323

Korean J Radiol. 2024 Jun;25(6):550-558. doi: 10.3348/kjr.2024.0070.

ABSTRACT

Hepatocellular carcinoma (HCC) is a biologically heterogeneous tumor characterized by varying degrees of aggressiveness. The current treatment strategy for HCC is predominantly determined by the overall tumor burden, and does not address the diverse prognoses of patients with HCC owing to its heterogeneity. Therefore, the prognostication of HCC using imaging data is crucial for optimizing patient management. Although some radiologic features have been demonstrated to be indicative of the biologic behavior of HCC, traditional radiologic methods for HCC prognostication are based on visually-assessed prognostic findings, and are limited by subjectivity and inter-observer variability. Consequently, artificial intelligence has emerged as a promising method for image-based prognostication of HCC. Unlike traditional radiologic image analysis, artificial intelligence based on radiomics or deep learning utilizes numerous image-derived quantitative features, potentially offering an objective, detailed, and comprehensive analysis of the tumor phenotypes. Artificial intelligence, particularly radiomics has displayed potential in a variety of applications, including the prediction of microvascular invasion, recurrence risk after locoregional treatment, and response to systemic therapy. This review highlights the potential value of artificial intelligence in the prognostication of HCC as well as its limitations and future prospects.

PMID:38807336 | DOI:10.3348/kjr.2024.0070

New Phytol. 2024 May 28. doi: 10.1111/nph.19857. Online ahead of print.

ABSTRACT

Automated pollen analysis is not yet efficient on environmental samples containing many pollen taxa and debris, which are typical in most pollen-based studies. Contrary to classification, detection remains overlooked although it is the first step from which errors can propagate. Here, we investigated a simple but efficient method to automate pollen detection for environmental samples, optimizing workload and performance. We applied the YOLOv5 algorithm on samples containing debris and c. 40 Mediterranean plant taxa, designed and tested several strategies for annotation, and analyzed variation in detection errors. About 5% of pollen grains were left undetected, while 5% of debris were falsely detected as pollen. Undetected pollen was mainly in poor-quality images, or of rare and irregular morphology. Pollen detection remained effective when applied to samples never seen by the algorithm, and was not improved by spending time to provide taxonomic details. Pollen detection of a single model taxon reduced annotation workload, but was only efficient for morphologically differentiated taxa. We offer guidelines to plant scientists to analyze automatically any pollen sample, providing sound criteria to apply for detection while using common and user-friendly tools. Our method contributes to enhance the efficiency and replicability of pollen-based studies.

PMID:38807290 | DOI:10.1111/nph.19857

J Exp Biol. 2024 May 15;227(10):jeb247046. doi: 10.1242/jeb.247046. Epub 2024 May 29.

ABSTRACT

Delineating developmental events is central to experimental research using early life stages, permitting widespread identification of changes in event timing between species and environments. Yet, identifying developmental events is incredibly challenging, limiting the scale, reproducibility and throughput of using early life stages in experimental biology. We introduce Dev-ResNet, a small and efficient 3D convolutional neural network capable of detecting developmental events characterised by both spatial and temporal features, such as the onset of cardiac function and radula activity. We demonstrate the efficacy of Dev-ResNet using 10 diverse functional events throughout the embryonic development of the great pond snail, Lymnaea stagnalis. Dev-ResNet was highly effective in detecting the onset of all events, including the identification of thermally induced decoupling of event timings. Dev-ResNet has broad applicability given the ubiquity of bioimaging in developmental biology, and the transferability of deep learning, and so we provide comprehensive scripts and documentation for applying Dev-ResNet to different biological systems.

PMID:38806151 | DOI:10.1242/jeb.247046

Sci Total Environ. 2024 May 26:173557. doi: 10.1016/j.scitotenv.2024.173557. Online ahead of print.

ABSTRACT

Despite the success of the growing data-driven landslide susceptibility prediction, the model training heavily relies on the quality of the data (involving topography, geology, hydrology, land cover, climate, and human activity), the structure of the model, and the fine-tuning of the model parameters. Few data-driven methods have considered incorporating 'landslide priors', as in this article the prior knowledge or statistics related to landslide occurrence, to enhance the model's perception in landslide mechanism. The main objective and contribution of this study is the coupling of landslide priors and a deep learning model to improve the model's transferability and stability. This is accomplished by selecting non-landslide sample grounded on landslide statistics, disentangling input landslide features using a variational autoencoder, and crafting a loss function with physical constraints. This study utilizes the SHAP method to interpret the deep learning model, aiding in the acquisition of feature permutation results to identify underlying landslide causes. The interpretation result indicates that 'slope' is the most influential factor. Considering the extreme rainfall impact on landslide occurrences in Hong Kong, we combine this prior into the deep learning model and find feature ranking for 'rainfall' improved, in comparison to the ranking result interpreted from a pure MLP. Further, the potency of MT-InSAR is utilized to augment the landslide susceptibility map and promote efficient cross-validation. A comparison of InSAR results with historical images reveals that detectable movement before their occurrence is evident in only a minority of landslides. Most landslides occur spontaneously, exhibiting no precursor motion. Comparing with other data-driven methods, the proposed methods outperform in accuracy (by 2 %-5 %), precision (by 2 %-7 %), recall (by 1 %-3 %), F1-score (by 8 %-10 %), and AuROC (by 2 %-4 %). Especially, the Cohen Kappa performance surpasses nearly 20 %, indicating that the knowledge-aware methodology enhances model generalization and mitigates training bias induced by unbalanced positive and negative samples.

PMID:38806128 | DOI:10.1016/j.scitotenv.2024.173557

Brain Res Bull. 2024 May 26:110984. doi: 10.1016/j.brainresbull.2024.110984. Online ahead of print.

ABSTRACT

This study introduces the Divergent Selective Focused Multi-heads Self-Attention Network (DSFMANet), an innovative deep learning model devised to automatically predict Hamilton Depression Rating Scale-17 (HAMD-17) scores in patients with depression. This model introduces a multi-branch structure for sub-bands and artificially configures attention focus factors on various branches, resulting in distinct attention distributions for different sub-bands. Experimental results demonstrate that when DSFMANet processes sub-band data, its performance surpasses current benchmarks in key metrics such as mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). This success is particularly evident in terms of MSE and MAE, where the performance of sub-band data is significantly superior, highlighting the model's potential in accurately predicting HAMD-17 scores. Concurrently, the experiment also compared the model's performance with sub-band and full-band data, affirming the superiority of the selective focus attention mechanism in electroencephalography (EEG) signal processing. DSFMANet, when utilizing sub-band data, exhibits higher data processing efficiency and reduced model complexity. The findings of this study underscore the significance of employing deep learning models based on sub-band analysis in depression diagnosis. The DSFMANet model not only effectively enhances the accuracy of depression diagnosis but also offers valuable research directions for similar applications in the future. This deep learning-based automated approach can effectively ascertain the HAMD-17 scores of patients with depression, thus offering more accurate and reliable support for clinical decision-making.

PMID:38806119 | DOI:10.1016/j.brainresbull.2024.110984

Radiother Oncol. 2024 May 26:110344. doi: 10.1016/j.radonc.2024.110344. Online ahead of print.

ABSTRACT

BACKGROUND: Accurate segmentation of lung tumors on chest computed tomography (CT) scans is crucial for effective diagnosis and treatment planning. Deep Learning (DL) has emerged as a promising tool in medical imaging, particularly for lung cancer segmentation. However, its efficacy across different clinical settings and tumor stages remains variable.

METHODS: We conducted a comprehensive search of PubMed, Embase, and Web of Science until November 7, 2023. We assessed the quality of these studies by using the Checklist for Artificial Intelligence in Medical Imaging and the Quality Assessment of Diagnostic Accuracy Studies-2 tools. This analysis included data from various clinical settings and stages of lung cancer. Key performance metrics, such as the Dice similarity coefficient, were pooled, and factors affecting algorithm performance, such as clinical setting, algorithm type, and image processing techniques, were examined.

RESULTS: Our analysis of 37 studies revealed a pooled Dice score of 79 % (95 % CI: 76 %-83 %), indicating moderate accuracy. Radiotherapy studies had a slightly lower score of 78 % (95 % CI: 74 %-82 %). A temporal increase was noted, with recent studies (post-2022) showing improvement from 75 % (95 % CI: 70 %-81 %). to 82 % (95 % CI: 81 %-84 %). Key factors affecting performance included algorithm type, resolution adjustment, and image cropping. QUADAS-2 assessments identified ambiguous risks in 78 % of studies due to data interval omissions and concerns about generalizability in 8 % due to nodule size exclusions., and CLAIM criteria highlighted areas for improvement, with an average score of 27.24 out of 42.

CONCLUSION: This meta-analysis demonstrates DL algorithms' promising but varied efficacy in lung cancer segmentation, particularly higher efficacy noted in early stages. The results highlight the critical need for continued development of tailored DL models to improve segmentation accuracy across diverse clinical settings, especially in advanced cancer stages with greater challenges. As recent studies demonstrate, ongoing advancements in algorithmic approaches are crucial for future applications.

PMID:38806113 | DOI:10.1016/j.radonc.2024.110344

J Hazard Mater. 2024 May 24;474:134724. doi: 10.1016/j.jhazmat.2024.134724. Online ahead of print.

ABSTRACT

The cardiotoxic effects of various pollutants have been a growing concern in environmental and material science. These effects encompass arrhythmias, myocardial injury, cardiac insufficiency, and pericardial inflammation. Compounds such as organic solvents and air pollutants disrupt the potassium, sodium, and calcium ion channels cardiac cell membranes, leading to the dysregulation of cardiac function. However, current cardiotoxicity models have disadvantages of incomplete data, ion channels, interpretability issues, and inability of toxic structure visualization. Herein, an interpretable deep-learning model known as CardioDPi was developed, which is capable of discriminating cardiotoxicity induced by the human Ether-à-go-go-related gene (hERG) channel, sodium channel (Na_v1.5), and calcium channel (Ca_v1.5) blockade. External validation yielded promising area under the ROC curve (AUC) values of 0.89, 0.89, and 0.94 for the hERG, Na_v1.5, and Ca_v1.5 channels, respectively. The CardioDPi can be freely accessed on the web server CardioDPipredictor (http://cardiodpi.sapredictor.cn/). Furthermore, the structural characteristics of cardiotoxic compounds were analyzed and structural alerts (SAs) can be extracted using the user-friendly CardioDPi-SAdetector web service (http://cardiosa.sapredictor.cn/). CardioDPi is a valuable tool for identifying cardiotoxic chemicals that are environmental and health risks. Moreover, the SA system provides essential insights for mode-of-action studies concerning cardiotoxic compounds.

PMID:38805819 | DOI:10.1016/j.jhazmat.2024.134724

Neural Netw. 2024 May 21;177:106401. doi: 10.1016/j.neunet.2024.106401. Online ahead of print.

ABSTRACT

Fluid motion can be considered as a point cloud transformation when using the SPH method. Compared to traditional numerical analysis methods, using machine learning techniques to learn physics simulations can achieve near-accurate results, while significantly increasing efficiency. In this paper, we propose an innovative approach for 3D fluid simulations utilizing an Attention-based Dual-pipeline Network, which employs a dual-pipeline architecture, seamlessly integrated with an Attention-based Feature Fusion Module. Unlike previous methods, which often make difficult trade-offs between global fluid control and physical law constraints, we find a way to achieve a better balance between these two crucial aspects with a well-designed dual-pipeline approach. Additionally, we design a Type-aware Input Module to adaptively recognize particles of different types and perform feature fusion afterward, such that fluid-solid coupling issues can be better dealt with. Furthermore, we propose a new dataset, Tank3D, to further explore the network's ability to handle more complicated scenes. The experiments demonstrate that our approach not only attains a quantitative enhancement in various metrics, surpassing the state-of-the-art methods, but also signifies a qualitative leap in neural network-based simulation by faithfully adhering to the physical laws. Code and video demonstrations are available at https://github.com/chenyu-xjtu/DualFluidNet.

PMID:38805793 | DOI:10.1016/j.neunet.2024.106401