Commun Biol. 2024 Jun 4;7(1):686. doi: 10.1038/s42003-024-06396-y.

ABSTRACT

Microbial necromass carbon (MNC) can reflect soil carbon (C) sequestration capacity. However, changes in the reserves of MNC in response to warming in alpine grasslands across the Tibetan Plateau are currently unclear. Based on large-scale sampling and published observations, we divided eco-clusters based on dominant phylotypes, calculated their relative abundance, and found that their averaged importance to MNC was higher than most other environmental variables. With a deep learning model based on stacked autoencoder, we proved that using eco-cluster relative abundance as the input variable of the model can accurately predict the overall distribution of MNC under current and warming conditions. It implied that warming could lead to an overall increase in the MNC in grassland topsoil across the Tibetan Plateau, with an average increase of 7.49 mg/g, a 68.3% increase. Collectively, this study concludes that alpine grassland has the tendency to increase soil C sequestration capacity on the Tibetan Plateau under future warming.

PMID:38834864 | DOI:10.1038/s42003-024-06396-y

PLOS Glob Public Health. 2024 Jun 4;4(6):e0003204. doi: 10.1371/journal.pgph.0003204. eCollection 2024.

ABSTRACT

Cardiovascular diseases (CVDs) are responsible for a large proportion of premature deaths in low- and middle-income countries. Early CVD detection and intervention is critical in these populations, yet many existing CVD risk scores require a physical examination or lab measurements, which can be challenging in such health systems due to limited accessibility. We investigated the potential to use photoplethysmography (PPG), a sensing technology available on most smartphones that can potentially enable large-scale screening at low cost, for CVD risk prediction. We developed a deep learning PPG-based CVD risk score (DLS) to predict the probability of having major adverse cardiovascular events (MACE: non-fatal myocardial infarction, stroke, and cardiovascular death) within ten years, given only age, sex, smoking status and PPG as predictors. We compare the DLS with the office-based refit-WHO score, which adopts the shared predictors from WHO and Globorisk scores (age, sex, smoking status, height, weight and systolic blood pressure) but refitted on the UK Biobank (UKB) cohort. All models were trained on a development dataset (141,509 participants) and evaluated on a geographically separate test (54,856 participants) dataset, both from UKB. DLS's C-statistic (71.1%, 95% CI 69.9-72.4) is non-inferior to office-based refit-WHO score (70.9%, 95% CI 69.7-72.2; non-inferiority margin of 2.5%, p<0.01) in the test dataset. The calibration of the DLS is satisfactory, with a 1.8% mean absolute calibration error. Adding DLS features to the office-based score increases the C-statistic by 1.0% (95% CI 0.6-1.4). DLS predicts ten-year MACE risk comparable with the office-based refit-WHO score. Interpretability analyses suggest that the DLS-extracted features are related to PPG waveform morphology and are independent of heart rate. Our study provides a proof-of-concept and suggests the potential of a PPG-based approach strategies for community-based primary prevention in resource-limited regions.

PMID:38833495 | DOI:10.1371/journal.pgph.0003204

IEEE J Biomed Health Inform. 2024 Jun 4;PP. doi: 10.1109/JBHI.2024.3409382. Online ahead of print.

ABSTRACT

Delineating 3D blood vessels of various anatomical structures is essential for clinical diagnosis and treatment, however, is challenging due to complex structure variations and varied imaging conditions. Although recent supervised deep learning models have demonstrated their superior capacity in automatic 3D vessel segmentation, the reliance on expensive 3D manual annotations and limited capacity for annotation reuse among different vascular structures hinder their clinical applications. To avoid the repetitive and costly annotating process for each vascular structure and make full use of existing annotations, this paper proposes a novel 3D shape-guided local discrimination (3D-SLD) model for 3D vascular segmentation under limited guidance from public 2D vessel annotations. The primary hypothesis is that 3D vessels are composed of semantically similar voxels and often exhibit tree-shaped morphology. Accordingly, the 3D region discrimination loss is firstly proposed to learn the discriminative representation measuring voxel-wise similarities and cluster semantically consistent voxels to form the candidate 3D vascular segmentation in unlabeled images. Secondly, the shape distribution from existing 2D structure-agnostic vessel annotations is introduced to guide the 3D vessels with the tree-shaped morphology by the adversarial shape constraint loss. Thirdly, to enhance training stability and prediction credibility, the highlighting-reviewing-summarizing (HRS) mechanism is proposed. This mechanism involves summarizing historical models to maintain temporal consistency and identifying credible pseudo labels as reliable supervision signals. Only guided by public 2D coronary artery annotations, our method achieves results comparable to SOTA barely-supervised methods in 3D cerebrovascular segmentation, and the best DSC in 3D hepatic vessel segmentation, demonstrating the effectiveness of our method.

PMID:38833403 | DOI:10.1109/JBHI.2024.3409382

IEEE Trans Pattern Anal Mach Intell. 2024 Jun 4;PP. doi: 10.1109/TPAMI.2024.3409634. Online ahead of print.

ABSTRACT

Superpixel aggregation is a powerful tool for automated neuron segmentation from electron microscopy (EM) volume. However, existing graph partitioning methods for superpixel aggregation still involve two separate stages-model estimation and model solving, and therefore model error is inherent. To address this issue, we integrate the two stages and propose an end-to-end aggregation framework based on deep learning of the minimum cost multicut problem called DeepMulticut. The core challenge lies in differentiating the NPhard multicut problem, whose constraint number is exponential in the problem size. With this in mind, we resort to relaxing the combinatorial solver-the greedy additive edge contraction (GAEC)-to a continuous Soft-GAEC algorithm, whose limit is shown to be the vanilla GAEC. Such relaxation thus allows the DeepMulticut to integrate edge cost estimators, Edge-CNNs, into a differentiable multicut optimization system and allows a decision-oriented loss to feed decision quality back to the Edge-CNNs for adaptive discriminative feature learning. Hence, the model estimators, Edge-CNNs, can be trained to improve partitioning decisions directly while beyond the NP-hardness. Also, we explain the rationale behind the DeepMulticut framework from the perspective of bi-level optimization. Extensive experiments on three public EM datasets demonstrate the effectiveness of the proposed DeepMulticut.

PMID:38833401 | DOI:10.1109/TPAMI.2024.3409634

IEEE Trans Neural Netw Learn Syst. 2024 Jun 4;PP. doi: 10.1109/TNNLS.2024.3405991. Online ahead of print.

ABSTRACT

Rumors in different topic domains have different text characteristics but similar emotional tendencies. To resolve the scarce-data problem in some rumor-topic domains, this study proposes a cross-domain rumor-propagation model, which is based on transfer learning. First, given the diversity and complexity of the rumor-propagation landscape, this study introduces a novel method, User-Retweet-Rumor2vec (URR2vec), which leverages the power of representation learning to uncover latent features within rumor topics. It also displays the forwarding relationship between users and rumors, user node information, and rumor-topic information in low-dimensional space. To capture the impact of human emotional cognition during rumor spreading, we also introduce a deep-learning model based on the natural language texts of rumor topics, which analyzes the sentiment in the text and uncovers the emotional correlations among users. Furthermore, a rumor-propagation prediction model based on the text-sentiment analysis-graph convolutional network (TSA-GCN) is proposed and pre-trained on existing rumor-topic data to ensure its prediction accuracy. Finally, considering the data sparsity at a rumor-topic outbreak, the trained propagation model is transferred to the rumor topic for prediction. Meanwhile, the rumor topic in different domains has different edges and conditional distribution, similar emotional characteristics, and network structure among the rumor topics. After fine-tuning the parameter and adding a domain adaptation layer in TSA-GCN, a domain adaptation model based on parameter and graph-structure migration is obtained.

PMID:38833394 | DOI:10.1109/TNNLS.2024.3405991

IEEE Trans Neural Netw Learn Syst. 2024 Jun 4;PP. doi: 10.1109/TNNLS.2024.3401589. Online ahead of print.

ABSTRACT

Accurately distinguishing between background and anomalous objects within hyperspectral images poses a significant challenge. The primary obstacle lies in the inadequate modeling of prior knowledge, leading to a performance bottleneck in hyperspectral anomaly detection (HAD). In response to this challenge, we put forth a groundbreaking coupling paradigm that combines model-driven low-rank representation (LRR) methods with data-driven deep learning techniques by learning disentangled priors (LDP). LDP seeks to capture complete priors for effectively modeling the background, thereby extracting anomalies from hyperspectral images more accurately. LDP follows a model-driven deep unfolding architecture, where the prior knowledge is separated into the explicit low-rank prior formulated by expert knowledge and implicit learnable priors by means of deep networks. The internal relationships between explicit and implicit priors within LDP are elegantly modeled through a skip residual connection. Furthermore, we provide a mathematical proof of the convergence of our proposed model. Our experiments, conducted on multiple widely recognized datasets, demonstrate that LDP surpasses most of the current advanced HAD techniques, exceling in both detection performance and generalization capability.

PMID:38833391 | DOI:10.1109/TNNLS.2024.3401589

Invest Ophthalmol Vis Sci. 2024 Jun 3;65(6):6. doi: 10.1167/iovs.65.6.6.

ABSTRACT

PURPOSE: To develop Choroidalyzer, an open-source, end-to-end pipeline for segmenting the choroid region, vessels, and fovea, and deriving choroidal thickness, area, and vascular index.

METHODS: We used 5600 OCT B-scans (233 subjects, six systemic disease cohorts, three device types, two manufacturers). To generate region and vessel ground-truths, we used state-of-the-art automatic methods following manual correction of inaccurate segmentations, with foveal positions manually annotated. We trained a U-Net deep learning model to detect the region, vessels, and fovea to calculate choroid thickness, area, and vascular index in a fovea-centered region of interest. We analyzed segmentation agreement (AUC, Dice) and choroid metrics agreement (Pearson, Spearman, mean absolute error [MAE]) in internal and external test sets. We compared Choroidalyzer to two manual graders on a small subset of external test images and examined cases of high error.

RESULTS: Choroidalyzer took 0.299 seconds per image on a standard laptop and achieved excellent region (Dice: internal 0.9789, external 0.9749), very good vessel segmentation performance (Dice: internal 0.8817, external 0.8703), and excellent fovea location prediction (MAE: internal 3.9 pixels, external 3.4 pixels). For thickness, area, and vascular index, Pearson correlations were 0.9754, 0.9815, and 0.8285 (internal)/0.9831, 0.9779, 0.7948 (external), respectively (all P < 0.0001). Choroidalyzer's agreement with graders was comparable to the intergrader agreement across all metrics.

CONCLUSIONS: Choroidalyzer is an open-source, end-to-end pipeline that accurately segments the choroid and reliably extracts thickness, area, and vascular index. Especially choroidal vessel segmentation is a difficult and subjective task, and fully automatic methods like Choroidalyzer could provide objectivity and standardization.

PMID:38833259 | DOI:10.1167/iovs.65.6.6

J Robot Surg. 2024 Jun 4;18(1):237. doi: 10.1007/s11701-024-01981-z.

ABSTRACT

A major obstacle in applying machine learning for medical fields is the disparity between the data distribution of the training images and the data encountered in clinics. This phenomenon can be explained by inconsistent acquisition techniques and large variations across the patient spectrum. The result is poor translation of the trained models to the clinic, which limits their implementation in medical practice. Patient-specific trained networks could provide a potential solution. Although patient-specific approaches are usually infeasible because of the expenses associated with on-the-fly labeling, the use of generative adversarial networks enables this approach. This study proposes a patient-specific approach based on generative adversarial networks. In the presented training pipeline, the user trains a patient-specific segmentation network with extremely limited data which is supplemented with artificial samples generated by generative adversarial models. This approach is demonstrated in endoscopic video data captured during fetoscopic laser coagulation, a procedure used for treating twin-to-twin transfusion syndrome by ablating the placental blood vessels. Compared to a standard deep learning segmentation approach, the pipeline was able to achieve an intersection over union score of 0.60 using only 20 annotated images compared to 100 images using a standard approach. Furthermore, training with 20 annotated images without the use of the pipeline achieves an intersection over union score of 0.30, which, therefore, corresponds to a 100% increase in performance when incorporating the pipeline. A pipeline using GANs was used to generate artificial data which supplements the real data, this allows patient-specific training of a segmentation network. We show that artificial images generated using GANs significantly improve performance in vessel segmentation and that training patient-specific models can be a viable solution to bring automated vessel segmentation to the clinic.

PMID:38833204 | DOI:10.1007/s11701-024-01981-z

Cancer Immunol Immunother. 2024 Jun 4;73(8):153. doi: 10.1007/s00262-024-03724-3.

ABSTRACT

BACKGROUND: The non-invasive biomarkers for predicting immunotherapy response are urgently needed to prevent both premature cessation of treatment and ineffective extension. This study aimed to construct a non-invasive model for predicting immunotherapy response, based on the integration of deep learning and habitat radiomics in patients with advanced non-small cell lung cancer (NSCLC).

METHODS: Independent patient cohorts from three medical centers were enrolled for training (n = 164) and test (n = 82). Habitat imaging radiomics features were derived from sub-regions clustered from individual's tumor by K-means method. The deep learning features were extracted based on 3D ResNet algorithm. Pearson correlation coefficient, T test and least absolute shrinkage and selection operator regression were used to select features. Support vector machine was applied to implement deep learning and habitat radiomics, respectively. Then, a combination model was developed integrating both sources of data.

RESULTS: The combination model obtained a strong well-performance, achieving area under receiver operating characteristics curve of 0.865 (95% CI 0.772-0.931). The model significantly discerned high and low-risk patients, and exhibited a significant benefit in the clinical use.

CONCLUSION: The integration of deep-leaning and habitat radiomics contributed to predicting response to immunotherapy in patients with NSCLC. The developed integration model may be used as potential tool for individual immunotherapy management.

PMID:38833187 | DOI:10.1007/s00262-024-03724-3

Ir J Med Sci. 2024 Jun 4. doi: 10.1007/s11845-024-03721-6. Online ahead of print.

ABSTRACT

Neurodegenerative diseases (ND) are disorders of the central nervous system (CNS) characterized by impairment in neurons' functions, and complete loss, leading to memory loss, and difficulty in learning, language, and movement processes. The most common among these NDs are Alzheimer's disease (AD) and Parkinson's disease (PD), although several other disorders also exist. These are frontotemporal dementia (FTD), amyotrophic lateral syndrome (ALS), Huntington's disease (HD), and others; the major pathological hallmark of NDs is the proteinopathies, either of amyloid-β (Aβ), tauopathies, or synucleinopathies. Aggregation of proteins that do not undergo normal configuration, either due to mutations or through some disturbance in cellular pathway contributes to the diseases. Artificial Intelligence (AI) and deep learning (DL) have proven to be successful in the diagnosis and treatment of various congenital diseases. DL approaches like AlphaFold (AF) are a major leap towards success in CNS disorders. This 3D protein geometry modeling algorithm developed by DeepMind has the potential to revolutionize biology. AF has the potential to predict 3D-protein confirmation at an accuracy level comparable to experimentally predicted one, with the additional advantage of precisely estimating protein interactions. This breakthrough will be beneficial to identify diseases' advancement and the disturbance of signaling pathways stimulating impaired functions of proteins. Though AlphaFold has solved a major problem in structural biology, it cannot predict membrane proteins-a beneficial approach for drug designing.

PMID:38833116 | DOI:10.1007/s11845-024-03721-6

Rev Sci Instrum. 2024 Jun 1;95(6):065105. doi: 10.1063/5.0189991.

ABSTRACT

The widespread use of deep learning in processing point cloud data promotes the development of neural networks designed for point clouds. Point-based methods are increasingly becoming the mainstream in point cloud neural networks due to their high efficiency and performance. However, most of these methods struggle to balance both the geometric and semantic space of the point cloud, which usually leads to unclear local feature aggregation in geometric space and poor global feature extraction in semantic space. To address these two defects, we propose a bilateral feature fusion module capable of combining geometric and semantic data from the point cloud to enhance local feature extraction. In addition, we propose an offset vector attention module for better extraction of global features from point clouds. We provide specific ablation studies and visualizations in the article to validate our key modules. Experimental results show that the proposed method performs superior in both point cloud classification and segmentation tasks.

PMID:38832851 | DOI:10.1063/5.0189991

Rev Esp Enferm Dig. 2024 Jun 4. doi: 10.17235/reed.2024.10456/2024. Online ahead of print.

ABSTRACT

The development and implementation of artificial intelligence (AI), particularly deep learning (DL) models, has generated significant interest across various fields of gastroenterology. While research in luminal endoscopy has seen rapid translation to clinical practice with approved AI devices, its potential extends far beyond, offering promising benefits for biliopancreatic endoscopy like optical characterization of strictures during cholangioscopy or detection and classification of pancreatic lesions during diagnostic endoscopic ultrasound (EUS). This narrative review provides an up-to-date of the latest literature and available studies in this field. Serving as a comprehensive guide to the current landscape of AI in biliopancreatic endoscopy, emphasizing technological advancements, main applications, ethical considerations, and future directions for research and clinical implementation.

PMID:38832589 | DOI:10.17235/reed.2024.10456/2024

Front Robot AI. 2024 May 20;11:1386464. doi: 10.3389/frobt.2024.1386464. eCollection 2024.

ABSTRACT

Visual place recognition (VPR) is a popular computer vision task aimed at recognizing the geographic location of a visual query, usually within a tolerance of a few meters. Modern approaches address VPR from an image retrieval standpoint using a kNN on top of embeddings extracted by a deep neural network from both the query and images in a database. Although most of these approaches rely on contrastive learning, which limits their ability to be trained on large-scale datasets (due to mining), the recently reported CosPlace proposes an alternative training paradigm using a classification task as the proxy. This has been shown to be effective in expanding the potential of VPR models to learn from large-scale and fine-grained datasets. In this work, we experimentally analyze CosPlace from a continual learning perspective and show that its sequential training procedure leads to suboptimal results. As a solution, we propose a different formulation that not only solves the pitfalls of the original training strategy effectively but also enables faster and more efficient distributed training. Finally, we discuss the open challenges in further speeding up large-scale image retrieval for VPR.

PMID:38832343 | PMC:PMC11145398 | DOI:10.3389/frobt.2024.1386464

Front Psychiatry. 2024 May 20;15:1397093. doi: 10.3389/fpsyt.2024.1397093. eCollection 2024.

ABSTRACT

BACKGROUND: Resting state Functional Magnetic Resonance Imaging fMRI (rs-fMRI) has been used extensively to study brain function in psychiatric disorders, yielding insights into brain organization. However, the high dimensionality of the rs-fMRI data presents significant challenges for data analysis. Variational autoencoders (VAEs), a type of neural network, have been instrumental in extracting low-dimensional latent representations of resting state functional connectivity (rsFC) patterns, thereby addressing the complex nonlinear structure of rs-fMRI data. Despite these advances, interpreting these latent representations remains a challenge. This paper aims to address this gap by developing explainable VAE models and testing their utility using rs-fMRI data in autism spectrum disorder (ASD).

METHODS: One-thousand one hundred and fifty participants (601 healthy controls [HC] and 549 patients with ASD) were included in the analysis. RsFC correlation matrices were extracted from the preprocessed rs-fMRI data using the Power atlas, which includes 264 regions of interest (ROIs). Then VAEs were trained in an unsupervised manner. Lastly, we introduce our latent contribution scores to explain the relationship between estimated representations and the original rs-fMRI brain measures.

RESULTS: We quantified the latent contribution scores for both the ASD and HC groups at the network level. We found that both ASD and HC groups share the top network connectivitives contributing to all estimated latent components. For example, latent 0 was driven by rsFC within ventral attention network (VAN) in both the ASD and HC. However, we found significant differences in the latent contribution scores between the ASD and HC groups within the VAN for latent 0 and the sensory/somatomotor network for latent 2.

CONCLUSION: This study introduced latent contribution scores to interpret nonlinear patterns identified by VAEs. These scores effectively capture changes in each observed rsFC feature as the estimated latent representation changes, enabling an explainable deep learning model that better understands the underlying neural mechanisms of ASD.

PMID:38832332 | PMC:PMC11145064 | DOI:10.3389/fpsyt.2024.1397093

Front Aging Neurosci. 2024 May 20;16:1397896. doi: 10.3389/fnagi.2024.1397896. eCollection 2024.

ABSTRACT

OBJECTIVES: The altered neuromelanin in substantia nigra pars compacta (SNpc) is a valuable biomarker in the detection of early-stage Parkinson's disease (EPD). Diagnosis via visual inspection or single radiomics based method is challenging. Thus, we proposed a novel hybrid model that integrates radiomics and deep learning methodologies to automatically detect EPD based on neuromelanin-sensitive MRI, namely short-echo-time Magnitude (setMag) reconstructed from quantitative susceptibility mapping (QSM).

METHODS: In our study, we collected QSM images including 73 EPD patients and 65 healthy controls, which were stratified into training-validation and independent test sets with an 8:2 ratio. Twenty-four participants from another center were included as the external validation set. Our framework began with the detection of the brainstem utilizing YOLO-v5. Subsequently, a modified LeNet was applied to obtain deep learning features. Meanwhile, 1781 radiomics features were extracted, and 10 features were retained after filtering. Finally, the classified models based on radiomics features, deep learning features, and the hybrid of both were established through machine learning algorithms, respectively. The performance was mainly evaluated using accuracy, net reclassification improvement (NRI), and integrated discrimination improvement (IDI). The saliency map was used to visualize the model.

RESULTS: The hybrid feature-based support vector machine (SVM) model showed the best performance, achieving ACC of 96.3 and 95.8% in the independent test set and external validation set, respectively. The model established by hybrid features outperformed the one radiomics feature-based (NRI: 0.245, IDI: 0.112). Furthermore, the saliency map showed that the bilateral "swallow tail" sign region was significant for classification.

CONCLUSION: The integration of deep learning and radiomic features presents a potent strategy for the computer-aided diagnosis of EPD. This study not only validates the accuracy of our proposed model but also underscores its interpretability, evidenced by differential significance across various anatomical sites.

PMID:38832074 | PMC:PMC11144908 | DOI:10.3389/fnagi.2024.1397896

iScience. 2024 Apr 26;27(6):109826. doi: 10.1016/j.isci.2024.109826. eCollection 2024 Jun 21.

ABSTRACT

New breast cancer cases have surpassed lung cancer, becoming the world's most prevalent cancer. Despite advancing medical image analysis, deep learning's lack of interpretability limits its adoption among pathologists. Hence, a nuclei-level prior knowledge constrained multiple instance learning (MIL) (NPKC-MIL) for breast whole slide image (WSI) classification is proposed. NPKC-MIL primarily involves the following steps: Initially, employing the transfer learning to extract patch-level features and aggregate them into slide-level features through attention pooling. Subsequently, abstract the extracted nuclei as nodes, establish nucleus topology using the K-NN (K-Nearest Neighbors, K-NN) algorithm, and create handcrafted features for nodes. Finally, combine patch-level deep learning features with nuclei-level handcrafted features to fine-tune classification results generated by slide-level deep learning features. The experimental results demonstrate that NPKC-MIL outperforms current comparable deep learning models. NPKC-MIL expands the analytical dimension of WSI classification tasks and integrates prior knowledge into deep learning models to improve interpretability.

PMID:38832012 | PMC:PMC11145340 | DOI:10.1016/j.isci.2024.109826

Natl Sci Rev. 2024 Mar 26;11(5):nwae109. doi: 10.1093/nsr/nwae109. eCollection 2024 May.

ABSTRACT

Quantitative analysis of activated neurons in mouse brains by a specific stimulation is usually a primary step to locate the responsive neurons throughout the brain. However, it is challenging to comprehensively and consistently analyze the neuronal activity trace in whole brains of a large cohort of mice from many terabytes of volumetric imaging data. Here, we introduce NEATmap, a deep learning-based high-efficiency, high-precision and user-friendly software for whole-brain neuronal activity trace mapping by automated segmentation and quantitative analysis of immunofluorescence labeled c-Fos+ neurons. We applied NEATmap to study the brain-wide differentiated neuronal activation in response to physical and psychological stressors in cohorts of mice.

PMID:38831937 | PMC:PMC11145917 | DOI:10.1093/nsr/nwae109

Data Brief. 2024 May 11;54:110513. doi: 10.1016/j.dib.2024.110513. eCollection 2024 Jun.

ABSTRACT

This article introduces a primary dataset sourced from diverse marketplaces in Bangladesh, encompassing six distinct banana varieties predominantly consumed locally. The dataset comprises the following banana types: Shagor, Shabri, Champa, Anaji, Deshi, and Bichi. High-resolution images of bananas from each category were acquired using a smartphone camera. A total of 1166 images were captured but did not maintain a uniform distribution. Only the augmented data has 1000 images per category which is a total of 6000 images. The proposed dataset exhibits substantial potential for impact and utility, offering a range of attributes, including but not limited to the representation of six diverse banana varieties, each possessing unique flavors and holding promise for various applications within the agriculture and food manufacturing industries.

PMID:38831906 | PMC:PMC11144790 | DOI:10.1016/j.dib.2024.110513

Front Neurorobot. 2024 May 20;18:1398703. doi: 10.3389/fnbot.2024.1398703. eCollection 2024.

ABSTRACT

INTRODUCTION: During the last few years, a heightened interest has been shown in classifying scene images depicting diverse robotic environments. The surge in interest can be attributed to significant improvements in visual sensor technology, which has enhanced image analysis capabilities.

METHODS: Advances in vision technology have a major impact on the areas of multiple object detection and scene understanding. These tasks are an integral part of a variety of technologies, including integrating scenes in augmented reality, facilitating robot navigation, enabling autonomous driving systems, and improving applications in tourist information. Despite significant strides in visual interpretation, numerous challenges persist, encompassing semantic understanding, occlusion, orientation, insufficient availability of labeled data, uneven illumination including shadows and lighting, variation in direction, and object size and changing background. To overcome these challenges, we proposed an innovative scene recognition framework, which proved to be highly effective and yielded remarkable results. First, we perform preprocessing using kernel convolution on scene data. Second, we perform semantic segmentation using UNet segmentation. Then, we extract features from these segmented data using discrete wavelet transform (DWT), Sobel and Laplacian, and textual (local binary pattern analysis). To recognize the object, we have used deep belief network and then find the object-to-object relation. Finally, AlexNet is used to assign the relevant labels to the scene based on recognized objects in the image.

RESULTS: The performance of the proposed system was validated using three standard datasets: PASCALVOC-12, Cityscapes, and Caltech 101. The accuracy attained on the PASCALVOC-12 dataset exceeds 96% while achieving a rate of 95.90% on the Cityscapes dataset.

DISCUSSION: Furthermore, the model demonstrates a commendable accuracy of 92.2% on the Caltech 101 dataset. This model showcases noteworthy advancements beyond the capabilities of current models.

PMID:38831877 | PMC:PMC11144911 | DOI:10.3389/fnbot.2024.1398703

J Oral Pathol Med. 2024 Jun 4. doi: 10.1111/jop.13560. Online ahead of print.

ABSTRACT

BACKGROUND: Neural tumors are difficult to distinguish based solely on cellularity and often require immunohistochemical staining to aid in identifying the cell lineage. This article investigates the potential of a Convolutional Neural Network for the histopathological classification of the three most prevalent benign neural tumor types: neurofibroma, perineurioma, and schwannoma.

METHODS: A model was developed, trained, and evaluated for classification using the ResNet-50 architecture, with a database of 30 whole-slide images stained in hematoxylin and eosin (106, 782 patches were generated from and divided among the training, validation, and testing subsets, with strategies to avoid data leakage).

RESULTS: The model achieved an accuracy of 70% (64% normalized), and showed satisfactory results for differentiating two of the three classes, reaching approximately 97% and 77% as true positives for neurofibroma and schwannoma classes, respectively, and only 7% for perineurioma class. The AUROC curves for neurofibroma and schwannoma classes was 0.83%, and 0.74% for perineurioma. However, the specificity rate for the perineurioma class was greater (83%) than in the other two classes (neurofibroma with 61%, and schwannoma with 60%).

CONCLUSION: This investigation demonstrated significant potential for proficient performance with a limitation regarding the perineurioma class (the limited feature variability observed contributed to a lower performance).

PMID:38831737 | DOI:10.1111/jop.13560