IEEE Trans Pattern Anal Mach Intell. 2024 Apr 24;PP. doi: 10.1109/TPAMI.2024.3393364. Online ahead of print.

ABSTRACT

This paper introduces a novel Perturbation-Assisted Inference (PAI) framework utilizing synthetic data generated by the Perturbation-Assisted Sample Synthesis (PASS) method. The framework focuses on uncertainty quantification in complex data scenarios, particularly involving unstructured data while utilizing deep learning models. On one hand, PASS employs a generative model to create synthetic data that closely mirrors raw data while preserving its rank properties through data perturbation, thereby enhancing data diversity and bolstering privacy. By incorporating knowledge transfer from large pre-trained generative models, PASS enhances estimation accuracy, yielding refined distributional estimates of various statistics via Monte Carlo experiments. On the other hand, PAI boasts its statistically guaranteed validity. In pivotal inference, it enables precise conclusions even without prior knowledge of the pivotal's distribution. In non-pivotal situations, we enhance the reliability of synthetic data generation by training it with an independent holdout sample. We demonstrate the effectiveness of PAI in advancing uncertainty quantification in complex, data-driven tasks by applying it to diverse areas such as image synthesis, sentiment word analysis, multimodal inference, and the construction of prediction intervals.

PMID:38656858 | DOI:10.1109/TPAMI.2024.3393364

IEEE Trans Image Process. 2024 Apr 24;PP. doi: 10.1109/TIP.2024.3387297. Online ahead of print.

ABSTRACT

In modern neuroscience, observing the dynamics of large populations of neurons is a critical step of understanding how networks of neurons process information. Light-field microscopy (LFM) has emerged as a type of scanless, high-speed, three-dimensional (3D) imaging tool, particularly attractive for this purpose. Imaging neuronal activity using LFM calls for the development of novel computational approaches that fully exploit domain knowledge embedded in physics and optics models, as well as enabling high interpretability and transparency. To this end, we propose a model-based explainable deep learning approach for LFM. Different from purely data-driven methods, the proposed approach integrates wave-optics theory, sparse representation and non-linear optimization with the artificial neural network. In particular, the architecture of the proposed neural network is designed following precise signal and optimization models. Moreover, the network's parameters are learned from a training dataset using a novel training strategy that integrates layer-wise training with tailored knowledge distillation. Such design allows the network to take advantage of domain knowledge and learned new features. It combines the benefit of both model-based and learning-based methods, thereby contributing to superior interpretability, transparency and performance. By evaluating on both structural and functional LFM data obtained from scattering mammalian brain tissues, we demonstrate the capabilities of the proposed approach to achieve fast, robust 3D localization of neuron sources and accurate neural activity identification.

PMID:38656840 | DOI:10.1109/TIP.2024.3387297

Proteins. 2024 Apr 24. doi: 10.1002/prot.26694. Online ahead of print.

ABSTRACT

This study introduces TooT-PLM-ionCT, a comprehensive framework that consolidates three distinct systems, each meticulously tailored for one of the following tasks: distinguishing ion channels (ICs) from membrane proteins (MPs), segregating ion transporters (ITs) from MPs, and differentiating ICs from ITs. Drawing upon the strengths of six Protein Language Models (PLMs)-ProtBERT, ProtBERT-BFD, ESM-1b, ESM-2 (650M parameters), and ESM-2 (15B parameters), TooT-PLM-ionCT employs a combination of traditional classifiers and deep learning models for nuanced protein classification. Originally validated on an existing dataset by previous researchers, our systems demonstrated superior performance in identifying ITs from MPs and distinguishing ICs from ITs, with the IC-MP discrimination achieving state-of-the-art results. In light of recommendations for additional validation, we introduced a new dataset, significantly enhancing the robustness and generalization of our models across bioinformatics challenges. This new evaluation underscored the effectiveness of TooT-PLM-ionCT in adapting to novel data while maintaining high classification accuracy. Furthermore, this study explores critical factors affecting classification accuracy, such as dataset balancing, the impact of using frozen versus fine-tuned PLM representations, and the variance between half and full precision in floating-point computations. To facilitate broader application and accessibility, a web server (https://tootsuite.encs.concordia.ca/service/TooT-PLM-ionCT) has been developed, allowing users to evaluate unknown protein sequences through our specialized systems for IC-MP, IT-MP, and IC-IT classification tasks.

PMID:38656743 | DOI:10.1002/prot.26694

Environ Sci Pollut Res Int. 2024 Apr 24. doi: 10.1007/s11356-024-33290-1. Online ahead of print.

ABSTRACT

The prediction of suspended sediment load (SSL) within riverine systems is critical to understanding the watershed's hydrology. Therefore, the novelty of our research is developing an interpretable (explainable) model based on deep learning (DL) and Shapley Additive ExPlanations (SHAP) interpretation technique for prediction of SSL in the riverine systems. This paper investigates the abilities of four DL models, including dense deep neural networks (DDNN), long short-term memory (LSTM), gated recurrent unit (GRU), and simple recurrent neural network (RNN) models for the prediction of daily SSL using river discharge and rainfall data at a daily time scale in the Taleghan River watershed, northwestern Tehran, Iran. The performance of models was evaluated by using several quantitative and graphical criteria. The effect of parameter settings on the performance of deep models on SSL prediction was also investigated. The optimal optimization algorithms, maximum iteration (MI), and batch size (BC) were obtained for modeling daily SSL, and structure of the model impact on prediction remarkably. The comparison of prediction accuracy of the models illustrated that DDNN (with R2 = 0.96, RMSE = 333.46) outperformed LSTM (R2 = 0.75, RMSE = 786.20), GRU (R2 = 0.73, RMSE = 825.67), and simple RNN (R2 = 0.78, RMSE = 741.45). Furthermore, the Taylor diagram confirmed that DDNN has the highest performance among other models. Interpretation techniques can address the black-box nature of models, and here, SHAP was applied to develop an interpretable DL model to interpret of DL model's output. The results of SHAP showed that river discharge has the strongest impact on the model's output in estimating SSL. Overall, we conclude that DL models have great potential in watersheds to predict SSL. Therefore, different interpretation techniques as tools to interpret DL model's output (DL model is as black-box model) are recommended in future research.

PMID:38656723 | DOI:10.1007/s11356-024-33290-1

J Chem Phys. 2024 Apr 28;160(16):164711. doi: 10.1063/5.0202963.

ABSTRACT

Metal organic frameworks (MOFs) are crystalline, three-dimensional structures with high surface areas and tunable porosities. Made from metal nodes connected by organic linkers, the exact properties of a given MOF are determined by node and linker choice. MOFs hold promise for numerous applications, including gas capture and storage. M2(4,4'-dioxidobiphenyl-3,3'-dicarboxylate)-henceforth simply M2(dobpdc), with M = Mg, Mn, Fe, Co, Ni, Cu, or Zn-is regarded as one of the most promising structures for CO2 capture applications. Further modification of the MOF with diamines or tetramines can significantly boost gas species selectivity, a necessity for the ultra-dilute CO2 concentrations in the direct-air capture of CO2. There are countless potential diamines and tetramines, paving the way for a vast number of potential sorbents to be probed for CO2 adsorption properties. The number of amines and their configuration in the MOF pore are key drivers of CO2 adsorption capacity and kinetics, and so a validation of computational prediction of these quantities is required to suitably use computational methods in the discovery and screening of amine-functionalized sorbents. In this work, we study the predictive accuracy of density functional theory and related calculations on amine loading and configuration for one diamine and two tetramines. In particular, we explore the Perdew-Burke-Ernzerhof (PBE) functional and its formulation for solids (PBEsol) with and without the Grimme-D2 and Grimme-D3 pairwise corrections (PBE+D2/3 and PBEsol+D2/3), two revised PBE functionals with the Grimme-D2 and Grimme-D3 pairwise corrections (RPBE+D2/3 and revPBE+D2/3), and the nonlocal van der Waals correlation (vdW-DF2) functional. We also investigate a universal graph deep learning interatomic potential's (M3GNet) predictive accuracy for loading and configuration. These results allow us to identify a useful screening procedure for configuration prediction that has a coarse component for quick evaluation and a higher accuracy component for detailed analysis. Our general observation is that the neural network-based potential can be used as a high-level and rapid screening tool, whereas PBEsol+D3 gives a completely qualitatively predictive picture across all systems studied, and can thus be used for high accuracy motif predictions. We close by briefly exploring the predictions of relative thermal stability for the different functionals and dispersion corrections.

PMID:38656447 | DOI:10.1063/5.0202963

Vascular. 2024 Apr 24:17085381241246312. doi: 10.1177/17085381241246312. Online ahead of print.

ABSTRACT

OBJECTIVES: Assessment of plaque stenosis severity allows better management of carotid source of stroke. Our objective is to create a deep learning (DL) model to segment carotid intima-media thickness and plaque and further automatically calculate plaque stenosis severity on common carotid artery (CCA) transverse section ultrasound images.

METHODS: Three hundred and ninety images from 376 individuals were used to train (235/390, 60%), validate (39/390, 10%), and test (116/390, 30%) on a newly proposed CANet model. We also evaluated the model on an external test set of 115 individuals with 122 images acquired from another hospital. Comparative studies were conducted between our CANet model with four state-of-the-art DL models and two experienced sonographers to re-evaluate the present model's performance.

RESULTS: On the internal test set, our CANet model outperformed the four comparative models with Dice values of 95.22% versus 90.15%, 87.48%, 90.22%, and 91.56% on lumen-intima (LI) borders and 96.27% versus 91.40%, 88.94%, 91.19%, and 92.88% on media-adventitia (MA) borders. On the external test set, our model still produced excellent results with a Dice value of 92.41%. Good consistency of stenosis severity calculation was observed between CANet model and experienced sonographers, with Intraclass Correlation Coefficient (ICC) of 0.927 and 0.702, Pearson's Correlation Coefficient of 0.928 and 0.704 on internal and external test set, respectively.

CONCLUSIONS: Our CANet model achieved excellent performance in the segmentation of carotid IMT and plaques as well as automated calculation of stenosis severity.

PMID:38656244 | DOI:10.1177/17085381241246312

J Int Med Res. 2024 Apr;52(4):3000605241244754. doi: 10.1177/03000605241244754.

ABSTRACT

OBJECTIVE: Osteoporosis is a systemic bone disease characterized by low bone mass, damaged bone microstructure, increased bone fragility, and susceptibility to fractures. With the rapid development of artificial intelligence, a series of studies have reported deep learning applications in the screening and diagnosis of osteoporosis. The aim of this review was to summary the application of deep learning methods in the radiologic diagnosis of osteoporosis.

METHODS: We conducted a two-step literature search using the PubMed and Web of Science databases. In this review, we focused on routine radiologic methods, such as X-ray, computed tomography, and magnetic resonance imaging, used to opportunistically screen for osteoporosis.

RESULTS: A total of 40 studies were included in this review. These studies were divided into three categories: osteoporosis screening (n = 20), bone mineral density prediction (n = 13), and osteoporotic fracture risk prediction and detection (n = 7).

CONCLUSIONS: Deep learning has demonstrated a remarkable capacity for osteoporosis screening. However, clinical commercialization of a diagnostic model for osteoporosis remains a challenge.

PMID:38656208 | DOI:10.1177/03000605241244754

Expert Rev Mol Diagn. 2024 Apr 24. doi: 10.1080/14737159.2024.2346545. Online ahead of print.

ABSTRACT

INTRODUCTION: Histological images contain phenotypic information predictive of patient outcomes. Due to the heavy workload of pathologists, the time-consuming nature of quantitatively assessing histological features, and human eye limitations to recognize spatial patterns, manually extracting prognostic information in routine pathological workflows remains challenging. Digital pathology has facilitated the mining and quantification of these features utilizing whole-slide image (WSI) scanners and artificial intelligence (AI) algorithms. AI algorithms to identify image-based biomarkers from the tumor microenvironment (TME) have the potential to revolutionize the field of oncology, reducing delays between diagnosis and prognosis determination, allowing for rapid stratification of patients and prescription of optimal treatment regimes, thereby improving patient outcomes.

AREAS COVERED: In this review, the authors discuss how AI algorithms and digital pathology can predict breast cancer patient prognosis and treatment outcomes using image-based biomarkers, along with the challenges of adopting this technology in clinical settings.

EXPERT OPINION: The integration of AI and digital pathology presents significant potential for analyzing the TME and its diagnostic, prognostic, and predictive value in breast cancer patients. Widespread clinical adoption of AI faces ethical, regulatory, and technical challenges, although prospective trials may offer reassurance and promote uptake, ultimately improving patient outcomes by reducing diagnosis-to-prognosis delivery delays.

PMID:38655907 | DOI:10.1080/14737159.2024.2346545

J Magn Reson Imaging. 2024 Apr 24. doi: 10.1002/jmri.29399. Online ahead of print.

ABSTRACT

BACKGROUND: MRI-based placental analyses have been used to improve fetal growth restriction (FGR) assessment by complementing ultrasound-based measurements. However, these are still limited by time-consuming manual annotation in MRI data and the lack of mother-based information.

PURPOSE: To develop and validate a hybrid model for accurate FGR assessment by automatic placental radiomics on T2-weighted imaging (T2WI) and multifeature fusion.

STUDY TYPE: Retrospective.

POPULATION: 274 pregnant women (29.5 ± $$ \pm $$ 4.0 years) from two centers were included and randomly divided into training (N = 119), internal test (N = 40), time-independent validation (N = 43), and external validation (N = 72) sets.

FIELD STRENGTH/SEQUENCE: 1.5-T, T2WI half-Fourier acquisition single-shot turbo spin-echo pulse sequence.

ASSESSMENT: First, the placentas on T2WI were manually annotated, and a deep learning model was developed to automatically segment the placentas. Then, the radiomic features were extracted from the placentas and selected by three-step feature selection. In addition, fetus-based measurement features and mother-based clinical features were obtained from ultrasound examinations and medical records, respectively. Finally, a hybrid model based on random forest was constructed by fusing these features, and further compared with models based on other machine learning methods and different feature combinations.

STATISTICAL TESTS: The performances of placenta segmentation and FGR assessment were evaluated by Dice similarity coefficient (DSC) and the area under the receiver operating characteristic curve (AUROC), respectively. A P-value <0.05 was considered statistically significant.

RESULTS: The placentas were automatically segmented with an average DSC of 90.0%. The hybrid model achieved an AUROC of 0.923, 0.931, and 0.880 on the internal test, time-independent validation, and external validation sets, respectively. The mother-based clinical features resulted in significant performance improvements for FGR assessment.

DATA CONCLUSION: The proposed hybrid model may be able to assess FGR with high accuracy. Furthermore, information complementation based on placental, fetal, and maternal features could also lead to better FGR assessment performance.

TECHNICAL EFFICACY: Stage 2.

PMID:38655903 | DOI:10.1002/jmri.29399

Front Hum Neurosci. 2024 Apr 9;18:1334721. doi: 10.3389/fnhum.2024.1334721. eCollection 2024.

ABSTRACT

INTRODUCTION: The significant role of emotional recognition in the field of human-machine interaction has garnered the attention of many researchers. Emotion recognition based on physiological signals can objectively reflect the most authentic emotional states of humans. However, existing labeled Electroencephalogram (EEG) datasets are often of small scale.

METHODS: In practical scenarios, a large number of unlabeled EEG signals are easier to obtain. Therefore, this paper adopts self-supervised learning methods to study emotion recognition based on EEG. Specifically, experiments employ three pre-defined tasks to define pseudo-labels and extract features from the inherent structure of the data.

RESULTS AND DISCUSSION: Experimental results indicate that self-supervised learning methods have the capability to learn effective feature representations for downstream tasks without any manual labels.

PMID:38655374 | PMC:PMC11035789 | DOI:10.3389/fnhum.2024.1334721

Heliyon. 2024 Apr 12;10(8):e29305. doi: 10.1016/j.heliyon.2024.e29305. eCollection 2024 Apr 30.

ABSTRACT

BACKGROUND: To investigate the correlation between retinal vessel density (VD) parameters with serum B-type natriuretic peptide (BNP) in patients with coronary heart disease (CHD) using novel optical coherence tomography angiography (OCTA) denoising images based on artificial intelligence (AI).

METHODS: OCTA images of the optic nerve and macular area were obtained using a Canon-HS100 OCT device in 176 patients with CHD. Baseline information and blood test results were recorded.

RESULTS: Retinal VD parameters of the macular and optic nerves on OCTA were significantly decreased in patients with CHD after denoising. Retinal VD of the superficial capillary plexus (SCP), deep capillary plexus (DCP) and radial peripapillary capillary (RPC) was strongly correlated with serum BNP levels in patients with CHD. Significant differences were noted in retinal thickness and retinal VD (SCP, DCP and RPC) between the increased BNP and normal BNP groups in patients with CHD.

CONCLUSION: Deep learning denoising can remove background noise and smooth rough vessel surfaces. SCP,DCP and RPC may be potential clinical markers of cardiac function in patients with CHD. Denoising shows great potential for improving the sensitivity of OCTA images as a biomarker for CHD progression.

PMID:38655359 | PMC:PMC11035033 | DOI:10.1016/j.heliyon.2024.e29305

Heliyon. 2024 Apr 15;10(8):e29670. doi: 10.1016/j.heliyon.2024.e29670. eCollection 2024 Apr 30.

ABSTRACT

OBJECTIVE: This study aimed to develop an automated detection schema for otosclerosis with interpretable deep learning using temporal bone computed tomography images.

METHODS: With approval from the institutional review board, we retrospectively analyzed high-resolution computed tomography scans of the temporal bone of 182 participants with otosclerosis (67 male subjects and 115 female subjects; average age, 36.42 years) and 157 participants without otosclerosis (52 male subjects and 102 female subjects; average age, 30.61 years) using deep learning. Transfer learning with the pretrained VGG19, Mask RCNN, and EfficientNet models was used. In addition, 3 clinical experts compared the system's performance by reading the same computed tomography images for a subset of 35 unseen subjects. An area under the receiver operating characteristic curve and a saliency map were used to further evaluate the diagnostic performance.

RESULTS: In prospective unseen test data, the diagnostic performance of the automatically interpretable otosclerosis detection system at the optimal threshold was 0.97 and 0.98 for sensitivity and specificity, respectively. In comparison with the clinical acumen of otolaryngologists at P < 0.05, the proposed system was not significantly different. Moreover, the area under the receiver operating characteristic curve for the proposed system was 0.99, indicating satisfactory diagnostic accuracy.

CONCLUSION: Our research develops and evaluates a deep learning system that detects otosclerosis at a level comparable with clinical otolaryngologists. Our system is an effective schema for the differential diagnosis of otosclerosis in computed tomography examinations.

PMID:38655358 | PMC:PMC11036044 | DOI:10.1016/j.heliyon.2024.e29670

Heliyon. 2024 Apr 12;10(8):e29438. doi: 10.1016/j.heliyon.2024.e29438. eCollection 2024 Apr 30.

ABSTRACT

With an emphasis on classifying diseases of sugarcane leaves, this research suggests an attention-based multilevel deep learning architecture for reliably classifying plant diseases. The suggested architecture comprises spatial and channel attention for saliency detection and blends features from lower to higher levels. On a self-created database, the model outperformed cutting-edge models like VGG19, ResNet50, XceptionNet, and EfficientNet_B7 with an accuracy of 86.53%. The findings show how essential all-level characteristics are for categorizing images and how they can improve efficiency even with tiny databases. The suggested architecture has the potential to support the early detection and diagnosis of plant diseases, enabling fast crop damage mitigation. Additionally, the implementation of the proposed AMRCNN model in the Android phone-based application gives an opportunity for the widespread use of mobile phones in the classification of sugarcane diseases.

PMID:38655338 | PMC:PMC11035994 | DOI:10.1016/j.heliyon.2024.e29438

Front Oncol. 2024 Apr 9;14:1389158. doi: 10.3389/fonc.2024.1389158. eCollection 2024.

NO ABSTRACT

PMID:38655142 | PMC:PMC11037079 | DOI:10.3389/fonc.2024.1389158

Magn Reson Imaging. 2024 Apr 21:S0730-725X(24)00134-6. doi: 10.1016/j.mri.2024.04.021. Online ahead of print.

ABSTRACT

Challenges arise in achieving high-resolution Magnetic Resonance Imaging (MRI) to improve disease diagnosis accuracy due to limitations in hardware, patient discomfort, long acquisition times, and high costs. While Convolutional Neural Networks (CNNs) have shown promising results in MRI super-resolution, they often don't look into the structural similarity and prior information available in consecutive MRI slices. By leveraging information from sequential slices, more robust features can be obtained, potentially leading to higher-quality MRI slices. We propose a multi-slice two-dimensional (2D) MRI super-resolution network that combines a Generative Adversarial Network (GAN) with feature fusion and a pre-trained slice interpolation network to achieve three-dimensional (3D) super-resolution. The proposed model requires consecutively acquired three low-resolution (LR) MRI slices along a specific axis, and achieves the reconstruction of the MRI slices in the remaining two axes. The network effectively enhances both in-plane and out-of-plane resolution along the sagittal axis while addressing computational and memory constraints in 3D super-resolution. The proposed generator has a in-plane and out-of-plane Attention (IOA) network that fuses both in-plane and out-plane features of MRI dynamically. In terms of out-of-plane attention, the network merges features by considering the similarity distance between features and for in-plane attention, the network employs a two-level pyramid structure with varying receptive fields to extract features at different scales, ensuring the inclusion of both global and local features. Subsequently, to achieve 3D MRI super-resolution, a pre-trained slice interpolation network is used that takes two consecutive super-resolved MRI slices to generate a new intermediate slice. To further enhance the network performance and perceptual quality, we introduce a feature up-sampling layer and a feature extraction block with Scaled Exponential Linear Unit (SeLU). Moreover, our super-resolution network incorporates VGG loss from a fine-tuned VGG-19 network to provide additional enhancement. Through experimental evaluations on the IXI dataset and BRATS dataset, using the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM) and the number of training parameters, we demonstrate the superior performance of our method compared to the existing techniques. Also, the proposed model can be adapted or modified to achieve super-resolution for both 2D and 3D MRI data.

PMID:38653336 | DOI:10.1016/j.mri.2024.04.021

Neural Netw. 2024 Apr 7;175:106296. doi: 10.1016/j.neunet.2024.106296. Online ahead of print.

ABSTRACT

Structural magnetic resonance imaging (sMRI) has shown great clinical value and has been widely used in deep learning (DL) based computer-aided brain disease diagnosis. Previous DL-based approaches focused on local shapes and textures in brain sMRI that may be significant only within a particular domain. The learned representations are likely to contain spurious information and have poor generalization ability in other diseases and datasets. To facilitate capturing meaningful and robust features, it is necessary to first comprehensively understand the intrinsic pattern of the brain that is not restricted within a single data/task domain. Considering that the brain is a complex connectome of interlinked neurons, the connectional properties in the brain have strong biological significance, which is shared across multiple domains and covers most pathological information. In this work, we propose a connectional style contextual representation learning model (CS-CRL) to capture the intrinsic pattern of the brain, used for multiple brain disease diagnosis. Specifically, it has a vision transformer (ViT) encoder and leverages mask reconstruction as the proxy task and Gram matrices to guide the representation of connectional information. It facilitates the capture of global context and the aggregation of features with biological plausibility. The results indicate that CS-CRL achieves superior accuracy in multiple brain disease diagnosis tasks across six datasets and three diseases and outperforms state-of-the-art models. Furthermore, we demonstrate that CS-CRL captures more brain-network-like properties, and better aggregates features, is easier to optimize, and is more robust to noise, which explains its superiority in theory.

PMID:38653077 | DOI:10.1016/j.neunet.2024.106296

Comput Biol Med. 2024 Apr 17;175:108487. doi: 10.1016/j.compbiomed.2024.108487. Online ahead of print.

ABSTRACT

Drug repurposing is promising in multiple scenarios, such as emerging viral outbreak controls and cost reductions of drug discovery. Traditional graph-based drug repurposing methods are limited to fast, large-scale virtual screens, as they constrain the counts for drugs and targets and fail to predict novel viruses or drugs. Moreover, though deep learning has been proposed for drug repurposing, only a few methods have been used, including a group of pre-trained deep learning models for embedding generation and transfer learning. Hence, we propose DeepSeq2Drug to tackle the shortcomings of previous methods. We leverage multi-modal embeddings and an ensemble strategy to complement the numbers of drugs and viruses and to guarantee the novel prediction. This framework (including the expanded version) involves four modal types: six NLP models, four CV models, four graph models, and two sequence models. In detail, we first make a pipeline and calculate the predictive performance of each pair of viral and drug embeddings. Then, we select the best embedding pairs and apply an ensemble strategy to conduct anti-viral drug repurposing. To validate the effect of the proposed ensemble model, a monkeypox virus (MPV) case study is conducted to reflect the potential predictive capability. This framework could be a benchmark method for further pre-trained deep learning optimization and anti-viral drug repurposing tasks. We also build software further to make the proposed model easier to reuse. The code and software are freely available at http://deepseq2drug.cs.cityu.edu.hk.

PMID:38653064 | DOI:10.1016/j.compbiomed.2024.108487

Comput Biol Med. 2024 Apr 16;175:108485. doi: 10.1016/j.compbiomed.2024.108485. Online ahead of print.

ABSTRACT

Various studies have linked several diseases, including cancer and COVID-19, to single nucleotide variations (SNV). Although single-cell RNA sequencing (scRNA-seq) technology can provide SNV and gene expression data, few studies have integrated and analyzed these multimodal data. To address this issue, we introduce Interpretable Single-cell Multimodal Data Integration Based on Variational Autoencoder (ISMI-VAE). ISMI-VAE leverages latent variable models that utilize the characteristics of SNV and gene expression data to overcome high noise levels and uses deep learning techniques to integrate multimodal information, map them to a low-dimensional space, and classify disease cells. Moreover, ISMI-VAE introduces an attention mechanism to reflect feature importance and analyze genetic features that could potentially cause disease. Experimental results on three cancer data sets and one COVID-19 data set demonstrate that ISMI-VAE surpasses the baseline method in terms of both effectiveness and interpretability and can effectively identify disease-causing gene features.

PMID:38653063 | DOI:10.1016/j.compbiomed.2024.108485

Comput Methods Programs Biomed. 2024 Apr 21;250:108178. doi: 10.1016/j.cmpb.2024.108178. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Gland segmentation of pathological images is an essential but challenging step for adenocarcinoma diagnosis. Although deep learning methods have recently made tremendous progress in gland segmentation, they have not given satisfactory boundary and region segmentation results of adjacent glands. These glands usually have a large difference in glandular appearance, and the statistical distribution between the training and test sets in deep learning is inconsistent. These problems make networks not generalize well in the test dataset, bringing difficulties to gland segmentation and early cancer diagnosis.

METHODS: To address these problems, we propose a Variational Energy Network named VENet with a traditional variational energy Lv loss for gland segmentation of pathological images and early gastric cancer detection in whole slide images (WSIs). It effectively integrates the variational mathematical model and the data-adaptability of deep learning methods to balance boundary and region segmentation. Furthermore, it can effectively segment and classify glands in large-size WSIs with reliable nucleus width and nucleus-to-cytoplasm ratio features.

RESULTS: The VENet was evaluated on the 2015 MICCAI Gland Segmentation challenge (GlaS) dataset, the Colorectal Adenocarcinoma Glands (CRAG) dataset, and the self-collected Nanfang Hospital dataset. Compared with state-of-the-art methods, our method achieved excellent performance for GlaS Test A (object dice 0.9562, object F1 0.9271, object Hausdorff distance 73.13), GlaS Test B (object dice 94.95, object F1 95.60, object Hausdorff distance 59.63), and CRAG (object dice 95.08, object F1 92.94, object Hausdorff distance 28.01). For the Nanfang Hospital dataset, our method achieved a kappa of 0.78, an accuracy of 0.9, a sensitivity of 0.98, and a specificity of 0.80 on the classification task of test 69 WSIs.

CONCLUSIONS: The experimental results show that the proposed model accurately predicts boundaries and outperforms state-of-the-art methods. It can be applied to the early diagnosis of gastric cancer by detecting regions of high-grade gastric intraepithelial neoplasia in WSI, which can assist pathologists in analyzing large WSI and making accurate diagnostic decisions.

PMID:38652995 | DOI:10.1016/j.cmpb.2024.108178

Int J Retina Vitreous. 2024 Apr 23;10(1):36. doi: 10.1186/s40942-024-00554-4.

ABSTRACT

BACKGROUND: Applications for artificial intelligence (AI) in ophthalmology are continually evolving. Fundoscopy is one of the oldest ocular imaging techniques but remains a mainstay in posterior segment imaging due to its prevalence, ease of use, and ongoing technological advancement. AI has been leveraged for fundoscopy to accomplish core tasks including segmentation, classification, and prediction.

MAIN BODY: In this article we provide a review of AI in fundoscopy applied to representative chorioretinal pathologies, including diabetic retinopathy and age-related macular degeneration, among others. We conclude with a discussion of future directions and current limitations.

SHORT CONCLUSION: As AI evolves, it will become increasingly essential for the modern ophthalmologist to understand its applications and limitations to improve patient outcomes and continue to innovate.

PMID:38654344 | DOI:10.1186/s40942-024-00554-4