Front Oncol. 2024 Feb 12;14:1281922. doi: 10.3389/fonc.2024.1281922. eCollection 2024.

ABSTRACT

X-ray mammography is currently considered the golden standard method for breast cancer screening, however, it has limitations in terms of sensitivity and specificity. With the rapid advancements in deep learning techniques, it is possible to customize mammography for each patient, providing more accurate information for risk assessment, prognosis, and treatment planning. This paper aims to study the recent achievements of deep learning-based mammography for breast cancer detection and classification. This review paper highlights the potential of deep learning-assisted X-ray mammography in improving the accuracy of breast cancer screening. While the potential benefits are clear, it is essential to address the challenges associated with implementing this technology in clinical settings. Future research should focus on refining deep learning algorithms, ensuring data privacy, improving model interpretability, and establishing generalizability to successfully integrate deep learning-assisted mammography into routine breast cancer screening programs. It is hoped that the research findings will assist investigators, engineers, and clinicians in developing more effective breast imaging tools that provide accurate diagnosis, sensitivity, and specificity for breast cancer.

PMID:38410114 | PMC:PMC10894909 | DOI:10.3389/fonc.2024.1281922

J Appl Toxicol. 2024 Feb 26. doi: 10.1002/jat.4591. Online ahead of print.

ABSTRACT

Machine learning (ML) has shown a great promise in predicting toxicity of small molecules. However, the availability of data for such predictions is often limited. Because of the unsatisfactory performance of models trained on a single toxicity endpoint, we collected toxic small molecules with multiple toxicity endpoints from previous study. The dataset comprises 27 toxic endpoints categorized into seven toxicity classes, namely, carcinogenicity and mutagenicity, acute oral toxicity, respiratory toxicity, irritation and corrosion, cardiotoxicity, CYP450, and endocrine disruption. In addition, a binary classification Common-Toxicity task was added based on the aforementioned dataset. To improve the performance of the models, we added marketed drugs as negative samples. This study presents a toxicity predictive model, ToxMPNN, based on the message passing neural network (MPNN) architecture, aiming to predict the toxicity of small molecules. The results demonstrate that ToxMPNN outperforms other models in capturing toxic features within the molecular structure, resulting in more precise predictions with the ROC_AUC testing score of 0.886 for the Toxicity_drug dataset. Furthermore, it was observed that adding marketed drugs as negative samples not only improves the predictive performance of the binary classification Common-Toxicity task but also enhances the stability of the model prediction. It shows that the graph-based deep learning (DL) algorithms in this study can be used as a trustworthy and effective tool to assess small molecule toxicity in the development of new drugs.

PMID:38409892 | DOI:10.1002/jat.4591

Histopathology. 2024 Feb 26. doi: 10.1111/his.15159. Online ahead of print.

ABSTRACT

BACKGROUND: Artificial intelligence (AI) has numerous applications in pathology, supporting diagnosis and prognostication in cancer. However, most AI models are trained on highly selected data, typically one tissue slide per patient. In reality, especially for large surgical resection specimens, dozens of slides can be available for each patient. Manually sorting and labelling whole-slide images (WSIs) is a very time-consuming process, hindering the direct application of AI on the collected tissue samples from large cohorts. In this study we addressed this issue by developing a deep-learning (DL)-based method for automatic curation of large pathology datasets with several slides per patient.

METHODS: We collected multiple large multicentric datasets of colorectal cancer histopathological slides from the United Kingdom (FOXTROT, N = 21,384 slides; CR07, N = 7985 slides) and Germany (DACHS, N = 3606 slides). These datasets contained multiple types of tissue slides, including bowel resection specimens, endoscopic biopsies, lymph node resections, immunohistochemistry-stained slides, and tissue microarrays. We developed, trained, and tested a deep convolutional neural network model to predict the type of slide from the slide overview (thumbnail) image. The primary statistical endpoint was the macro-averaged area under the receiver operating curve (AUROCs) for detection of the type of slide.

RESULTS: In the primary dataset (FOXTROT), with an AUROC of 0.995 [95% confidence interval [CI]: 0.994-0.996] the algorithm achieved a high classification performance and was able to accurately predict the type of slide from the thumbnail image alone. In the two external test cohorts (CR07, DACHS) AUROCs of 0.982 [95% CI: 0.979-0.985] and 0.875 [95% CI: 0.864-0.887] were observed, which indicates the generalizability of the trained model on unseen datasets. With a confidence threshold of 0.95, the model reached an accuracy of 94.6% (7331 classified cases) in CR07 and 85.1% (2752 classified cases) for the DACHS cohort.

CONCLUSION: Our findings show that using the low-resolution thumbnail image is sufficient to accurately classify the type of slide in digital pathology. This can support researchers to make the vast resource of existing pathology archives accessible to modern AI models with only minimal manual annotations.

PMID:38409878 | DOI:10.1111/his.15159

Biophys J. 2024 Feb 26:S0006-3495(24)00138-3. doi: 10.1016/j.bpj.2024.02.018. Online ahead of print.

ABSTRACT

DNA molecules are vital macromolecules that play a fundamental role in many cellular processes and have broad applications in medicine. For example, DNA aptamers have been rapidly developed for diagnosis, biosensors, and clinical therapy. Recently, we proposed a computational method of predicting DNA 3D structures, called 3dDNA. However, it lacks a scoring function to evaluate the predicted DNA 3D structures and so they are not ranked for users. Here we report a scoring function, 3dDNAscoreA, for evaluation of DNA 3D structures based on a deep learning model ARES for RNA 3D structure evaluation but using a new strategy for training. 3dDNAscoreA is benchmarked on two test sets to show its ability to rank DNA 3D structures and select the native and near-native structures.

PMID:38409781 | DOI:10.1016/j.bpj.2024.02.018

Sci Rep. 2024 Feb 26;14(1):4678. doi: 10.1038/s41598-024-53997-y.

ABSTRACT

Manual delineation of liver segments on computed tomography (CT) images for primary/secondary liver cancer (LC) patients is time-intensive and prone to inter/intra-observer variability. Therefore, we developed a deep-learning-based model to auto-contour liver segments and spleen on contrast-enhanced CT (CECT) images. We trained two models using 3d patch-based attention U-Net ([Formula: see text] and 3d full resolution of nnU-Net ([Formula: see text] to determine the best architecture ([Formula: see text]. BA was used with vessels ([Formula: see text] and spleen ([Formula: see text] to assess the impact on segment contouring. Models were trained, validated, and tested on 160 ([Formula: see text]), 40 ([Formula: see text]), 33 ([Formula: see text]), 25 (CCH) and 20 (CPVE) CECT of LC patients. [Formula: see text] outperformed [Formula: see text] across all segments with median differences in Dice similarity coefficients (DSC) ranging 0.03-0.05 (p < 0.05). [Formula: see text], and [Formula: see text] were not statistically different (p > 0.05), however, both were slightly better than [Formula: see text] by DSC up to 0.02. The final model, [Formula: see text], showed a mean DSC of 0.89, 0.82, 0.88, 0.87, 0.96, and 0.95 for segments 1, 2, 3, 4, 5-8, and spleen, respectively on entire test sets. Qualitatively, more than 85% of cases showed a Likert score [Formula: see text] 3 on test sets. Our final model provides clinically acceptable contours of liver segments and spleen which are usable in treatment planning.

PMID:38409252 | DOI:10.1038/s41598-024-53997-y

NPJ Parkinsons Dis. 2024 Feb 26;10(1):43. doi: 10.1038/s41531-024-00647-9.

ABSTRACT

Parkinson's disease (PD) is the second most common neurodegenerative disease. Accurate PD diagnosis is crucial for effective treatment and prognosis but can be challenging, especially at early disease stages. This study aimed to develop and evaluate an explainable deep learning model for PD classification from multimodal neuroimaging data. The model was trained using one of the largest collections of T1-weighted and diffusion-tensor magnetic resonance imaging (MRI) datasets. A total of 1264 datasets from eight different studies were collected, including 611 PD patients and 653 healthy controls (HC). These datasets were pre-processed and non-linearly registered to the MNI PD25 atlas. Six imaging maps describing the macro- and micro-structural integrity of brain tissues complemented with age and sex parameters were used to train a convolutional neural network (CNN) to classify PD/HC subjects. Explainability of the model's decision-making was achieved using SmoothGrad saliency maps, highlighting important brain regions. The CNN was trained using a 75%/10%/15% train/validation/test split stratified by diagnosis, sex, age, and study, achieving a ROC-AUC of 0.89, accuracy of 80.8%, specificity of 82.4%, and sensitivity of 79.1% on the test set. Saliency maps revealed that diffusion tensor imaging data, especially fractional anisotropy, was more important for the classification than T1-weighted data, highlighting subcortical regions such as the brainstem, thalamus, amygdala, hippocampus, and cortical areas. The proposed model, trained on a large multimodal MRI database, can classify PD patients and HC subjects with high accuracy and clinically reasonable explanations, suggesting that micro-structural brain changes play an essential role in the disease course.

PMID:38409244 | DOI:10.1038/s41531-024-00647-9

BMC Biol. 2024 Feb 27;22(1):44. doi: 10.1186/s12915-023-01804-x.

ABSTRACT

BACKGROUND: Circular RNAs (circRNAs) can regulate microRNA activity and are related to various diseases, such as cancer. Functional research on circRNAs is the focus of scientific research. Accurate identification of circRNAs is important for gaining insight into their functions. Although several circRNA prediction models have been developed, their prediction accuracy is still unsatisfactory. Therefore, providing a more accurate computational framework to predict circRNAs and analyse their looping characteristics is crucial for systematic annotation.

RESULTS: We developed a novel framework, CircDC, for classifying circRNAs from other lncRNAs. CircDC uses four different feature encoding schemes and adopts a multilayer convolutional neural network and bidirectional long short-term memory network to learn high-order feature representation and make circRNA predictions. The results demonstrate that the proposed CircDC model is more accurate than existing models. In addition, an interpretable analysis of the features affecting the model is performed, and the computational framework is applied to the extended application of circRNA identification.

CONCLUSIONS: CircDC is suitable for the prediction of circRNA. The identification of circRNA helps to understand and delve into the related biological processes and functions. Feature importance analysis increases model interpretability and uncovers significant biological properties. The relevant code and data in this article can be accessed for free at https://github.com/nmt315320/CircDC.git .

PMID:38408987 | DOI:10.1186/s12915-023-01804-x

BMC Cancer. 2024 Feb 26;24(1):269. doi: 10.1186/s12885-024-12008-z.

ABSTRACT

BACKGROUND: Immune checkpoint inhibitors (ICIs) can lead to life-threatening pneumonitis, and pre-existing interstitial lung abnormalities (ILAs) are a risk factor for checkpoint inhibitor pneumonitis (CIP). However, the subjective assessment of ILA and the lack of standardized methods restrict its clinical utility as a predictive factor. This study aims to identify non-small cell lung cancer (NSCLC) patients at high risk of CIP using quantitative imaging.

METHODS: This cohort study involved 206 cases in the training set and 111 cases in the validation set. It included locally advanced or metastatic NSCLC patients who underwent ICI therapy. A deep learning algorithm labeled the interstitial lesions and computed their volume. Two predictive models were developed to predict the probability of grade ≥ 2 CIP or severe CIP (grade ≥ 3). Cox proportional hazard models were employed to analyze predictors of progression-free survival (PFS).

RESULTS: In a training cohort of 206 patients, 21.4% experienced CIP. Two models were developed to predict the probability of CIP based on different predictors. Model 1 utilized age, histology, and preexisting ground glass opacity (GGO) percentage of the whole lung to predict grade ≥ 2 CIP, while Model 2 used histology and GGO percentage in the right lower lung to predict grade ≥ 3 CIP. These models were validated, and their accuracy was assessed. In another exploratory analysis, the presence of GGOs involving more than one lobe on pretreatment CT scans was identified as a risk factor for progression-free survival.

CONCLUSIONS: The assessment of GGO volume and distribution on pre-treatment CT scans could assist in monitoring and manage the risk of CIP in NSCLC patients receiving ICI therapy.

CLINICAL RELEVANCE STATEMENT: This study's quantitative imaging and computational analysis can help identify NSCLC patients at high risk of CIP, allowing for better risk management and potentially improved outcomes in those receivingICI treatment.

PMID:38408928 | DOI:10.1186/s12885-024-12008-z

BMC Plant Biol. 2024 Feb 26;24(1):136. doi: 10.1186/s12870-024-04825-y.

ABSTRACT

Subsistence farmers and global food security depend on sufficient food production, which aligns with the UN's "Zero Hunger," "Climate Action," and "Responsible Consumption and Production" sustainable development goals. In addition to already available methods for early disease detection and classification facing overfitting and fine feature extraction complexities during the training process, how early signs of green attacks can be identified or classified remains uncertain. Most pests and disease symptoms are seen in plant leaves and fruits, yet their diagnosis by experts in the laboratory is expensive, tedious, labor-intensive, and time-consuming. Notably, how plant pests and diseases can be appropriately detected and timely prevented is a hotspot paradigm in smart, sustainable agriculture remains unknown. In recent years, deep transfer learning has demonstrated tremendous advances in the recognition accuracy of object detection and image classification systems since these frameworks utilize previously acquired knowledge to solve similar problems more effectively and quickly. Therefore, in this research, we introduce two plant disease detection (PDDNet) models of early fusion (AE) and the lead voting ensemble (LVE) integrated with nine pre-trained convolutional neural networks (CNNs) and fine-tuned by deep feature extraction for efficient plant disease identification and classification. The experiments were carried out on 15 classes of the popular PlantVillage dataset, which has 54,305 image samples of different plant disease species in 38 categories. Hyperparameter fine-tuning was done with popular pre-trained models, including DenseNet201, ResNet101, ResNet50, GoogleNet, AlexNet, ResNet18, EfficientNetB7, NASNetMobile, and ConvNeXtSmall. We test these CNNs on the stated plant disease detection and classification problem, both independently and as part of an ensemble. In the final phase, a logistic regression (LR) classifier is utilized to determine the performance of various CNN model combinations. A comparative analysis was also performed on classifiers, deep learning, the proposed model, and similar state-of-the-art studies. The experiments demonstrated that PDDNet-AE and PDDNet-LVE achieved 96.74% and 97.79%, respectively, compared to current CNNs when tested on several plant diseases, depicting its exceptional robustness and generalization capabilities and mitigating current concerns in plant disease detection and classification.

PMID:38408925 | DOI:10.1186/s12870-024-04825-y

Br J Ophthalmol. 2024 Feb 26:bjo-2023-323592. doi: 10.1136/bjo-2023-323592. Online ahead of print.

ABSTRACT

PURPOSE: To classify fleck lesions and assess artificial intelligence (AI) in identifying flecks in Stargardt disease (STGD).

METHODS: A retrospective study of 170 eyes from 85 consecutive patients with confirmed STGD. Fundus autofluorescence images were extracted, and flecks were manually outlined. A deep learning model was trained, and a hold-out testing subset was used to compare with manually identified flecks and for graders to assess. Flecks were clustered using K-means clustering.

RESULTS: Of the 85 subjects, 45 were female, and the median age was 37 years (IQR 25-59). A subset of subjects (n=41) had clearly identifiable fleck lesions, and an AI was successfully trained to identify these lesions (average Dice score of 0.53, n=18). The AI segmentation had smaller (0.018 compared with 0.034 mm2, p<0.001) but more numerous flecks (75.5 per retina compared with 40.0, p<0.001), but the total size of flecks was not different. The AI model had higher sensitivity to detect flecks but resulted in more false positives. There were two clusters of flecks based on morphology: broadly, one cluster of small round flecks and another of large amorphous flecks. The per cent frequency of small round flecks negatively correlated with subject age (r=-0.31, p<0.005).

CONCLUSIONS: AI-based detection of flecks shows greater sensitivity than human graders but with a higher false-positive rate. With further optimisation to address current shortcomings, this approach could be used to prescreen subjects for clinical research. The feasibility and utility of quantifying fleck morphology in conjunction with AI-based segmentation as a biomarker of progression require further study.

PMID:38408857 | DOI:10.1136/bjo-2023-323592

J Neuroradiol. 2024 Feb 24:S0150-9861(24)00109-3. doi: 10.1016/j.neurad.2024.02.006. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: Olfaction is an early marker of neurodegenerative disease. Standard olfactory function is essential due to the importance of olfaction in human life. The psychophysical evaluation assesses the olfactory function commonly. It is patient-reported, and results rely on the patient's answers and collaboration. However, methodological difficulties attributed to the psychophysical evaluation of olfactory-related cerebral areas led to limited assessment of olfactory function in the human brain.

MATERIALS AND METHODS: The current study utilized clustering approaches to assess olfactory function in fMRI data and used brain activity to parcellate the brain with homogeneous properties. Deep neural network architecture based on ResNet convolutional neural networks (CNN) and Long Short-Term Model (LSTM) designed to classify healthy with olfactory disorders subjects.

RESULTS: The fMRI result obtained by k-means unsupervised machine learning model was within the expected outcome and similar to those found with the conn toolbox in detecting active areas. There was no significant difference between the means of subjects and every subject. Proposing a CRNN deep learning model to classify fMRI data in two different healthy and with olfactory disorders groups leads to an accuracy score of 97%.

CONCLUSIONS: The K-means unsupervised algorithm can detect the active regions in the brain and analyze olfactory function. Classification results prove the CNN-LSTM architecture using ResNet provides the best accuracy score in olfactory fMRI data. It is the first attempt conducted on olfactory fMRI data in detail until now.

PMID:38408721 | DOI:10.1016/j.neurad.2024.02.006

World Neurosurg. 2024 Feb 24:S1878-8750(24)00325-5. doi: 10.1016/j.wneu.2024.02.112. Online ahead of print.

ABSTRACT

INTRODUCTION: Cervical spine procedures represent a major proportion of all spine surgery. Mitigating the revision rate following cervical procedures requires careful patient selection. While complication risk has successfully been predicted, revision risk has proven more challenging. This is likely due to the absence of granular variables in claims databases. The objective of this study was to develop a state-of-the-art of revision prediction of cervical spine surgery using laboratory and operative variables.

METHODS: Using the Stanford Research Repository, patients undergoing a cervical spine procedure between 2016-2022 were identified (N=3151) and recent laboratory values were collected. Patients were classified into separate cohorts by revision outcome and timeframe. Machine and deep learning models were trained to predict each revision outcome from laboratory and operative variables.

RESULTS: Red blood cell count, Hemoglobin, Hematocrit, Mean Corpuscular Hemoglobin Concentration, Red Blood Cell Distribution Width, Platelet Count, CO2, Anion Gap, and Calcium were all significantly associated with one or more revision cohorts. For the prediction of 3-month revision, the deep neural network achieved AUC of 0.833. The model demonstrated increased performance for anterior than posterior and arthrodesis than decompression procedures.

CONCLUSIONS: Our deep learning approach successfully predicted 3-month revision outcomes from demographic variables, standard laboratory values, and operative variables, in a cervical spine surgery cohort. This work introduces standard laboratory values and operative codes as meaningful predictive variables for revision outcome prediction. The increased performance on certain procedures evidences the need for careful development and validation of "one-size-fits-all" risk scores for spine procedures.

PMID:38408699 | DOI:10.1016/j.wneu.2024.02.112

PLoS Comput Biol. 2024 Feb 26;20(2):e1011887. doi: 10.1371/journal.pcbi.1011887. Online ahead of print.

ABSTRACT

Despite decades of research, much is still unknown about the computations carried out in the human face processing network. Recently, deep networks have been proposed as a computational account of human visual processing, but while they provide a good match to neural data throughout visual cortex, they lack interpretability. We introduce a method for interpreting brain activity using a new class of deep generative models, disentangled representation learning models, which learn a low-dimensional latent space that "disentangles" different semantically meaningful dimensions of faces, such as rotation, lighting, or hairstyle, in an unsupervised manner by enforcing statistical independence between dimensions. We find that the majority of our model's learned latent dimensions are interpretable by human raters. Further, these latent dimensions serve as a good encoding model for human fMRI data. We next investigate the representation of different latent dimensions across face-selective voxels. We find that low- and high-level face features are represented in posterior and anterior face-selective regions, respectively, corroborating prior models of human face recognition. Interestingly, though, we find identity-relevant and irrelevant face features across the face processing network. Finally, we provide new insight into the few "entangled" (uninterpretable) dimensions in our model by showing that they match responses in the ventral stream and carry information about facial identity. Disentangled face encoding models provide an exciting alternative to standard "black box" deep learning approaches for modeling and interpreting human brain data.

PMID:38408105 | DOI:10.1371/journal.pcbi.1011887

PLoS Comput Biol. 2024 Feb 26;20(2):e1011108. doi: 10.1371/journal.pcbi.1011108. Online ahead of print.

ABSTRACT

Biophysically detailed neural models are a powerful technique to study neural dynamics in health and disease with a growing number of established and openly available models. A major challenge in the use of such models is that parameter inference is an inherently difficult and unsolved problem. Identifying unique parameter distributions that can account for observed neural dynamics, and differences across experimental conditions, is essential to their meaningful use. Recently, simulation based inference (SBI) has been proposed as an approach to perform Bayesian inference to estimate parameters in detailed neural models. SBI overcomes the challenge of not having access to a likelihood function, which has severely limited inference methods in such models, by leveraging advances in deep learning to perform density estimation. While the substantial methodological advancements offered by SBI are promising, their use in large scale biophysically detailed models is challenging and methods for doing so have not been established, particularly when inferring parameters that can account for time series waveforms. We provide guidelines and considerations on how SBI can be applied to estimate time series waveforms in biophysically detailed neural models starting with a simplified example and extending to specific applications to common MEG/EEG waveforms using the the large scale neural modeling framework of the Human Neocortical Neurosolver. Specifically, we describe how to estimate and compare results from example oscillatory and event related potential simulations. We also describe how diagnostics can be used to assess the quality and uniqueness of the posterior estimates. The methods described provide a principled foundation to guide future applications of SBI in a wide variety of applications that use detailed models to study neural dynamics.

PMID:38408099 | DOI:10.1371/journal.pcbi.1011108

Med Phys. 2024 Feb 26. doi: 10.1002/mp.17000. Online ahead of print.

ABSTRACT

BACKGROUND: Deep learning-based unsupervised image registration has recently been proposed, promising fast registration. However, it has yet to be adopted in the online adaptive magnetic resonance imaging-guided radiotherapy (MRgRT) workflow.

PURPOSE: In this paper, we design an unsupervised, joint rigid, and deformable registration framework for contour propagation in MRgRT of prostate cancer.

METHODS: Three-dimensional pelvic T2-weighted MRIs of 143 prostate cancer patients undergoing radiotherapy were collected and divided into 110, 13, and 20 patients for training, validation, and testing. We designed a framework using convolutional neural networks (CNNs) for rigid and deformable registration. We selected the deformable registration network architecture among U-Net, MS-D Net, and LapIRN and optimized the training strategy (end-to-end vs. sequential). The framework was compared against an iterative baseline registration. We evaluated registration accuracy (the Dice and Hausdorff distance of the prostate and bladder contours), structural similarity index, and folding percentage to compare the methods. We also evaluated the framework's robustness to rigid and elastic deformations and bias field perturbations.

RESULTS: The end-to-end trained framework comprising LapIRN for the deformable component achieved the best median (interquartile range) prostate and bladder Dice of 0.89 (0.85-0.91) and 0.86 (0.80-0.91), respectively. This accuracy was comparable to the iterative baseline registration: prostate and bladder Dice of 0.91 (0.88-0.93) and 0.86 (0.80-0.92). The best models complete rigid and deformable registration in 0.002 (0.0005) and 0.74 (0.43) s (Nvidia Tesla V100-PCIe 32 GB GPU), respectively. We found that the models are robust to translations up to 52 mm, rotations up to 15 ∘ $^\circ$ , elastic deformations up to 40 mm, and bias fields.

CONCLUSIONS: Our proposed unsupervised, deep learning-based registration framework can perform rigid and deformable registration in less than a second with contour propagation accuracy comparable with iterative registration.

PMID:38408022 | DOI:10.1002/mp.17000

IEEE Trans Neural Netw Learn Syst. 2024 Feb 26;PP. doi: 10.1109/TNNLS.2024.3367873. Online ahead of print.

ABSTRACT

Community detection has become a prominent task in complex network analysis. However, most of the existing methods for community detection only focus on the lower order structure at the level of individual nodes and edges and ignore the higher order connectivity patterns that characterize the fundamental building blocks within the network. In recent years, researchers have shown interest in motifs and their role in network analysis. However, most of the existing higher order approaches are based on shallow methods, failing to capture the intricate nonlinear relationships between nodes. In order to better fuse higher order and lower order structural information, a novel deep learning framework called motif-based contrastive learning for community detection (MotifCC) is proposed. First, a higher order network is constructed based on motifs. Subnetworks are then obtained by removing isolated nodes, addressing the fragmentation issue in the higher order network. Next, the concept of contrastive learning is applied to effectively fuse various kinds of information from nodes, edges, and higher order and lower order structures. This aims to maximize the similarity of corresponding node information, while distinguishing different nodes and different communities. Finally, based on the community structure of subnetworks, the community labels of all nodes are obtained by using the idea of label propagation. Extensive experiments on real-world datasets validate the effectiveness of MotifCC.

PMID:38408012 | DOI:10.1109/TNNLS.2024.3367873

J Neural Eng. 2024 Feb 26. doi: 10.1088/1741-2552/ad2cea. Online ahead of print.

ABSTRACT

Using functional magnetic resonance imaging (fMRI) and deep learning to discover the spatial pattern of brain function, or functional brain networks (FBNs) has been attracted many reseachers. Most existing works focus on static FBNs or dynamic functional connectivity among fixed spatial network nodes, but ignore the potential dynamic/time-varying characteristics of the spatial networks themselves. And most of works based on the assumption of linearity and independence, that oversimplify the relationship between blood-oxygen level dependence (BOLD) signal changes and the heterogeneity of neuronal activity within voxels. To overcome these problems, we proposed a novel spatial-wise attention based method called Spatial and Channel-wise Attention Autoencoder (SCAAE) to discover the dynamic FBNs without the assumptions of linearity or independence. The core idea of SCAAE is to apply the spatial-wise attention to generate FBNs directly, relying solely on the spatial information present in fMRI volumes. Specifically, we trained the SCAAE in a self-supervised manner, using the autoencoder to guide the spatial-wise attention (SA) to focus on the activation regions. Experimental results show that the SA can generate multiple meaningful FBNs at each fMRI time point, which spatial similarity are close to the FBNs derived by known classical methods, such as ICA. To validate the generalization of the method, we evaluate the approach on HCP-rest, HCP-task and ADHD-200 dataset. The results demonstrate that spatial-wise attention mechanism can be used to discover time-varying FBNs, and the identified dynamic FBNs over time clearly show the process of time-varying spatial patterns fading in and out. Thus we provide a novel method to understand human brain better.

PMID:38407988 | DOI:10.1088/1741-2552/ad2cea

Psychol Sci. 2024 Feb 26:9567976241228503. doi: 10.1177/09567976241228503. Online ahead of print.

ABSTRACT

A major challenge in assessing psychological constructs such as impulsivity is the weak correlation between self-report and behavioral task measures that are supposed to assess the same construct. To address this issue, we developed a real-time driving task called the "highway task," in which participants often exhibit impulsive behaviors mirroring real-life impulsive traits captured by self-report questionnaires. Here, we show that a self-report measure of impulsivity is highly correlated with performance in the highway task but not with traditional behavioral task measures of impulsivity (47 adults aged 18-33 years). By integrating deep neural networks with an inverse reinforcement learning (IRL) algorithm, we inferred dynamic changes of subjective rewards during the highway task. The results indicated that impulsive participants attribute high subjective rewards to irrational or risky situations. Overall, our results suggest that using real-time tasks combined with IRL can help reconcile the discrepancy between self-report and behavioral task measures of psychological constructs.

PMID:38407962 | DOI:10.1177/09567976241228503

J Am Soc Mass Spectrom. 2024 Feb 26. doi: 10.1021/jasms.3c00357. Online ahead of print.

ABSTRACT

Matrix-assisted laser desorption ionization mass spectrometry imaging (MALDI-MSI) enables label-free imaging of biomolecules in biological tissues. However, many species remain undetected due to their poor ionization efficiencies. MALDI-2 (laser-induced post-ionization) is the most widely used post-ionization method for improving analyte ionization efficiencies. Mass spectra acquired using MALDI-2 constitute a combination of ions generated by both MALDI and MALDI-2 processes. Until now, no studies have focused on a detailed comparison between the ion images (as opposed to the generated m/z values) produced by MALDI and MALDI-2 for mass spectrometry imaging (MSI) experiments. Herein, we investigated the ion images produced by both MALDI and MALDI-2 on the same tissue section using correlation analysis (to explore similarities in ion images for ions common to both MALDI and MALDI-2) and a deep learning approach. For the latter, we used an analytical workflow based on the Xception convolutional neural network, which was originally trained for human-like natural image classification but which we adapted to elucidate similarities and differences in ion images obtained using the two MSI techniques. Correlation analysis demonstrated that common ions yielded similar spatial distributions with low-correlation species explained by either poor signal intensity in MALDI or the generation of additional unresolved signals using MALDI-2. Using the Xception-based method, we identified many regions in the t-SNE space of spatially similar ion images containing MALDI and MALDI-2-related signals. More notably, the method revealed distinct regions containing only MALDI-2 ion images with unique spatial distributions that were not observed using MALDI. These data explicitly demonstrate the ability of MALDI-2 to reveal molecular features and patterns as well as histological regions of interest that are not visible when using conventional MALDI.

PMID:38407924 | DOI:10.1021/jasms.3c00357

J Egypt Natl Canc Inst. 2024 Feb 26;36(1):6. doi: 10.1186/s43046-024-00210-w.

ABSTRACT

BACKGROUND: More and more genetic and metabolic abnormalities are now known to cause cancer, which is typically deadly. Any bodily part may become infected by cancerous cells, which can be fatal. Skin cancer is one of the most prevalent types of cancer, and its prevalence is rising across the globe. Squamous and basal cell carcinomas, as well as melanoma, which is clinically aggressive and causes the majority of deaths, are the primary subtypes of skin cancer. Screening for skin cancer is therefore essential.

METHODS: The best way to quickly and precisely detect skin cancer is by using deep learning techniques. In this research deep learning techniques like MobileNetv2 and Dense net will be used for detecting or identifying two main kinds of tumors malignant and benign. For this research HAM10000 dataset is considered. This dataset consists of 10,000 skin lesion images and the disease comprises nonmelanocytic and melanocytic tumors. These two techniques can be used for detecting the malignant and benign. All these methods are compared and then a result can be inferred from their performance.

RESULTS: After the model evaluation, the accuracy for the MobileNetV2 was 85% and customized CNN was 95%. A web application has been developed with the Python framework that provides a graphical user interface with the best-trained model. The graphical user interface allows the user to enter the patient details and upload the lesion image. The image will be classified with the appropriate trained model which can predict whether the uploaded image is cancerous or non-cancerous. This web application also displays the percentage of cancer affected.

CONCLUSION: As per the comparisons between the two techniques customized CNN gives higher accuracy for the detection of melanoma.

PMID:38407684 | DOI:10.1186/s43046-024-00210-w