A Reparametrized CNN Model to Distinguish Alzheimer's Disease Applying Multiple Morphological Metrics and Deep Semantic Features From Structural MRI.
Ontology highlight
ABSTRACT:
SUBMITTER: Chen Z
PROVIDER: S-EPMC9204294 | biostudies-literature | 2022
REPOSITORIES: biostudies-literature
Publications
A Reparametrized CNN Model to Distinguish Alzheimer's Disease Applying Multiple Morphological Metrics and Deep Semantic Features From Structural MRI.
Chen Zhenpeng Z Mo Xiao X Chen Rong R Feng Pujie P Li Haiyun H
Frontiers in aging neuroscience 20220526
It is of potential clinical value to improve the accuracy of Alzheimer's disease (AD) recognition using structural MRI. We proposed a reparametrized convolutional neural network (Re-CNN) to discriminate AD from NC by applying morphological metrics and deep semantic features. The deep semantic features were extracted through Re-CNN on structural MRI. Considering the high redundancy in deep semantic features, we constrained the similarity of the features and retained the most distinguishing featur ...[more]
Similar Datasets
Project description:BackgroundMyxoid tumors pose diagnostic challenges for radiologists and pathologists. All myxoid tumors can be differentiated from each other using fluorescent in-situ hybridization (FISH) or immunohistochemical markers, except for myxomas and myxofibrosarcomas. Myxomas and myxofibrosarcomas are rare tumors. Myxomas are benign and histologically bland, whereas myxofibrosarcomas are malignant and histologically heterogenous. Because of the histological heterogeneity, low grade myxofibrosarcomas may be mistaken for myxomas on core needle biopsies. We evaluated the performance of T1-weighted signal intensity (T1SI), tumor volume, and radiomic features extracted from magnetic resonance imaging (MRI) to differentiate myxomas from myxofibrosarcomas.MethodsThe MRIs of 56 patients (29 with myxomas, 27 with myxofibrosarcomas) were analyzed. We extracted 89 radiomic features. Random forests based classifiers using the T1SI, volume features, and radiomic features were used to differentiate myxomas from myxofibrosarcomas. The classifiers were validated using a leave-one-out cross-validation. The performances of the classifiers were then compared.ResultsMyxomas had lower normalized T1SI than myxofibrosaromas (p = 0.006) and the AUC using the T1SI was 0.713. However, the classification model using radiomic features had an AUC of 0.885 (accuracy = 0.839, sensitivity = 0.852, specificity = 0.828), and outperformed the classification models using T1SI (AUC = 0.713) and tumor volume (AUC = 0.838). The classification model using radiomic features was significantly better than the classifier using T1SI values (p = 0.039).ConclusionsMyxofibrosarcomas are on average higher in T1-weighted signal intensity than myxomas. Myxofibrosarcomas are larger and have shape differences compared to myxomas. Radiomic features performed best for differentiating myxomas from myxofibrosarcomas compared to T1-weighted signal intensity and tumor volume features.
| S-EPMC6694512 | biostudies-literature
Project description:Understanding spoken language is crucial for conversational agents, with intent detection and slot filling being the primary tasks in natural language understanding (NLU). Enhancing the NLU tasks can lead to an accurate and efficient virtual assistant thereby reducing the need for human intervention and expanding their applicability in other domains. Traditionally, these tasks have been addressed individually, but recent studies have highlighted their interconnection, suggesting better results when solved together. Recent advances in natural language processing have shown that pretrained word embeddings can enhance text representation and improve the generalization capabilities of models. However, the challenge of poor generalization in joint learning models for intent detection and slot filling remains due to limited annotated datasets. Additionally, traditional models face difficulties in capturing both the semantic and syntactic nuances of language, which are vital for accurate intent detection and slot filling. This study proposes a hybridized text representation method using a multichannel convolutional neural network with three embedding channels: non-contextual embeddings for semantic information, part-of-speech (POS) tag embeddings for syntactic features, and contextual embeddings for deeper contextual understanding. Specifically, we utilized word2vec for non-contextual embeddings, one-hot vectors for POS tags, and bidirectional encoder representations from transformers (BERT) for contextual embeddings. These embeddings are processed through a convolutional layer and a shared bidirectional long short-term memory (BiLSTM) network, followed by two softmax functions for intent detection and slot filling. Experiments on the air travel information system (ATIS) and SNIPS datasets demonstrated that our model significantly outperformed the baseline models, achieving an intent accuracy of 97.90% and slot filling F1-score of 98.86% on the ATIS dataset, and an intent accuracy of 98.88% and slot filling F1-score of 97.07% on the SNIPS dataset. These results highlight the effectiveness of our proposed approach in advancing dialogue systems, and paving the way for more accurate and efficient natural language understanding in real-world applications.
| S-EPMC11623216 | biostudies-literature
Project description:Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease whose diagnosis depends on the presence of combined lower motor neuron (LMN) and upper motor neuron (UMN) degeneration. LMN degeneration assessment is aided by electromyography, whereas no equivalent exists to assess UMN dysfunction. Magnetic resonance imaging (MRI) is primarily used to exclude conditions that mimic ALS. We have identified four different clinical/radiological phenotypes of ALS patients. We hypothesize that these ALS phenotypes arise from distinct pathologic processes that result in unique MRI signatures. To our knowledge, no machine learning (ML)-based data analyses have been performed to stratify different ALS phenotypes using MRI measures. During routine clinical evaluation, we obtained T1-, T2-, PD-weighted, diffusion tensor (DT) brain MRI of 15 neurological controls and 91 ALS patients (UMN-predominant ALS with corticospinal tract CST) hyperintensity, n = 21; UMN-predominant ALS without CST hyperintensity, n = 26; classic ALS, n = 23; and ALS patients with frontotemporal dementia, n = 21). From these images, we obtained 101 white matter (WM) attributes (including DT measures, graph theory measures from DT and fractal dimension (FD) measures using T1-weighted), 10 grey matter (GM) attributes (including FD based measures from T1-weighted), and 10 non-imaging attributes (2 demographic and 8 clinical measures of ALS). We employed classification and regression tree, Random Forest (RF) and also artificial neural network for the classifications. RF algorithm provided the best accuracy (70-94%) in classifying four different phenotypes of ALS patients. WM metrics played a dominant role in classifying different phenotypes when compared to GM or clinical measures. Although WM measures from both right and left hemispheres need to be considered to identify ALS phenotypes, they appear to be differentially affected by the degenerative process. Longitudinal studies can confirm and extend our findings.
| S-EPMC10177762 | biostudies-literature
Project description:PurposeTo assess amide proton transfer-weighted (APTW) imaging features in patients with malignant gliomas after chemoradiation and the diagnostic performance of APT imaging for distinguishing true progression from pseudoprogression.Materials and methodsAfter approval by the Institutional Review Board, 32 patients with clinically suspected tumor progression in the first 3 months after chemoradiation were enrolled and scanned at 3T. Longitudinal routine magnetic resonance imaging (MRI) changes and medical records were assessed to confirm true progression versus pseudoprogression. True progression was defined as lesions progressing on serial imaging over 6 months, and pseudoprogression was defined as lesions stabilizing or regressing without intervention. The APTWmean and APTWmax signals were obtained from three to five regions of interests for each patient and compared between the true progression and pseudoprogression groups. The diagnostic performance was assessed with receiver operating characteristic curve analysis.ResultsThe true progression was associated with APTW hyperintensity (APTWmean = 2.75% ± 0.42%), while pseudoprogression was associated with APTW isointensity to mild hyperintensity (APTWmean = 1.56% ± 0.42%). The APTW signal intensities were significantly higher in the true progression group (n = 20) than in the pseudoprogression group (P < 0.001; n = 12). The cutoff APTWmean and APTWmax intensity values to distinguish between true progression and pseudoprogression were 2.42% (with a sensitivity of 85.0% and a specificity of 100%) and 2.54% (with a sensitivity of 95.0% and a specificity of 91.7%), respectively.ConclusionThe APTW-MRI signal is a valuable imaging biomarker for distinguishing pseudoprogression from true progression in glioma patients. J. Magn. Reson. Imaging 2016;44:456-462.
| S-EPMC4946988 | biostudies-literature
Project description:BackgroundStereotactic radiotherapy is the preferred treatment for managing patients with fewer than five brain metastases (BMs). However, some lesions recur after irradiation. The purpose of this study was to identify patients who are at a higher risk of failure, which can help in adjusting treatments and preventing recurrence.MethodsIn this retrospective multicenter study, we analyzed the predictive significance of a set of interpretable morphological features derived from contrast-enhanced (CE) T1-weighted MR images as imaging biomarkers using Kaplan-Meier analysis. The feature sets studied included the total and necrotic volumes, the surface regularity and the CE rim width. Additionally, we evaluated other nonmorphological variables and performed multivariate Cox analysis.ResultsA total of 183 lesions in 128 patients were included (median age 61 [31-95], 64 men and 64 women) treated with stereotactic radiotherapy (57% single fraction, 43% fractionated radiotherapy). None of the studied variables measured at diagnosis were found to have prognostic value. However, the total and necrotic volumes and the CE rim width measured at the first follow-up after treatment and the change in volume due to irradiation can be used as imaging biomarkers for recurrence. The optimal classification was achieved by combining the changes in tumor volume before and after treatment with the presence or absence of necrosis (p < < 0.001).ConclusionThis study demonstrated the prognostic significance of interpretable morphological features extracted from routine clinical MR images following irradiation in brain metastases, offering valuable insights for personalized treatment strategies.
| S-EPMC11334491 | biostudies-literature
Project description:IntroductionArabic, a Semitic language, displays a particularly rich derivational morphological system with all verb stems consisting of a semantic root and a prosodic verb-pattern. Such regular and frequently encountered knowledge is expected to be acquired early. The present study presents a developmental perspective on the relative contribution of morphological and semantic complexity to the acquisition of verbs in Spoken Arabic.MethodVerbs in a spontaneous corpus from 133 typically developing children, 2; 6-6; 0-year-old, were coded for type and token frequency of verbal patterns and root type, and classified according to semantic complexity.ResultsResults support an item-based emergence driven by semantic complexity at the earliest stages of acquisition. A developmental expansion in the diversity of verbal patterns and morphological complexity was observed with age. Morphological complexity is only identified when the same root appears in different verb patterns.DiscussionThe late emergence of the same root in different verb patterns indicates that the perception of verb patterns as abstract linguistic entities beyond the actual verbs is attained later than the semantically-constrained verbs in earlier childhood. We conclude that whereas semantic complexity obstructs verbs from emerging in the lexicon in younger age groups, morphological complexity constitutes no such obstruction, since their perception as morphological devices is attained later in acquisition.
| S-EPMC10213558 | biostudies-literature
Project description:When viewing the actions of others, we not only see patterns of body movements, but we also "see" the intentions and social relations of people. Experienced forensic examiners - Closed Circuit Television (CCTV) operators - have been shown to convey superior performance in identifying and predicting hostile intentions from surveillance footage than novices. However, it remains largely unknown what visual content CCTV operators actively attend to, and whether CCTV operators develop different strategies for active information seeking from what novices do. Here, we conducted computational analysis for the gaze-centered stimuli captured by experienced CCTV operators and novices' eye movements when viewing the same surveillance footage. Low-level image features were extracted by a visual saliency model, whereas object-level semantic features were extracted by a deep convolutional neural network (DCNN), AlexNet, from gaze-centered regions. We found that the looking behavior of CCTV operators differs from novices by actively attending to visual contents with different patterns of saliency and semantic features. Expertise in selectively utilizing informative features at different levels of visual hierarchy may play an important role in facilitating the efficient detection of social relationships between agents and the prediction of harmful intentions.
| S-EPMC11358171 | biostudies-literature
Project description:Alzheimer's disease (AD) is a debilitating neurodegenerative disorder that requires accurate diagnosis for effective management and treatment. In this article, we propose an architecture for a convolutional neural network (CNN) that utilizes magnetic resonance imaging (MRI) data from the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset to categorize AD. The network employs two separate CNN models, each with distinct filter sizes and pooling layers, which are concatenated in a classification layer. The multi-class problem is addressed across three, four, and five categories. The proposed CNN architecture achieves exceptional accuracies of 99.43%, 99.57%, and 99.13%, respectively. These high accuracies demonstrate the efficacy of the network in capturing and discerning relevant features from MRI images, enabling precise classification of AD subtypes and stages. The network architecture leverages the hierarchical nature of convolutional layers, pooling layers, and fully connected layers to extract both local and global patterns from the data, facilitating accurate discrimination between different AD categories. Accurate classification of AD carries significant clinical implications, including early detection, personalized treatment planning, disease monitoring, and prognostic assessment. The reported accuracy underscores the potential of the proposed CNN architecture to assist medical professionals and researchers in making precise and informed judgments regarding AD patients.
| S-EPMC10859371 | biostudies-literature
Project description:In this paper, we present an evaluation of four encoder-decoder CNNs in the segmentation of the prostate gland in T2W magnetic resonance imaging (MRI) image. The four selected CNNs are FCN, SegNet, U-Net, and DeepLabV3+, which was originally proposed for the segmentation of road scene, biomedical, and natural images. Segmentation of prostate in T2W MRI images is an important step in the automatic diagnosis of prostate cancer to enable better lesion detection and staging of prostate cancer. Therefore, many research efforts have been conducted to improve the segmentation of the prostate gland in MRI images. The main challenges of prostate gland segmentation are blurry prostate boundary and variability in prostate anatomical structure. In this work, we investigated the performance of encoder-decoder CNNs for segmentation of prostate gland in T2W MRI. Image pre-processing techniques including image resizing, center-cropping and intensity normalization are applied to address the issues of inter-patient and inter-scanner variability as well as the issue of dominating background pixels over prostate pixels. In addition, to enrich the network with more data, to increase data variation, and to improve its accuracy, patch extraction and data augmentation are applied prior to training the networks. Furthermore, class weight balancing is used to avoid having biased networks since the number of background pixels is much higher than the prostate pixels. The class imbalance problem is solved by utilizing weighted cross-entropy loss function during the training of the CNN model. The performance of the CNNs is evaluated in terms of the Dice similarity coefficient (DSC) and our experimental results show that patch-wise DeepLabV3+ gives the best performance with DSC equal to 92 . 8 % . This value is the highest DSC score compared to the FCN, SegNet, and U-Net that also competed the recently published state-of-the-art method of prostate segmentation.
| S-EPMC7309110 | biostudies-literature
Project description:This prospective study explored whether an approach combining structural [cortical thickness and white matter (WM) microstructure] and resting state functional MRI can aid differentiation between 62 early onset Alzheimer's disease (EOAD) and 27 behavioural variant of frontotemporal dementia (bvFTD) patients. Random forest and receiver operator characteristic curve analyses assessed the ability of MRI in classifying the two clinical syndromes. All patients showed a distributed pattern of brain alterations relative to controls. Compared to bvFTD, EOAD patients showed bilateral inferior parietal cortical thinning and decreased default mode network functional connectivity. Compared to EOAD, bvFTD patients showed bilateral orbitofrontal and temporal cortical thinning, and WM damage of the corpus callosum, bilateral uncinate fasciculus, and left superior longitudinal fasciculus. Random forest analysis revealed that left inferior parietal cortical thickness (accuracy 0.78, specificity 0.76, sensitivity 0.83) and WM integrity of the right uncinate fasciculus (accuracy 0.81, specificity 0.96, sensitivity 0.43) were the best predictors of clinical diagnosis. The combination of cortical thickness and DT MRI measures was able to distinguish patients with EOAD and bvFTD with accuracy 0.82, specificity 0.76, and sensitivity 0.96. The diagnostic ability of MRI models was confirmed in a subsample of patients with biomarker-based clinical diagnosis. Multiparametric MRI is useful to identify brain alterations which are specific to EOAD and bvFTD. A severe cortical involvement is suggestive of EOAD, while a prominent WM damage is indicative of bvFTD.
| S-EPMC5458769 | biostudies-literature