PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “feature fusion”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources
PubMed2004

Intact feature fusion in schizophrenic patients.

How the various features of an object are bound to a unified percept is one of the most fundamental problems the human brain has to solve. Whereas healthy observers usually do not reveal binding errors, it has been proposed that schizophrenic patients suffer from binding deficits. To elucidate such deficits, we investigated one of the most basic binding or integration paradigms: feature fusion. In feature fusion, two stimuli are presented in rapid succession. Using a vernier paradigm, we could, recently, show that the second stimulus determines feature fusion more strongly than the first one (Herzog et al. 2003). However, the first presented stimulus determines feature fusion when a grating follows the two stimuli. Reversal of dominance has occurred. In this study, we show that schizophrenic patients reveal qualitatively the same integration characteristics in feature fusion as healthy controls do. Hence, although some aspects of visual processing are strongly disturbed in schizophrenia as revealed by masking studies, feature fusion appears to be, at least qualitatively, spared. Our fusion paradigm allows one to investigate intact and deficient visual processing in schizophrenic patients with great detail and to elucidate the nature of deficits of visual processing in schizophrenia.

Adult↗
PubMed2006

Long lasting effects of unmasking in a feature fusion paradigm.

In spite of more than 100 years of research, the mechanisms underlying visual masking are still unknown. In recent publications, we introduced an unmasking paradigm involving the fusion of features that revealed interesting spatial characteristics. Here, we investigate the temporal aspects of this paradigm showing very long lasting effects that impose serious restrictions on models of masking. We used a simple feed-forward neural network model to explain these results.

Humans↗
PubMed2006

Prediction of protein homo-oligomer types by pseudo amino acid composition: Approached with an improved feature extraction and Naive Bayes Feature Fusion.

The interaction of non-covalently bound monomeric protein subunits forms oligomers. The oligomeric proteins are superior to the monomers within the scope of functional evolution of biomacromolecules. Such complexes are involved in various biological processes, and play an important role. It is highly desirable to predict oligomer types automatically from their sequence. Here, based on the concept of pseudo amino acid composition, an improved feature extraction method of weighted auto-correlation function of amino acid residue index and Naive Bayes multi-feature fusion algorithm is proposed and applied to predict protein homo-oligomer types. We used the support vector machine (SVM) as base classifiers, in order to obtain better results. For example, the total accuracies of A, B, C, D and E sets based on this improved feature extraction method are 77.63, 77.16, 76.46, 76.70 and 75.06% respectively in the jackknife test, which are 6.39, 5.92, 5.22, 5.46 and 3.82% higher than that of G set based on conventional amino acid composition method with the same SVM. Comparing with Chou's feature extraction method of incorporating quasi-sequence-order effect, our method can increase the total accuracy at a level of 3.51 to 1.01%. The total accuracy improves from 79.66 to 80.83% by using the Naive Bayes Feature Fusion algorithm. These results show: 1) The improved feature extraction method is effective and feasible, and the feature vectors based on this method may contain more protein quaternary structure information and appear to capture essential information about the composition and hydrophobicity of residues in the surface patches that buried in the interfaces of associated subunits; 2) Naive Bayes Feature Fusion algorithm and SVM can be referred as a powerful computational tool for predicting protein homo-oligomer types.

Algorithms↗
PubMed2026

SurvGRN: a multi-feature fusion framework for bladder cancer survival prediction.

Bladder cancer survival outcomes exhibit significant heterogeneity, influenced by multifaceted factors. While digital pathology-based survival models leveraging artificial intelligence show promise, they often overlook complementary data sources. Conversely, imaging lacks cellular detail, and genomics/proteomics entail complexity and cost. To integrate multidimensional data for enhanced survival prediction, we propose SurvGRN, a multi-feature fusion framework. SurvGRN synergistically combines clinical variables, transcriptomics, and digital pathology slides using a gated residual network architecture. Pathological features are extracted via multiple instance learning, while clinical and transcriptomic data are processed as static inputs. These features are dynamically fused using a long short-term memory (LSTM) network for comprehensive survival risk assessment. Evaluated on 400 bladder cancer patients, SurvGRN significantly outperformed existing methods: improving the C-index by 12.6% over DeepMISL; 20.6% and 7.1% over graph-based models (DeepGraphConv and Patch-GCN); and 5.4% and 4.0% over attention-based approaches (Surformer and HVTSurv). Ablation studies confirmed the contributions of pathology features (extracted via ResNet-50 pre-trained on bladder tissue), clinical/transcriptomic data, and the LSTM fusion. SurvGRN also enabled significant stratification of patients into distinct risk cohorts. This work demonstrates that holistic integration of multi-source data through tailored fusion architectures substantially improves bladder cancer survival prediction.

bladder cancer↗
PubMed2005

Intact and deficient feature fusion in schizophrenia.

In patients with schizophrenia, early as well as late stages of information processing can be deficient. Therefore, it is important to determine the earliest occurrences of aberrant processing since deficits on these stages may cause abnormal processing on later, e. g. cognitive, levels. In order to investigate this issue in the visual domain, we studied one of the most basic feature integration mechanisms, namely feature fusion. Our results indicate that in schizophrenic patients this integration mechanism is qualitatively intact but reveals quantitative impairments that may influence later processing stages.

Adult↗
PubMed2005

Design-based texture feature fusion using Gabor filters and co-occurrence probabilities.

A design-based method to fuse Gabor filter and grey level co-occurrence probability (GLCP) features for improved texture recognition is presented. The fused feature set utilizes both the Gabor filter's capability of accurately capturing lower and mid-frequency texture information and the GLCP's capability in texture information relevant to higher frequency components. Evaluation methods include comparing feature space separability and comparing image segmentation classification rates. The fused feature sets are demonstrated to produce higher feature space separations, as well as higher segmentation accuracies relative to the individual feature sets. Fused feature sets also outperform individual feature sets for noisy images, across different noise magnitudes. The curse of dimensionality is demonstrated not to affect segmentation using the proposed the 48-dimensional fused feature set. Gabor magnitude responses produce higher segmentation accuracies than linearly normalized Gabor magnitude responses. Feature reduction using principal component analysis is acceptable for maintaining the segmentation performance, but feature reduction using the feature contrast method dramatically reduced the segmentation accuracy. Overall, the designed fused feature set is advocated as a means for improving texture segmentation performance.

Algorithms↗
PubMed2003

Fusion of competing features is not serial.

How features of an object are bound into a unique percept is one of the puzzling problems in the cognitive and neuro-sciences. In order to investigate the spatio-temporal mechanisms of feature binding, we serially present two verniers with opposite offset directions for very short durations. Only one vernier is perceived with its offset dominated by the vernier presented second. This dominance reverses if the two verniers are followed by masking gratings, i.e. the first presented vernier dominates performance. Therefore, feature fusion can neither be explained completely by spatially local mechanisms nor by the temporal order of appearance of elements.

Adult↗
PubMed2026

A multi-scale fusion model based on multi-phase contrast-enhanced CT for predicting pancreatic cancer resectability.

Purpose.Develop a multi-scale fusion model (MSFM) based on multi-phase contrast-enhanced computed tomography (CECT) to predict pancreatic cancer (PC) resectability, thereby assisting expert decision-making.Methods.This retrospective study enrolled 280 patients with PC from four institutions, which were randomly divided into a training cohort (202 patients) and an independent test cohort (78 patients). Three-phase CECT images (arterial, venous, and delayed phases) were used for modeling. The MSFM comprises two sub-networks: (1) a multi-phase fusion network for extracting cross-phase shared fusion features, (2) a phase-specific branch network for capturing phase-specific features; and a post-fusion strategy to generate the final predictive score by integrating the shared fusion features and three groups of phase-specific features. Additionally, a human-machine fusion deep learning model (HMfDL) was constructed by fusing the predictive score of the MSFM with expert assessments.Results.In the independent test, the MSFM achieved an AUC (area under the receiver operating characteristic curve) of 0.8385 (95% CI: 0.7521-0.9249), accuracy of 84.62%, sensitivity of 72.00%, and specificity of 90.57%. This performance outperformed single-phase models (AUC range: 0.7638-0.7781), two-phase models (AUC range: 0.7826-0.7864), and ten states-of-the-art classifiers (AUC range: 0.7404-0.7796). The HMfDL further improved the performance, reaching an AUC of 0.8626 (95% CI: 0.7853-0.9400), accuracy of 91.03%, sensitivity of 80.00%, and specificity of 96.23%. Notably, the HMfDL corrected 58.82% of misdiagnosis made by experts.Conclusions. The MSFM effectively fuses multi-phase CECT to enable highly accurate predictions of PC resectability, and provides valuable support for expert decision-making through HMfDL.

Humans↗
PubMed1999

Mixed-lineage leukemia with t(10;11)(p13;q21): an analysis of AF10-CALM and CALM-AF10 fusion mRNAs and clinical features.

A fusion transcript of AF10 and CALM was isolated recently from the U937 cell line with t(10;11)(p13;q21). We performed reverse transcription-polymerase chain reaction and sequencing analysis on the t(10;11) leukemia samples obtained from four patients and one cell line, and we identified reciprocal fusion transcripts of AF10 and CALM in all the samples. The fusion transcripts in the five samples showed four different breakpoints in AF10 and three different breakpoints in CALM. In addition, the fusion transcripts in one sample showed a nucleotide sequence deletion in AF10, and those in two samples showed a nucleotide sequence deletion in CALM; the deletions were thought to be caused by alternative splicing. The variety of breakpoints and splice sites in the two genes resulted in five different-sized AF10-CALM mRNAs and in four different-sized CALM-AF10 mRNAs. Clinical features of 11 patients, including 6 of our own and 5 reported by others, in whom the fusion of AF10 and CALM was identified, are characterized by young age of the patients, mixed-lineage immunophenotype with coexpression of T-cell and myeloid antigens, frequent occurrence of a mediastinal mass, and poor clinical outcome.

Adolescent↗
PubMed2005

Lipomatous hypertrophy of the interatrial septum: prevalence and features on fusion 18F fluorodeoxyglucose positron emission tomography/CT.

OBJECTIVE: To determine the prevalence of lipomatous hypertrophy of the interatrial septum (LHIS) on CT and its metabolic pattern on 18F fluorodeoxyglucose (FDG)-positron emission tomography (PET). METHOD AND MATERIALS: Eight hundred two CT PET scans were reviewed. Patients were included if the interatrial septum was > or = 1 cm and excluded if there was evidence of malignancy in the adjacent lung, hilum, or mediastinum. CT scans were fused with PET scans, and the mean standardized uptake value (SUV) was calculated over the LHIS, chest wall (CW) fat, and mediastinal blood pool. CT scans were reviewed for presence of excessive fat in the mediastinum, pericardial, peridiaphragmatic, peritoneal, and retroperitoneal regions and for the presence of emphysema. Medical records were reviewed for body mass index (BMI) and history of arrhythmia. RESULTS: Twenty-three of 802 patients (2.8%) had LHIS on CT (9 women and 14 men); average age was 75.6 years (range, 58 to 95 years). Average BMI of 17 patients (+/- SD) was 31 +/- 4.9 (range, 22.1 to 39.9). Mean CT values were as follows: thickening of LHIS, 1.47 +/- 0.35 cm (range, 1.07 to 2.25 cm); LHIS, - 79.6 + 24.5 Hounsfield unit (HU) [range, - 11 to - 121 HU]. LHIS was dumbbell shaped in 18 patients. Mean SUVs were as follows: LHIS, 1.84 +/- 0.10 (range, 0.48 to 3.48); CW fat, 0.36 + 0.37 (range, 0.04 to 1.98); blood pool, 1.74 + 0.51 (range, 0.25 to 2.71). The SUV of LHIS was greater than the SUV of CW wall fat in all patients (p < 0.0001). There was significant correlation between SUV and thickness of the LHIS on CT (p < 0.0001, r = 0.883). Those with dumbbell-shaped LHIS (p < 0.003) and presence of emphysema (p < 0.0377) had greater LHIS mean SUV. CONCLUSION: The SUV of LHIS was greater than the SUV of CW fat in all patients. LHIS with greater thickness or dumbbell shape had greater FDG uptake. These findings on CT and PET are important to recognize in order to avoid false-positive FDG-PET interpretations.

Aged↗
PubMed2002

Element mixing distribution and structure feature of fusion zone in laser welding between different alloys and pure titanium.

OBJECTIVE: To study micro morphology and element-mixing distribution of different alloys welded in laser and analyze the feasibility of laser welding different alloys. METHODS: Alloys and titanium were matched into 4 groups: Au-Pt with Ni-Cr; Au-Pt with pure Ti; pure Ti with Ni-Cr; Ni-Cr with Co-Cr. They were welded in laser. Changes in metallography after hybridization of crystalline grain, ranges of heat-affected zone and pores were observed through SEM with ultra-thin windowed X-ray energy atlas. Meanwhile 10 testing points were chosen with area of 300 micro m x 900 micro m along the welding surface from the side A alloy to the side B alloy, than the element mixing distribution and tendency were analyzed with X-ray energy atlas. RESULTS: 1. Hybridization of different alloys: (l) in the group of Au-Pt with Ti, there was titanium element mixing into Au-Pt tissue gradually and evenly on the Au-Pt side of the interface without clear boundary and increasing in size of crystalline grain. However, there was titanium crystalline grain increasing in size, irregular morphology and small sacks on the titanium side with clear boundary. (2) in the group of Ni-Cr with Ti, there was mixing regularly, slow transition and interlocks between crystalline grains on the Ni-Cr side of the in terface. Poor transition, clear boundary and small cracks were observed on titanium side. (3) in the group of Co-Cr with Ni-Cr, there was good transition, obscure boundary on both sides resulting from network, cylinder and branch structure growing. 2. Element-mixing distribution of different alloys. In fusion zone, the metal elements in matched groups mixed well and hybridized into new alloys except titanium blocks. The location of wave peak depended on the composition of alloys. Most of elements were from the alloy far from the fusion zone. CONCLUSION: The hybridization between pure titanium and any other alloys is not good The effect of laser welding different alloys is ideal except with pure titanium.

Alloys↗
PubMedDate not supplied

Feature and classifier fusion for 12-lead ECG classification.

Two methodologies, feature and classifier fusion, for the problem of computerized 12-lead electrocardiogram classification, are investigated. Firstly, the entire classification problem is subdivided into a number of smaller bi-dimensional ones. By employing bi-group Neural Network classifiers, independent feature vectors for each diagnostic class are examined individually and the output from each classifier are fused together to produce one single result. Secondly, two classifiers, namely the aforementioned and a decision tree, are fused together through a novel approach of a Specificity Matrix. This methodology addresses the problem of unresolved conflict during fusion of classifiers and aims to exploit the merits of each classifier and suppress their weaknesses. 290 validated 12-lead electrocardiogram recordings, comprising six diagnostic classes, were used to train, validate and test both methodologies. The framework of bi-group classifiers enhanced the overall performance by 12.0% in comparison with conventional approaches. In the second instance, the fusion of the two classifiers produced a performance level of 81.3%; superior to either classifier in isolation. This approach offers a viable solution to the unresolved problem of conflict between classifiers during fusion and can be extended readily to accommodate any number of diagnostic classes and classifiers.

Decision Trees↗
PubMed1996

Detection of the EWS/WT1 gene fusion by reverse transcriptase-polymerase chain reaction in the diagnosis of intra-abdominal desmoplastic small round cell tumor.

We report two cases of intra-abdominal desmoplastic small round cell tumor with characteristic clinical, histological, immunohistochemical, and ultrastructural features. Fusion of the EWS gene on chromosome 22 and the WT1 gene on chromosome 11, resulting from the chromosomal translocation t(11;22)(p13;q12), was detected by reverse transcriptase polymerase chain reaction (RT-PCR) in both cases. This translocation has been previously reported in this type of tumor using either cytogenetic or molecular biological techniques. Tumor tissue from both cases revealed no chimeric fusion transcripts characteristic of the Ewing sarcoma family of peripheral primitive neuroectodermal tumors or of alveolar rhabdomyosarcoma, two tumors in the differential diagnosis of intra-abdominal desmoplastic small round cell tumor. This report demonstrates the utility of molecular studies as an adjunct in the diagnosis of this rare and aggressive tumor.

Abdominal Neoplasms↗
PubMed2003

ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis.

Breast cancer diagnosis through ultrasound tissue characterization was studied using receiver operating characteristic (ROC) analysis of combinations of acoustic features, patient age, and radiological findings. A feature fusion method was devised that operates even if only partial diagnostic data are available. The ROC methodology uses ordinal dominance theory and bootstrap resampling to evaluate A(z) and confidence intervals in simple as well as paired data analyses. The combined diagnostic feature had an A(z) of 0.96 with a confidence interval of at a significance level of 0.05. The combined features show statistically significant improvement over prebiopsy radiological findings. These results indicate that ultrasound tissue characterization, in combination with patient record and clinical findings, may greatly reduce the need to perform biopsies of benign breast lesions.

Age Factors↗
PubMed1982

Rods of actin filaments in type I hair cells of the Shaker-2 mouse.

The shaker-2 mouse with inherited inner ear disease suffers from deafness and a shaking-waltzing behavior. The hair cell type I in cristae ampullares and maculae utriculi show a specific pathology, featuring fusion of the stereocilia and presence of a rod-shaped inclusion body. The inclusion body is composed of filaments that could be identified as the protein actin by the method of decoration with subfragment S-1 of myosin. The functional polarity was determined, and S-1 fragments were found to point apically, that is, from the nucleus up toward the cuticular plate. These observations are identical to those earlier described in the waltzing guinea pig. It is concluded that the identical pathology at a cellular level in two different species may indicate a pathologic disorder in a process fundamental to the normal development of this type of hair cell.

Actins↗
PubMed2005

A multi-feature and multi-channel univariate selection process for seizure prediction.

OBJECTIVE: To develop a prospective method for optimizing seizure prediction, given an array of implanted electrodes and a set of candidate quantitative features computed at each contact location. METHODS: The method employs a genetic-based selection process, and then tunes a probabilistic neural network classifier to predict seizures within a 10 min prediction horizon. Initial seizure and interictal data were used for training, and the remaining IEEG data were used for testing. The method continues to train and learn over time. RESULTS: Validation of these results over two workshop patients demonstrated a sensitivity of 100%, and 1.1 false positives per hour for Patient E, using a 2.4s block predictor, and a failure of the method on Patient B. CONCLUSIONS: This study demonstrates a prospective, exploratory implementation of a seizure prediction method designed to adapt to individual patients with a wide variety of pre-ictal patterns, implanted electrodes and seizure types. Its current performance is limited likely by the small number of input channels and quantitative features employed in this study, and segmentation of the data set into training and testing sets rather than using all continuous data available. SIGNIFICANCE: This technique theoretically has the potential to address the challenge presented by the heterogeneity of EEG patterns seen in medication-resistant epilepsy. A more comprehensive implementation utilizing all electrode sites, a broader feature library, and automated multi-feature fusion will be required to fully judge the method's potential for predicting seizures.

Algorithms↗
PubMed2026

Conditional Diffusion Model-Based Method for Annotation of Antibiotic Resistance Gene Properties.

The crisis of bacterial antibiotic resistance, which has led to a decline in the effectiveness of antibiotics originally used to combat bacterial infections, has emerged as an urgent challenge for public health. Antibiotic resistance genes (ARGs) are one of the key reasons for bacteria to develop resistance to antibiotics. Therefore, accurately identifying and annotating the critical properties of ARGs is of great importance for addressing the antibiotic resistance emergency. Although existing deep learning models demonstrate remarkable effectiveness in extracting local features from sequence data, they still face limitations in the capacity to further gain the enriched latent representations within the data. To address the critical challenge of extracting higher-quality representations from ARGs sequence data, we propose a novel ARGs properties annotation method based on the conditional diffusion model which is used to learn latent representations through domain-specific knowledge injection. Specifically, during the conditional information integration phase, we systematically incorporate ARGs' domain knowledge to guide the diffusion process in generating high-quality latent representations. To overcome information redundancy caused by direct concatenation of conditional information and intermediate features, we design a cross-attention mechanism that enables feature fusion between heterogeneous information sources, thereby enhancing further the quality of obtained representations. Experimental results on widely used data sets demonstrate the framework's effectiveness in achieving superior prediction performance compared to existing methods.

Anti-Bacterial Agents↗