45 Hits in 3.1 sec

Emphysema classification based on embedded probabilistic PCA

Teresa Zulueta-Coarasa, Sila Kurugol, James C. Ross, George G. Washko, Raul San Jose Estepar
2013 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)  
In this article we investigate the suitability of a manifold learning technique to classify different types of emphysema based on embedded Probabilistic PCA (PPCA).  ...  A quantitative comparison with a texture-based approach based on Local Binary Patterns and with an approach based on local intensity distributions shows that our method is competitive.  ...  In this article we propose a novel approach to classify different patterns of emphysema based on a probabilistic interpretation of the manifold in which each pattern is embedded.  ... 
doi:10.1109/embc.2013.6610414 pmid:24110601 pmcid:PMC3918501 dblp:conf/embc/Zulueta-Coarasa13 fatcat:k2vsnw7uq5dpnf5ty3ch7vnclq

Extended Gabor approach applied to classification of emphysematous patterns in computed tomography

Rodrigo Nava, Boris Escalante-Ramírez, Gabriel Cristóbal, Raúl San José Estépar
2014 Medical and Biological Engineering and Computing  
In this paper, we propose a new emphysema classification framework based on complex Gabor filters and local binary patterns.  ...  The results have shown the effectiveness of our approach for quantifying lesions due to emphysema and that the combination of descriptors yields to a better classification performance.  ...  Also in [29] , the dataset was used with a technique based on an embedded probabilistic PCA that resulted in a precision of 69 %.  ... 
doi:10.1007/s11517-014-1139-9 pmid:24496558 pmcid:PMC4254807 fatcat:zcpwrrmxpndorktquidak7g2pa

Inferring Disease Status by Non-parametric Probabilistic Embedding [chapter]

Nematollah Kayhan Batmanghelich, Ardavan Saeedi, Raul San Jose Estepar, Michael Cho, William M. Wells
2017 Lecture Notes in Computer Science  
We validate our method on a large-scale lung CT scan study and demonstrate the state-of-the-art prediction on an important physiologic measure of airflow (the forced expiratory volume in one second, FEV1  ...  A common method to compute similarities is based on image registration. Gerber et al.  ...  Even 2D embedding captures the structure of the disease; subjects on the bottom right are healthier than subjects on top left of the embedding space.  ... 
doi:10.1007/978-3-319-61188-4_5 fatcat:gjy5pqnrqzanjcajwko77ikspa

Feature Extraction and Classification Methods for Lung Sounds

It is a major challenge to analyze and differentiate the type of pulmonary disorder based on lung sounds.  ...  All the discussed methods automatically recognise the different types of lung sounds and pulmonary disorder based on features extracted from recorded lung sounds.  ...  Methods based on spectral analysis Literature [25] classified LS captured from emphysema, asthma, fibrosis alveolitis and healthy subjects by using Self Organizing Maps (SOM) based on FFT spectra.  ... 
doi:10.35940/ijitee.a8100.1110120 fatcat:lo6527eji5gmzgmjxvlm5qwf6a

Proceedings 16th International Conference on Pattern Recognition

2002 Object recognition supported by user interaction for service robots  
Ding A Robust Algorithm for Probabilistic Human Recognition from Video 226 Multiresolution Block Sampling-Based Method for Texture Synthesis 239 Y. Yu, J. Luo, and C.  ...  Bloch On the Classification of Temporal Lobe Epilepsy Using MR Image Appearance 520 S. Duchesne. N. Bernasconi, A. Bernasconi, and D.  ... 
doi:10.1109/icpr.2002.1044572 fatcat:3yvquccps5aqdmizmzyhbkybwi

Diagnosis of Chronic Obstructive Pulmonary Disease Based on Transfer Learning

Qian Wang, Hong Wang, Lutong Wang, Fengping Yu
2020 IEEE Access  
Given the limited data samples available in current COPD studies, we propose a method for diagnosing COPD based on transfer learning called balanced probability distribution (BPD) algorithm; this algorithm  ...  integrates instance-and feature-based transfers to improve the prediction accuracy of the model.  ...  In fact, there are other methods, such as principal component analysis (PCA), t-distributed neighborhood embedding (t-SNE), and singular value decomposition (SVD), which can achieve the goal of feature  ... 
doi:10.1109/access.2020.2979218 fatcat:3carn5ebnbcxzhchmdbwu4gyu4

Front Matter: Volume 6915

Proceedings of SPIE, Maryellen L. Giger, Nico Karssemeijer
2008 Medical Imaging 2008: Computer-Aided Diagnosis  
The last two digits indicate publication order within the volume using a Base 36 numbering system employing both numerals and letters.  ...  The CID number appears on each page of the manuscript. The complete citation is used on the first page, and an abbreviated version on subsequent pages.  ...  Maidment, Univ. of Pennsylvania (USA) SESSION 3 COLON CAD 6915 0B Automated matching of supine and prone colonic polyps based on PCA and SVMs [6915-01] S. Wang, R. L. Van Uitert, R. M.  ... 
doi:10.1117/12.797938 dblp:conf/micad/X08 fatcat:ofuszodznnbhdjgavmgo26tugi

A Low-Dose CT-Based Radiomic Model to Improve Characterization and Screening Recall Intervals of Indeterminate Prevalent Pulmonary Nodules

Leonardo Rundo, Roberta Eufrasia Ledda, Christian di Noia, Evis Sala, Giancarlo Mauri, Gianluca Milanese, Nicola Sverzellati, Giovanni Apolone, Maria Carla Gilardi, Maria Cristina Messa, Isabella Castiglioni, Ugo Pastorino
2021 Diagnostics  
In this work, we investigated the potential impact of radiomics on indeterminate prevalent pulmonary nodule (PN) characterization and risk stratification in subjects undergoing LDCT-based LC screening.  ...  ), and in particular for sub-solid lesions, as non-solid versus part-solid (second-level classification).  ...  Compared to PCA, t-SNE is not a linear algebra technique, but it is based on a probabilistic framework.  ... 
doi:10.3390/diagnostics11091610 pmid:34573951 fatcat:l6mbxbw3xreffpy4223e24oepa

Intelligent Pneumonia Identification from Chest X-Rays: A Systematic Literature Review

Wasif Khan, Nazar Zaki, Luqman Ali
2021 IEEE Access  
A better classification performance can be obtained based on the MSFE when compared with that obtained based on the MSE [41] ; however, the improvement is only minor [35] [40] .  ...  ), and kernel PCA (KPCA).  ... 
doi:10.1109/access.2021.3069937 fatcat:yzvzg2ywxrae3ba3egot63oryi

Method development of glycoprotein biomarkers for cancers

Shuang Yang, Perry G Wang
2017 Bioanalysis  
Conclusion: Combining multiplatform metabolic phenotyping with knowledge-based mapping gives mechanistic insights into disease development, which can be applied to next-generation tobacco and nicotine  ...  For instance one of the NMR profiles gives the comprehensive information on lipoprotein subfractions while RP UPLC-MS is optimum for the individual lipid species that are embedded in many of the different  ...  Top perturbed pathways based on impact and -log 2 (p-value) are labeled on the graph. The -log 2 (p-value) is the enrichment score.  ... 
doi:10.4155/bio-2017-0077 pmid:28644045 fatcat:qiae7o5ukzgibl6vyrhswsqeqi

Multiplatform serum metabolic phenotyping combined with pathway mapping to identify biochemical differences in smokers

Manuja R Kaluarachchi, Claire L Boulangé, Isabel Garcia-Perez, John C Lindon, Emmanuel F Minet
2016 Bioanalysis  
Conclusion: Combining multiplatform metabolic phenotyping with knowledge-based mapping gives mechanistic insights into disease development, which can be applied to next-generation tobacco and nicotine  ...  For instance one of the NMR profiles gives the comprehensive information on lipoprotein subfractions while RP UPLC-MS is optimum for the individual lipid species that are embedded in many of the different  ...  Top perturbed pathways based on impact and -log 2 (p-value) are labeled on the graph. The -log 2 (p-value) is the enrichment score.  ... 
doi:10.4155/bio-2016-0108 pmid:27635669 fatcat:fbjfuavcdzeslbxlas24j3nujm

A survey on computational intelligence approaches for predictive modeling in prostate cancer

Georgina Cosma, David Brown, Matthew Archer, Masood Khan, A. Graham Pockley
2017 Expert systems with applications  
These advanced approaches are based on mathematical models that have been especially developed for dealing with the uncertainty and imprecision which is typically found in clinical and biological datasets  ...  approaches, and hybrids of these, as well as Bayesian based approaches, and Markov models.  ...  Naive Bayesian Classifier Naive Bayesian classification is based on Bayesian theorem of posterior probability.  ... 
doi:10.1016/j.eswa.2016.11.006 fatcat:ii6gbq6qcbai5kxvcy4l7kkg54

Involvement of Machine Learning Tools in Healthcare Decision Making

Senerath Mudalige Don Alexis Chinthaka Jayatilake, Gamage Upeksha Ganegoda, Massimo Martorelli
2021 Journal of Healthcare Engineering  
Reaching to its peak now the concern is being diverted towards treating patients not only based on the type of disease but also their genetics, which is known as precision medicine.  ...  In addition, patient care, resource allocation, and research on treatments for various diseases are also being performed using machine learning-based computational decision making.  ...  can be obtained based on PCA and genetic algorithm (GA).  ... 
doi:10.1155/2021/6679512 pmid:33575021 pmcid:PMC7857908 fatcat:tkjpjybmife4vhugy4gq3f2tiy

Towards the Interpretability of Machine Learning Predictions for Medical Applications Targeting Personalised Therapies: A Cancer Case Survey

Antonio Jesús Banegas-Luna, Jorge Peña-García, Adrian Iftene, Fiorella Guadagni, Patrizia Ferroni, Noemi Scarpato, Fabio Massimo Zanzotto, Andrés Bueno-Crespo, Horacio Pérez-Sánchez
2021 International Journal of Molecular Sciences  
In this sense, learning tools are becoming a commodity but, to be able to assist doctors on a daily basis, it is essential to fully understand how models can be interpreted.  ...  Artificial Intelligence is providing astonishing results, with medicine being one of its favourite playgrounds. Machine Learning and, in particular, Deep Neural Networks are behind this revolution.  ...  To identify them, a three-stage protocol is implemented: (i) the SNPs are selected using a gradient boosting classification technique: XGBoost; (ii) based on the XGBoost output data, an adaptive iterative  ... 
doi:10.3390/ijms22094394 pmid:33922356 fatcat:z3mxbx7fajge7pkyrp2odlauz4

Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models [article]

Jialin Peng, Ye Wang
2021 arXiv   pre-print
Despite the remarkable performance of deep learning methods on various tasks, most cutting-edge models rely heavily on large-scale annotated training examples, which are often unavailable for clinical  ...  [117] introduced a probabilistic image estimated by computing the pixel-wise empirical proportion of each class based on aligned ground truth label fields of the training images.  ...  While principal component analysis (PCA) based statistical shape model (SSM) [30] was widely adopted by traditional segmentation methods, it is not straightforward to combine SSM with deep networks.  ... 
arXiv:2103.00429v1 fatcat:p44a5e34sre4nasea5kjvva55e
« Previous Showing results 1 — 15 out of 45 results