Marios S. Pattichis
University of New Mexico
Pattern recognitionComputer visionMathematicsComputer scienceImage texture
What is this?
Publications 280
Medical image analysis methods require the use of effective representations for differentiating between lesions, diseased regions, and normal structure. Amplitude Modulation - Frequency Modulation (AM-FM) models provide effective representations through physically meaningful descriptors of complex non-stationary structures that can differentiate between the different lesions and normal structure. Based on AM-FM models, medical images are decomposed into AM-FM components where the instantaneous f...
#2Marios S. PattichisH-Index: 26
Last. Constantinos S. PattichisH-Index: 35
view all 5 authors...
Video compression is the core technology in mobile (mHealth) and electronic (eHealth) health video streaming applications. With global video traffic projected to reach 82% of all Internet traffic by 2022, there is a strong need to develop efficient compression algorithms to accommodate expected future growth. For the first time in decades, and especially since ISO/IEC MPEG and ITU-T VCEG expert groups strategically joined forces to develop the highly successful H.264/AVC standard, we have two di...
#1Venkatesh JatlaH-Index: 1
#2Marios S. PattichisH-Index: 26
Last. Charles Nickolos Arge (GSFC: Goddard Space Flight Center)H-Index: 5
view all 3 authors...
The paper presents the results from a multi-year effort to develop and validate image processing methods for selecting the best physical models based on solar image observations. The approach consists of selecting the physical models based on their agreement with coronal holes extracted from the images. Ultimately, the goal is to use physical models to predict geomagnetic storms. We decompose the problem into three subproblems: (i) coronal hole segmentation based on physical constraints, (ii) ma...
#1Rogers F. SilvaH-Index: 9
#2Sergey M. PlisH-Index: 2
Last. Vince D. CalhounH-Index: 93
view all 5 authors...
In the last two decades, unsupervised latent variable models---blind source separation (BSS) especially---have enjoyed a strong reputation for the interpretable features they produce. Seldom do these models combine the rich diversity of information available in multiple datasets. Multidatasets, on the other hand, yield joint solutions otherwise unavailable in isolation, with a potential for pivotal insights into complex systems. To take advantage of the complex multidimensional subspace structur...
1 Citations
#1Andreas S. Panayides (UCY: University of Cyprus)H-Index: 10
#2Marios S. Pattichis (UNM: University of New Mexico)H-Index: 26
Last. Constantinos S. Pattichis (UCY: University of Cyprus)H-Index: 35
view all 6 authors...
Precision medicine promises better healthcare delivery by improving clinical practice. Using evidence-based substratification of patients, the objective is to achieve better prognosis, diagnosis, and treatment that will transform existing clinical pathways toward optimizing care for the specific needs of each patient. The wealth of today's healthcare data, often characterized as big data, provides invaluable resources toward new knowledge discovery that has the potential to advance precision med...
2 CitationsSource
#1S. Wallace (UNM: University of New Mexico)H-Index: 1
#2C. N. Arge (GSFC: Goddard Space Flight Center)H-Index: 1
Last. Carl John Henney (AFRL: Air Force Research Laboratory)H-Index: 19
view all 5 authors...
Over the solar-activity cycle, there are extended periods where significant discrepancies occur between the spacecraft-observed total (unsigned) open magnetic flux and that determined from coronal models. In this article, the total open heliospheric magnetic flux is computed using two different methods and then compared with results obtained from in-situ interplanetary magnetic-field observations. The first method uses two different types of photospheric magnetic-field maps as input to the Wang–...
4 CitationsSource
#2Marios S. Pattichis (UNM: University of New Mexico)H-Index: 26
Last. Brandon K. FornwaltH-Index: 15
view all 8 authors...
We present an interpretable neural network for predicting an important clinical outcome (1-year mortality) from multi-modal Electronic Health Record (EHR) data. Our approach builds on prior multi-modal machine learning models by now enabling visualization of how individual factors contribute to the overall outcome risk, assuming other factors remain constant, which was previously impossible. We demonstrate the value of this approach using a large multi-modal clinical dataset including both EHR d...
3 Citations
#1Carlos LopezLeiva (UNM: University of New Mexico)H-Index: 2
#2Marios S. Pattichis (UNM: University of New Mexico)H-Index: 26
Last. Sylvia Celedón-Pattichis (UNM: University of New Mexico)H-Index: 5
view all 3 authors...
Whilst Science, Technology, Engineering and Mathematics (STEM) interdisciplinary teaching and learning in the USA K-12 education still needs greater promotion, middle school students demonstrated that they can, using low-cost, single board computers that promote the teaching of computer science (in this case Raspberry Pis), successfully engage with computer programming of digital images and videos. The context for these students’ engagement was the Advancing Out-of-School Learning in Mathematics...
#1Alvaro UlloaH-Index: 6
#2Linyuan JingH-Index: 9
Last. Brandon K. FornwaltH-Index: 15
view all 16 authors...
Predicting future clinical events helps physicians guide appropriate intervention. Machine learning has tremendous promise to assist physicians with predictions based on the discovery of complex patterns from historical data, such as large, longitudinal electronic health records (EHR). This study is a first attempt to demonstrate such capabilities using raw echocardiographic videos of the heart. We show that a large dataset of 723,754 clinically-acquired echocardiographic videos (~45 million ima...
2 Citations
Oct 1, 2018 in ICIP (International Conference on Image Processing)
#1Cesar Carranza (PUCP: Pontifical Catholic University of Peru)H-Index: 6
#2Marios S. Pattichis (UNM: University of New Mexico)H-Index: 26
Last. Daniel Llamocca (UR: University of Rochester)H-Index: 9
view all 3 authors...
The Discrete Periodic Radon Transform (DPRT) has many important applications in reconstructing images from their projections and has recently been used in fast and scalable architectures for computing 2D convolutions. Unfortunately, the direct computation of the DPRT involves O(N^{3})additions and memory accesses that can be very costly in single-core architectures. The current paper presents new and efficient algorithms for computing the DPRT and its inverse on multi-core CPUs and GPUs. The ...
1 CitationsSource