Luca Giancardo

The University of Texas Health Science Center at Houston

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Sunil A. Sheth

The University of Texas Health Science Center at Houston

Edward Chaum

Vanderbilt University Medical Center

Thomas P. Karnowski

Oak Ridge National Laboratory

Kenneth W. Tobin

Oak Ridge National Laboratory

Rania Abdelkhaleq

The University of Texas Health Science Center at Houston

Sergio Salazar‐Marioni

The University of Texas Health Science Center at Houston

Fabrice Mériaudeau

Université de Bourgogne

Samiksha Pachade

The University of Texas Health Science Center at Houston

Teresa Arroyo‐Gallego

QMedic

Arash Niktabe

The University of Texas Health Science Center at Houston

Cooperative Institutions

The University of Texas Health Science Center at Houston

153

Conference Board Math Sciences

University of Zurich

Memorial Hermann

University of Houston

Texas Medical Center

The University of Texas MD Anderson Cancer Center

Harvard University

Technical University of Munich

Shanghai Jiao Tong University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

IDRiD: Diabetic Retinopathy – Segmentation and Grading Challenge

Medical Image Analysis (2019)

Prasanna Porwal Samiksha Pachade Manesh Kokare Girish Deshmukh Jaemin Son

Grading (engineering)

10.1016/j.media.2019.101561

Cite

Citations (249)

Computer-aided detection of cerebral microbleeds in susceptibility-weighted imaging

Computerized Medical Imaging and Graphics (2015)

Amir Fazlollahi Fabrice Mériaudeau Luca Giancardo Victor L. Villemagne Christopher C. Rowe

Blob detection

Binary classification

10.1016/j.compmedimag.2015.10.001

Cite

Citations (39)

Longitudinal Connectomes as a Candidate Progression Marker for Prodromal Parkinson’s Disease

Frontiers in Neuroscience (2019)

Óscar Peña‐Nogales Timothy M. Ellmore Rodrigo de Luis‐García Jessika Suescun Mya C. Schiess

Parkinson's disease is the second most prevalent neurodegenerative disorder in the Western world. It is estimated that the neuronal loss related to Parkinson's disease precedes the clinical diagnosis by more than 10 years (prodromal phase) which leads to a subtle decline that translates into non-specific clinical signs and symptoms. By leveraging diffusion magnetic resonance imaging brain (MRI) data evaluated longitudinally, at least at two different time points, we have the opportunity of detecting and measuring brain changes early on in the neurodegenerative process, thereby allowing early detection and monitoring that can enable development and testing of disease modifying therapies. In this study, we were able to define a longitudinal degenerative Parkinson's disease progression pattern using diffusion magnetic resonance imaging connectivity information. Such pattern was discovered using a de novo early Parkinson's disease cohort (n = 21), and a cohort of Controls (n = 30). Afterward, it was tested in a cohort at high risk of being in the Parkinson's disease prodromal phase (n = 16). This progression pattern was numerically quantified with a longitudinal brain connectome progression score. This score is generated by an interpretable machine learning (ML) algorithm trained, with cross-validation, on the longitudinal connectivity information of Parkinson's disease and Control groups computed on a nigrostriatal pathway-specific parcellation atlas. Experiments indicated that the longitudinal brain connectome progression score was able to discriminate between the progression of Parkinson's disease and Control groups with an area under the receiver operating curve of 0.89 [confidence interval (CI): 0.81-0.96] and discriminate the progression of the High Risk Prodromal and Control groups with an area under the curve of 0.76 [CI: 0.66-0.92]. In these same subjects, common motor and cognitive clinical scores used in Parkinson's disease research showed little or no discriminative ability when evaluated longitudinally. Results suggest that it is possible to quantify neurodegenerative patterns of progression in the prodromal phase with longitudinal diffusion magnetic resonance imaging connectivity data and use these image-based patterns as progression markers for neurodegeneration.

Connectomics

10.3389/fnins.2018.00967

Cite

Citations (21)

Retinal image analysis for disease screening through local tetra patterns

Computers in Biology and Medicine (2018)

Prasanna Porwal Samiksha Pachade Manesh Kokare Luca Giancardo Fabrice Mériaudeau

Local Binary Patterns

AdaBoost

10.1016/j.compbiomed.2018.09.028

Cite

Citations (10)

Author Correction: Computer keyboard interaction as an indicator of early Parkinson’s disease

Scientific Reports (2018)

Luca Giancardo Álvaro Sánchez‐Ferro Teresa Arroyo‐Gallego I. Butterworth Carlos S. Mendoza

A correction has been published and is appended to both the HTML and PDF versions of this paper. The error has not been fixed in the paper.

10.1038/s41598-018-32121-x

Cite

Citations (2)

X-Ray Based Automatic Detection Of Brain Coil Compaction Using Unsupervised Learning

2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI) (2021)

Shuyang Fan Mehmet Enes Inam Danilo Peña Peng Roc Chen Luca Giancardo

Endovascular coiling (EC) is a vital procedure that treats intracranial aneurysms (IA) but a common complication is aneurysm recurrence as a result of coil compaction, when the implanted coil fails to isolate IA from cerebrovascular circulation. Such an event may lead to devastating hemorrhages. Hence, frequent follow-up imaging sessions using Digital Subtraction Angiography (DSA) are critical. However, DSA is invasive, expensive and not widely available. Recently, it has been shown that skull X-rays could be used as a proxy. In this work, we present a new pipeline that enables the semi-automatic evaluation of coil compaction based on X-ray images. Our pipeline involves coil segmentation with GrabCut and an autoencoder that learns image embeddings with a location-sensitive loss function. This approach generates efficient representations without training on image labels. We show that the image embeddings capture information relevant to coil compaction and that a simple distance measure between embeddings outperforms other baseline methods including a Siamese network.

Autoencoder

Subtraction

Digital subtraction angiography

Ground truth

10.1109/isbi48211.2021.9433992

Cite

Citations (2)

iGWAS: image-based genome-wide association of self-supervised deep phenotyping of human medical images

medRxiv (Cold Spring Harbor Laboratory) (2022)

Ziqian Xie Tao Zhang Sangbae Kim Jiaxiong Lu Wanheng Zhang

Abstract Existing imaging genetics studies have been mostly limited in scope by using imaging-derived phenotypes defined by human experts. Here, leveraging new breakthroughs in self-supervised deep representation learning, we propose a new approach, image-based genome-wide association study (iGWAS), for identifying genetic factors associated with phenotypes discovered from medical images using contrastive learning. Using retinal fundus photos, our model extracts a 128-dimensional vector representing features of the retina as phenotypes. After training the model on 40,000 images from the EyePACS dataset, we generated phenotypes from 130,329 images of 65,629 British White participants in the UK Biobank. We conducted GWAS on three sets of phenotypes: raw image phenotype, phenotypes derived from the original photos; retina color, the average color of the center region of the retinal fundus photos; and vessel-enriched phenotypes, phenotypes derived from vasculature-segmented images. GWAS of raw image phenotypes identified 14 loci with genome-wide significance (p<5×10 -8 and intersection of hits from left and right eyes), while GWAS of retina colors identified 34 loci, 7 are overlapping with GWAS of raw image phenotype. Finally, a GWAS of vessel-enriched phenotypes identified 34 loci. While 25 are overlapping with the raw image loci and color loci, 9 are unique to vessel-enriched GWAS. We found that vessel-enriched GWAS not only retains most of the loci from raw image GWAS but also discovers new loci related to vessel development. Our results establish the feasibility of this new framework of genomic study based on self-supervised phenotyping of medical images.

Genome-wide Association Study

Genetic Association

10.1101/2022.05.26.22275626

Cite

Citations (8)

Texture-less Macula Swelling Detection with Multiple Retinal Fundus Images

HAL (Le Centre pour la Communication Scientifique Directe) (2011)

Luca Giancardo Fabrice Mériaudeau Thomas P. Karnowski Kenneth W. Tobin Enrico Grisan

Fundus (uterus)

Texture (cosmology)

Source

Cite

Citations (3)

Elliptical local vessel density: A fast and robust quality metric for retinal images

Luca Giancardo Michael D. Abràmoff Edward Chaum Thomas P. Karnowski Fabrice Mériaudeau

A great effort of the research community is geared towards the creation of an automatic screening system able to promptly detect diabetic retinopathy with the use of fundus cameras. In addition, there are some documented approaches for automatically judging the image quality. We propose a new set of features independent of field of view or resolution to describe the morphology of the patient's vessels. Our initial results suggest that these features can be used to estimate the image quality in a time one order of magnitude shorter than previous techniques.

Fundus (uterus)

10.1109/iembs.2008.4649968

Cite

Citations (61)

Towards Stroke Biomarkers on Fundus Retinal Imaging: A Comparison Between Vasculature Embeddings and General Purpose Convolutional Neural Networks

2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (2021)

Ivan Coronado Rania Abdelkhaleq Juntao Yan Sergio Salazar Marioni Amanda Jagolino‐Cole

Fundus Retinal imaging is an easy-to-acquire modality typically used for monitoring eye health. Current evidence indicates that the retina, and its vasculature in particular, is associated with other disease processes making it an ideal candidate for biomarker discovery. The development of these biomarkers has typically relied on predefined measurements, which makes the development process slow. Recently, representation learning algorithms such as general purpose convolutional neural networks or vasculature embeddings have been proposed as an approach to learn imaging biomarkers directly from the data, hence greatly speeding up their discovery. In this work, we compare and contrast different state-of-the-art retina biomarker discovery methods to identify signs of past stroke in the retinas of a curated patient cohort of 2,472 subjects from the UK Biobank dataset. We investigate two convolutional neural networks previously used in retina biomarker discovery and directly trained on the stroke outcome, and an extension of the vasculature embedding approach which infers its feature representation from the vasculature and combines the information of retinal images from both eyes.In our experiments, we show that the pipeline based on vasculature embeddings has comparable or better performance than other methods with a much more compact feature representation and ease of training.Clinical Relevance-This study compares and contrasts three retinal biomarker discovery strategies, using a curated dataset of subject evidence, for the analysis of the retina as a proxy in the assessment of clinical outcomes, such as stroke risk.

Biomarker Discovery

10.1109/embc46164.2021.9629856

Cite

Citations (6)