Computer Vision and Pattern Discovery for Bioimages

Tumor-adjacent tissue co-expression profile analysis reveals pro-oncogenic ribosomal gene signature for prognosis of resectable hepatocellular carcinoma

Published date : 12 Dec 2017

Currently, molecular markers are not used when determining the prognosis and treatment strategy for patients with hepatocellular carcinoma (HCC). In the present study, we proposed that the identification of common pro-oncogenic pathways in primary tumors (PT) and adjacent non-malignant tissues (AT) typically used to predict HCC patient risks may result in HCC biomarker discovery. We examined the genome-wide mRNA expression profiles of paired PT and AT samples from 321 HCC patients.

type
Journal Paper
journal
Molecular Oncology, 8 Nov 2017, doi: 10.1002/1878-0261.12153
Impact Factor
5.314

Semi-automated quantitative Drosophila wings measurements

Published date : 28 Jun 2017

BACKGROUND:
Drosophila melanogaster is an important organism used in many fields of biological research such as genetics and developmental biology. Drosophila wings have been widely used to study the genetics of development, morphometrics and evolution. Therefore there is much interest in quantifying wing structures of Drosophila. Advancement in technology has increased the ease in which images of Drosophila can be acquired. However such studies have been limited by the slow and tedious process of acquiring phenotypic data.

RESULTS:

type
Journal Paper
journal
BMC Bioinformatics 2017 Jun 28;18(1):319. doi: 10.1186/s12859-017-1720-y
Impact Factor
2.435

Gland segmentation in prostatehistopathological images

Published date : 21 Jun 2017

Glandular structural features are important for the tumor pathologist in the assessment of cancer malignancy of prostate tissue slides. The varying shapes and sizes of glands combined with the tedious manual observation task can result in inaccurate assessment. There are also discrepancies and low-level agreement among pathologists, especially in cases of Gleason pattern 3 and pattern 4 prostate adenocarcinoma. An automated gland segmentation system can highlight various glandular shapes and structures for further analysis by the pathologist.

type
Journal Paper
journal
Journal of Medical Imaging, 2017 Apr;4(2):027501, doi: 10.1117/1.JMI.4.2.027501

A Study of Nuclei Classification Methods in Histopathological Images

Published date : 21 May 2017

Cancer is a group of diseases involving abnormal cell growth with varying malignancy and extent across different patients. Cytological features like prominent nucleoli, nuclear enlargement, and hyperchromasia are important to the tumor pathologist in assessment of cancer malignancy from tissue biopsies. In a recent study, Yap et al. [21] proposed effective prominent nucleoli detectors in histopathological images and developed different feature generation methods.

type
Conference Paper/Poster
journal
Proceedings of the 5th KES International Conference on Innovation in Medicine and Healthcare (KES-InMed 2017)

A novel toolbox to investigate tissue spatial organization applied to the study of the islets of Langerhans

Published date : 17 Mar 2017

Thanks to the development of new 3D Imaging techniques, volumetric data of thick samples, especially tissues, are commonly available. Several algorithms were proposed to analyze cells or nuclei in tissues, however these tools are limited to two dimensions. Within any given tissue, cells are not likely to be organized randomly and as such have specific patterns of cell-cell interaction forming complex communication networks. In this paper, we propose a new set of tools as an approach to segment and analyze tissues in 3D with single cell resolution.

type
Journal Paper
journal
Scientific Reports 7, Article number: 44261 (2017), doi:10.1038/srep44261
Impact Factor
5.228

Anterior segment imaging-based subdivision of subjects with primary angle-closure glaucoma

Published date : 09 Dec 2016

Purpose
The purpose of this study was to identify whether it was possible to subdivide subjects with primary angle-closure glaucoma (PACG) based on anterior segment optical coherence tomography (ASOCT) imaging, and to determine the characteristics of such subgroups.

Methods

type
Journal Paper
journal
Eye, 31, Pg 572-577 (2017), doi:10.1038/eye.2016.267
Impact Factor
2.275

Automated Classification for Pathological Prostate Images using AdaBoost-based

Published date : 06 Dec 2016

We present an AdaBoost-based Ensemble Learning for supporting automated Gleason grading of prostate adenocarcinoma (PRCA). The method is able to differentiate Gleason patterns 4–5 from patterns 1–3 as the patterns 4-5 are correlated to more aggressive disease while patterns 1-3 tend to reflect more favorable patient outcome. This method is based on various feature descriptors and classifiers for multiple color channels, including color channels of red, green and blue, as well as the optical intensity of hematoxylin and eosin stainings.

type
Conference Paper/Poster
journal
2016 IEEE Sympsosium Series on Computational Intelligence (IEEE SSCI 2016) Dec 6 to 9, Athens, Greece,

Weibel-Palade body size modulates the adhesive activity of its von Willebrand Factor cargo in cultured endothelial cells

Published date : 31 Aug 2016

Changes in the size of cellular organelles are often linked to modifications in their function. Endothelial cells store von Willebrand Factor (vWF), a glycoprotein essential to haemostasis in Weibel-Palade bodies (WPBs), cigar-shaped secretory granules that are generated in a wide range of sizes. We recently showed that forcing changes in the size of WPBs modifies the activity of this cargo. We now find that endothelial cells treated with statins produce shorter WPBs and that the vWF they release at exocytosis displays a reduced capability to recruit platelets to the endothelial cell surface.

type
Journal Paper
journal
Scientific Reports 6, Article no. 32473 (2016), doi:10.1038/srep32473
Impact Factor
5.228

Large-scale image-based screening and profiling of cellular phenotypes

Published date : 19 Jul 2016

Cellular phenotypes are observable characteristics of cells resulting from the interactions of intrinsic and extrinsic chemical or biochemical factors. Image-based phenotypic screens under large numbers of basal or perturbed conditions can be used to study the influences of these factors on cellular phenotypes. Hundreds to thousands of phenotypic descriptors can also be quantified from the images of cells under each of these experimental conditions. Therefore, huge amounts of data can be generated, and the analysis of these data has become a major bottleneck in large-scale phenotypic screens.

type
Journal Paper
journal
Cytometry Part A, 2016, doi: 10.1002/cyto.a.22909
Impact Factor
3.18

Optimal processing for gel electrophoresis images: Applying Monte Carlo Tree Search in GelApp

Published date : 02 Jun 2016

In biomedical research, gel band size estimation in electrophoresis analysis is a routine process. To facilitate and automate this process, numerous software have been released, notably the GelApp mobile app. However, the band detection accuracy is limited due to a band detection algorithm that cannot adapt to the variations in input images. To address this, we used the Monte Carlo Tree Search with Upper Confidence Bound (MCTS-UCB) method to efficiently search for optimal image processing pipelines for the band detection task, thereby improving the image processing algorithm.

type
Journal Paper
journal
Electrophoresis 2016, 10.1002/elps.201600197
Impact Factor
3.028