scholarly journals Risk Biomarker Assessment for Breast Cancer Progression: Replication Precision of Nuclear Morphometry

2003 ◽  
Vol 25 (3) ◽  
pp. 129-138 ◽  
Author(s):  
N. Poulin ◽  
A. Frost ◽  
A. Carraro ◽  
E. Mommers ◽  
M. Guillaud ◽  
...  
Keyword(s):  
Cancer Progression ◽  
Texture Features ◽  
Relevant Information ◽  
Nuclear Grade ◽  
Cell Nuclei ◽  
Tubule Formation ◽  
Nuclear Morphometry ◽  
Breast Neoplasia ◽  
Single Feature ◽  
Uniform Manner

Nuclear morphometry is a method for quantitative measurement of histopathologic changes in the appearance of stained cell nuclei. Numerous studies have indicated that these assessments may provide clinically relevant information related to the degree of progression and malignant potential of breast neoplasia. Nuclear features are derived from computerized analysis of digitized microscope images, and a quantitative Feulgen stain for DNA was used. Features analyzed included: (1) DNA content; (2) nuclear size and shape; and (3) texture features, describing spatial features of chromatin distribution. In this study replicated measurements are described on a series of 54 breast carcinoma specimens of differing pathologic grades. Duplicate measurements were performed using two serial sections, which were processed and analyzed separately. The value of a single feature measurement, the nuclear area profile, was shown to be the strongest indicator of progression. A quantitative nuclear grade was derived and shown to be strongly correlated with not only the pathologic nuclear grade, but also with tubule formation, mitotic grade, and with the overall histopathologic grade. Analysis of replication precision showed that the standard methods of the histopathology laboratory, if practiced in a uniform manner, are sufficient to ensure reproducibility of these assessments. We argue that nuclear morphometry provides a standardized and reproducible framework for quantitative pathologic assessments.

scholarly journals Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture Features

2018 ◽  
Vol 8 (9) ◽  
pp. 1632 ◽  
Author(s):  
Zahra Rezaei ◽  
Ali Selamat ◽  
Arash Taki ◽  
Mohd Mohd Rahim ◽  
Mohammed Abdul Kadir ◽  
...  
Keyword(s):  
Vulnerable Plaque ◽  
Plaque Rupture ◽  
Back Propagation ◽  
Texture Features ◽  
Local Binary Patterns ◽  
Relevant Information ◽  
Back Propagation Neural Network ◽  
Common Mechanism ◽  
Support Vector ◽  
Virtual Histology

Atherosclerotic plaque rupture is the most common mechanism responsible for a majority of sudden coronary deaths. The precursor lesion of plaque rupture is thought to be a thin cap fibroatheroma (TCFA), or “vulnerable plaque”. Virtual Histology-Intravascular Ultrasound (VH-IVUS) images are clinically available for visualising colour-coded coronary artery tissue. However, it has limitations in terms of providing clinically relevant information for identifying vulnerable plaque. The aim of this research is to improve the identification of TCFA using VH-IVUS images. To more accurately segment VH-IVUS images, a semi-supervised model is developed by means of hybrid K-means with Particle Swarm Optimisation (PSO) and a minimum Euclidean distance algorithm (KMPSO-mED). Another novelty of the proposed method is fusion of different geometric and informative texture features to capture the varying heterogeneity of plaque components and compute a discriminative index for TCFA plaque, while the existing research on TCFA detection has only focused on the geometric features. Three commonly used statistical texture features are extracted from VH-IVUS images: Local Binary Patterns (LBP), Grey Level Co-occurrence Matrix (GLCM), and Modified Run Length (MRL). Geometric and texture features are concatenated in order to generate complex descriptors. Finally, Back Propagation Neural Network (BPNN), kNN (K-Nearest Neighbour), and Support Vector Machine (SVM) classifiers are applied to select the best classifier for classifying plaque into TCFA and Non-TCFA. The present study proposes a fast and accurate computer-aided method for plaque type classification. The proposed method is applied to 588 VH-IVUS images obtained from 10 patients. The results prove the superiority of the proposed method, with accuracy rates of 98.61% for TCFA plaque.

scholarly journals Over-Expression of βII-Tubulin and Especially Its Localization in Cell Nuclei Correlates with Poorer Outcomes in Colorectal Cancer

Cells ◽  
2019 ◽  
Vol 8 (1) ◽  
pp. 25 ◽  
Author(s):  
Kseniya Ruksha ◽  
Artur Mezheyeuski ◽  
Alexander Nerovnya ◽  
Tatyana Bich ◽  
Gennady Tur ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Monoclonal Antibody ◽  
Cancer Progression ◽  
Nuclear Localization ◽  
Cancer Growth ◽  
Transformed Cells ◽  
Regulatory Pathway ◽  
Cell Nuclei ◽  
Normal Cells ◽  
Over Expression

Tubulin is a heterodimer of α and β subunits, both existing as isotypes differing in amino acid sequence encoded by different genes. Specific isotypes of tubulin have associations with cancer that are not well understood. Previous studies found that βII-tubulin is expressed in a number of transformed cells and that this isotype is found in cell nuclei in non-microtubule form. The association of βII expression and its nuclear localization with cancer progression has not previously been addressed. We here used a monoclonal antibody to βII to examine patients with colorectal cancer and found that patients whose tumors over-express βII have a greatly decreased life expectancy which is even shorter in those patients with nuclear βII. Our results suggest that βII-tubulin may facilitate cancer growth and metastasis and, to accomplish this, may not need to be in microtubule form. Furthermore, βII expression and localization could be a useful prognostic marker. We also found that βII appears in the nuclei of otherwise normal cells adjacent to the tumor. It is possible therefore that cancer cells expressing βII influence nearby cells to do the same and to localize βII in their nuclei by an as yet uncharacterized regulatory pathway.

Abstract 425: Nuclear morphometry predicts prostate cancer progression

2016 ◽  
Author(s):  
Guangjing Zhu ◽  
Aniq ur rehman Gajdhar ◽  
Jonathan I. Epstein ◽  
Neil Carleton ◽  
Christine Davis ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Cancer Progression ◽  
Prostate Cancer Progression ◽  
Nuclear Morphometry

scholarly journals Nuclear Morphometry is a superior Prognostic Predictor in comparison to Histological grading in Renal cell Carcinoma: A Retrospective Clinico-pathological study

2021 ◽  
Author(s):  
Shruti Agrawal ◽  
Nikunj Jain
Keyword(s):  
Renal Cell Carcinoma ◽  
Clinical Outcome ◽  
Cell Carcinoma ◽  
Renal Cell ◽  
Histological Grade ◽  
Inverse Correlation ◽  
Nuclear Grade ◽  
Renal Tumors ◽  
Computer Assisted ◽  
Nuclear Morphometry

Background: Renal cell carcinoma (RCC) comprises of a spectrum of clinico-pathologically distinct entities thereby making it difficult to accurately predict the clinical outcome. Though many predictive factors have been described in literature, tumor stage and nuclear grade have been established to consistently correlate with the tumor behaviour. However, tumors in the same stage have shown to behave differently. Similarly subjectivity and lack of reproducibility in nuclear grade mandates use of more objective parameters such as digital nuclear morphometry which could provide consistent and more reliable results in predicting prognosis. The study was conducted with the main objective of comparing the histological grade and the nuclear morphometric variables in RCC for predicting the clinical outcome. Material and methods: A total of 219 cases of renal tumors in adults were retrieved retrospectively from the archives of pathology department in Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow and their clinical, gross and microscopic features were noted. Nuclear grading was done in 181 cases of clear cell and papillary RCC of which computer-assisted morphometry for various nuclear parameters was done in 100 cases where a follow-up data of at least 3 years was available. Nuclear grade and morphometric parameters were correlated statistically with the clinical outcome of the patients. Results: Histological nuclear grade did not show statistically significant correlation with progression free survival (PFS). Higher values of mean nuclear area, mean nuclear circumference, mean nuclear major diameter and mean nuclear minor diameter were significant predictors of PFS with a strong inverse correlation. Conclusion: Nuclear morphometry is a more reliable predictor of clinical outcome in patients of RCC when compared to histological grade and should be included in predictive model with other clinical and pathological parameters to accurately determine tumor behaviour

scholarly journals SHIP DETECTION BASED ON MULTIPLE FEATURES IN RANDOM FOREST MODEL FOR HYPERSPECTRAL IMAGES

2018 ◽  
Vol XLII-3 ◽  
pp. 891-895
Author(s):  
N. Li ◽  
L. Ding ◽  
H. Zhao ◽  
J. Shi ◽  
D. Wang ◽  
...  
Keyword(s):  
Random Forest ◽  
Near Infrared ◽  
Texture Features ◽  
Short Wave ◽  
Hyperspectral Images ◽  
Support Vector ◽  
High Signal ◽  
Detection Accuracy ◽  
Multiple Features ◽  
Single Feature

A novel method for detecting ships which aim to make full use of both the spatial and spectral information from hyperspectral images is proposed. Firstly, the band which is high signal-noise ratio in the range of near infrared or short-wave infrared spectrum, is used to segment land and sea on Otsu threshold segmentation method. Secondly, multiple features that include spectral and texture features are extracted from hyperspectral images. Principal components analysis (PCA) is used to extract spectral features, the Grey Level Co-occurrence Matrix (GLCM) is used to extract texture features. Finally, Random Forest (RF) model is introduced to detect ships based on the extracted features. To illustrate the effectiveness of the method, we carry out experiments over the EO-1 data by comparing single feature and different multiple features. Compared with the traditional single feature method and Support Vector Machine (SVM) model, the proposed method can stably achieve the target detection of ships under complex background and can effectively improve the detection accuracy of ships.

scholarly journals Blunt duct adenosis: a separate entity from columnar cell lesions?

2021 ◽  
pp. jclinpath-2020-207359
Author(s):  
Mirthe de Boer ◽  
Paul J van Diest
Keyword(s):  
Diagnostic Criteria ◽  
Breast Lesion ◽  
Benign Lesion ◽  
Nuclear Grade ◽  
Columnar Cell ◽  
Separate Entity ◽  
Terminal Duct Lobular Unit ◽  
Breast Neoplasia ◽  
Columnar Cell Lesions ◽  
Cell Changes

Blunt duct adenosis (BDA) is a breast lesion first described by Foote and Stewart in 1945 as a proliferative benign lesion of the terminal duct lobular unit. Throughout recent decades, further literature descriptions of BDA have been confusing. Some consider BDA to be a separate entity, some a growth pattern of columnar cell changes. The WHO 2012 considered BDA and columnar cell changes to be synonyms, while columnar cell lesions, especially those with atypia, are part of a spectrum of early precursors of the low nuclear grade breast neoplasia family. In the updated WHO 2019 version, BDA is mentioned as ‘not recommended’ terminology for columnar cell lesions without further discussing it, leaving the question open if BDA should be considered a separate entity.Good diagnostic criteria for BDA have however largely been lacking, and its biological background has not yet been unravelled. In this paper, we point out that BDA is mainly associated with benign breast lesions and not with other recognised precursor lesions. Further, 16q loss, which is the hallmark molecular event in the low nuclear grade breast neoplasia family, is lacking in BDA. We therefore hypothesise that BDA may not be a true precursor lesion but a benign polyclonal lesion, and propose morphological diagnostic criteria to better differentiate it from columnar cell lesions.

Approach of Using Texture and Shape for Image Retrieval

2013 ◽  
pp. 30-45
Author(s):  
Gang Zhang ◽  
Zongmin Ma ◽  
Li Yan
Keyword(s):  
Feature Extraction ◽  
Image Retrieval ◽  
Texture Features ◽  
Gabor Wavelet ◽  
Feature Integration ◽  
Shape Features ◽  
Important Research ◽  
Information Redundancy ◽  
Single Feature ◽  
Descriptor Approach

Feature integration is one of important research contents in content-based image retrieval. Single feature extraction and description is foundation of the feature integration. Features from a single feature extraction approach are a single feature or composite features, whether integration features are more discriminative than them or not. An approach of integrating shape and texture features was presented and used to study these problems. Gabor wavelet transform with minimum information redundancy was used to extract texture features, which would be used for feature analyses. Fourier descriptor approach with brightness was used to extract shape features. Then both features were integrated in parallel by weights. Comparisons were carried out among the integration features, the texture features, and the shape features, so that discrimination of the integration features can be testified.

scholarly journals Research on Techniques of Multifeatures Extraction for Tongue Image and Its Application in Retrieval

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Liyan Chen ◽  
Beizhan Wang ◽  
Zhihong Zhang ◽  
Fan Lin ◽  
Yihan Ma
Keyword(s):  
Traditional Medicine ◽  
Detection Rate ◽  
Texture Features ◽  
Experimental Results ◽  
Chinese Traditional Medicine ◽  
Image Information ◽  
Novel Approach ◽  
Single Feature ◽  
Main Color ◽  
Tongue Color

Tongue diagnosis is one of the important methods in the Chinese traditional medicine. Doctors can judge the disease’s situation by observing patient’s tongue color and texture. This paper presents a novel approach to extract color and texture features of tongue images. First, we use improved GLA (Generalized Lloyd Algorithm) to extract the main color of tongue image. Considering that the color feature cannot fully express tongue image information, the paper analyzes tongue edge’s texture features and proposes an algorithm to extract them. Then, we integrate the two features in retrieval by different weight. Experimental results show that the proposed method can improve the detection rate of lesion in tongue image relative to single feature retrieval.

Sign in / Sign up

Export Citation Format

Share Document