Fast unsupervised nuclear segmentation and classification scheme for automatic allred cancer scoring in immunohistochemical breast tissue images

Mouelhi, Aymen; Rmili, Hana; Ali, Jaouher Ben; Sayadi, Mounir; Doghri, Raoudha; Mrad, Karima

doi:10.1016/j.cmpb.2018.08.005

Cited by 37 publications

(28 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the [Mouelhi et al 2018] work, the authors developed a software able to segment and classify cancer nuclei in IHC images in order to provide quantitative evalua-tion of ER or PR status. The workflow had two stages: cell nuclei segmentation and cancer nuclei classification using histogram equalization for contrast enhancement and background elimination and adaptive morphological criterion to highlight the cancerous nuclei.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatic ER and PR scoring in Immunohistochemistry H-DAB Breast Cancer images

Rogalsky¹,

Ioshii

Oliveira³

2021

Anais Do XXI Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2021)

View full text Add to dashboard Cite

Breast Cancer (BC) is the most frequently diagnosed cancer for women. This way, the Brazilian Uniﬁed Health System (SUS) focuses on studying the disease and improving all the steps involved in dealing with BC. The presence or absence of the Estrogen Receptor (ER) and the Progesterone Receptor (PR), which deﬁne invasive subtypes, is detected through Immunohistochemistry (IHC). One way to assist the manual assessment of pathologists and histopathologists is to develop automatic scoring systems. Fortunately, digital pathology is increasingly achieving higher agreement with the pathologist. Therefore we create an automatic scoring system composed of image preprocessing, feature extracting, and classiﬁcation achieves a 69% f-score rate.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Based on the work of [Mouelhi et al 2018], we pre-processed our images with contrast enhancement and thresholding methods, both using local and adaptive approaches. For contrast enhancement, a histogram equalization limits the contrast amplification, reducing noise amplification.…”

Section: Pre-processingmentioning

confidence: 99%

Automatic ER and PR scoring in Immunohistochemistry H-DAB Breast Cancer images

Rogalsky¹,

Ioshii

Oliveira³

2021

Anais Do XXI Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2021)

View full text Add to dashboard Cite

show abstract

“…Mouelhi et al [23] Adaptive local thresholding and improved morphological algorithm used for the segmentation process. The unsupervised ordering of the cancer nuclei was attained by a grouping of four regular color separation methods.…”

Section: Classification Accuracy 8802% (Ddsm Database)mentioning

confidence: 99%

A Research on Breast Cancer Detection using Mammography

Ittannavar*,

Havaldar,

Khot

2019

IJITEE

View full text Add to dashboard Cite

The digital mammogram has developed as the standard screening approach for breast cancer detection and further defects in human breast tissue problem. Early detection is an efficient manner to decrease mortality in worldwide. In the past decades, several researchers implemented many methods to consistently identify the breast cancer by mammogram images. Those methods were employed to produce systems to support radiologists and physicians attain more accurate diagnosis. Accurate segmentation and classification of various tumors in the mammography plays a complex role in the early diagnosis of breast cancer. This paper defines the research on Breast Cancer Detection (BCD) methods which includes two major steps such as segmentation and classification. This research presented the different types of BCD methods with their main contributions. Additionally, it assists the researchers in the area of breast cancer detection by providing the basic knowledge and common understanding of the newest BCD methods.

show abstract

“…Recently, machine learning methods have been received considerable attention and have been widely used in cancer diagnosing [11]- [13] and other common diseases diagnosis [14], [15]. They have also been applied to understand complex disease progresses [16] and generate disease-specific medications from biomedical literature and clinical data repository [17].…”

Section: Introductionmentioning

confidence: 99%

“…M represents the number of samples flowing to the last stage. On the basis of(14),w 1 , w 2 , • • • , w L , b in(13) are calculated using the gradient descent.D. PSEUDOCODE AND DETAILS OF THE ALGORITHM shows the pseudocode of the CVIFLR algorithm.…”

mentioning

confidence: 99%

Down Syndrome Prediction Using a Cascaded Machine Learning Framework Designed for Imbalanced and Feature-correlated Data

Liu

Zhang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Down syndrome (DS) caused by the presence of part or all of a third copy of chromosome 21 is the most common form of aneuploidy. The prenatal screening for DS is a key component of antenatal care and is recommended to be universally offered to women irrespective of age or background. The objective of this paper is to introduce a noninvasive and accurate diagnosis procedure for DS and to minimize social and financial cost of prenatal diagnosis. Recently, machine learning has received considerable attention in predictive analytics for medical problems. However, there is few its applications on DS prediction reported due to the difficulty of dealing with highly imbalanced and feature-correlated screening data. In this paper, we propose a cascaded machine learning framework designed for DS prediction based on three complementary stages: 1) pre-judgment with isolation forest technique, 2) model ensemble by voting strategy, and 3) final judgment using logistic regression approach. The experimental results show that the performance of this framework on maternal serum screening data set, when evaluated with different evaluation parameters, is superior to those of some machine learning methods. The best suggested combination of input features for DS screening is the group of alpha-fetoprotein, human chorionic gonadotropin, unconjugated estriol, and maternal age. In addition, our method has the potential to generate further accurate prediction for imbalanced and feature-correlated data, thereby providing a novel and effective approach for certain diseases analysis. INDEX TERMS Bioinformatics, down syndrome prediction, imbalanced learning, cascaded framework, ensemble learning, noninvasive prenatal diagnosis.

show abstract

Fast unsupervised nuclear segmentation and classification scheme for automatic allred cancer scoring in immunohistochemical breast tissue images

Cited by 37 publications

References 34 publications

Automatic ER and PR scoring in Immunohistochemistry H-DAB Breast Cancer images

Automatic ER and PR scoring in Immunohistochemistry H-DAB Breast Cancer images

A Research on Breast Cancer Detection using Mammography

Down Syndrome Prediction Using a Cascaded Machine Learning Framework Designed for Imbalanced and Feature-correlated Data

Contact Info

Product

Resources

About