Two-step segmentation of Hematoxylin-Eosin stained histopathological images for prognosis of breast cancer

Qu, Ang; Jiamei, Chen; Wang, Linwei; Yuan, Jingping; Yang, Fang; Xiang, Qingming; Maskey, Ninu; Yang, Guifang; Liu, Juan; Li, Yan

doi:10.1109/bibm.2014.6999158

Cited by 17 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The consistency of the features from different readers was presented in Supplemental Material, Appendix A2. The support vector machine (SVM) model to find representative features we used in this paper has been widely applied for classification in different fields333435. Each feature was ranked according to its predictive ability on the training dataset by a 5-fold cross-validation process (Detail information of the 5-fold cross-validation was presented in Supplemental Material, Appendix A3).…”

Section: Methodsmentioning

confidence: 99%

Non-small cell lung cancer: quantitative phenotypic analysis of CT images as a potential marker of prognosis

Song

Liu

Zhong

et al. 2016

Sci Rep

View full text Add to dashboard Cite

This was a retrospective study to investigate the predictive and prognostic ability of quantitative computed tomography phenotypic features in patients with non-small cell lung cancer (NSCLC). 661 patients with pathological confirmed as NSCLC were enrolled between 2007 and 2014. 592 phenotypic descriptors was automatically extracted on the pre-therapy CT images. Firstly, support vector machine (SVM) was used to evaluate the predictive value of each feature for pathology and TNM clinical stage. Secondly, Cox proportional hazards model was used to evaluate the prognostic value of these imaging signatures selected by SVM which subjected to a primary cohort of 138 patients, and an external independent validation of 61 patients. The results indicated that predictive accuracy for histopathology, N staging, and overall clinical stage was 75.16%, 79.40% and 80.33%, respectively. Besides, Cox models indicated the signatures selected by SVM: “correlation of co-occurrence after wavelet transform” was significantly associated with overall survival in the two datasets (hazard ratio [HR]: 1.65, 95% confidence interval [CI]: 1.41–2.75, p = 0.010; and HR: 2.74, 95%CI: 1.10–6.85, p = 0.027, respectively). Our study indicates that the phenotypic features might provide some insight in metastatic potential or aggressiveness for NSCLC, which potentially offer clinical value in directing personalized therapeutic regimen selection for NSCLC.

show abstract

Section: Methodsmentioning

confidence: 99%

Non-small cell lung cancer: quantitative phenotypic analysis of CT images as a potential marker of prognosis

Song

Liu

Zhong

et al. 2016

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In order to extract image features related to prognosis, we need to automatic identify and segment histological structures by image analysis methods at first. We applied an image processing pipeline by the following steps: preprocessing, segmentation, postprocessing and feature extraction 24 . First, three preprocessing methods were applied to enhance image quality.…”

Section: Methodsmentioning

confidence: 99%

“…Computer-aided image (CAI) analysis has great potential to overcome the inconsistence arise from subjective interpretation, and extract new information beyond conventional pathological parameters at the same time 18 19 20 . Quantitative analysis of HE images is an emerging field gaining more and more importance 20 .Various methods have been proposed for objects (gland, nuclei, and mitosis) segmentation 21 , malignant regions classification 22 , and computer-aid diagnosis, grade, and prognosis 23 24 .…”

mentioning

confidence: 99%

“…To achieve this goal, a sound methodology should be established to define the TNs and to distinguish major features of TNs. In previous work 24 , we proposed an algorithm, which based on a pixel-wise support vector machine (SVM) classifier to segment TNs-stroma and a marker-controlled watershed to segment cell nuclei, to realize the automatic analysis of HE histopathological images from IDC.…”

mentioning

confidence: 99%

“…In this work, we used the method proposed in Qu 24 on 1,150 HE histopathology images from IDC patients. We extracted a rich set of quantitative morphological features from pixel-level, object-level and semantic-level information, and analyzed their correlations with 8-year disease free survival (8-DFS).…”

mentioning

confidence: 99%

See 2 more Smart Citations

New breast cancer prognostic factors identified by computer-aided image analysis of HE stained histopathology images

Jiamei

Wang

et al. 2015

Sci Rep

Self Cite

View full text Add to dashboard Cite

Computer-aided image analysis (CAI) can help objectively quantify morphologic features of hematoxylin-eosin (HE) histopathology images and provide potentially useful prognostic information on breast cancer. We performed a CAI workflow on 1,150 HE images from 230 patients with invasive ductal carcinoma (IDC) of the breast. We used a pixel-wise support vector machine classifier for tumor nests (TNs)-stroma segmentation, and a marker-controlled watershed algorithm for nuclei segmentation. 730 morphologic parameters were extracted after segmentation, and 12 parameters identified by Kaplan-Meier analysis were significantly associated with 8-year disease free survival (P < 0.05 for all). Moreover, four image features including TNs feature (HR 1.327, 95%CI [1.001 - 1.759], P = 0.049), TNs cell nuclei feature (HR 0.729, 95%CI [0.537 - 0.989], P = 0.042), TNs cell density (HR 1.625, 95%CI [1.177 - 2.244], P = 0.003), and stromal cell structure feature (HR 1.596, 95%CI [1.142 - 2.229], P = 0.006) were identified by multivariate Cox proportional hazards model to be new independent prognostic factors. The results indicated that CAI can assist the pathologist in extracting prognostic information from HE histopathology images for IDC. The TNs feature, TNs cell nuclei feature, TNs cell density, and stromal cell structure feature could be new prognostic factors.

show abstract

Nuclei Perception Network for Pathology Image Analysis

Gao

et al. 2019

Intelligence Science and Big Data Engineering. Visual Data Engineering

View full text Add to dashboard Cite

Two-step segmentation of Hematoxylin-Eosin stained histopathological images for prognosis of breast cancer

Cited by 17 publications

References 33 publications

Non-small cell lung cancer: quantitative phenotypic analysis of CT images as a potential marker of prognosis

Non-small cell lung cancer: quantitative phenotypic analysis of CT images as a potential marker of prognosis

New breast cancer prognostic factors identified by computer-aided image analysis of HE stained histopathology images

Nuclei Perception Network for Pathology Image Analysis

Contact Info

Product

Resources

About