Automatic Detection of Tubules in Breast Histopathological Images

Maqlin, P.; Thamburaj, Robinson; Mammen, Joy John; Nagar, Atulya K.

doi:10.1007/978-81-322-1041-2_27

Cited by 13 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An accuracy of 89% was obtained in the classification task of low (tubular BR score 2 and 3) and high tubule formation (tubular BR score 1). A similar strategy, using k-means to identify lumen followed by a level set based segmentation approach enabled the identification of the surrounding nuclei layer 11 . The deep neural network (DNN) is a deep learning architecture that comprises more than two hidden layers.…”

mentioning

confidence: 99%

Automated tubule nuclei quantification and correlation with oncotype DX risk categories in ER+ breast cancer whole slide images

et al. 2016

View full text Add to dashboard Cite

mentioning

confidence: 99%

Automated tubule nuclei quantification and correlation with oncotype DX risk categories in ER+ breast cancer whole slide images

et al. 2016

View full text Add to dashboard Cite

“…The tubule scoring problem, which was mentioned above, is addressed in Ojansivu et al 3 by using textural features and support vector machine classifier. Finally, the tubule segmentation problem, which is similar to our work, is addressed in Dalle et al 4 and Maqlin et al 5 However, compared to the previous work, our method differs in that:…”

Section: Related Workmentioning

confidence: 71%

“…• Similar to the methods in Dalle et al 4 and Maqlin et al, 5 we first detect all nuclei from the image.…”

Section: Related Workmentioning

confidence: 96%

“…• Since the methods in Dalle et al 4 and Maqlin et al 5 only associate the lumen and its closest nuclei, they cannot handle the case where a lumen is surrounded by multiple layers of nuclei. However, by constructing the graph of lumina and nuclei and using the normalized cut method 6 to perform the segmentation, we take into account the global distribution of the nuclei and lumina in the image, hence, we are able to form the tubule which contains one lumen and multiple layers of nuclei.…”

Section: Lumen Candidate Detectionmentioning

confidence: 97%

“…True lumen identification Glandular and tubule region segmentation • In order to identify true lumina from other white regions (e.g., fatty regions, broken tissue), we employ the learning -classification scheme (rather than using heuristic rules as in Maqlin et al 5 ). By doing this, we are able to incorporate a large number of relevant features for lumen identification.…”

Section: Lumen Candidate Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic glandular and tubule region segmentation in histological grading of breast cancer

et al. 2015

View full text Add to dashboard Cite

In the popular Nottingham histologic score system for breast cancer grading, the pathologist analyzes the H&E tissue slides and assigns a score, in the range of 1-3, for tubule formation, nuclear pleomorphism and mitotic activity in the tumor regions. The scores from these three factors are added to give a final score, ranging from 3-9 to grade the cancer. Tubule score (TS), which reflects tubular formation, is a value in 1-3 given by manually estimating the percentage of glandular regions in the tumor that form tubules. In this paper, given an H&E tissue image representing a tumor region, we propose an automated algorithm to segment glandular regions and detect the presence of tubules in these regions. The algorithm first detects all nuclei and lumen candidates in the input image, followed by identifying tumor nuclei from the detected nuclei and identifying true lumina from the lumen candidates using a random forest classifier. Finally, it forms the glandular regions by grouping the closely located tumor nuclei and lumina using a graph-cut-based method. The glandular regions containing true lumina are considered as the ones that form tubules (tubule regions). To evaluate the proposed method, we calculate the tubule percentage (TP), i.e., the ratio of the tubule area to the total glandular area for 353 H&E images of the three TSs, and plot the distribution of these TP values. This plot shows the clear separation among these three scores, suggesting that the proposed algorithm is useful in distinguishing images of these TSs.

show abstract

Boundary Extraction for Imperfectly Segmented Nuclei in Breast Histopathology Images – A Convex Edge Grouping Approach

Paramanandam¹,

Thamburaj²,

Manipadam

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Automatic Detection of Tubules in Breast Histopathological Images

Cited by 13 publications

References 11 publications

Automated tubule nuclei quantification and correlation with oncotype DX risk categories in ER+ breast cancer whole slide images

Automated tubule nuclei quantification and correlation with oncotype DX risk categories in ER+ breast cancer whole slide images

Automatic glandular and tubule region segmentation in histological grading of breast cancer

Boundary Extraction for Imperfectly Segmented Nuclei in Breast Histopathology Images – A Convex Edge Grouping Approach

Contact Info

Product

Resources

About