Structure and Context in Prostatic Gland Segmentation and Classification

Nguyen, Kien; Sarkar, Anindya; Jain, Anil K.

doi:10.1007/978-3-642-33415-3_15

Cited by 64 publications

(77 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gland lumen were automatically segmented from digital images of the cancerous regions of RP whole mount slide images using the approach described in Nguyen et al 32 To segment lumen, the algorithm first performed k-means clustering of the colors of 10,000 randomly selected pixels in an image with k ¼ 4. Pixels were given a label based on their cluster to define the prototypical color of nuclei, stroma, cytoplasm, and lumen in an image.…”

Section: Segmentationmentioning

confidence: 99%

Evaluating stability of histomorphometric features across scanner and staining variations: prostate cancer diagnosis from whole slide images

et al. 2016

View full text Add to dashboard Cite

Abstract. Quantitative histomorphometry (QH) is the process of computerized feature extraction from digitized tissue slide images to predict disease presence, behavior, and outcome. Feature stability between sites may be compromised by laboratory-specific variables including dye batch, slice thickness, and the whole slide scanner used. We present two new measures, preparation-induced instability score and latent instability score, to quantify feature instability across and within datasets. In a use case involving prostate cancer, we examined QH features which may detect cancer on whole slide images. Using our method, we found that five feature families (graph, shape, co-occurring gland tensor, sub-graph, and texture) were different between datasets in 19.7% to 48.6% of comparisons while the values expected without site variation were 4.2% to 4.6%. Color normalizing all images to a template did not reduce instability. Scanning the same 34 slides on three scanners demonstrated that Haralick features were most substantively affected by scanner variation, being unstable in 62% of comparisons. We found that unstable feature families performed significantly worse in inter-than intrasite classification. Our results appear to suggest QH features should be evaluated across sites to assess robustness, and class discriminability alone should not represent the benchmark for digital pathology feature selection.

show abstract

Section: Segmentationmentioning

confidence: 99%

Evaluating stability of histomorphometric features across scanner and staining variations: prostate cancer diagnosis from whole slide images

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The number of subjects used was not specified. Nguyen et al [18] perform K-means in the RGB space to distinguish between nuclei, stroma, lumen, and cytoplasm prior to segmentation and two-/three-way classification based on structural and contextual information. They experiment on 48 900 1500 pixel images from 20 patients with manual labeling of 525 artefacts, 931 normal glands and 1375 cancer glands, and report % accuracy on gland versus artefact classification, % accuracy on normal gland versus cancer gland classification, and % accuracy on a three-way artefact versus normal gland versus cancer gland classification.…”

Section: Related Workmentioning

confidence: 99%

Prostate Histopathology: Learning Tissue Component Histograms for Cancer Detection and Classification

Gorelick

Veksler

Gaed

et al. 2013

IEEE Trans. Med. Imaging

106

View full text Add to dashboard Cite

Abstract-Radical prostatectomy is performed on approximately 40% of men with organ-confined prostate cancer. Pathologic information obtained from the prostatectomy specimen provides important prognostic information and guides recommendations for adjuvant treatment. The current pathology protocol in most centers involves primarily qualitative assessment. In this paper, we describe and evaluate our system for automatic prostate cancer detection and grading on hematoxylin & eosin-stained tissue images. Our approach is intended to address the dual challenges of large data size and the need for high-level tissue information about the locations and grades of tumors. Our system uses two stages of AdaBoost-based classification. The first provides high-level tissue component labeling of a superpixel image partitioning. The second uses the tissue component labeling to provide a classification of cancer versus noncancer, and low-grade versus high-grade cancer. We evaluated our system using 991 sub-images extracted from digital pathology images of 50 whole-mount tissue sections from 15 prostatectomy patients. We measured accuracies of 90% and 85% for the cancer versus noncancer and high-grade versus low-grade classification tasks, respectively. This system represents a first step toward automated cancer quantification on prostate digital histopathology imaging, which could pave the way for more accurately informed postprostatectomy patient care.

show abstract

“…Broadly speaking, previous studies in the literature can be categorized into two classes: (1) pixel based methods. For this kind of method, various hand-crafted features including texture, color, morphological cues and Haar-like features were utilized to detect the glandular structure from histology images [11,38,13,36,37,28,23,32]; (2) structure based methods. Most of approaches in this category take advantage of prior knowledge about the glandular structure, such as graph based methods [2,20], glandular boundary delineation with geodesic distance transform [16], polar space random field model [18], stochastic polygons model [35], etc.…”

Section: Introductionmentioning

confidence: 99%

DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation

Chen

et al. 2016

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

510

339

View full text Add to dashboard Cite

The morphology of glands has been used routinely by pathologists to assess the malignancy degree of adenocarcinomas. Accurate segmentation of glands from histology images is a crucial step to obtain reliable morphological statistics for quantitative diagnosis. In this paper, we proposed an efficient deep contour-aware network (DCAN) to solve this challenging problem under a unified multi-task learning framework. In the proposed network, multi-level contextual features from the hierarchical architecture are explored with auxiliary supervision for accurate gland segmentation. When incorporated with multi-task regularization during the training, the discriminative capability of intermediate features can be further improved. Moreover, our network can not only output accurate probability maps of glands, but also depict clear contours simultaneously for separating clustered objects, which further boosts the gland segmentation performance. This unified framework can be efficient when applied to large-scale histopathological data without resorting to additional steps to generate contours based on low-level cues for post-separating. Our method won the 2015 MICCAI Gland Segmentation Challenge out of 13 competitive teams, surpassing all the other methods by a significant margin.

show abstract

Structure and Context in Prostatic Gland Segmentation and Classification

Cited by 64 publications

References 7 publications

Evaluating stability of histomorphometric features across scanner and staining variations: prostate cancer diagnosis from whole slide images

Evaluating stability of histomorphometric features across scanner and staining variations: prostate cancer diagnosis from whole slide images

Prostate Histopathology: Learning Tissue Component Histograms for Cancer Detection and Classification

DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation

Contact Info

Product

Resources

About