Automatic Gleason grading of H and E stained microscopic prostate images using deep convolutional neural networks

Gummeson, Anna; Arvidsson, Ida; Ohlsson, Mattias; Overgaard, Niels Christian; Krzyzanowska, Agnieszka; Heyden, Anders; Bjartell, Anders; Åström, Kalle

doi:10.1117/12.2253620

Cited by 11 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this review, fifteen studies used Histopath model with CNN for classification and detection of different types of cancers as provided in Table 9. Six of these studies provided the source of data [49,50,52,54,85] while nine studies did not publish the source of data [90,91,92,93,95,101,102,104]. Two research studies used mammographs for detection along with CNN and published data source [51,53].…”

Section: Discussionmentioning

confidence: 99%

Cancer Diagnosis Using Deep Learning: A Bibliographic Review

Munir

Elahi

Ayub

et al. 2019

Cancers

344

182

View full text Add to dashboard Cite

In this paper, we first describe the basics of the field of cancer diagnosis, which includes steps of cancer diagnosis followed by the typical classification methods used by doctors, providing a historical idea of cancer classification techniques to the readers. These methods include Asymmetry, Border, Color and Diameter (ABCD) method, seven-point detection method, Menzies method, and pattern analysis. They are used regularly by doctors for cancer diagnosis, although they are not considered very efficient for obtaining better performance. Moreover, considering all types of audience, the basic evaluation criteria are also discussed. The criteria include the receiver operating characteristic curve (ROC curve), Area under the ROC curve (AUC), F1 score, accuracy, specificity, sensitivity, precision, dice-coefficient, average accuracy, and Jaccard index. Previously used methods are considered inefficient, asking for better and smarter methods for cancer diagnosis. Artificial intelligence and cancer diagnosis are gaining attention as a way to define better diagnostic tools. In particular, deep neural networks can be successfully used for intelligent image analysis. The basic framework of how this machine learning works on medical imaging is provided in this study, i.e., pre-processing, image segmentation and post-processing. The second part of this manuscript describes the different deep learning techniques, such as convolutional neural networks (CNNs), generative adversarial models (GANs), deep autoencoders (DANs), restricted Boltzmann’s machine (RBM), stacked autoencoders (SAE), convolutional autoencoders (CAE), recurrent neural networks (RNNs), long short-term memory (LTSM), multi-scale convolutional neural network (M-CNN), multi-instance learning convolutional neural network (MIL-CNN). For each technique, we provide Python codes, to allow interested readers to experiment with the cited algorithms on their own diagnostic problems. The third part of this manuscript compiles the successfully applied deep learning models for different types of cancers. Considering the length of the manuscript, we restrict ourselves to the discussion of breast cancer, lung cancer, brain cancer, and skin cancer. The purpose of this bibliographic review is to provide researchers opting to work in implementing deep learning and artificial neural networks for cancer diagnosis a knowledge from scratch of the state-of-the-art achievements.

show abstract

Section: Discussionmentioning

confidence: 99%

Cancer Diagnosis Using Deep Learning: A Bibliographic Review

Munir

Elahi

Ayub

et al. 2019

Cancers

344

182

View full text Add to dashboard Cite

show abstract

“…The results are compared with manually annotated regions and show a good accuracy for benign tissue, and for high-grade and low-grade cancer. Gummeson et al (2017) describe the classification of prostate tissue into classes benign, and Gleason grades 3, 4, 5 with a proprietary network. The training dataset is created by cropping tissue images so that each training image contains only one grade.…”

Section: Related Workmentioning

confidence: 99%

Glandular Segmentation of Prostate Cancer: An Illustration of How the Choice of Histopathological Stain Is One Key to Success for Computational Pathology

Avenel¹,

Tamburini

Dragomir

et al. 2019

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Digital pathology offers the potential for computer-aided diagnosis, significantly reducing the pathologists' workload and paving the way for accurate prognostication with reduced inter-and intra-observer variations. But successful computer-based analysis requires careful tissue preparation and image acquisition to keep color and intensity variations to a minimum. While the human eye may recognize prostate glands with significant color and intensity variations, a computer algorithm may fail under such conditions. Since malignancy grading of prostate tissue according to Gleason or to the International Society of Urological Pathology (ISUP) grading system is based on architectural growth patterns of prostatic carcinoma, automatic methods must rely on accurate identification of the prostate glands. But due to poor color differentiation between stroma and epithelium from the common stain hematoxylin-eosin, no method is yet able to segment all types of glands, making automatic prognostication hard to attain. We address the effect of tissue preparation on glandular segmentation with an alternative stain, Picrosirius red-hematoxylin, which clearly delineates the stromal boundaries, and couple this stain with a color decomposition that removes intensity variation. In this paper we propose a segmentation algorithm that uses image analysis techniques based on mathematical morphology and that can successfully determine the glandular boundaries. Accurate determination of the stromal and glandular morphology enables the identification of the architectural pattern that determine the malignancy grade and classify each gland into its appropriate Gleason grade or ISUP Grade Group. Segmentation of prostate tissue with the new stain and decomposition method has been successfully tested on more than 11000 objects including well-formed glands (Gleason grade 3), cribriform and fine caliber glands (grade 4), and single cells (grade 5) glands.

show abstract

“…Quite a few [25,72,73,94] have utilized deep learning to perform a multimodal registration. Deep learning is also used for the separation of staining colors [3,3,20,39,93] or for registration [10,27,28].…”

Section: Deep Learningmentioning

confidence: 99%

The tempest in a cubic millimeter: Image-based refinements necessitate the reconstruction of 3D microvasculature from a large series of damaged alternately-stained histological sections

Lobachev

2019

Preprint

View full text Add to dashboard Cite

This work presents two methods that facilitate a 3D reconstruction of microscopic blood vessels in the volume slightly larger than 1 mm 3 . The source of the data are histological serial sections, i. e., microscopic images of probes, stained with immunohistochemistry. Odd and even sections have different stainings in our primary data set. Thus, firstly, an approach to register an alternately-stained series is presented. With image filtering and a feature-detection-based registration we obtain a registered stack of 148 serial sections. The series has missing sections, locally damaged sections, artifacts from acquisition. All these hinder correct connectivity of blood vessels. With our second approach we interpolate the missing information while maintaining the connectivity. We achieve this with deformations based on dense optical flow. The presented methodology is applicable to further histological series. A combination of both approaches allows us to reconstruct more than 76 % larger volumes. An important detail was the composition mode of images. Summarizing, we use methods from image processing and computer vision to create large-scale 3D models from immunostained histological serial sections.

show abstract

Automatic Gleason grading of H and E stained microscopic prostate images using deep convolutional neural networks

Cited by 11 publications

References 6 publications

Cancer Diagnosis Using Deep Learning: A Bibliographic Review

Cancer Diagnosis Using Deep Learning: A Bibliographic Review

Glandular Segmentation of Prostate Cancer: An Illustration of How the Choice of Histopathological Stain Is One Key to Success for Computational Pathology

The tempest in a cubic millimeter: Image-based refinements necessitate the reconstruction of 3D microvasculature from a large series of damaged alternately-stained histological sections

Contact Info

Product

Resources

About