Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis

Rakhlin, Alexander; Shvets, Alexey A.; Iglovikov, Vladimir I.; Kalinin, Alexandr A.

doi:10.1101/259911

Cited by 107 publications

(129 citation statements)

References 19 publications

Supporting

Mentioning

126

Contrasting

Unclassified

Order By: Relevance

“…The size of the produced 3D morphological dataset should be big enough to use segmentation-free deep learning-based morphology analysis approaches [5,15]. Recent examples in medical image analysis have already demonstrated successful applications of such models in the small data regime [13,26]. Finally, we assume each cell in the same image to be representative of the same phenotypic label that is provided on the level of the whole image.…”

Section: Discussionmentioning

confidence: 99%

3D Cell Nuclear Morphology: Microscopy Imaging Dataset and Voxel-Based Morphometry Classification Results

Kalinin

Allyn-Feuer

Ade

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

Cell deformation is regulated by complex underlying biological mechanisms associated with spatial and temporal morphological changes in the nucleus. Quantitative analysis of changes in size and shape of nuclear structures in 3D microscopic images is important not only for investigating nuclear organization, but also for detecting and treating pathological conditions such as cancer. Multiple methods have been proposed to classify cell and nuclear morphological phenotypes in 3D, however, there is a lack of publicly available 3D data for the evaluation and comparison of such algorithms. To address this problem, we present a dataset containing a of total of 1,433 segmented nuclear and 3,282 nucleolar binary masks. We also provide a baseline evaluation of a number of popular classification algorithms using voxel-based morphometric measures. Original and derived imaging data are made publicly available for downloading on the project web-page: http://www.socr.umich.edu/ projects/3d-cell-morphometry/data.html.

show abstract

Section: Discussionmentioning

confidence: 99%

3D Cell Nuclear Morphology: Microscopy Imaging Dataset and Voxel-Based Morphometry Classification Results

Kalinin

Allyn-Feuer

Ade

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…1,2 Research interest in applying deep-learning and morphometry to diagnostic medicine has increased exponentially in recent years and many compelling results have been reported. [4][5][6][7][8][9][10][11] Early applications of machine learning have already entered clinical use in cytopathology (BD FocalPoint; Becton, Dickinson and Company, Franklin Lakes, NJ). 12 Because the Paris System criteria are partially objective (N:C ratio calculation) and partially subjective (nuclear atypia/irregularity/hyperchromasia), we determined that a hybrid approach would be required for automation.…”

Section: Cancer Cytopathology February 2019mentioning

confidence: 99%

Automating the Paris System for urine cytopathology—A hybrid deep‐learning and morphometric approach

Vaickus

Suriawinata

Wei

et al. 2019

Cancer Cytopathology

103

View full text Add to dashboard Cite

Background The Paris System for Urine Cytopathology (the Paris System) has succeeded in making the analysis of liquid‐based urine preparations more reproducible. Any algorithm seeking to automate this system must accurately estimate the nuclear‐to‐cytoplasmic (N:C) ratio and produce a qualitative “atypia score.” The authors propose a hybrid deep‐learning and morphometric model that reliably automates the Paris System. Methods Whole‐slide images (WSI) of liquid‐based urine cytology specimens were extracted from 51 negative, 60 atypical, 52 suspicious, and 54 positive cases. Morphometric algorithms were applied to decompose images to their component parts; and statistics, including the NC ratio, were tabulated using segmentation algorithms to create organized data structures, dubbed rich information matrices (RIMs). These RIM objects were enhanced using deep‐learning algorithms to include qualitative measures. The augmented RIM objects were then used to reconstruct WSIs with filtering criteria and to generate pancellular statistical information. Results The described system was used to calculate the N:C ratio for all cells, generate object classifications (atypical urothelial cell, squamous cell, crystal, etc), filter the original WSI to remove unwanted objects, rearrange the WSI to an efficient, condensed‐grid format, and generate pancellular statistics containing quantitative/qualitative data for every cell in a WSI. In addition to developing novel techniques for managing WSIs, a system capable of automatically tabulating the Paris System criteria also was generated. Conclusions A hybrid deep‐learning and morphometric algorithm was developed for the analysis of urine cytology specimens that could reliably automate the Paris System and provide many avenues for increasing the efficiency of digital screening for urine WSIs and other cytology preparations.

show abstract

“…Comparing this performance to previous work, we note that in one study of histopathology images [42], classification performance reached 81.14% accuracy using the extracted features from a pre-trained VGG 19 (similar to VGG 16) network. In a similar study of histopathological images of breast cancer [43], classification performance on 400 HE-stained images of 2048 1536 pixels each reached an AUC of 0.963 for distinguishing between non-carcinomas vs. carcinomas samples. In our study, we have larger histopathological images with median 5601 x 2249.5 pixels indicating more sample information which may explain the better performance.…”

Section: Discussionmentioning

confidence: 88%

Prognostic Analysis of Histopathological Images Using Pre-Trained Convolutional Neural Networks

Daigle

2019

Preprint

View full text Add to dashboard Cite

Background: Histopathological images contain rich phenotypic descriptions of the molecular processes underlying disease progression. Convolutional neural networks (CNNs), a state-of-the-art image analysis technique in computer vision, automatically learns representative features from such images which can be useful for disease diagnosis, prognosis, and subtyping. Despite hepatocellular carcinoma (HCC) being the sixth most common type of primary liver malignancy with a high mortality rate, little previous work has made use of CNN models to delineate the importance of histopathological images in diagnosis and clinical survival of HCC. Results:We applied three pre-trained CNN models -VGG 16, Inception V3, and ResNet 50 -to extract features from HCC histopathological images. The visualization and classification showed clear separation between cancer and normal samples using image features. In a univariate Cox regression analysis, 21.4% and 16% of image features on average were significantly associated with overall survival and disease-free survival, respectively. We also observed significant correlations between these features and integrated biological pathways derived from gene expression and copy number variation. Using an elastic net regularized CoxPH model of overall survival, we obtained a concordance index (C-index) of 0.789 and a significant log-rank test (p = 7.6E-18) after applying Inception image features. We also performed unsupervised classification to identify HCC subgroups from image features. The optimal two subgroups discovered using Inception image features were significantly associated with both overall (C-index = 0.628 and p = 7.39E-07) and disease-free survival (C-index = 0.558 and p = 0.012). Our results suggest the feasibility of feature extraction using pre-trained models, as well as the utility of the resulting features to build an accurate prognosis model of HCC and highlight significant correlations with clinical survival and biological pathways. Conclusions:The image features extracted from HCC histopathological images using the pre-trained CNN models VGG 16, Inception V3 and ResNet 50 can accurately distinguish normal and cancer samples. Furthermore, these image features are significantly correlated with relevant biological outcomes.

show abstract

Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis

Cited by 107 publications

References 19 publications

3D Cell Nuclear Morphology: Microscopy Imaging Dataset and Voxel-Based Morphometry Classification Results

3D Cell Nuclear Morphology: Microscopy Imaging Dataset and Voxel-Based Morphometry Classification Results

Automating the Paris System for urine cytopathology—A hybrid deep‐learning and morphometric approach

Prognostic Analysis of Histopathological Images Using Pre-Trained Convolutional Neural Networks

Contact Info

Product

Resources

About