Detection and classification of cancer in whole slide breast histopathology images using deep convolutional networks

Geçer, Barış; Aksoy, Selim; Mercan, Ezgi; Shapiro, Linda G.; Weaver, Donald L.; Elmore, Joann G.

doi:10.1016/j.patcog.2018.07.022

Cited by 170 publications

(122 citation statements)

References 36 publications

Supporting

Mentioning

120

Contrasting

Unclassified

Order By: Relevance

“…CNNs, by virtue of their representational power and capacity for capturing structural information, have made such classification and segmentation tasks possible [11,8]. The segmentationbased method in [10] and saliency map-based method in [5] are most similar to our work. Mehta et al [10] developed a CNN-based method for segmenting breast biopsy images that produces a tissue-level segmentation mask for each WSI.…”

Section: Statement Of Problemsupporting

confidence: 54%

“…Furthermore, the discriminative tissue-level segmentation masks produced using Y-Net provide powerful features for diagnosis. Our results suggest that Y-Net is 7% more accurate than state-of-the-art segmentation and saliency-based methods [10,5].…”

Section: Introductionmentioning

confidence: 78%

“…Pathologists (# 44) 70.0 LAB + LBP features [5] 45.0 Segmentation mask [10] 54.5 Saliency map [5] 55.0 (b) Diagnostic classification results Table 2: Comparison with state-of-the-art methods. seg: training Y-Net only for the segmentation task; joint: joint learning for segmentation and classification tasks.…”

Section: (A) Segmentation Resultsmentioning

confidence: 99%

“…The histogram features they extracted from the segmentation masks were used for diagnostic classification. Geçer [5] proposed a saliency-based method for diagnosing cancer in breast biopsy images that identified relevant regions in breast biopsy WSIs to be used for diagnostic classification. Our main contribution in this paper is a method for joint learning of both segmentation and classification.…”

Section: Statement Of Problemmentioning

confidence: 99%

“…Training CNNs directly on whole slide images (WSIs) is difficult due to their massive size. Sliding-window-based approaches for classifying [8,5] and segmenting [11,10] medical images have shown promising results. Segmentation and classification are usually separate steps in automated diagnosis systems.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images

Mehta

Mercan

Bartlett

et al. 2018

Lecture Notes in Computer Science

Self Cite

159

102

View full text Add to dashboard Cite

In this paper, we introduce a conceptually simple network for generating discriminative tissue-level segmentation masks for the purpose of breast cancer diagnosis. Our method efficiently segments different types of tissues in breast biopsy images while simultaneously predicting a discriminative map for identifying important areas in an image. Our network, Y-Net, extends and generalizes U-Net by adding a parallel branch for discriminative map generation and by supporting convolutional block modularity, which allows the user to adjust network efficiency without altering the network topology. Y-Net delivers state-of-the-art segmentation accuracy while learning 6.6× fewer parameters than its closest competitors. The addition of descriptive power from Y-Net's discriminative segmentation masks improve diagnostic classification accuracy by 7% over state-of-the-art methods for diagnostic classification. Source code is available at:

show abstract

Section: Statement Of Problemsupporting

confidence: 54%

Section: Introductionmentioning

confidence: 78%

Section: (A) Segmentation Resultsmentioning

confidence: 99%

Section: Statement Of Problemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images

Mehta

Mercan

Bartlett

et al. 2018

Lecture Notes in Computer Science

Self Cite

159

102

View full text Add to dashboard Cite

show abstract

Artificial Intelligence Algorithms to Assess Hormonal Status From Tissue Microarrays in Patients With Breast Cancer

et al. 2019

View full text Add to dashboard Cite

Key Points Question Can molecular markers of cancer be extracted from tissue morphology as seen in hematoxylin-eosin–stained images? Findings In this diagnostic study of tissue microarray hematoxylin-eosin–stained images from 5356 patients with breast cancer, molecular biomarker expression was found to be significantly associated with tissue histomorphology. A deep learning model was able to predict estrogen receptor expression solely from hematoxylin-eosin–stained images with noninferior accuracy to standard immunohistochemistry. Meaning These results suggest that deep learning models may assist pathologists in molecular profiling of cancer with practically no added cost and time.

show abstract

Assessment of Machine Learning of Breast Pathology Structures for Automated Differentiation of Breast Cancer and High-Risk Proliferative Lesions

et al. 2019

Self Cite

View full text Add to dashboard Cite

IMPORTANCE Following recent US Food and Drug Administration approval, adoption of whole slide imaging in clinical settings may be imminent, and diagnostic accuracy, particularly among challenging breast biopsy specimens, may benefit from computerized diagnostic support tools. OBJECTIVE To develop and evaluate computer vision methods to assist pathologists in diagnosing the full spectrum of breast biopsy samples, from benign to invasive cancer. DESIGN, SETTING, AND PARTICIPANTS In this diagnostic study, 240 breast biopsies from Breast Cancer Surveillance Consortium registries that varied by breast density, diagnosis, patient age, and biopsy type were selected, reviewed, and categorized by 3 expert pathologists as benign, atypia, ductal carcinoma in situ (DCIS), and invasive cancer. The atypia and DCIS cases were oversampled to increase statistical power. High-resolution digital slide images were obtained, and 2 automated image features (tissue distribution feature and structure feature) were developed and evaluated according to the consensus diagnosis of the expert panel. The performance of the automated image analysis methods was compared with independent interpretations from 87 practicing US pathologists. Data analysis was performed between February 2017 and February 2019. MAIN OUTCOMES AND MEASURES Diagnostic accuracy defined by consensus reference standard of 3 experienced breast pathologists. RESULTS The accuracy of machine learning tissue distribution features, structure features, and pathologists for classification of invasive cancer vs noninvasive cancer was 0.94, 0.91, and 0.98, respectively; the accuracy of classification of atypia and DCIS vs benign tissue was 0.70, 0.70, and 0.81, respectively; and the accuracy of classification of DCIS vs atypia was 0.83, 0.85, and 0.80, respectively. The sensitivity of both machine learning features was lower than that of the pathologists for the invasive vs noninvasive classification (tissue distribution feature, 0.70; structure feature, 0.49; pathologists, 0.84) but higher for the classification of atypia and DCIS vs benign cases (tissue distribution feature, 0.79; structure feature, 0.85; pathologists, 0.72) and the classification of DCIS vs atypia (tissue distribution feature, 0.88; structure feature, 0.89; pathologists, 0.70). For the DCIS vs atypia classification, the specificity of the machine learning feature classification was similar to that of the pathologists (tissue distribution feature, 0.78; structure feature, 0.80; pathologists, 0.82). CONCLUSION AND RELEVANCE The computer-based automated approach to interpreting breast pathology showed promise, especially as a diagnostic aid in differentiating DCIS from atypical hyperplasia.

show abstract

Detection and classification of cancer in whole slide breast histopathology images using deep convolutional networks

Cited by 170 publications

References 36 publications

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images

Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images

Artificial Intelligence Algorithms to Assess Hormonal Status From Tissue Microarrays in Patients With Breast Cancer

Assessment of Machine Learning of Breast Pathology Structures for Automated Differentiation of Breast Cancer and High-Risk Proliferative Lesions

Contact Info

Product

Resources

About