Fine-Tuning and training of densenet for histopathology image representation using TCGA diagnostic slides

Riasatian, Abtin; Babaie, Morteza; Maleki, Danial; Kalra, Shivam; Valipour, Mojtaba; Hemati, Sobhan; Zaveri, Manit; Safarpoor, Amir; Shafiei, Sobhan; Afshari, Mehdi; Rasoolijaberi, Maral; Sikaroudi, Milad; Adnan, Mohd Shalahuddin; Shah, Sultaan; Choi, Charles Q.; Damaskinos, Savvas; Campbell, Clinton J. V.; Diamandis, Phedias; Pantanowitz, Liron; Kashani, Hany; Ghodsi, Ali; Tizhoosh, Hamid R.

doi:10.1016/j.media.2021.102032

Cited by 117 publications

(118 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DenseNet-161 has demonstrated a superb performance for ILSVRC ImageNet classification task [ 43 ]. Moreover, DenseNet-161 has shown a great success in several histopathological image analysis pipelines [ 10 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 ]. In order to supply the patch-wise feature extractor network with image patches, we extract a number of patches k based on the following equation [ 7 ]:

where W and H are width and height dimensions of the input image, respectively.…”

Section: Proposed 3e-net Modelmentioning

confidence: 99%

3E-Net: Entropy-Based Elastic Ensemble of Deep Convolutional Neural Networks for Grading of Invasive Breast Carcinoma Histopathological Microscopic Images

Senousy

Abdelsamea

Mohamed

et al. 2021

Entropy

View full text Add to dashboard Cite

Automated grading systems using deep convolution neural networks (DCNNs) have proven their capability and potential to distinguish between different breast cancer grades using digitized histopathological images. In digital breast pathology, it is vital to measure how confident a DCNN is in grading using a machine-confidence metric, especially with the presence of major computer vision challenging problems such as the high visual variability of the images. Such a quantitative metric can be employed not only to improve the robustness of automated systems, but also to assist medical professionals in identifying complex cases. In this paper, we propose Entropy-based Elastic Ensemble of DCNN models (3E-Net) for grading invasive breast carcinoma microscopy images which provides an initial stage of explainability (using an uncertainty-aware mechanism adopting entropy). Our proposed model has been designed in a way to (1) exclude images that are less sensitive and highly uncertain to our ensemble model and (2) dynamically grade the non-excluded images using the certain models in the ensemble architecture. We evaluated two variations of 3E-Net on an invasive breast carcinoma dataset and we achieved grading accuracy of 96.15% and 99.50%.

show abstract

where W and H are width and height dimensions of the input image, respectively.…”

Section: Proposed 3e-net Modelmentioning

confidence: 99%

3E-Net: Entropy-Based Elastic Ensemble of Deep Convolutional Neural Networks for Grading of Invasive Breast Carcinoma Histopathological Microscopic Images

Senousy

Abdelsamea

Mohamed

et al. 2021

Entropy

View full text Add to dashboard Cite

show abstract

“…Deep feature vectors were used for tissue source classi cation in order to verify whether such bias affects what deep neural networks learn from training data, or in other words whether some supposedly irrelevant clues in data would mislead the network. Deep features were extracted from WSIs by the KimiaNet proposed by Riasatian et al 19 It is important to note that the feature extractor network employed had been trained for cancer subtype classi cation and not for source site detection. On average, to represent tissue samples, KimiaNet uses approximately 55 tissue patches per WSI through clustering the tissue samples in different groups.…”

Section: Resultsmentioning

confidence: 99%

Biased Data, Biased AI: Deep Networks Predict the Acquisition Site of TCGA Images

Dehkharghanian

Bidgoli

Riasatian

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning models applied to healthcare applications including digital pathology have been increasing their scope and importance in recent years. Many of these models have been trained on The Cancer Genome Atlas (TCGA) atlas of digital images, or use it as a validation source. This study shows that there are tissue source site (tss) specific patterns of TCGA images that could be used to identify contributing institutions without any explicit training. Furthermore, it was observed that a model trained for cancer subtype classification has discovered such tss specific patterns within digital slides to classify cancer types. Digital scanner configuration and noise, tissue stain variation and artifacts, and source site patient demographics are among factors that likely account for the observed bias. Therefore, researchers should be cautious of such bias when using histopathology datasets for developing and training deep networks.

show abstract

“…KimiaNet 22 borrowed DenseNet's topology with four dense blocks 28 for the purpose of becoming a domain specific feature extractor for histopathologic images. Technical details regarding KimiaNet development, validation and application have been previously published.…”

Section: Kimianet Dnnmentioning

confidence: 99%

“…Technical details regarding KimiaNet development, validation and application have been previously published. 22 This network was trained to classify 30 cancer types based upon the TCGA dataset using tissue patches of size 1000 by 1000 pixels at 20x magnification. KimiaNet achieved 86% accuracy when used for image search in lung cancer images of TCGA data.…”

Section: Kimianet Dnnmentioning

confidence: 99%

See 1 more Smart Citation

Selection, Visualization, and Interpretation of Deep Features in Lung Adenocarcinoma and Squamous Cell Carcinoma

Dehkharghanian

Rahnamayan

Riasatian

et al. 2021

The American Journal of Pathology

Self Cite

View full text Add to dashboard Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

show abstract

Fine-Tuning and training of densenet for histopathology image representation using TCGA diagnostic slides

Cited by 117 publications

References 25 publications

3E-Net: Entropy-Based Elastic Ensemble of Deep Convolutional Neural Networks for Grading of Invasive Breast Carcinoma Histopathological Microscopic Images

3E-Net: Entropy-Based Elastic Ensemble of Deep Convolutional Neural Networks for Grading of Invasive Breast Carcinoma Histopathological Microscopic Images

Biased Data, Biased AI: Deep Networks Predict the Acquisition Site of TCGA Images

Selection, Visualization, and Interpretation of Deep Features in Lung Adenocarcinoma and Squamous Cell Carcinoma

Contact Info

Product

Resources

About