Patch-based system for Classification of Breast Histology images using deep learning

Roy, Kaushiki; Banik, Debapriya; Bhattacharjee, Debotosh; Nasipuri, Mita

doi:10.1016/j.compmedimag.2018.11.003

Cited by 160 publications

(115 citation statements)

References 15 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…Nawaz, W., et al [28] 75.73 -Golatkar, A., et al [64] 79 85 Mahbod A., et al [29] -88.5 Roy, K., et al [65] 77.4 90 Wang, Z., et al [42] 87 92 Ferreira, C. A., et al [66] -93 Our model with Experiment 4 (same domain transfer Learning) 90.5 97.4…”

Section: Methods Patch-wise (%) Image-wise (%)mentioning

confidence: 95%

Optimizing the Performance of Breast Cancer Classification by Employing the Same Domain Transfer Learning from Hybrid Deep Convolutional Neural Network Model

et al. 2020

View full text Add to dashboard Cite

Breast cancer is a significant factor in female mortality. An early cancer diagnosis leads to a reduction in the breast cancer death rate. With the help of a computer-aided diagnosis system, the efficiency increased, and the cost was reduced for the cancer diagnosis. Traditional breast cancer classification techniques are based on handcrafted features techniques, and their performance relies upon the chosen features. They also are very sensitive to different sizes and complex shapes. However, histopathological breast cancer images are very complex in shape. Currently, deep learning models have become an alternative solution for diagnosis, and have overcome the drawbacks of classical classification techniques. Although deep learning has performed well in various tasks of computer vision and pattern recognition, it still has some challenges. One of the main challenges is the lack of training data. To address this challenge and optimize the performance, we have utilized a transfer learning technique which is where the deep learning models train on a task, and then fine-tune the models for another task. We have employed transfer learning in two ways: Training our proposed model first on the same domain dataset, then on the target dataset, and training our model on a different domain dataset, then on the target dataset. We have empirically proven that the same domain transfer learning optimized the performance. Our hybrid model of parallel convolutional layers and residual links is utilized to classify hematoxylin–eosin-stained breast biopsy images into four classes: invasive carcinoma, in-situ carcinoma, benign tumor and normal tissue. To reduce the effect of overfitting, we have augmented the images with different image processing techniques. The proposed model achieved state-of-the-art performance, and it outperformed the latest methods by achieving a patch-wise classification accuracy of 90.5%, and an image-wise classification accuracy of 97.4% on the validation set. Moreover, we have achieved an image-wise classification accuracy of 96.1% on the test set of the microscopy ICIAR-2018 dataset.

show abstract

Section: Methods Patch-wise (%) Image-wise (%)mentioning

confidence: 95%

Optimizing the Performance of Breast Cancer Classification by Employing the Same Domain Transfer Learning from Hybrid Deep Convolutional Neural Network Model

et al. 2020

View full text Add to dashboard Cite

show abstract

“…They improved the classification accuracy on this dataset from 68.6 to 85.6 for estrogen receptor (ER) task in breast images. Recently, MIL has also been used for breast cancer classification in [239] and [240]…”

Section: Breastmentioning

confidence: 99%

Going Deep in Medical Image Analysis: Concepts, Methods, Challenges, and Future Directions

et al. 2019

View full text Add to dashboard Cite

Medical Image Analysis is currently experiencing a paradigm shift due to Deep Learning. This technology has recently attracted so much interest of the Medical Imaging community that it led to a specialized conference in 'Medical Imaging with Deep Learning' in the year 2018. This article surveys the recent developments in this direction, and provides a critical review of the related major aspects. We organize the reviewed literature according to the underlying Pattern Recognition tasks, and further sub-categorize it following a taxonomy based on human anatomy. This article does not assume prior knowledge of Deep Learning and makes a significant contribution in explaining the core Deep Learning concepts to the non-experts in the Medical community. Unique to this study is the Computer Vision/Machine Learning perspective taken on the advances of Deep Learning in Medical Imaging. This enables us to single out 'lack of appropriately annotated large-scale datasets' as the core challenge (among other challenges) in this research direction. We draw on the insights from the sister research fields of Computer Vision, Pattern Recognition and Machine Learning etc.; where the techniques of dealing with such challenges have already matured, to provide promising directions for the Medical Imaging community to fully harness Deep Learning in the future.

show abstract

“…Como exemplos de estruturas acidófilas podemos citar o citoplasma celular (também chamado de citosol) e as mitocôndrias [Kumar et al 2016]. Já a Hematoxilina, corante de tom azulado, tem caráter básico e carga positiva (catiônico), corando estruturas celulares de caráteŕ acido denominados basófilos [Roy et al 2019]. Como exemplo de estrutura basófila podemos citar o próprio núcleo celular, queé composto pelos seus grupamentosácidos.…”

Section: Histopatologia Aplicada Ao Câncer De Mamaunclassified

“…Contudo os processos de preparação, coloração e digitalização de lâminas de tecidos podem sofrer com fixações inadequadas, que podem gerar alterações na morfologia do tecido e induzir a morfometria incorreta desse tecido pela análise de imagens [Roy et al 2019]. Outra dificuldade encontrada são seções que não foram adequadamente coradas (podendo ser essas super ou sub-manchadas) e montadas, isto poderá resultar em regiões fora de foco e/ou peças ausentes [Li et al 2018].…”

Section: Histopatologia Aplicada Ao Câncer De Mamaunclassified

“…As seções de tecido coletadas daárea suspeita são geralmente coradas com Hematoxilina e Eosina (H&E) [Roy et al 2019]. A hematoxilinaé responsável pela coloração do DNA do núcleo celular, do RNA do citoplasma e da cartilagem, produzindo uma cor azulada nas estruturas [Roy et al 2019]. Enquanto a eosina tinge estruturas do citoplasma e o colágeno de tons rosas [Yan et al 2019].…”

Section: Introductionunclassified

See 1 more Smart Citation

Análise comparativa da influência dos espaços de cores na segmentação multi-classe de Whole Slide Imaging do câncer de mama utilizando deep learning

Zeiser¹,

Costa²,

Ramos³

et al. 2020

Anais Principais Do Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2020)

View full text Add to dashboard Cite

O diagnóstico em estágios iniciais normalmente resulta em um prognóstico melhor nos casos de câncer. Atualmente, a análise histopatológica e o padrão ouro para o diagnóstico, estadiamento e definição do tratamento de neoplasias de mama. Contudo, a técnica possui algumas restrições que dificultam o processo de análise pelo patologista, como diferentes protocolos de coloração, variações de coloração nas lâminas, e sobreposição de tecidos. Assim, a representação computacional das cores pode exercer uma influência significativa no comportamento dos modelos convolucionais. Desta forma, este estudo propõe uma análise comparativa da influência de quatro espaços de cores (RGB, HSV, YCrCb e LAB) para a segmentação multi-classe de Whole Slide Imaging (WSI) do câncer de mama. A metodologia proposta e composta por uma etapa de pré-processamento das WSI, data augmentation e multi- segmentação utilizando a arquitetura convolucional U-Net com uma ResNet-50 pré-treinada como codificador. Os resultados obtidos demonstram que o espaço de cores HSV apresentou de maneira geral índices melhores para a segmentação das WSI utilizando a metodologia proposta neste estudo.

show abstract

Patch-based system for Classification of Breast Histology images using deep learning

Cited by 160 publications

References 15 publications

Optimizing the Performance of Breast Cancer Classification by Employing the Same Domain Transfer Learning from Hybrid Deep Convolutional Neural Network Model

Optimizing the Performance of Breast Cancer Classification by Employing the Same Domain Transfer Learning from Hybrid Deep Convolutional Neural Network Model

Going Deep in Medical Image Analysis: Concepts, Methods, Challenges, and Future Directions

Análise comparativa da influência dos espaços de cores na segmentação multi-classe de Whole Slide Imaging do câncer de mama utilizando deep learning

Contact Info

Product

Resources

About