Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology

Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

doi:10.1016/j.compmedimag.2017.06.001

Cited by 274 publications

(163 citation statements)

References 22 publications

Supporting

Mentioning

159

Contrasting

Unclassified

Order By: Relevance

“…It seems that the deeper and more complex structures of CNN have great potential to deal with unbalanced data problems. In this work, we developed complete detection and classification algorithms for M. tuberculosis identification using microscopy images. In further study, we will spread the system to other pathological image classifications such as gastric carcinoma (Sharma, Zerbe, Klempert, Hellwich, & Hufnagl, ) and hepatocellular carcinoma nuclei grading (Li, Jiang, & Pang, ).…”

Section: Resultsmentioning

confidence: 99%

An effective and accurate identification system of Mycobacterium tuberculosis using convolution neural networks

Kuok

Horng

Liao

et al. 2019

Microscopy Res & Technique

View full text Add to dashboard Cite

Tuberculosis (TB) remains the leading cause of morbidity and mortality from infectious disease in developing countries. The sputum smear microscopy remains the primary diagnostic laboratory test. However, microscopic examination is always time‐consuming and tedious. Therefore, an effective computer‐aided image identification system is needed to provide timely assistance in diagnosis. The current identification system usually suffers from complex color variations of the images, resulting in plentiful of false object detection. To overcome the dilemma, we propose a two‐stage Mycobacterium tuberculosis identification system, consisting of candidate detection and classification using convolution neural networks (CNNs). The refined Faster region‐based CNN was used to distinguish candidates of M. tuberculosis and the actual ones were classified by utilizing CNN‐based classifier. We first compared three different CNNs, including ensemble CNN, single‐member CNN, and deep CNN. The experimental results showed that both ensemble and deep CNNs were on par with similar identification performance when analyzing more than 19,000 images. A much better recall value was achieved by using our proposed system in comparison with conventional pixel‐based support vector machine method for M. tuberculosis bacilli detection.

show abstract

Section: Resultsmentioning

confidence: 99%

An effective and accurate identification system of Mycobacterium tuberculosis using convolution neural networks

Kuok

Horng

Liao

et al. 2019

Microscopy Res & Technique

View full text Add to dashboard Cite

show abstract

“…This is directly followed by max pooling with window size of (2, 2), and identically sized strides. The output from this part is of size (16,16,64), where the values are: reduced width, reduced height and the number of filters. These operations decrease the spatial dimensions by a factor of 8, which in turn significantly reduces memory usage and can be considered an adaptation of network topology to a relatively simple texture structure of the input 51 .…”

Section: Network Architecturementioning

confidence: 99%

“…Since 2012, when the groundbreaking AlexNet was created by Alex Krizevsky 6 , the state of the art has rapidly shifted from machine learning algorithms using manual feature engineering (henceforth referred to as 'traditional' machine learning approaches) to new deep learning ones 7 . Medical imaging in general [8][9][10][11][12] , and histopathological image classification in particular [13][14][15][16][17][18][19][20] , became important applications of these methods. Multiple machine learning methods go beyond the tasks of tissue type classification and whole-slide segmentation, confirming there is more information about the patients encrypted in histopathological images than immediately visible by eye 5 .…”

Section: Introductionmentioning

confidence: 99%

ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning

Rączkowski

Możejko

Zambonelli

et al. 2019

Preprint

View full text Add to dashboard Cite

Machine learning algorithms hold the promise to effectively automate the analysis of histopathological images that are routinely generated in clinical practice. Any machine learning method used in the clinical diagnostic process has to be extremely accurate and, ideally, provide a measure of uncertainty for its predictions. Such accurate and reliable classifiers need enough labelled data for training, which requires time-consuming and costly manual annotation by pathologists. Thus, it is critical to minimise the amount of data needed to reach the desired accuracy by maximising the efficiency of training. We propose an accurate, reliable and active (ARA) image classification framework and introduce a new Bayesian Convolutional Neural Network (ARA-CNN) for classifying histopathological images of colorectal cancer. The model achieves exceptional classification accuracy, outperforming other models trained on the same dataset. The network outputs an uncertainty measurement for each tested image. We show that uncertainty measures can be used to detect mislabelled training samples and can be employed in an efficient active learning workflow. Using a variational dropout-based entropy measure of uncertainty in the workflow speeds up the learning process by roughly 45%. Finally, we utilise our model to segment whole-slide images of colorectal tissue and compute segmentation-based spatial statistics.

show abstract

“…AlexNet has been used widely recently as a feature extractor in areas such as mineral processing [21], medical image analysis [22,23], audio processing [24], text analysis [25], botany [26], and remote sensing [27].…”

Section: Alexnetmentioning

confidence: 99%

Predicting the Operating States of Grinding Circuits by Use of Recurrence Texture Analysis of Time Series Data

2018

View full text Add to dashboard Cite

Abstract:Grinding circuits typically contribute disproportionately to the overall cost of ore beneficiation and their optimal operation is therefore of critical importance in the cost-effective operation of mineral processing plants. This can be challenging, as these circuits can also exhibit complex, nonlinear behavior that can be difficult to model. In this paper, it is shown that key time series variables of grinding circuits can be recast into sets of descriptor variables that can be used in advanced modelling and control of the mill. Two real-world case studies are considered. In the first, it is shown that the controller states of an autogenous mill can be identified from the load measurements of the mill by using a support vector machine and the abovementioned descriptor variables as predictors. In the second case study, it is shown that power and temperature measurements in a horizontally stirred mill can be used for online estimation of the particle size of the mill product.

show abstract

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology

Cited by 274 publications

References 22 publications

An effective and accurate identification system of Mycobacterium tuberculosis using convolution neural networks

An effective and accurate identification system of Mycobacterium tuberculosis using convolution neural networks

ARA: accurate, reliable and active histopathological image classification framework with Bayesian deep learning

Predicting the Operating States of Grinding Circuits by Use of Recurrence Texture Analysis of Time Series Data

Contact Info

Product

Resources

About