Deep Learning in Digital Pathology
Posted 2nd February 2018 by Jane Williams
“Deep Learning is an algorithm which has no theoretical limitations of what it can learn; the more data you give and the more computational time you provide, the better it is” – Geoffrey Hinton (Google)
The revolutionary step of tissue glass slide digitisation has opened up exciting possibilities in the world of digital pathology. We have seen gradual evolution over the years aimed at reducing manual intervention and automating digital pathology workflow. In the initial phase of digital pathology, traditional computer vision methodologies which were more suited for radiology were used for tissue detection, segmentation, morphometry etc. The main challenges for getting accurate interpretations were:
- Variability in staining of slides
- Slide preparation
- Different makes of scanners available in the market
The limited information from pixel intensity space was insufficient for reliable and consistent outputs. Moreover, the domain experts give their interpretations based on years of knowledge and experience which was needed to be captured in the image processing tools. The complexity and variety of the image analysis problems necessitated the use of machine learning techniques to solve these problems.
The supervised machine learning approach to solving the image analysis problems is to train a statistical model using a set of training images labelled as ground truth by domain experts. The model maps the features computed by image analysis algorithms to the output labels.
Efficient image analysis algorithms have been researched and developed for image analysis modules, including image pre-processing to improve initial image quality and segmentation techniques for detecting foreground objects. Other issues such as staining variation have been handled by stain normalisation techniques (colour normalisation from photography), such as histogram equalisation. Additional techniques like colour deconvolution, separates components of histological stains (DAB, AEC, H&E) as they cannot be easily separated by splitting into the red, green and blue channels recorded by colour cameras.
However, feature engineering is a crucial aspect of conventional machine learning techniques. Traditional handcrafted features rely heavily on domain expertise of pathologists and clinicians. Finding the informative, discriminative and independent set of features for training the machine learning model is complex. Sometimes it is difficult to explicitly define a feature which can be interpreted and intuitive to the user and the domain experts. Since most of the features are derived from pixel intensity space, they are not invariant to differences to the input images and the staining variations.
With the advancements in digital pathology, high volume of quality digitised data is available for the algorithm developers, scientists and pathologists around the world. Integration of telepathology in clinician’s workflow has resulted in greater collaborative work. With the advent of cloud computing and high-end processors computing, resources are available like never before. The environment is conducive to a novel approach to image analysis problems in digital pathology, known as deep learning, a learning system with multi-layered neural network architectures.
We saw the limitations of handcrafted features with conventional machine learning approaches. Deep learning takes feature engineering to the next level by automating feature engineering. There are deep learning methodologies to directly learn from the raw data and map to the intended goals. The combination of handcrafted features and the deep learning discovered features can lead to reproducible and accurate results for problems related either to prediction or classification. The system could be partially supervised in the sense that the initial training is done with the labelled ground truth and then the system uses this training for unsupervised learning.
However, some deep learning algorithms can become computationally-expensive when dealing with high-dimensional image data, due to the often slow learning process associated with a hierarchy of learning data abstractions and representations between layers. Convolutional neural networks effectively scale up high-dimensional data.
The development of convoluted neural networks (modelled on the human brain) as a deep network for analysing and classifying image patterns have revolutionised medical imaging through deep learning. According to studies [Janowczyk et al. 2016], CNNs are the basis of some recent outstanding breakthroughs in the analysis of digital pathology images with applications (mitosis detection, nucleus segmentation, gland segmentation, and metastasis detection).
Fusion of modalities for better predictive modelling could be an application area of deep learning-based algorithms. Content-based image retrieval for research and diagnostic purposes utilising the vast digitised databases could be another application area.
Despite the possibilities presented by CNN and deep learning algorithms in general, they have some limitations which are being overcome:
- Deep learning requires huge amounts of training data
- Deep learning requires extensive computing power
- Architectures can be complex and must often be highly tailored to a specific application
- The resulting models may not be easily interpretable
Field-programmable gate arrays (FPGAs), graphic processor units (GPUs) and application-specific integrated circuits (ASICs) are being explored to exploit the parallelism of the computational structure of neural networks, more so than the CPUs in parallel.
Besides the training time, the major problem of these networks is the overfitting domains which offer very small amounts of data. Many regularisation methods are being developed to prevent overfitting.
Drawbacks are being addressed as the possibilities are mind-boggling with the application of deep learning in digital pathology.
This article was written by Guru Kamble, the Head of Imaging at OptraScan. OptraScan work on introducing affordable solutions to improve the performance of pathology services.
If you liked this post, check out ‘Selecting the Right Digital Pathology System‘ by Anil Parwani.
2 Responses to “Deep Learning in Digital Pathology”
Leave a Reply
Seems to be written by a pro… very informative article !!!