Deep Learning

19 Dec 2019


2020-02-24T18:55:44+02:00Categories: Deep Learning|Tags: , , , |0 Comments

Deep Learning technology is changing the lives of millions of people all over the world. Deep Learning is technology that transfers artificial intelligence to a new generation thanks to its results and new applications: from natural language recognition to translation systems, including control systems in series (manufacturing processes), and artificial vision. Due to its great potential, many companies are planning large investments in advanced manufacturing and artificial intelligence. In the US over 70% of companies have invested in this technology or plan to do so. The implementation of Deep Learning will help to resolve problems by achieving results that were previously impossible to achieve. It is capable of changing the lives of millions of people all around the world, and its application covers several areas and sectors of activity – from industry 4.0 to personalised medicine, including precision agriculture, optimisation of energy consumption and recycling. At TECNALIA [...]

31 Oct 2019


2019-12-10T19:05:24+02:00Categories: Deep Learning|Tags: , , , |0 Comments

Deep learning diagnostic algorithms are proving comparable results with human experts in a wide variety of tasks, they still require a huge amount of well annotated data for training which is often non-affordable. Metric learning techniques have allowed a reduction on the required annotated data allowing few-shot learning. Existing deep metric learning loss functions have made possible generating models capable of tackling complex scenarios with the presence of many classes and scarcity on the number of images per class, not only work for classification tasks, but to many other clinical applications where measuring similarity is the key. Currently used state-of-the-art loss functions still suffer from slow convergence due to the selection of effective training samples that has been partially solved by the multi-class N-pair loss by simultaneously adding additional samples from the different classes. The constellation loss goes one step further by simultaneously learning distances [...]

11 Jul 2019

ISBI 2019

2019-10-11T11:48:32+02:00Categories: Deep Learning|0 Comments

Last April 8th-11th took place the IEEE International Symposium on Biomedical Imaging (ISBI), a scientific conference dedicated to mathematical, algorithmic, and computational aspects of biological and biomedical imaging, across all scales of observation. The member of piccolo team and Tecnalia Research & Innovation, Alfonso Medela, presented the paper “Few-shot learning in histopathological images: reducing the need of labelled data on biological datasets”. The team has been working on a few-shot approach in parallel with the acquisition of the datasets. To overcome the problem of scarce data in new imaging modalities such as OCT and MPT, few-shot techniques provide a solution to create algorithms out of a small number of images. The results showed that by using the proposed method it is possible to beat classical transfer-learning approach when only few images per class are available. The results encouraged the team to continue working on the same track and as [...]

8 Aug 2018

Siamese Neural Networks

2019-10-25T11:20:16+02:00Categories: Deep Learning|Tags: , , |1 Comment

Siamese networks were first introduced by Bromley and LeCun [1] in early 1990s to solve signature verification as an image matching problem. A similar Siamese architecture was independently proposed for fingerprint identification by Baldi and Chauvin [2] in 1992.  Later in 2015, Gregory Koch et al. [3] proposed to use Siamese neural networks for one-shot image recognition. Siamese neural networks are designed as two twin networks that are connected by their final layer by means of a distance layer that is trained to predict whether two images belong to the same category or not. The networks that compose the siamese architecture are called twins because all the weights and biases are tied, which means that both networks are symmetric. Symmetry is important as the network should be invariant to switching the input images. Moreover, this characteristic makes the networks much faster to train since the number of [...]

24 May 2018

Optical biopsy for the early diagnosis of skin cancer based on images

2019-10-25T11:26:40+02:00Categories: Deep Learning, Photonics|Tags: , , , , , , , |0 Comments

Currently, the analysis of a suspicious skin lesions is done through biopsy, a process than usually takes several weeks until the definitive diagnosis is obtained. This means high personal costs, due to the uncertainty during the wait, and high economical costs to the health system, attributable to the cost of the procedure and consequent visits to the physician. Besides, the incidence of melanoma has nearly doubled in the last 10 years in the Basque Country and is growing at 10% rate per year in Spain. The 23th of May is the World Melanoma day. Tecnalia works in collaboration with the University of the Basque Country, Ibermática and NorayBio on the development of a computer aided diagnosis tool (CAD) for the early diagnosis of melanoma and basal cell carcinoma (BCC) based on images and clinical data. Molecular data related to prognosis is also being studied, as it can help to define [...]

20 Mar 2018


2019-10-25T13:20:00+02:00Categories: Deep Learning|Tags: , , |0 Comments

The correct analysis and quantification of images is fundamental in the biological and medical fields of science. Examples of images used in the medical field are X-rays, tomography, biopsies, PET and pathology images. The biological field also employs images, such as similar vegetable images and the detection and quantifying of cell anomalies. The analysis of these images is linked to the subjectivity of a person, the onset of new techniques, as well as the associated learning curve. BIOSIMIL (Automated system for similar image searches in medical image databases) is a development line that allows for an automated search of similar images based on image features (texture, colour, distribution, etc.) in large databases.The aim is to make available new processing tools for these types of images which can be applied to several fields, such as training with a quicker learning curve, or in the field of research, with faster and [...]

27 Apr 2017


2019-10-29T16:18:20+02:00Categories: Deep Learning|Tags: , |0 Comments

The digitalization of medical images has allowed in recent years the automation of many tasks with the aim of supporting the clinicians in his diagnostic work. Histological images, obtained through tissue samples, have also been digitized thanks to the powerful scanning microscopes available on the market, which are gradually adopted by the pathological anatomy services in hospitals. In this context, software packages that facilitate the daily operation of pathologists emerge. The Computer Vision group in Tecnalia is currently working in diagnosis support systems for the pathologists, such as the histological images search engine based on similar visual content and clinical relevance, which deserved 1st EARTO Innovation Prize in 2014. Under this strategic approach, one of the most tedious tasks that pathologists must perform is mitosis counting in a tissue sample that turns out to be tumoral. The lower or higher proliferation of mitosis in a tissue is one of [...]

6 Oct 2016

Convolutional neural networks make Tecnalia’s SURFIN Hot surface inspection® system evolve to assure automatic quality control

2019-10-25T13:20:14+02:00Categories: Deep Learning, Quality Control|Tags: , , , , , , , |0 Comments

Tecnalia has presented the new version of its SURFIN Hot surface inspection® system at the First European Machine Vision Forum of the European Machine Vision Association (EMVA). SURFIN performs in-line real-time detection and classification of surface defects (e.g. roll marks, cracks, etc.) from the manufacturing process of metallic products such as bars, tubes, billets, slabs, beam blanks or structural profiles. The systems are installed in the production line. It can detect defects at the early stages in the production process, when the product is still incandescent (>1000ºC). This allows preventing the unnecessary addition of value to it and having traceability of all the production, allowing a preemptive maintenance due to the information it obtains. The system is based on special 2D imaging with laser or LED-based imaging, and makes use of machine learning techniques. SURFIN has been upgraded by replacing the previous detection and classification module –supported by opaque handcrafted [...]