It is rewarding that a project you have been involved and have given birth has been awarded by an European Prize. In this case, Tecnalia has been awarded for the development of a histological image based search engine that is able to extract and capture the visual information that is clinically relevant.

This is really useful for biomedical researchers that need to access biological tissue samples that are stored in biobanks among the world. This search allows them locate candidate tissues by means of their visual appearance as you can see in this video:

The system analyzes the histological images and extracts the subtle architectural, textural and morphological features that are inherently included on an image. It is noteworthy that each of this histological images consists of a pyramidal ‘google maps similar structure’ that describes each tissue. This image can weight more that 2GB. Biosimil extract relevant information from the image describing the discriminative patterns and thus, reducing a 2GB image into a small one dimensional vector. This vector is indexed on a large scalable database for similarity search… as you can note, euclidean distance is not the most suitable measurement of similarity among these vectors… we will discuss about this another day…

It is still lot of work to do, improvements we want to integrate into the system, larger scale pilots… but we are in the good path and eager to continue working on Biosimil 🙂

See the full details of the award at: Tecnalia Press Room
See details of the technical aspects at: Technical details
See Biopool, the first sandbox for biosimil at: Project Biopool

I am involved on a personal DIY (Do It Yourself) technology project to develop a home-made low cost Raman spectrometer. This will involve electronics, optics, 3D modeling and printing, SW development… But, before starting with the details of the development, let us explain what’s Raman spectroscopy about…

Raman spectroscopy basics

Spectroscopy techniques are instrumental analysis techniques that take advantage on how matter interacts with light to detect the composition of samples. The vibration of the molecular bonds of a material causes light absortion on the wavelengths related to those vibrations. These vibrations are normally seen in the infrared region of the spectra (700-50000nm) and it is necessary specific detectors (like FTIR spectrometers) to capture this information. FTIR spectroscopy is a common technique to measure IR absorption and thus, extracting a IR absortion fingerprint related to the molecular composition of the sample. Each material presents a specific spectral signature that can be recorded on spectral databases or libraries. Specific algorithms like PLS or other signal processing techniques can be used to preprocess and analyse this signature and be able to detect and quantify the composition of the sample.

Raman spectroscopy is an alternative way to extract a spectral signature related to the molecular composition of the sample. It can be seen as a ‘cheat’ (physicists won’t forgive me) where, under the incidence of light, some of the incident photons are unelastically scattered and so, the reflected photons present a change on their wavelength. The increment on their wavelength is related on the spectral position of the molecular absorption bands.

Although this unelastic scattering has much lower intensity than normal scattering (called Raighleigh scattering) where the wavelengths of the photons remain unchanged, it can be detected though a specific sensor designs. If we illuminate the sample with a monochromatic light (e.g. a green laser), a fingerprint spectra is created around green wavelength (i.e. in the visible spectrum). This fingerprint can be used to detect the presence of certain molecules in the sample.

In the next video we can see the basics on Raman effect and some biography of Chandrasekhara Raman

Raman spectroscopy applications

Classic Raman applications include forensics, material analysis and involves laboratory Raman spectroscopes. This spectroscopes are normally coupled to microscopes that allow advanced analysis of samples including biological analysis. Modern Raman devices have been sucessfully miniaturized and can be combined with fiber optic and optics elements in order to achieve a wider set of applications. Mars Rover Curiosity includes a instrument called supercam that incorporates two kind of spectrometers: A LIBS (Laser Induced Breakdown Spectroscopy) that is able to measure atomic composition of the element and a Raman spectrometer that get molecular information.

The first stage on the development of this DIY Raman spectrometer is the development of the spectrometer. In this case we will fabricate an optical spectrometer. An optical spectrometer is a device that is able to separate a light ray into a line that contains the different wavelength (like a rainbow). This is a common effect that is seen when a white light passes through a prism. This light line will be acquired by a spectral sensing device (e.g. a linear CCD).

In next entries we will go through the process of developing the spectrometer.


There has been more that 7 years since I setup my old webpage and blog. Now I would like to share thoughts and concerns about computer vision world in which I have been working for the last 14 years. I wish you enjoy these posts.


– Artzai –