Diatoms are one of the largest groups of microalgae present in marine, freshwater and transitional environments and their reactivity to environmental changes makes them suitable to be employed as biomarkers for monitoring tasks. Anyway, their presence in a large number of species makes it arduous to perform diatoms taxonomy during monitoring tasks considering that, to date, analysis is conducted by marine biologists on the basis of their own experience and, hence, in a subjective way. Hence, the need for automatic and objective methodologies for the identification and classification of diatoms samples rises. Research efforts in the field of Computer Vision led to a plethora of highly effective deep learning strategies surpassing human capabilities for image classification, as showed in the recent Imagenet challenge editions where they were initially introduced. Despite the very promising results of the proposed solutions, the difficulty arises to determine which technique is most suitable among them for real tasks and in particular for diatoms classification. This work proposes an end-to-end pipeline for automatic recognition of diatoms, acquired by means of holographic microscopy in water samples, employing deep learning techniques. In particular the most recently introduced Convolution Neural Networks (CNNs) architectures have been deeply investigated and compared in order to highlight the pros and cons of each of them. Moreover, in order to feed the CNNs training stages with a suitable amount of labeled data, a strategy to build a synthetic dataset, starting from a single image per class available from commercial glass slides specifically prepared for taxonomy purposes, is introduced. Besides, models ensembling strategies, in order to improve the single model scores, have been exploited. Finally, the proposed approach has been validated employing a dataset built up of holographic images of diatoms sampled in natural water bodies.
The identification and classification of biological samples is high-demanded in biomedical imaging for diagnostic purposes. Among all imaging modalities, digital holography has gained credits as a powerful solutions, thanks to its ability to perform full-field and label –free quantitative phase imaging. On the other hand, machine learning is nowadays the most used approach for classification purposes. The robustness and the accuracy of the classification depend of the features used for the training step. Therefore, the identification of micro-organism becomes strictly related to the features that can be extracted from their images. In other word, the more the image contains information, the higher the possibility of extracting highly distinctive descriptors to differentiate biological phenotypes. Digital holography can be considered one of the richest in terms of information content due to the fact that a single digital hologram encode both amplitude and phase information about the imaged cells. This opens the way to improve the features extraction, thus making more accurate the classification step. In this paper we analyze a test case by using a holographic image dataset for classification, by extracting unique features that can be solely obtained by holographic images.
Conference Committee Involvement (4)
Multimodal Sensing and Artificial Intelligence for Sustainable Future
23 June 2025 | Munich, Germany
Multimodal Sensing and Artificial Intelligence: Technologies and Applications III
27 June 2023 | Munich, Germany
Multimodal Sensing and Artificial Intelligence: Technologies and Applications II
21 June 2021 | Online Only, Germany
Multimodal Sensing and Artificial Intelligence: Technologies and Applications
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.