RESUMO
An unresolved issue in contemporary biomedicine is the overwhelming number and diversity of complex images that require annotation, analysis and interpretation. Recent advances in Deep Learning have revolutionized the field of computer vision, creating algorithms that compete with human experts in image segmentation tasks. However, these frameworks require large human-annotated datasets for training and the resulting "black box" models are difficult to interpret. In this study, we introduce Kartezio, a modular Cartesian Genetic Programming-based computational strategy that generates fully transparent and easily interpretable image processing pipelines by iteratively assembling and parameterizing computer vision functions. The pipelines thus generated exhibit comparable precision to state-of-the-art Deep Learning approaches on instance segmentation tasks, while requiring drastically smaller training datasets. This Few-Shot Learning method confers tremendous flexibility, speed, and functionality to this approach. We then deploy Kartezio to solve a series of semantic and instance segmentation problems, and demonstrate its utility across diverse images ranging from multiplexed tissue histopathology images to high resolution microscopy images. While the flexibility, robustness and practical utility of Kartezio make this fully explicable evolutionary designer a potential game-changer in the field of biomedical image processing, Kartezio remains complementary and potentially auxiliary to mainstream Deep Learning approaches.
Assuntos
Algoritmos , Processamento de Imagem Assistida por Computador , Humanos , Processamento de Imagem Assistida por Computador/métodos , Microscopia , Evolução Biológica , SemânticaRESUMO
The class distribution of a training dataset is an important factor which influences the performance of a deep learning-based system. Understanding the optimal class distribution is therefore crucial when building a new training set which may be costly to annotate. This is the case for histological images used in cancer diagnosis where image annotation requires domain experts. In this paper, we tackle the problem of finding the optimal class distribution of a training set to be able to train an optimal model that detects cancer in histological images. We formulate several hypotheses which are then tested in scores of experiments with hundreds of trials. The experiments have been designed to account for both segmentation and classification frameworks with various class distributions in the training set, such as natural, balanced, over-represented cancer, and over-represented non-cancer. In the case of cancer detection, the experiments show several important results: (a) the natural class distribution produces more accurate results than the artificially generated balanced distribution; (b) the over-representation of non-cancer/negative classes (healthy tissue and/or background classes) compared to cancer/positive classes reduces the number of samples which are falsely predicted as cancer (false positive); (c) the least expensive to annotate non-ROI (non-region-of-interest) data can be useful in compensating for the performance loss in the system due to a shortage of expensive to annotate ROI data; (d) the multi-label examples are more useful than the single-label ones to train a segmentation model; and (e) when the classification model is tuned with a balanced validation set, it is less affected than the segmentation model by the class distribution of the training set.
Assuntos
Aprendizado Profundo , Neoplasias , Humanos , Processamento de Imagem Assistida por Computador/métodos , Neoplasias/diagnóstico por imagemRESUMO
The large spectrum of hearing sensitivity observed in primates results from the impact of environmental and behavioral pressures to optimize sound perception and localization. Although evidence of positive selection in auditory genes has been detected in mammals including in Hominoids, selection has never been investigated in other primates. We analyzed 123 genes highly expressed in the inner ear of 27 primate species and tested to what extent positive selection may have shaped these genes in the order Primates tree. We combined both site and branch-site tests to obtain a comprehensive picture of the positively selected genes (PSGs) involved in hearing sensitivity, and drew a detailed description of the most affected branches in the tree. We chose a conservative approach, and thus focused on confounding factors potentially affecting PSG signals (alignment, GC-biased gene conversion, duplications, heterogeneous sequencing qualities). Using site tests, we showed that around 12% of these genes are PSGs, an α selection value consistent with average human genome estimates (10-15%). Using branch-site tests, we showed that the primate tree is heterogeneously affected by positive selection, with the black snub-nosed monkey, the bushbaby, and the orangutan, being the most impacted branches. A large proportion of these genes is inclined to shape hair cells and stereocilia, which are involved in the mechanotransduction process, known to influence frequency perception. Adaptive selection, and more specifically recurrent adaptive evolution, could have acted in parallel on a set of genes (ADGRV1, USH2A, PCDH15, PTPRQ, and ATP8A2) involved in stereocilia growth and the whole complex of bundle links connecting them, in species across different habitats, including high altitude and nocturnal environments.
Assuntos
Mecanotransdução Celular , Estereocílios , Animais , Células Ciliadas Auditivas/fisiologia , Audição/genética , Primatas/genéticaRESUMO
Motivation: Segmental Duplications (SDs) are DNA fragments longer than 1 kbp, distributed within and between chromosomes and sharing more than 90% identity. Although they hold a significant role in genomic fluidity and adaptability, many key questions about their intrinsic characteristics and mutability remain unsolved due to the persistent difficulty of sequencing highly duplicated genomic regions. The recent development of long and linked-read NGS technologies will increase the need to search for SDs in genomes newly sequenced with these technics. The main limitation of SD analysis will soon be the availability of efficient detection software, to retrieve and compare SD genomic component between species or lineages. Results: In this paper, we present the open-source ASGART, 'A Segmental duplications Gathering And Refining Tool', developed to search for segmental duplications (SDs) in any assembled sequence. We have tested and benchmarked ASGART on five models organisms. Our results demonstrate ASGART's ability to extract SDs from any genome-wide sequence, regardless of genomic size or organizational complexity and quicker than any other software available. Availability and implementation: The online version of ASGART is available at http://asgart.irit.fr. The source code of ASGART is available both on the ASGART website and at https://github.com/delehef/asgart. Supplementary information: Supplementary data are available at Bioinformatics online.