Browsing by Author "Silva, Romuere Rodrigues Veloso e"

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Active contours for overlapping cervical cell segmentation.
    (2021) Araujo, Flavio Henrique Duarte de; Silva, Romuere Rodrigues Veloso e; Medeiros, Fátima Nelsizeuma Sombra de; Rocha Neto, Jeová Farias Sales; Oliveira, Paulo Henrique Calaes; Bianchi, Andrea Gomes Campos; Ushizima, Daniela Mayumi
    The nuclei and cytoplasm segmentation of cervical cells is a well studied problem. However, the current segmentation algorithms are not robust to clinical practice due to the high computational cost or because they cannot accurately segment cells with high overlapping. In this paper, we propose a method that is capable of segmenting both cytoplasm and nucleus of each individual cell in a clump of overlapping cells. The proposed method consists of three steps: 1) cellular mass segmentation; 2) nucleus segmentation; 3)cytoplasm identification based on an active contour method. We carried out experiments on both synthetic and real cell images. The performance evaluation of the proposed method showed that it was less sensitive to the increase in the number of cells per image and the overlapping ratio against two other existing algorithms. It has also achieved a promising low processing time and, hence, it has the potential to support expert systems for cervical cell recognition.
  • No Thumbnail Available
    Item
    Deep learning for cell image segmentation and ranking.
    (2019) Araujo, Flavio Henrique Duarte de; Silva, Romuere Rodrigues Veloso e; Ushizima, Daniela Mayumi; Rezende, Mariana Trevisan; Carneiro, Claudia Martins; Bianchi, Andrea Gomes Campos; Medeiros, Fátima Nelsizeuma Sombra de
    Ninety years after its invention, the Pap test continues to be the most used method for the early identification of cervical precancerous lesions. In this test, the cytopathologists look for microscopic abnormalities in and around the cells, which is a time-consuming and prone to human error task. This paper introduces computational tools for cytological analysis that incorporate cell segmentation deep learning techniques. These techniques are capable of processing both free-lying and clumps of abnormal cells with a high overlapping rate from digitized images of conventional Pap smears. Our methodology employs a preprocessing step that discards images with a low probability of containing abnormal cells without prior segmentation and, therefore, performs faster when compared with the existing methods. Also, it ranks outputs based on the likelihood of the images to contain abnormal cells. We evaluate our methodology on an image database of conventional Pap smears from real scenarios, with 108 fields-of-view containing at least one abnormal cell and 86 containing only normal cells, corresponding to millions of cells. Our results show that the proposed approach achieves accurate results (MAP = 0.936), runs faster than existing methods, and it is robust to the presence of white blood cells, and other contaminants.
  • No Thumbnail Available
    Item
    Método de visão computacional baseado em laser para monitoramento de defeitos em correias transportadoras.
    (2019) Netto, Guilherme Gaigher; Bianchi, Andrea Gomes Campos; Coelho, Bruno Nazário; Silva, Romuere Rodrigues Veloso e; Cámara Chávez, Guillermo; Reis, Agnaldo José da Rocha
    O monitoramento contínuo de correias transportadoras é de extrema importância já que defeitos em sua superfície podem se desenvolver em desgaste, rasgos e até rupturas, o que pode resultar na interrupção do transportador, e consequentemente, perda de capital, ou ainda pior, acidentes sérios ou fatais. Com o propósito de resolver o problema de monitoramento, o estudo apresentado a seguir propõe um método de visão computacional baseado em laser para detecção de defeitos em correias transportadoras. A abordagem transforma a imagem do feixe de laser em um sinal unidimensional, e então analisa o sinal para identificar os defeitos, considerando que variações no sinal são causados por defeitos/imperfeições na superfície da correia. Diferentemente de outros trabalhos, o método proposto consegue identificar defeitos através de uma reconstrução 2D, e reconstruir uma aproximação 3D da correia, simulando um scanner 3D. Resultados mostram que o método proposto foi capaz de identificar e reconstruir imperfeições superficiais em ambos ambientes, real e simulado, alcançando valores altos em métricas como precisão e evocação. Além disso, análises em imagens com ruído permitiram investigar a robustez da proposta de solução.
  • No Thumbnail Available
    Item
    Radial feature descriptors for cell classification and recommendation.
    (2019) Silva, Romuere Rodrigues Veloso e; Araujo, Flavio Henrique Duarte de; Ushizima, Daniela Mayumi; Bianchi, Andrea Gomes Campos; Carneiro, Cláudia Martins; Medeiros, Fátima Nelsizeuma Sombra de
    This paper introduces computational tools for cell classification into normal and abnormal, as well as content-based-image-retrieval (CBIR) for cell recommendation. It also proposes the radial feature descriptors (RFD), which define evenly interspaced segments around the nucleus, and proportional to the convexity of the nuclear boundary. Experiments consider Herlev and CRIC image databases as input to classification via Random Forest and bootstrap; we compare 14 different feature sets by means of False Negative Rate (FNR) and Kappa (k), obtaining FNR = 0.02 and k = 0.89 for Herlev, and FNR = 0.14 and k = 0.78 for CRIC. Next, we sort and rank cell images using convolutional neural networks and evaluate performance with the Mean Average Precision (MAP), achieving MAP = 0.84 and MAP = 0.82 for Herlev and CRIC, respectively. Cell classification show encouraging results regarding RFD, including its sensitivity to intensity variation around the nuclear membrane as it bypasses cytoplasm segmentation.
  • No Thumbnail Available
    Item
    Reverse image search for scientific data within and beyond the visible spectrum.
    (2018) Araujo, Flavio Henrique Duarte de; Silva, Romuere Rodrigues Veloso e; Medeiros, Fátima Nelsizeuma Sombra de; Parkinson, Dilworth Dula; Hexemer, Alexander; Carneiro, Cláudia Martins; Ushizima, Daniela Mayumi
    The explosion in the rate, quality and diversity of image acquisition instruments has propelled the de- velopment of expert systems to organize and query image collections more efficiently. Recommendation systems that handle scientific images are rare, particularly if records lack metadata. This paper intro- duces new strategies to enable fast searches and image ranking from large pictorial datasets with or without labels. The main contribution is the development of pyCBIR , a deep neural network software to search scientific images by content. This tool exploits convolutional layers with locality sensitivity hashing for querying images across domains through a user-friendly interface. Our results report image searches over databases ranging from thousands to millions of samples. We test pyCBIR search capabilities using three convNets against four scientific datasets, including samples from cell microscopy, microtomography, atomic diffraction patterns, and materials photographs to demonstrate 95% accurate recommendations in most cases. Furthermore, all scientific data collections are released.