Segmentation and quantification of COVID-19 infections in CT using pulmonary vessels extraction and deep learning.

At the end of 2019, the World Health Organization (WHO) reported pneumonia that started in Wuhan, China, as a global emergency problem. Researchers quickly advanced in research to try to understand this COVID-19 and sough solutions for the front-line professionals fighting this fatal disease. One of the tools to aid in the detection, diagnosis, treatment, and prevention of this disease is computed tomography (CT). CT images provide valuable information on how this new disease affects the lungs of patients. However, the analysis of these images is not trivial, especially when researchers are searching for quick solutions. Detecting and evaluating this disease can be tiring, time-consuming, and susceptible to errors. Thus, in this study, we aim to automatically segment infections caused by COVID19 and provide quantitative measures of these infections to specialists, thus serving as a support tool. We use a database of real clinical cases from Pedro Ernesto University Hospital of the State of Rio de Janeiro, Brazil. The method involves five steps: lung segmentation, segmentation and extraction of pulmonary vessels, infection segmentation, infection classification, and infection quantification. For the lung segmentation and infection segmentation tasks, we propose modifications to the traditional U-Net, including batch normalization, leaky ReLU, dropout, and residual block techniques, and name it as Residual U-Net. The proposed method yields an average Dice value of 77.1% and an average specificity of 99.76%. For quantification of infectious findings, the proposed method achieves results like that of specialists, and no measure presented a value of ρ < 0.05 in the paired t-test. The results demonstrate the potential of the proposed method as a tool to help medical professionals combat COVID-19. fight the COVID-19.

Superpixel-based deep convolutional neural networks and active contour model for automatic prostate segmentation on 3D MRI scans.

Automatic and reliable prostate segmentation is an essential prerequisite for assisting the diagnosis and treatment, such as guiding biopsy procedure and radiation therapy. Nonetheless, automatic segmentation is challenging due to the lack of clear prostate boundaries owing to the similar appearance of prostate and surrounding tissues and the wide variation in size and shape among different patients ascribed to pathological changes or different resolutions of images. In this regard, the state-of-the-art includes methods based on a probabilistic atlas, active contour models, and deep learning techniques. However, these techniques have limitations that need to be addressed, such as MRI scans with the same spatial resolution, initialization of the prostate region with well-defined contours and a set of hyperparameters of deep learning techniques determined manually, respectively. Therefore, this paper proposes an automatic and novel coarse-to-fine segmentation method for prostate 3D MRI scans. The coarse segmentation step combines local texture and spatial information using the Intrinsic Manifold Simple Linear Iterative Clustering algorithm and probabilistic atlas in a deep convolutional neural networks model jointly with the particle swarm optimization algorithm to classify prostate and non-prostate tissues. Then, the fine segmentation uses the 3D Chan-Vese active contour model to obtain the final prostate surface. The proposed method has been evaluated on the Prostate 3T and PROMISE12 databases presenting a dice similarity coefficient of 84.86%, relative volume difference of 14.53%, sensitivity of 90.73%, specificity of 99.46%, and accuracy of 99.11%. Experimental results demonstrate the high performance potential of the proposed method compared to those previously published.

Breast cancer diagnosis from histopathological images using textural features and CBIR.

Currently, breast cancer diagnosis is an extensively researched topic. An effective method to diagnose breast cancer is to use histopathological images. However, extracting features from these images is a challenging task. Thus, we propose a method that uses phylogenetic diversity indexes to characterize images for creating a model to classify histopathological breast images into four classes - invasive carcinoma, in situ carcinoma, normal tissue, and benign lesion. The classifiers used were the most robust ones according to the existing literature: XGBoost, random forest, multilayer perceptron, and support vector machine. Moreover, we performed content-based image retrieval to confirm the classification results and suggest a ranking for sets of images that were not labeled. The results obtained were considerably robust and proved to be effective for the composition of a CADx system to help specialists at large medical centers.

Correction to: Semivariogram and Semimadogram functions as descriptors for AMD diagnosis on SD-OCT topographic maps using Support Vector Machine.

After publication, it was highlighted that the original publication [1] contained a spelling mistake in the first name of Marcelo Gattas. This was incorrectly captured as Marelo Gattass in the original article which has since been updated.

Semivariogram and Semimadogram functions as descriptors for AMD diagnosis on SD-OCT topographic maps using Support Vector Machine.

BACKGROUND: Age-related macular degeneration (AMD) is a degenerative ocular disease that develops by the formation of drusen in the macula region leading to blindness. This condition can be detected automatically by automated image processing techniques applied in spectral domain optical coherence tomography (SD-OCT) volumes. The most common approach is the individualized analysis of each slice (B-Scan) of the SD-OCT volumes. However, it ends up losing the correlation between pixels of neighboring slices. The retina representation by topographic maps reveals the similarity of these structures with geographic relief maps, which can be represented by geostatistical descriptors. In this paper, we present a methodology based on geostatistical functions for the automatic diagnosis of AMD in SD-OCT. METHODS: The proposed methodology is based on the construction of a topographic map of the macular region. Over the topographic map, we compute geostatistical features using semivariogram and semimadogram functions as texture descriptors. The extracted descriptors are then used as input for a Support Vector Machine classifier. RESULTS: For training of the classifier and tests, a database composed of 384 OCT exams (269 volumes of eyes exhibiting AMD and 115 control volumes) with layers segmented and validated by specialists were used. The best classification model, validated with cross-validation k-fold, achieved an accuracy of 95.2% and an AUROC of 0.989. CONCLUSION: The presented methodology exclusively uses geostatistical descriptors for the diagnosis of AMD in SD-OCT images of the macular region. The results are promising and the methodology is competitive considering previous results published in literature.

Segmentação de massas em imagens mamográficas utilizando índices de similaridade / Mass segmentation in mammographic images using similarity indixes

Uma forma de segmentação de massas em imagens mamográficas é pela análise bilateral dos pares de mamografias. Sabe-se que mamografias da mama esquerda e direita apresentam alto grau de simetria e quando há uma diferença brusca entre os pares, pode-se considerar algo suspeito. OBJETIVO: Uma metodologia para segmentação de massas baseado em análise bilateral de mamografias usando técnicas de similaridade de espécies para encontrar regiões assimétricas. Materiais e MÉTODOS: Fluxo de cinco etapas: Materiais, Pré-processamento de imagens, Registro de imagens,Segmentação de regiões assimétricas e Filtragem de regiões. RESULTADOS: Os resultados preliminares mostram que essa metodologia é promissora na detecção de regiões assimétricas apresentando 95% de acerto na etapa de segmentação e 90,8% após a filtragem de regiões. CONCLUSÃO: Os índices de similaridade mostram-se promissores na tarefa de encontrar regiões suspeitas em pares de mamografias, além de formalização de técnicas para filtragem de regiões que não são massas.

One way of segmenting masses in mammographic images is the bilateral analysis of mammograms pairs. It isknown that mammograms of the left and right breast, has a high degree of symmetry and when there is an abrupt difference between the pairs may be considered something suspicious. OBJECTIVE: A methodology to segmentation mass based on bilateralanalysis of mammograms using species similarity techniques to find asymmetric regions. Materials and METHODS: A five-step flow: Materials, Pre-processing, Image Registration, Segmentation of asymmetric regions and Filtering regions. RESULTS: Preliminary results show that this method is promising in detecting asymmetrical regions showing 95%accuracy in segmentation step and 90.8% after filtering regions. CONCLUSION: The similarity indices show promise in the task of finding suspicious areas in mammograms pairs, there is also formalization of techniques to filtering regions.

Segmentação de microcalcificações em imagens mamográficas utilizando algoritmo FireFly / Microcalcifications segmentation in mammographic images using algorithm FireFly

OBJETIVO: propor um método para segmentação de microcalcificações em imagens mamográficas por meio do algoritmo firefly. MATERIAIS E MÉTODO: aplicar as etapas de aquisição das imagens, pré-processamento e segmentação. RESULTADOS: foram obtidos para as imagens densas 91% de acerto e para as imagens não densas 95% de acerto na detecção das microcalcificações. CONCLUSÃO: o método mostrou-se viável como instrumento para auxílio na detecção de microcalcificações em imagens mamográficas densas e não densas.

OBJECTIVE: proposing a method for microcalcifications segmentation in mammographic images by means of firefly algorithm. MATERIALS AND METHODS: apply the steps of acquisition, preprocessing and segmentation. RESULTS: the dense images resulted 91% of accuracy and non-dense images 95% of accuracy in the detection of microcalcifications. CONCLUSION: The method proved to be feasible as a tool to aid in the detection of microcalcifications in both dense and non-dense mammographic images.

Análise temporal de lesões em mamografias utilizando índices de similaridade / Temporal analysis of mammogram lesions using similarity indexes

Uma forma de verificar a malignidade de lesões em mamografias é o acompanhamento periódico, analisando mudanças em medições de geometria (forma) e textura (tecido). Uma das medidas de forma mais utilizadas é a taxa de crescimento. No entanto, somada a medidas de tecido, obtém-se informações úteis sobre o desenvolvimento interno da lesão. OBJETIVOS: Uma metodologia para estabelecer uma correspondência entre lesões em mamografias de tempos diferentes e analisar as mudanças no tecido através de índices de similaridade. MÉTODOS: Executado em cinco etapas: Aquisição das Imagens, Pré-processamento, Registro de Imagens, Correspondência entre as Lesões e Análise Temporal de Texturas. RESULTADOS: Os resultados preliminares mostram que essa metodologia é promissora na detecção de mudanças no tecido das lesões. CONCLUSÃO: Os índices de similaridade se mostraram eficientes na quantificação de mudanças na textura e podem ser usados como informações para auxiliar o acompanhamento e diagnóstico de doenças associadas as lesões.

One way to verify the malignancy of breast lesions is the temporal analysis measurement geometry (shape) and texture (tissue). In this sense, one of the most used form measures is the growth rate. However, in addition to tissue measurements over time, you get useful information about their behavior. OBJECTIVES: A methodology for establishing a correspondence between injuries at different times and analyze changes in tissue through similarity indices. METHODS: Executed in five steps: image acquisition, preprocessing, Image Registration, Correspondence between Lesions and Temporal Analysis of Lesions Texture. RESULTS: Preliminary results show that this method is promising for detecting changes in tissue lesions. CONCLUSION: The similarity indices were effective in quantitating changes in texture and can be used as information to assist the monitoring and diagnosis of lesions associated diseases.