No abstract

Breast cancer (BC) is the most common cancer among women worldwide, approximately 20-25% of BCs are HER-2 positive. Analysis of HER-2 is fundamental to defining the appropriate therapy for patients with breast cancer. Inter-pathologist variability in the test results can affect diagnostic accuracy. The present study intends to propose an automatic scoring HER-2 algorithm. Based on color features, the technique is fully-automated and avoids segmentation, showing a concordance higher than 90% with a pathologist in the experiments realized.

No abstract

Analysis of cancer and other pathological diseases, like the interstitial lung diseases (ILDs), is usually possible through Computed Tomography (CT) scans. To aid this, a preprocessing step of segmentation is performed to reduce the area to be analyzed, segmenting the lungs and removing unimportant regions. Generally, complex methods are developed to extract the lung region, also using hand-made feature extractors to enhance segmentation. With the popularity of deep learning techniques and its automated feature learning, we propose a lung segmentation approach using fully convolutional networks (FCNs) combined with fully connected conditional random fields (CRF), employed in many state-of-the-art segmentation works. Aiming to develop a generalized approach, the publicly available datasets from University Hospitals of Geneva (HUG) and VESSEL12 challenge were studied, including many healthy and pathological CT scans for evaluation. Experiments using the dataset individually, its trained model on the other dataset and a combination of both datasets were employed. Dice scores of 98.67% ± 0.94% for the HUG-ILD dataset and 99.19% ± 0.37% for the VESSEL12 dataset were achieved, outperforming works in the former and obtaining similar state-of-the-art results in the latter dataset, showing the capability in using deep learning approaches.

Diffuse Pulmonary Diseases can affect the lung parenchyma, causing respiratory deficiencies and even cause almost complete loss of function, requiring a more accurate evaluation for a concrete diagnosis. Using computational techniques, the purpose of this work is to use feature descriptors (LBP, CLBP, gray-level histogram and GLCM) for classification of lung patterns, assisting radiologists in the diagnosis of these diseases. Using a patch-based approach, SMOTE resampling and the SVM classifier, accuracy of 87.41% and sensitivity of 88.31% were achieved.Resumo. Doenças Pulmonares Difusas podem afetar o parênquima pulmonar, causando deficiências respiratórias até a quase completa perda de função, sendo necessária uma avaliação mais precisa para um diagnóstico concreto. Utilizando-se de técnicas computacionais, a proposta deste trabalho é utilizar descritores de características (LBP, CLBP, histograma de níveis de cinza e GLCM) para a classificação de padrões pulmonares, auxiliando radiologistas no diagnóstico dessas doenças. Utilizando uma abordagem baseada em blocos, resampling SMOTE e o classificador SVM, uma taxa de acerto de 87,41% e sensibilidade de 88,31% foram alcançadas.