A new model for classification of medical CT images using CNN: a COVID-19 case study.

SARS-CoV-2 is the causative agent of COVID-19 and leaves characteristic impressions on chest Computed Tomography (CT) images in infected patients and this analysis is performed by radiologists through visual reading of lung images, and failures may occur. In this article, we propose a classification model, called Wavelet Convolutional Neural Network (WCNN) that aims to improve the differentiation of images of patients with COVID-19 from images of patients with other lung infections. The WCNN model was based on a Convolutional Neural Network (CNN) and wavelet transform. The model proposes a new input layer added to the neural network, which was called Wave layer. The hyperparameters values were defined by ablation tests. WCNN was applied to chest CT images to images from two internal and one external repositories. For all repositories, the average results of Accuracy (ACC), Sensitivity (Sen) and Specificity (Sp) were calculated. Subsequently, the average results of the repositories were consolidated, and the final values were ACC = 0.9819, Sen = 0.9783 and Sp = 0.98. The WCNN model uses a new Wave input layer, which standardizes the network input, without using data augmentation, resizing and segmentation techniques, maintaining the integrity of the tomographic image analysis. Thus, applications developed based on WCNN have the potential to assist radiologists with a second opinion in the analysis.1.

Novel Mahalanobis-based feature selection improves one-class classification of early hepatocellular carcinoma.

Detection of early hepatocellular carcinoma (HCC) is responsible for increasing survival rates in up to 40%. One-class classifiers can be used for modeling early HCC in multidetector computed tomography (MDCT), but demand the specific knowledge pertaining to the set of features that best describes the target class. Although the literature outlines several features for characterizing liver lesions, it is unclear which is most relevant for describing early HCC. In this paper, we introduce an unconstrained GA feature selection algorithm based on a multi-objective Mahalanobis fitness function to improve the classification performance for early HCC. We compared our approach to a constrained Mahalanobis function and two other unconstrained functions using Welch's t-test and Gaussian Data Descriptors. The performance of each fitness function was evaluated by cross-validating a one-class SVM. The results show that the proposed multi-objective Mahalanobis fitness function is capable of significantly reducing data dimensionality (96.4%) and improving one-class classification of early HCC (0.84 AUC). Furthermore, the results provide strong evidence that intensity features extracted at the arterial to portal and arterial to equilibrium phases are important for classifying early HCC.

Three-dimensional reconstruction and surface extraction of lower limbs as visualization methodologies of ecchymosis.

This paper presents a computational system for three-dimensional reconstruction and surface extraction of the human lower limb as a new methodology of visualizing images of multifaceted ecchymosis on the lower limbs. Through standardization of image acquisition by a mechanical system, an algorithm was developed for three-dimensional and surface reconstruction based on the extraction of depth from silhouettes. In order to validate this work, a three-dimensional model of the human lower limb was used inside a virtual environment. At this environment the mechanical procedure of image acquisition was simulated, resulting in 100 images which was later submitted to all algorithms developed. It was observed that the systems for three-dimensional reconstruction and surface extraction of the object were able to generate a new visualization method of the lesion. The results allow us to conclude that the developed systems provided adequate three-dimensional and two-dimensional visualization of the surface of the simulated model. Despite the lack of experiments with real ecchymoses, the systems developed in this work show great potential to be included in the standard methods for the visualization of ecchymoses.

Breast density pattern characterization by histogram features and texture descriptors

Abstract Introduction Breast cancer is the first leading cause of death for women in Brazil as well as in most countries in the world. Due to the relation between the breast density and the risk of breast cancer, in medical practice, the breast density classification is merely visual and dependent on professional experience, making this task very subjective. The purpose of this paper is to investigate image features based on histograms and Haralick texture descriptors so as to separate mammographic images into categories of breast density using an Artificial Neural Network. Methods We used 307 mammographic images from the INbreast digital database, extracting histogram features and texture descriptors of all mammograms and selecting them with the K-means technique. Then, these groups of selected features were used as inputs of an Artificial Neural Network to classify the images automatically into the four categories reported by radiologists. Results An average accuracy of 92.9% was obtained in a few tests using only some of the Haralick texture descriptors. Also, the accuracy rate increased to 98.95% when texture descriptors were mixed with some features based on a histogram. Conclusion Texture descriptors have proven to be better than gray levels features at differentiating the breast densities in mammographic images. From this paper, it was possible to automate the feature selection and the classification with acceptable error rates since the extraction of the features is suitable to the characteristics of the images involving the problem.

Evaluation of the clinical efficacy of minimally invasive procedures for breast cancer screening at a teaching hospital.

AIMS: To assess the clinical efficacy of diagnostic procedures for breast cancer at a teaching hospital using internal auditing tools and quality control measures. METHODS: A retrospective assessment of 500 patients who underwent core needle biopsy (wide-bore needle biopsy; WBN) of palpable or non-palpable breast nodes that were submitted for at least one cytological examination (fine needle aspiration (FNA) cytology and/or imprint of a WBN specimen). For statistical analysis the auditing tool and quality control proposed by the National Health Service breast screening programme was utilised. RESULTS: For FNA, full specificity, positive predictive value, inadequate rates and suspicious rates were satisfactory while absolute sensitivity, complete sensitivity, false negatives and false positives were unsatisfactory. For imprint, absolute sensitivity, complete sensitivity, inadequate rate from cancers and suspicious rates were satisfactory, and the remaining indicators were unsatisfactory. WBN displayed the best performance with absolute sensitivity, complete sensitivity, false negative, suspicious rates, full specificity and predictive value showing satisfactory results and only one unsatisfactory result (false positive). CONCLUSIONS: Based on an overall analysis, WBN displayed the highest clinical efficacy compared with FNA and imprint, and demonstrated adequate safety for confirming the appropriate diagnosis and management of patients, ensuring the efficacy of the service.

Uso de software como ferramenta pedagógica no processo de ensino-aprendizagem da mamografia digital / Educational software as a tool for teaching & learning of digital mammography

OBJETIVO: Avaliar o impacto sobre o treinamento de residentes utilizando uma ferramenta computacional dedicada à avaliação do desempenho da leitura de imagens radiológicas convencionais e digitais. MATERIAIS E MÉTODOS: O treinamento foi realizado no Laboratório de Qualificação de Imagens Médicas (QualIM). Os residentes de radiologia efetuaram cerca de 1.000 leituras de um total de 60 imagens obtidas de um simulador estatístico (Alvim®) que apresenta fibras e microcalcificações de dimensões variadas. O desempenhodos residentes na detecção dessas estruturas foi avaliado por meio de parâmetros estatísticos. RESULTADOS:Os resultados da probabilidade de detectabilidade foram de 0,789 e 0,818 para os sistemas convencional e digital, respectivamente. As taxas de falso-positivos foram de 8% e 6% e os valores de verdadeiro- -positivos, de 66% e 70%, respectivamente. O valor de kappa total foi 0,553 para as leituras em negatoscópio e 0,615 em monitor. A área sob a curva ROC foi de 0,716 para leitura em filme e 0,810 para monitor.CONCLUSÃO: O treinamento proposto mostrou ser efetivo e apresentou impacto positivo sobre o desempenhodos residentes, constituindo-se em interessante ferramenta pedagógica. Os resultados sugerem que o método de treinamento baseado na leitura de simuladores pode produzir um melhor desempenho dos profissionais na interpretação das imagens mamográficas.

OBJECTIVE: The present study was aimed at evaluating the performance of residents trained in the reading of conventional and digital mammography images with a specific computational tool. MATERIALS AND METHODS: The training was accomplished in the Laboratory of Medical Images Qualification (QualIM û Laboratório de Qualificação de Imagens Médicas). Residents in radiology performed approximately 1,000 readings of a set of 60 images acquired from a statistical phantom (Alvim®) presenting microcalcifications and fibers with different sizes. The analysis of the residents' performance in the detection of these structures was based on statistical parameters. RESULTS: Values for detection probability were respectively 0.789 and 0.818 for conventional and digital systems. False-positive rates were 8% and 6%, and true-positive rates, 66% and 70% respectively. The total kappa value was 0.553 for readings on the negatoscope (hard-copy readings), and 0.615 on the monitor (soft-copy readings). The area under the ROC curve was 0.716 forhard-copy readings and 0.810 for soft-copy readings. CONCLUSION: The training has showed to be effective,with a positive impact on the residents' performance, representing an interesting educational tool. The resultsof the present study suggest that this method of training based on the reading of images from phantoms can improve the practitioners' performance in the interpretation of mammographic images.