Taxonomic indexes for differentiating malignancy of lung nodules on CT images

Abstract Introduction Lung cancer remains the leading cause of cancer mortality worldwide, with one of the lowest survival rates after diagnosis. Therefore, early detection greatly increases the chances of improving patient survival. Methods This study proposes a method for diagnosis of lung nodules in benign and malignant tumors based on image processing and pattern recognition techniques. Taxonomic indexes and phylogenetic trees were used as texture descriptors, and a Support Vector Machine was used for classification. Results The proposed method shows promising results for accurate diagnosis of benign and malignant lung tumors, achieving an accuracy of 88.44%, sensitivity of 84.22%, specificity of 90.06% and area under the ROC curve of 0.8714. Conclusion The results demonstrate the promising performance of texture extraction techniques by means of taxonomic indexes combined with phylogenetic trees. The proposed method achieves results comparable to those previously published.

Predição volumétrica de lesões pulmonares aplicando modelo oculto de Markov / Prediction volumetric of lung lesions applying hidden Markov model

OBJETIVO: predizer o estado volumétrico de lesões pulmonares aplicando o modelo oculto de Markov (HMM). MATERIAIS E MÉTODOS: Aquisição de imagens de lesões pulmonares temporais, geração do HMM e a aplicação do HMM. RESULTADOS: Os testes foram aplicados em 24 lesões pulmonares, adquiridas da Public Lung Database to Address Drug Response (PLDADR). Dividimos os resultados desta pesquisa em 3. O primeiro utilizando a base completa para predição volumétrica da lesão e comparação com o Response Evaluation Criteria in Solid Tumors (RECIST), atingindo uma taxa de acerto de 70,83%. No segundo, Aplica - se o método leave-one-out, separando os dados em dois grupos, treino e teste, obtendo-se uma taxa de acerto de 75,00%. Por fim, realizamos a predição volumétrica de cada lesão no intervalo de 5 tempos. O resultado mostrou que é possível predizer se o estado da lesão está progredindo, regredindo ou estabilizando, a partir das alterações ocorridas nos diâmetros e volumes.

OBJECTIVE: predicting the volume status of lung lesions by applying the hidden Markov model (HMM). MATERIALS AND METHODS: Acquisition of images of temporal lung lesions, HMM generation and application of HMM. RESULTS: The tests were applied in 24 pulmonary lesions, acquired from Public Lung Database to Address Drug Response(PLDADR). We have divided this search in 3. The first using the full volumetric basis for prediction of the lesion and compared to the Response Evaluation Criteria in Solid Tumors (RECIST), reaching a 70.83% success rate. Then, weapply the leave-one-out method, separating the data into two groups, training and testing, yielding a 75.00% successrate. Finally, we volumetric prediction of each lesion in 5 days interval. The result showed that it is possible to predict the state of the injury is progressing, regressing or stabilizing, from changes in the diameters and volumes.

Diagnóstico de glaucoma em retinografias baseado em geoestatística / Glaucoma diagnosis in retinography based on geostatistics

O glaucoma é uma das doenças que mais causam cegueira em todo o mundo. O Conselho Brasileiro de Oftalmologia (CBO) estima que no Brasil existam 985 mil portadores de glaucoma com mais de 40 anos de idade. A utilização de sistemas CAD e CADx tem contribuído para aumentar as chances de detecção e diagnósticos corretos,auxiliando os especialistas na tomada de decisões sobre o tratamento do glaucoma. OBJETIVO: Apresentar um método para diagnóstico do glaucoma em retinografias utilizando o LBP para representar a região do disco ótico, funções geoestatísticas para descrever padrões e o MVS para classificar as imagens. MÉTODOS: Executado em 3 etapas: Representação da imagem (1), Extração de Características com geoestatística (2) e Classificação e Validação (3). RESULTADOS: Foram obtidos 88% de especificidade, 82% de sensibilidade e 84% de acurácia no diagnóstico do glaucoma. CONCLUSÃO: O método mostrou-se promissor como uma forma de auxílio ao diagnóstico de glaucoma.

Glaucoma is one of the diseases that more cause blindness worldwide. The Brazilian Council of Ophthalmology (CBO) estimates that in Brazil there are 985,000 people with glaucoma over 40 years old. The use of CAD and CADxsystems has contributed to increase the chances of detection and correct diagnoses, they provide, helping specialists inmaking decisions on glaucoma treatment. OBJECTIVE: To introduce a method for diagnosing glaucoma in fundus imageusing the LBP to represent the optic disk region, geostatistical functions to describe patterns and SVM to classify the images. METHODS: Run in 3 steps: Image representation (2), Feature extraction with geostatistic (3) and Classification and Validation (4). RESULTS: we obtained 88% specificity, 82% sensitivity and 84% accuracy in the diagnosis of glaucoma. CONCLUSION: The method has shown promise as a tool to aid the diagnosis of glaucoma.

Visualização imersiva e interação gestual com dados médicos / Immersive visualization and gestural interaction withmMedical data

As tecnologias de Realidade Virtual vêm se desenvolvendo bastante nos últimos anos e com elas a sua utilização em diversas áreas, dentre as quais, a medicina. Testes, treinamentos, e alguns tipos de tratamento que seriam complicados de serem ser feitos com abordagens tradicionais agora podem ser produzidos graças aos elementos disponíveis nas tecnologias de realidade virtual. OBJETIVO: Propor uma ferramenta de visualização volumétrica em realidade virtual que possua interação gestual e ferramentas de segmentação de imagens e que facilite o processo de análise de dados médicos. MÉTODOS: Aquisição das imagens, geração dos dados volumétricos, desenvolvimento das ferramentas de interação e desenvolvimento da interface gestual. RESULTADOS: O sistema obteve êxito na geração e visualização de dados médicos tendo bom desempenho em testes realizados na avaliação de usabilidade de sua interface gestual. CONCLUSÃO: O sistemas e mostra como uma promissora alternativa para a visualização de dados médicos em realidade virtual.

The Virtual Reality technologies have been developing greatly in recent years and with them their use in various fields, among which the medicine. Some testings, trainings, and some types of treatments that would be complicated to be made with traditional approaches can now be produced thanks to the elements available in the virtual reality technologies. OBJECTIVE: To propose a volume visualization tool in virtual reality that has gestural interaction and image segmentation tools and facilitates the process of analysis of medical data. METHODS: Image acquisition volumetric data generation, development of the interaction tools and development of the gestural interface. RESULTS: The system was successful in the generation and visualization of medical data, having good performance in usability tests of its gestural interface. CONCLUSION: The system is a promising alternative for viewing medical data in virtual reality.

Texture analysis of masses in digitized mammograms using Gleason and Menhinick diversity indexes

INTRODUCTION: Breast cancer is the second most common type of cancer in the world, being more common among women and representing 22% of all new cancer cases every year. The sooner it is diagnosed, the better the chances of a successful treatment are. Mammography is one way to detect non-palpable tumors that cause breast cancer. However, it is known that the sensitivity of this exam can vary considerably due to factors such as the specialist's experience, the patient's age and the quality of the images obtained in the exam. The use of computational techniques involving artificial intelligence and image processing has contributed more and more to support the specialists in obtaining a more precise diagnosis. METHODS: This paper proposes a methodology that exclusively uses texture analysis to describe features of masses in digitized mammograms. To increase the efficiency of texture feature extraction, the diversity index's capability to detect patterns of species co-occurrence is used. For this purpose, the Gleason and Menhinick indexes are used. Finally, the extracted texture is classified using the Support Vector Machine, looking to differentiate the malignant masses from the benign. RESULTS: The best result was obtained using the Gleason index, with 86.66% accuracy, 90% sensitivity, 83.33% specificity and an area under the ROC Curve (Az) of 0.86. CONCLUSION: Both indexes showed statistically similar performance; however, the Gleason index was slightly superior.