ABSTRACT
ABSTRACT The objective of this work is to identify the malignant lung nodules accurately and early with less false positives. 'Nodule' is the 3mm to 30mm diameter size tissue clusters present inside the lung parenchyma region. Segmenting such a small nodules from consecutive CT scan slices are a challenging task. In our work Auto-seed clustering based segmentation technique is used to segment all the possible nodule candidates. Efficient shape and texture features (2D and 3D) were computed to eliminate the false nodule candidates. The change in centroid position of nodule candidates from consecutive slices was used as a measure to remove the vessels. The two-stage classifier is used in this work to classify the malignant and benign nodules. First stage rule-based classifier producing 100 % sensitivity, but with high false positive of 12.5 per patient scan. The BPN based ANN classifier is used as the second-stage classifier which reduces a false positive to 2.26 per patient scan with a reasonable sensitivity of 88.8%. The Rate of Nodule Growth (RNG) was computed in our work to measure the nodules growth between the two scans of the same patient taken at different time interval. Finally, the nodule growth predictive measure was modeled through the features such as compactness (CO), mass deficit (MD), mass excess (ME) and isotropic factor(IF). The developed model results show that the nodules which have low CO, low IF, high MD and high ME values might have the potential to grow in future.
ABSTRACT
Breast cancer is an important global health problem, and the most common type of cancer among women. Late diagnosis significantly decreases the survival rate of the patient; however, using mammography for early detection has been demonstrated to be a very important tool increasing the survival rate. The purpose of this paper is to obtain a multivariate model to classify benign and malignant tumor lesions using a computer-assisted diagnosis with a genetic algorithm in training and test datasets from mammography image features. A multivariate search was conducted to obtain predictive models with different approaches, in order to compare and validate results. The multivariate models were constructed using: Random Forest, Nearest centroid, and K-Nearest Neighbor (K-NN) strategies as cost function in a genetic algorithm applied to the features in the BCDR public databases. Results suggest that the two texture descriptor features obtained in the multivariate model have a similar or better prediction capability to classify the data outcome compared with the multivariate model composed of all the features, according to their fitness value. This model can help to reduce the workload of radiologists and present a second opinion in the classification of tumor lesions.