Antonio Oseas de Carvalho Filho

Automatic detection of solitary lung nodules using quality threshold clustering, genetic algorithm and diversity index

OBJECTIVE The present work has the objective of developing an automatic methodology for the detection of lung nodules. METHODOLOGY The proposed methodology is based on image processing and pattern recognition techniques and can be summarized in three stages. In the first stage, the extraction and reconstruction of the pulmonary parenchyma is carried out and then enhanced to highlight its structures. In the second stage, nodule candidates are segmented. Finally, in the third stage, shape and texture features are extracted, selected and then classified using a support vector machine. RESULTS In the testing stage, with 140 new exams from the Lung Image Database Consortium image collection, 80% of which are for training and 20% are for testing, good results were achieved, as indicated by a sensitivity of 85.91%, a specificity of 97.70% and an accuracy of 97.55%, with a false positive rate of 1.82 per exam and 0.008 per slice and an area under the free response operating characteristic of 0.8062. CONCLUSION Lung cancer presents the highest mortality rate in addition to one of the smallest survival rates after diagnosis. An early diagnosis considerably increases the survival chance of patients. The methodology proposed herein contributes to this diagnosis by being a useful tool for specialists who are attempting to detect nodules.

Classification of breast regions as mass and non-mass based on digital mammograms using taxonomic indexes and SVM

Breast cancer is the second most common type of cancer in the world. Several computer-aided detection and diagnosis systems have been used to assist health experts identify suspicious areas that are difficult to perceive with the human eye, thus aiding in the detection and diagnosis of cancer. This work proposes a methodology for the discrimination and classification of regions extracted from mammograms as mass and non-mass. The Digital Database for Screening Mammography (DDSM) was used in this work for the acquisition of mammograms. The taxonomic diversity index (Δ) and the taxonomic distinctness (Δ(⁎)), which were originally used in ecology, were used to describe the texture of the regions of interest. These indexes were computed based on phylogenetic trees, which were applied to describe the patterns in regions of breast images. Two approaches were used for the analysis of texture: internal and external masks. A support vector machine was used to classify the regions as mass and non-mass. The proposed methodology successfully classified the masses and non-masses, with an average accuracy of 98.88%.

Automatic detection of small lung nodules in 3D CT data using Gaussian mixture models, Tsallis entropy and SVM

Lung cancer stands out among all other types of cancer for presenting one of the highest incidence rates and one of the highest rates of mortality. Unfortunately, this disease is often diagnosed late, affecting the treatment result. One of the hopes for changing this scenario lies in achieving a more precocious diagnosis of lung cancer through low-dose computed tomography, used as a screening method in risk groups of smokers or former smokers with elevated tobacco load. In order to help specialists in this search and identification of lung nodules in tomographic images, many research centers develop computer-aided detection systems (CAD systems) which are intended to automate procedures. This work has the purpose of developing a methodology for automatic detection of small lung nodules (with sizes between 2 and 10mm) through image processing and pattern recognition techniques. Some of these techniques are widely used in similar applications, as is the case of the region growing technique for segmentation of the pulmonary parenchyma. Other techniques, with more restricted application, are the Gaussian mixture models and the Hessian matrix for segmentation of structures inside the lung, Tsalliss and Shannons entropy measurements as texture descriptors, and support vector machine to classify suspect regions as either nodules or non-nodules. The results achieved with the use of this set of techniques, applied to a sample with 28 exams from a public database, showed that small nodules were detected with a sensitivity of 90.6%, a specificity of 85% and an accuracy of 88.4%. The rate of false positives per exam was of 1.17. Graphical abstractDisplay Omitted HighlightsWe present a methodology for automatic detection of small lung nodules.Gaussian Mixture Models are used to segment regions that are likely to be nodules.False positive reduction with SVM and entropy measures of Tsallis and Shannon.Tests use a sample of 72 nodules occurring in 28 exams from LIDC image database.Presents sensitivity of 90.6%, specificity of 85%, accuracy of 88.4%, and 1.17 FP/i.

Automatic Detection of Masses in Mammograms Using Quality Threshold Clustering, Correlogram Function, and SVM

Breast cancer is the second most common type of cancer in the world. Several computer-aided detection and diagnosis systems have been used to assist health experts and to indicate suspect areas that would be difficult to perceive by the human eye; this approach has aided in the detection and diagnosis of cancer. The present work proposes a method for the automatic detection of masses in digital mammograms by using quality threshold (QT), a correlogram function, and the support vector machine (SVM). This methodology comprises the following steps: The first step is to perform preprocessing with a low-pass filter, which increases the scale of the contrast, and the next step is to use an enhancement to the wavelet transform with a linear function. After the preprocessing is segmentation using QT; then, we perform post-processing, which involves the selection of the best mass candidates. This step is performed by analyzing the shape descriptors through the SVM. For the stage that involves the extraction of texture features, we used Haralick descriptors and a correlogram function. In the classification stage, the SVM was again used for training, validation, and final test. The results were as follows: sensitivity 92.31 %, specificity 82.2 %, accuracy 83.53 %, mean rate of false positives per image 1.12, and area under the receiver operating characteristic (ROC) curve 0.8033. Breast cancer is notable for presenting the highest mortality rate in addition to one of the smallest survival rates after diagnosis. An early diagnosis means a considerable increase in the survival chance of the patients. The methodology proposed herein contributes to the early diagnosis and survival rate and, thus, proves to be a useful tool for specialists who attempt to anticipate the detection of masses.

Lung nodule classification using artificial crawlers, directional texture and support vector machine

Abstract Lung cancer is the major cause of death among patients with cancer throughout the world. The main symptom that indicate the lung cancer is the presence of lung nodules. This work proposes a methodology to classify lung nodule and non-nodule using texture features. The state-of-art of the presented work are the adaption of the Artificial Crawlers and Rose Diagram techniques for representing patterns over 3D images. Several information are extracted based on the texture behavior of these methods, allowing the correct classification of lung nodules candidates using Support Vector. Objective: This work proposes a methodology to classify lung nodule candidates and non-nodule candidates based on computed tomography (CT) images. Methodology: The Lung Image Database Consortium (LIDC-IDRI) image database is employed for our tests. Three techniques are employed to extract texture measurements. The first technique is artificial crawlers (ACs), an artificial life algorithm. The second technique uses the rose diagram (RD) to extract directional measurements. The third technique is a hybrid model that combines texture measurements from artificial crawlers and the rose diagram. The support vector machine (SVM) classifier with a radial basis kernel is employed. Results: In the testing stage, we used 833 scans from the LIDC-IDRI database. For the application of the methodology, we decided to divide the whole database into two groups, training and testing. We used partitions of training and testing of 20/80%, 40/60%, 60/40% and 80/20%. The division was repeated 5 times at random. We reached a mean accuracy (mACC) of 94.30%, a mean sensitivity (mSEN) of 91.86%, a mean specificity (mSPC) of 94.78%, a coefficient of accuracy variance (CAv) of 1.61% and a mean area under the receiver operating characteristic (mROC) curves of 0.922. Conclusion: Lung cancer has the highest mortality rate and one of the smallest survival rates after diagnosis. An early diagnosis increases the survival chance of patients. The proposed methodology is a useful tool for specialists in the detection of nodules. We believe we contribute for the expert system field because 1) the adaption of the Artificial Crawlers and Rose Diagram methods as 3D texture descriptors is innovative and contains great potential; 2) we adapted and developed measurements from the 3D texture descriptors; and 3) the simplicity and discriminative power of the methodology can be extended to applications based on images with other contexts.

Lung-Nodule Classification Based on Computed Tomography Using Taxonomic Diversity Indexes and an SVM

The present work aims to develop a methodology for classifying lung nodules using the LIDC-IDRI image database. The proposed methodology is based on image-processing and pattern-recognition techniques. To describe the texture of nodule and non-nodule candidates, we use the Taxonomic Diversity and Taxonomic Distinctness Indexes from ecology. The calculation of these indexes is based on phylogenetic trees, which, in this work, are applied to the candidate characterization. Finally, we apply a Support Vector Machine (SVM) as a classifier. In the testing stage, we used 833 exams from the LIDC-IDRI image database. To apply the methodology, we divided the complete database into two groups for training and testing. We used training and testing partitions of 20/80 %, 40/60 %, 60/40 %, and 80/20 %. The division was repeated five times at random. The presented methodology shows promising results for classifying nodules and non-nodules, presenting a mean accuracy of 98.11 %. Lung cancer presents the highest mortality rate and has one of the lowest survival rates after diagnosis. Therefore, the earlier the diagnosis, the higher the chances of a cure for the patient. In addition, the more information available to the specialist, the more precise the diagnosis will be. The methodology proposed here contributes to this.

Computer-Aided Diagnosis of Lung Nodules in Computed Tomography by Using Phylogenetic Diversity, Genetic Algorithm, and SVM

Lung cancer is pointed as the major cause of death among patients with cancer throughout the world. This work is intended to develop a methodology for diagnosis of lung nodules using images from the Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). The proposed methodology uses image processing and pattern recognition techniques. In order to differentiate between the patterns of malignant and benign nodules, we used phylogenetic diversity by means of particular indexes, that are: intensive quadratic entropy, extensive quadratic entropy, average taxonomic distinctness, total taxonomic distinctness, and pure diversity indexes. After that, we applied the genetic algorithm for selection of the best model. In the tests’ stage, we applied the proposed methodology to 1405 (394 malignant and 1011 benign) nodules. The proposed work presents promising results at the classification into malignant and benign, achieving accuracy of 92.52%, sensitivity of 93.1% and specificity of 92.26%. The results demonstrated a good rate of correct detections using texture features. Since a precocious detection allows a faster therapeutic intervention, thus a more favorable prognostic to the patient, we propose herein a methodology that contributes to the area in this aspect.

Taxonomic indexes for differentiating malignancy of lung nodules on CT images

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.

Method of differentiation of benign and malignant masses in digital mammograms using texture analysis based on phylogenetic diversity

Abstract Breast cancer is a disease resulting from the multiplication of abnormal breast cells, which form masses. Every year, breast cancer kills more than 500,000 women around the world. In 2015, 570,000 women died of breast cancer. When detected early, the five-year survival rate for breast cancer exceeds 80% of cases. Early diagnosis of breast cancer is critical for the survival of the patient. Screening by mammography is the most promising means for early diagnosis. This article presents a method of classifying malignant and benign breast tissue using digital mammography exams. This method employs texture descriptors from all image regions, including to the inner regions. This approach enables a more detailed texture description of the analyzed region of interest. The feature extraction is based on phylogenetic indexes. Then, classification is conducted using multiple classifiers. Experiments are performed to verify the performance of the proposed method. Results show that the method achieves 99.73% accuracy, 99.41% sensitivity, 99.84% specificity, and a receiver operating characteristic (ROC) curve with a value of one when using images of the Digital Database for Screening Mammography. An accuracy of 100% is achieved when using the Mammography Imaging Analysis Society image database. The use of phylogenetic indexes to describe patterns in regions of mammography images in both external and internal areas is thus effective in the categorization of malignant and benign tumors, thereby making the proposed method a robust tool for specialists.

Classification of breast tissues into mass and non-mass by means of the micro-genetic algorithm, phylogenetic trees, LBP and SVM

This work has the objective of developing a methodology for the classification of regions of interest (ROI) extracted from mammograms into masses and non-masses. To this end, we conducted a comparative study by combining several techniques in the various stages of the problem. We compared several texture-based techniques for the classification of ROIs. This study combines image processing, phylogenetic trees (PT), local binary patterns (LBP), support vector machines (SVM) and the micro-genetic algorithm (GA). The analysis of texture is performed, either through the combination PT/LBP or with grey levels, to compute the taxonomic diversity () and taxonomic distinction (*) indexes extracted from sub-regions (circular, circular crown, internal mask, external mask and the combination of internal and external mask) of an ROI. A GA is used to estimate the best phylogenetic weights. Then, its results are compared with the results achieved with the use of PT only. We also analyse the behaviour of the methodology when using the ROIs with and without enhancement. This enhancement consists of the application of a mean filter and the contrast-limited adaptive histogram equalisation (CLAHE). PTs and SVM were used to perform the selection of features. To evaluate the performance of the methodologies under analysis, we used the following metrics: sensitivity, specificity, accuracy and area under the receiver operating characteristic (ROC) curve (). Sensitivity and specificity measure the efficiency of the classifier at the correct detection of positive (masses) and negative (non-masses) cases, respectively. Accuracy measures the performance of the classification in both cases. The ROC curve is the graphical representation of the pairs (1-specificity, sensitivity). is the area formed by the ROC curve, which equals to 1 in an ideal test. The comparison of the possible combinations for each stage of the study revealed the following results. In the analyses without feature selection, the best results were (1) 100% accuracy and of 0.99 for the combination of PT, LBP and internal masks and (2) 99.5% accuracy and of 0.99 for the combination of GA, LBP and internal masks for the extraction of features. In the analyses with feature selection, the best results were (1) 100% accuracy and of 1.0 for the combination of GA and LBP (feature extraction) with the union of internal and external masks and (2) 98.5% accuracy and of 0.99 for the combination of PT, LBP and the union of internal and external masks.