An automatic microcalcification detection system based on a hybrid neural network classifier

This paper presents a machine learning based approach for the discrimination of malignant and benign microcalcification (MC) clusters in digital mammograms. A series of morphological operations was carried out to facilitate the feature extraction from segmented microcalcification. A combination of morphological, texture, and distribution features from individual MC components and MC clusters were extracted and a correlation-based feature selection technique was used. The clinical relevance of the selected features is discussed. The proposed method was evaluated using three different databases: Optimam Mammography Image Database (OMI-DB), Digital Database for Screening Mammography (DDSM), and Mammographic Image Analysis Society (MIAS) database. The best classification accuracy (%) was achieved for OPTIMAM using a stack generalization classifier with 10-fold cross validation obtaining an A value equal to .

This paper presents an approach for early breast cancer diagnostic by employing combination of artificial neural networks (ANN) and wavelet based subband image decomposition which detect microcalcification in digital mammograms. The microcalcifications correspond to high-frequency components of the image spectrum, detection of microcalcifications is achieved by decomposing the mammograms into different frequency subbands, suppressing the low-frequency subband, and finally, reconstructing the mammogram from the subbands containing only high frequencies. For this approach we employed different types of wavelet packets. We used the result as an input of neural network for classification. The proposed methodology is tested using the Nijmegen and the Mammographic Image Analysis Society (MIAS) mammographic databases and images collected from local hospitals. Results are presented as the receiver operating characteristic (ROC) performance and are quantified by the area under the ROC curve.

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.

Receiver Operating Characteristic (ROC) curves can be used to describe detectability of noise-limited signals. The basic concepts underlying the theory of ROC curves and the experimental determination of ROC curves are discussed. ROC curves are used to describe the detectability of the image of 2 mm Lucite beads (similar to certain kinds of small gall-stones) in a noisy background of radiographic mottle. Results are shown for four typical radiographic screen-film combinations of differing optical and noise properties. The qualitative relationship between the ROC curves and the mathematical model describing radiographic mottle is examined. The ROC curves describing the detectability of the bad images when radiographed with two screen-film combinations of equal system speed but different optical characteristics are compared to the quality of blood vessel images obtained with the same screen-film combinations. It is concluded that it is important to distinguish between the assessment of image quality based on the relative sharpness of high contrast images, versus the assessment of image quality based on the relative detectability of low contrast noise-limited images.

295: Accuracy of Various Methods of B-Line Assessment In the Diagnosis of Congestive Heart Failure Compared by Receiver Operating Characteristic Curves

Background: HER2+ breast cancer (BC) is a heterogeneous disease. Despite the novel targeted therapies against HER2, 20% of patients relapse. In this context, the identification of prognostic and predictor biomarkers is needed.MicroRNAs are involved in BC development and prognosis. We aim at assessing the prognostic significance of two micro-RNAs (named as A and B) in HER2+ BC tissue, to propose signature to predict relapse in this setting of patients.Methods: This study was conducted in a cohort of 46 non-consecutive HER2+ BC patients diagnosed at Hospital Clínico València-INCLIVA. All BC patients received standard treatment for localized disease. RNA was isolated from formalin-fixed paraffin-embedded primary tumor and retro-transcribed to cDNA. MicroRNA expression levels were measured by real-time qPCR and results were normalized according to the expression of housekeeping mir-16 miRNA.Non-parametric Mann-Whitney U test was used to ascertain the statistical significance of differences in miRNA expression levels between disease-free and relapse. Receiver operator characteristics (ROC) curves were constructed and AUC, accuracy, specificity and sensitivity, were calculated as a biomarker performance parameter. The best cutoff value was established based on the highest value obtained in ROC curve analysis according to the maximization of the sum of sensitivity and specificity. Kaplan-Meier curves were plotted for disease-free survival (DFS) based on the best cutoff value. As both microRNA showed high correlation (r=0.85), a genetic signature was developed using Principal Component Analysis (PCA) and extracting the first component. MicroRNA targeted genes were downloaded from miRTarBase (release 7.0). Cytoscape (v3.8.0) and ClueGo (v2.5.6) and were used to perform functional enrichment analysis with the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway database. To select significant terms/pathways, p-values were adjusted by the Benjamni-Hochberg method (p<0.05). Results: The expression of both microRNA-A and B was higher in the primary tumor of those patients who relapsed after treatment compared to those free of disease (p= 0.003 and 0.0002, respectively). ROC curves demonstrated that microRNA-A and B might discriminate those HER2+ BC patients who relapse. MicroRNA-A predicts relapse with an AUC 0.740, sensitivity of 0.810, specificity of 0.583 and accuracy of 0.689, and microRNA-B presented an AUC 0.821, sensitivity of 0.810, specificity of 0.750, and accuracy of 0.778. The survival analysis showed that microRNA-A and B strongly predicted shorter DFS (p= 0.014 and 0.0012, respectively).Two-microRNA signature combining (PCA1= 99.4% absorbed variance) microRNA-A and microRNA-B expression levels had high performance in discriminating relapsed from non-relapsed HER2+ BC patients (AUC 0.748, accuracy 0.689, sensitivity 1, specificity 0.417). Signature predicted DFS (p= 0.009). Functional enrichment analysis returned 55 significant pathways. Of these, important pathways related to tumorigenesis and response to treatment were enriched. Interestingly, P53 pathway, apoptosis, and cell cycle were in the top 5 enriched pathways. Conclusions: We demonstrated the value of microRNA A and B as potential prognostic biomarkers. High expression was related to poor prognosis in over cohort of HER2+ BC patients. Both microRNAs were able to strongly discriminate patients who will relapse and predict shorter DFS. Moreover, our signature was able to predict the outcome, suggesting a potential prognostic role at diagnosis. Both microRNAs are related to important biological pathways associated to BC progression. Further investigations to optimize the micro-RNA signature are on-going. Citation Format: Anna Adam-Artigues, Juan Antonio Carbonell-Asíns, Sheila Zúñiga-Trejos, Santiago Moragón, Maria Teresa Martínez, Cristina Hernando, Eduardo Tormo, Octavio Burgués, Ana Lluch, Begoña Bermejo, Pilar Eroles, Juan Miguel Cejalvo. Identification of a novel two-microRNA signature for recurrence prediction in HER2 positive breast cancer [abstract]. In: Proceedings of the 2020 San Antonio Breast Cancer Virtual Symposium; 2020 Dec 8-11; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2021;81(4 Suppl):Abstract nr PS19-20.

Summary form only given. There has been substantial progress in both intelligent systems and robotics in recent years. While in the past robots were most successful in traditional industrial environments, new generations of hybrid intelligent robotic systems are being developed which focus on higher cognitive capabilities, including reasoning learning and language communication. In this paper we give an overview of learning neural robots from a perspective of integrative hybrid intelligent systems and illustrate some new developments including also examples under development in the Centre for Hybrid Intelligent Systems.

High false-positive recall rate is an important clinical issue that reduces efficacy of screening mammography. Aiming to help improve accuracy of classification between the benign and malignant breast masses and then reduce false-positive recalls, we developed and tested a new computer-aided diagnosis (CAD) scheme for mass classification using a database including 600 verified mass regions. The mass regions were segmented from regions of interest (ROIs) with a fixed size of 512×512 pixels. The mass regions were first segmented by an automated scheme, with manual corrections to the mass boundary performed if there was noticeable segmentation error. We randomly divided the 600 ROIs into 400 ROIs (200 malignant and 200 benign) for training, and 200 ROIs (100 malignant and 100 benign) for testing. We computed and analyzed 124 shape, texture, contrast, and spiculation based features in this study. Combining with previously computed 27 regional and shape based features for each of the ROIs in our database, we built an initial image feature pool. From this pool of 151 features, we extracted 13 features by applying the Sequential Forward Floating Selection algorithm on the ROIs in the training dataset. We then trained a multilayer perceptron model using these 13 features, and applied the trained model to the ROIs in the testing dataset. Receiver operating characteristic (ROC) analysis was used to evaluate classification accuracy. The area under the ROC curve was 0.8814±0.025 for the testing dataset. The results show a higher CAD mass classification performance, which needs to be validated further in a more comprehensive study.

In this paper, we present a novel approach to detect microcalcifications (MCCs) in the mammograms. Microcalcification has approximately a size of several pixels in diameter on early cancer mammograms and has low contrast. So it is difficult to detection the microcalcifications. The essential idea of propose approach is to apply morphological and wavelet transform to locate the micro calcifications in digital mammograms. The presented method overcome higher true positive rate (TPR) but higher false positive (FP) problem by using single wavelet transform or morphology. The experiment results show the presented method has higher TPR and reducing FP obviously. Using the mammogram data form the Mammographic Image Analysis Society (MIAS) database the TPR is 80.2% at the cost of average 2.5 false microcalcifications per region of interest (ROI)

A hybrid intelligent system for medical data classification

Objective To investigate features of fasting plasma glucose (FPG) during different trimesters and hemoglobin A1c (HbA1c) in the third trimester of pregnant women in Zhujing Region of Shanghai. Methods A total of 606 cases of pregnant women who received prenatal examination and 75 g oral glucose tolerance test (OGTT) in Jinshan Branch of Shanghai Sixth People′s Hospital from January 1 to December 31, 2014 were collected as research subjects. According to the results of 75 g OGTT, they were divided into gestational diabetes mellitus (GDM) group (n=136) and non-GDM group (n=470). The clinical data, such as age, body mass index (BMI), as well as the concentration of FPG during different pregnancy trimesters and level of HbA1c in the third trimester were collected retrospectively in both two groups by retrospective analysis method. According to the quartile method, level of HbA1c in the third trimester of all subjects were divided into four ranges: Q1 (HbA1c level<5.1%), Q2 (5.1%≤HbA1c level<5.2%), Q3 (5.2%≤HbA1c level<5.5%), and Q4 (HbA1c level≥5.5%), respectively. The age, BMI, concentrations of FPG and the level of HbA1c between two groups were compared by independent-samples t test. Chi-square test was used to compare the GDM incidence of all subjects with different ranges of HbA1c level in the third trimester, and further comparison was conducted by adjusting inspection level. Then receiver operator characteristic (ROC) curve of HbA1c level in the third trimester for predicting the incidence of GDM was drawn, and the area under ROC curve (ROC-AUC) was calculated. The optimal critical value of HbA1c level in the third trimester for predicting the incidence of GDM was obtained when the Youden index reaching the maximum value. And its sensitivity and specificity were calculated. This study met the requirements of the World Medical Association Declaration of Helsinki revised in 2013. Results ①The age and BMI of GDM group were higher than those in non-GDM group, and there were statistically significant differences (t=5.306, 5.250; P<0.001). Among the subjects in GDM group, the concentration of FPG in second trimester was the highest among 3 trimesters, which was (4.9±0.6) mmol/L, and the concentration of FPG in second trimester was higher than that in first and third trimester, respectively, and both the differences were statistically significant (t=2.087, 1.960; P=0.039, 0.041). Among the subjects in non-GDM group, the concentration of FPG in first trimester was the highest among 3 trimesters, which was (4.6±0.3) mmol/L, and the concentration of FPG in first trimester was higher than that in second and third trimester, respectively, and both the differences were statistically significant (t=15.230, 5.613; P<0.001). The concentration of FPG in first, second and third trimesters of GDM group were higher than those of non-GDM group, respectively, and there were statistically significant differences (t=5.416, 15.526, 4.471; P<0.001). Besides, HbA1c level in third trimester of GDM group was (5.6±0.4)%, which was higher than that of non-GDM group (5.4±0.4)%, and there was significant difference (t=5.845, P<0.01). ②There was statistical difference in GDM incidences in all subjects with different ranges of HbA1c levels in third trimester (χ2=22.707, P<0.001). Multiple comparison results showed that the incidences of GDM in all subjects with Q1 and Q2 ranges of HbA1c levels in third trimester were higher than that in subjects with Q4 range of HbA1c levels in third trimester, respectively, and both the differences were statistically significant (χ2=15.071, 16.785; P<0.001). ③The results of ROC curve analysis of HbA1c level in third trimester in predicting the incidence of GDM showed that the ROC-AUC was 0.647 (95%CI: 0.625-0.672, P<0.001), and the optimal cut-off value of HbA1c level in third trimester to predict GDM incidence was 5.5%, and the sensitivity of HbA1c level in predicting the incidence of GDM was 63.4%, and the sensitivity was 69.7%. Conclusions The concentrations of FPG in GDM pregnant women in Zhujing Region of Shanghai begin to increase from the first trimester and peak during the second trimester, and decrease during the third trimester after lifestyle intervention. It is advisable for GDM pregnant women to control HbA1c levels below 5.5% during the third trimester. Key words: Diabetes, gestational; Fasting plasma glucose; Hemoglobin A, glycosylated; Glucose tolerance test; ROC curve; Forecasting; Pregnant women

The presence of microcalcification clusters in digital mammograms is a primary indicator of early stages of malignant types of breast cancer and its detection is important to prevent the disease. This paper uses a procedure for the classification of microcalcification clusters in mammograms using sequential Difference of Gaussian filters (DoG) and feedforward Neural Networks (NN). Three methods using class separability, forward sequential search and genetic algorithms for feature selection are compared. We found that the use of Genetic Algorithms (GAs) for selecting the features from microcalcifications and microcalcification clusters that will be the inputs of a feedforward Neural Network (NN) results mainly in improvements in overall accuracy, sensitivity and specificity of the classification.

This paper presents a computer-aided diagnosis (CAD) system for automatic detection of clustered microcalcifications (MCs) in digitized mammograms. The proposed system consists of two main steps. First, potential MC pixels in the mammograms are segmented out by using four mixed features consisting of two wavelet features and two gray level statistical features and then the potential MC pixels are labeled into potential individual MC objects by their spatial connectivity. Second, MCs are detected by extracting a set of 17 features from the potential individual MC objects. The classifier which is used in the first step is a multilayer feedforward neural network classifier but for the second step we have used Adaboost with SVM-based component classifier. Component classifiers which we used in our combining method are SVM classifiers with RBF kernel. The method was applied to a database of 40 mammograms (Nijmegen database) containing 105 clusters of MCs. A free-response operating characteristics (FROC) curve is used to evaluate the performance of CAD system. Results show that the proposed system gives quite satisfactory performance. In particular, 89.55% mean true positive detection rate is achieved at the cost of 0.921 false positive per image.

Receiver operating characteristic (ROC) analysis has been used in a variety of settings since it was first declassified by the United States government over 60 years ago. One venue in which it has received particular attention is in the field of radiology. In radiology, as in other areas of application, ROC analysis is used to assess the ability of a diagnostic test to distinguish between two opposing states. One useful descriptor in ROC analysis is the area under the ROC curve. At times, it is useful and insightful to average ROC curves in order to create a single curve that summarizes all of the data from multiple readers. In this paper, we investigate the impact of correlated readings on the average area under two readers' ROC curves using several common averaging strategies, and then apply the results to a radiologic study.

We investigated the application of multiresolution global and local texture features to reduce false-positive detection in a computerized mass detection program. One hundred and sixty-eight digitized mammograms were randomly and equally divided into training and test groups. From these mammograms, two datasets were formed. The first dataset (manual) contained four regions of interest (ROIs) selected manually from each of the mammograms. One of the four ROIs contained a biopsy-proven mass and the other three contained normal parenchyma, including dense, mixed dense/fatty, and fatty tissues. The second dataset (hybrid) contained the manually extracted mass ROIs, along with normal tissue ROIs extracted by an automated Density-Weighted Contrast Enhancement (DWCE) algorithm as false-positive detections. A wavelet transform was used to decompose an ROI into several scales. Global texture features were derived from the low-pass coefficients in the wavelet transformed images. Local texture features were calculated from the suspicious object and the peripheral subregions. Linear discriminant models using effective features selected from the global, local, or combined feature spaces were established to maximize the separation between masses and normal tissue. Receiver Operating Characteristic (ROC) analysis was conducted to evaluate the classifier performance. The classification accuracy using global features were comparable to that using local features. With both global and local features, the average area, Az, under the test ROC curve, reached 0.92 for the manual dataset and 0.96 for the hybrid dataset, demonstrating statistically significant improvement over those obtained with global or local features alone. The results indicated the effectiveness of the combined global and local features in the classification of masses and normal tissue for false-positive reduction.