Detection of single and clustered microcalcifications in mammograms using fractals models and neural networks

A Computer Aided Breast Cancer Detection Using Unit-Linking Pulse Coupled Neural Network & Multiphase Level Set Method

Breast cancer is one of the lethal diseases with high mortality rates among women. An early detection and diagnosis of the disease can help increase the survival rate. Distinguishing a normal breast tissue from a cancerous one proves to be ambiguous for a Radiologist. A computer aided system can help a radiologist in better and efficient diagnosis. This paper aims at detection and classification of benign and malignant mammogram images with Unit-linking Pulse Coupled Neural Network combined with Multiphase level set Method. While Unit linking Pulse Coupled Neural Network (PCNN) helps in coarse feature extraction, Multi phase Level Set method helps in extracting minute details and hence, better classification. The proposed method is tested with images from MIAS open-source database. Performance of the proposed method is measured using sensitivity, accuracy, specificity and false positive rate. Experiments show that the proposed method gives satisfactory results when compared to the state-of-art methods. The sensitivity obtained by the proposed method is 95.16%, an accuracy of 96.76%, the False Positive Rate (FPR) is as less as 0.85% and specificity of 97.12%.

Deep Learning Capabilities for the Categorization of Microcalcification

Breast cancer is the most common cancer in women worldwide. It is the most frequently diagnosed cancer among women in 140 countries out of 184 reporting countries. Lesions of breast cancer are abnormal areas in the breast tissues. Various types of breast cancer lesions include (1) microcalcifications, (2) masses, (3) architectural distortion, and (4) bilateral asymmetry. Microcalcification can be classified as benign, malignant, and benign without a callback. In the present manuscript, we propose an automatic pipeline for the detection of various categories of microcalcification. We performed deep learning using convolution neural networks (CNNs) for the automatic detection and classification of all three categories of microcalcification. CNN was applied using four different optimizers (ADAM, ADAGrad, ADADelta, and RMSProp). The input images of a size of 299 × 299 × 3, with fully connected RELU and SoftMax output activation functions, were utilized in this study. The feature map was obtained using the pretrained InceptionResNetV2 model. The performance evaluation of our classification scheme was tested on a curated breast imaging subset of the DDSM mammogram dataset (CBIS–DDSM), and the results were expressed in terms of sensitivity, specificity, accuracy, and area under the curve (AUC). Our proposed classification scheme outperforms the ability of previously used deep learning approaches and classical machine learning schemes.

Machine-learning models for predicting survivability in COVID-19 patients

COVID-19 is a disease currently ravaging the world, bringing unprecedented health and economic challenges to several nations. There are presently close to five million reported cases in over 200 countries with fatalities numbering over 300,000 persons. This study presents machine-learning models for the prediction and visualization of the significant factors that determine the survivability of COVID-19 patients. This study develops prediction models using a decision tree, logistic regression (LR), gradient boosting, and LR algorithms to identify the significant factors and predict the survivability of COVID-19 patients. The results of the simulation showed that the LR model had the lowest prediction accuracy. The other three showed over 95% correct accuracy and indicated that the essential factors in determining patients' survivability were underlying health conditions and age. The findings of this study agreed with the medical claims that patients with underlying health challenges and those advanced in age are liable to have complications; hence, providing a research-based credence to this belief. This proposed model thus serves as a decision support system for the management of COVID-19 patients, as well as predicts a patient’s chances of survival at the first presentation at the hospitals.

Predicting Inpatient Length of Stay After Brain Tumor Surgery: Developing Machine Learning Ensembles to Improve Predictive Performance

BACKGROUND

Current outcomes prediction tools are largely based on and limited by regression methods. Utilization of machine learning (ML) methods that can handle multiple diverse inputs could strengthen predictive abilities and improve patient outcomes. Inpatient length of stay (LOS) is one such outcome that serves as a surrogate for patient disease severity and resource utilization.

OBJECTIVE

To develop a novel method to systematically rank, select, and combine ML algorithms to build a model that predicts LOS following craniotomy for brain tumor.

METHODS

A training dataset of 41 222 patients who underwent craniotomy for brain tumor was created from the National Inpatient Sample. Twenty-nine ML algorithms were trained on 26 preoperative variables to predict LOS. Trained algorithms were ranked by calculating the root mean square logarithmic error (RMSLE) and top performing algorithms combined to form an ensemble. The ensemble was externally validated using a dataset of 4592 patients from the National Surgical Quality Improvement Program. Additional analyses identified variables that most strongly influence the ensemble model predictions.

RESULTS

The ensemble model predicted LOS with RMSLE of .555 (95% confidence interval, .553-.557) on internal validation and .631 on external validation. Nonelective surgery, preoperative pneumonia, sodium abnormality, or weight loss, and non-White race were the strongest predictors of increased LOS.

CONCLUSION

An ML ensemble model predicts LOS with good performance on internal and external validation, and yields clinical insights that may potentially improve patient outcomes. This systematic ML method can be applied to a broad range of clinical problems to improve patient care.

Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives

Although computer-aided diagnosis (CAD) is widely used in mammography, conventional CAD programs that use prompts to indicate potential cancers on the mammograms have not led to an improvement in diagnostic accuracy. Because of the advances in machine learning, especially with use of deep (multilayered) convolutional neural networks, artificial intelligence has undergone a transformation that has improved the quality of the predictions of the models. Recently, such deep learning algorithms have been applied to mammography and digital breast tomosynthesis (DBT). In this review, the authors explain how deep learning works in the context of mammography and DBT and define the important technical challenges. Subsequently, they discuss the current status and future perspectives of artificial intelligence-based clinical applications for mammography, DBT, and radiomics. Available algorithms are advanced and approach the performance of radiologists-especially for cancer detection and risk prediction at mammography. However, clinical validation is largely lacking, and it is not clear how the power of deep learning should be used to optimize practice. Further development of deep learning models is necessary for DBT, and this requires collection of larger databases. It is expected that deep learning will eventually have an important role in DBT, including the generation of synthetic images.

Can machine learning predict resecability of a peritoneal carcinomatosis?

BACKGROUND

Approximately 20% of initially eligible patients in a HIPEC procedure eventually underwent a simple surgical exploration. These procedures are called 'open & close' (O & C) representing up to 48% of surgery. The objective of this study was to predict the resecability of peritoneal carcinomatosis using a machine-learning model for decision-making support, for eligible patients of HIPEC.

METHODS

The study was conducted as an intention to treat based on three databases including a prospective, between January 2000 and December 2015. A propensity score allowed us to obtain two groups of comparable and matched patients. Subsequently, several algorithm models of classification were studied (simple classification, conditional tree, support vector machine, random forest) to determine the model having the best performance and accuracy.

RESULTS

Two groups of 155 patients were obtained: one group without resection and one group with resection. Nine criteria of non-resecability reflecting the organ involvement have been retained. They were coded according to their importance. Five classification algorithms were tested. The training data included 218 patients and 92 test data. The random forest model exhibited the best performance with an accuracy of close to 98%. Only two errors of predictions were observed.

DISCUSSION

The largest number of patients will allow us to improve the precision prediction. Gathering more data such as biologic, radiologic, and even laparoscopic features, should improve the knowledge of the disease and decrease the number of 'O & C' procedures.

Multiple Human-Behaviour Indicators for Predicting Lung Cancer Mortality with Support Vector Machine

Lung cancer is still one of the most common causes of death around the world, while there is overwhelming evidence that the environment and lifestyle factors are predominant causes of most sporadic cancers. However, when applying human-behaviour indicators to the prediction of cancer mortality (CM), we are often caught in a dilemma with inadequate sample size. Thus, this study extracted 30 human-behaviour indicators of seven categories (air pollution, tobacco smoking & alcohol consumption, socioeconomic status, food structure, working culture, medical level, and demographic structure) from Organization for Economic Cooperation and Development Database and World Health Organization Mortality Database for 13 countries (1998-2013), and employed Support Vector Machine (SVM) to examine the weights of 30 indicators across the 13 countries and the power for predicting lung CM for the years between 2014-2016. The weights of different human-behaviour indicators indicate that every country has its own lung cancer killers, that is, the human-behaviour indicators are country specific; Moreover, SVM has an excellent power in predicting their lung CM. The average accuracy in prediction offered by SVM can be as high as 96.08% for the 13 countries tested between 2014 and 2016.

Applications of Machine Learning in Cancer Prediction and Prognosis

Machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to “learn” from past examples and to detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to medical applications, especially those that depend on complex proteomic and genomic measurements. As a result, machine learning is frequently used in cancer diagnosis and detection. More recently machine learning has been applied to cancer prognosis and prediction. This latter approach is particularly interesting as it is part of a growing trend towards personalized, predictive medicine. In assembling this review we conducted a broad survey of the different types of machine learning methods being used, the types of data being integrated and the performance of these methods in cancer prediction and prognosis. A number of trends are noted, including a growing dependence on protein biomarkers and microarray data, a strong bias towards applications in prostate and breast cancer, and a heavy reliance on “older” technologies such artificial neural networks (ANNs) instead of more recently developed or more easily interpretable machine learning methods. A number of published studies also appear to lack an appropriate level of validation or testing. Among the better designed and validated studies it is clear that machine learning methods can be used to substantially (15–25%) improve the accuracy of predicting cancer susceptibility, recurrence and mortality. At a more fundamental level, it is also evident that machine learning is also helping to improve our basic understanding of cancer development and progression.

Using a Guided Machine Learning Ensemble Model to Predict Discharge Disposition following Meningioma Resection

Objective  Machine learning (ML) algorithms are powerful tools for predicting patient outcomes. This study pilots a novel approach to algorithm selection and model creation using prediction of discharge disposition following meningioma resection as a proof of concept. Materials and Methods  A diversity of ML algorithms were trained on a single-institution database of meningioma patients to predict discharge disposition. Algorithms were ranked by predictive power and top performers were combined to create an ensemble model. The final ensemble was internally validated on never-before-seen data to demonstrate generalizability. The predictive power of the ensemble was compared with a logistic regression. Further analyses were performed to identify how important variables impact the ensemble. Results  Our ensemble model predicted disposition significantly better than a logistic regression (area under the curve of 0.78 and 0.71, respectively, p  = 0.01). Tumor size, presentation at the emergency department, body mass index, convexity location, and preoperative motor deficit most strongly influence the model, though the independent impact of individual variables is nuanced. Conclusion  Using a novel ML technique, we built a guided ML ensemble model that predicts discharge destination following meningioma resection with greater predictive power than a logistic regression, and that provides greater clinical insight than a univariate analysis. These techniques can be extended to predict many other patient outcomes of interest.

Lung cancer prediction using neural network ensemble with histogram of oriented gradient genomic features

This paper reports an experimental comparison of artificial neural network (ANN) and support vector machine (SVM) ensembles and their "nonensemble" variants for lung cancer prediction. These machine learning classifiers were trained to predict lung cancer using samples of patient nucleotides with mutations in the epidermal growth factor receptor, Kirsten rat sarcoma viral oncogene, and tumor suppressor p53 genomes collected as biomarkers from the IGDB.NSCLC corpus. The Voss DNA encoding was used to map the nucleotide sequences of mutated and normal genomes to obtain the equivalent numerical genomic sequences for training the selected classifiers. The histogram of oriented gradient (HOG) and local binary pattern (LBP) state-of-the-art feature extraction schemes were applied to extract representative genomic features from the encoded sequences of nucleotides. The ANN ensemble and HOG best fit the training dataset of this study with an accuracy of 95.90% and mean square error of 0.0159. The result of the ANN ensemble and HOG genomic features is promising for automated screening and early detection of lung cancer. This will hopefully assist pathologists in administering targeted molecular therapy and offering counsel to early stage lung cancer patients and persons in at risk populations.

Wavelet-based 3D reconstruction of microcalcification clusters from two mammographic views: new evidence that fractal tumors are malignant and Euclidean tumors are benign

The 2D Wavelet-Transform Modulus Maxima (WTMM) method was used to detect microcalcifications (MC) in human breast tissue seen in mammograms and to characterize the fractal geometry of benign and malignant MC clusters. This was done in the context of a preliminary analysis of a small dataset, via a novel way to partition the wavelet-transform space-scale skeleton. For the first time, the estimated 3D fractal structure of a breast lesion was inferred by pairing the information from two separate 2D projected mammographic views of the same breast, i.e. the cranial-caudal (CC) and mediolateral-oblique (MLO) views. As a novelty, we define the “CC-MLO fractal dimension plot”, where a “fractal zone” and “Euclidean zones” (non-fractal) are defined. 118 images (59 cases, 25 malignant and 34 benign) obtained from a digital databank of mammograms with known radiologist diagnostics were analyzed to determine which cases would be plotted in the fractal zone and which cases would fall in the Euclidean zones. 92% of malignant breast lesions studied (23 out of 25 cases) were in the fractal zone while 88% of the benign lesions were in the Euclidean zones (30 out of 34 cases). Furthermore, a Bayesian statistical analysis shows that, with 95% credibility, the probability that fractal breast lesions are malignant is between 74% and 98%. Alternatively, with 95% credibility, the probability that Euclidean breast lesions are benign is between 76% and 96%. These results support the notion that the fractal structure of malignant tumors is more likely to be associated with an invasive behavior into the surrounding tissue compared to the less invasive, Euclidean structure of benign tumors. Finally, based on indirect 3D reconstructions from the 2D views, we conjecture that all breast tumors considered in this study, benign and malignant, fractal or Euclidean, restrict their growth to 2-dimensional manifolds within the breast tissue.

A new approach for clustered MCs classification with sparse features learning and TWSVM

In digital mammograms, an early sign of breast cancer is the existence of microcalcification clusters (MCs), which is very important to the early breast cancer detection. In this paper, a new approach is proposed to classify and detect MCs. We formulate this classification problem as sparse feature learning based classification on behalf of the test samples with a set of training samples, which are also known as a “vocabulary” of visual parts. A visual information-rich vocabulary of training samples is manually built up from a set of samples, which include MCs parts and no-MCs parts. With the prior ground truth of MCs in mammograms, the sparse feature learning is acquired by the l_P-regularized least square approach with the interior-point method. Then we designed the sparse feature learning based MCs classification algorithm using twin support vector machines (TWSVMs). To investigate its performance, the proposed method is applied to DDSM datasets and compared with support vector machines (SVMs) with the same dataset. Experiments have shown that performance of the proposed method is more efficient or better than the state-of-art methods.

A Hybrid Image Filtering Method for Computer-Aided Detection of Microcalcification Clusters in Mammograms

The presence of microcalcification clusters (MCs) in mammogram is a major indicator of breast cancer. Detection of an MC is one of the key issues for breast cancer control. In this paper, we present a highly accurate method based on a morphological image processing and wavelet transform technique to detect the MCs in mammograms. The microcalcifications are firstly enhanced by using multistructure elements morphological processing. Then, the candidates of microcalcifications are refined by a multilevel wavelet reconstruction approach. Finally, MCs are detected based on their distributions feature. Experiments are performed on 138 clinical mammograms. The proposed method is capable of detecting 92.9% of true microcalcification clusters with an average of 0.08 false microcalcification clusters detected per image.

Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms

OBJECTIVE

This paper presents a detailed study of fractal-based methods for texture characterization of mammographic mass lesions and architectural distortion. The purpose of this study is to explore the use of fractal and lacunarity analysis for the characterization and classification of both tumor lesions and normal breast parenchyma in mammography.

MATERIALS AND METHODS

We conducted comparative evaluations of five popular fractal dimension estimation methods for the characterization of the texture of mass lesions and architectural distortion. We applied the concept of lacunarity to the description of the spatial distribution of the pixel intensities in mammographic images. These methods were tested with a set of 57 breast masses and 60 normal breast parenchyma (dataset1), and with another set of 19 architectural distortions and 41 normal breast parenchyma (dataset2). Support vector machines (SVM) were used as a pattern classification method for tumor classification.

RESULTS

Experimental results showed that the fractal dimension of region of interest (ROIs) depicting mass lesions and architectural distortion was statistically significantly lower than that of normal breast parenchyma for all five methods. Receiver operating characteristic (ROC) analysis showed that fractional Brownian motion (FBM) method generated the highest area under ROC curve (A ( z ) = 0.839 for dataset1, 0.828 for dataset2, respectively) among five methods for both datasets. Lacunarity analysis showed that the ROIs depicting mass lesions and architectural distortion had higher lacunarities than those of ROIs depicting normal breast parenchyma. The combination of FBM fractal dimension and lacunarity yielded the highest A ( z ) value (0.903 and 0.875, respectively) than those based on single feature alone for both given datasets. The application of the SVM improved the performance of the fractal-based features in differentiating tumor lesions from normal breast parenchyma by generating higher A ( z ) value.

CONCLUSION

FBM texture model is the most appropriate model for characterizing mammographic images due to self-affinity assumption of the method being a better approximation. Lacunarity is an effective counterpart measure of the fractal dimension in texture feature extraction in mammographic images. The classification results obtained in this work suggest that the SVM is an effective method with great potential for classification in mammographic image analysis.

Improvement of microcalcification cluster detection in mammography utilizing image enhancement techniques

In this work, the effect of an image enhancement processing stage and the parameter tuning of a computer-aided detection (CAD) system for the detection of microcalcifications in mammograms is assessed. Five (5) image enhancement algorithms were tested introducing the contrast-limited adaptive histogram equalization (CLAHE), the local range modification (LRM) and the redundant discrete wavelet (RDW) linear stretching and shrinkage algorithms. CAD tuning optimization was targeted to the percentage of the most contrasted pixels and the size of the minimum detectable object which could satisfactorily represent a microcalcification. The highest performance in two mammographic datasets, were achieved for LRM (A(Z)=0.932) and the wavelet-based linear stretching (A(Z)=0.926) methodology.

Shape analysis of microcalcifications using Radon transform

Microcalcifications are one of the early signs of breast cancer, and they are of great importance for an early diagnosis. Moreover, the spatial distribution and the shape of the microcalcifications have a significant impact in medical practice to evaluate the probability of malignancy of the tumor. In this work a method, performing computer-aided classification of the shape of calcifications accordingly to the classification scheme proposed by Le Gal, is presented. In the first stage, in order to remove mammographic background, the image is preprocessed with a matched filter, designed by modeling the microcalcifications as Gaussian spots and the image as a Fractional Brownian Motion. Afterwards, morphology of spots has been evaluated using two different sets of parameters. The first set utilizes the moments of inertia of the second and third order to compute a set of features, which are invariant to rotations and translations of the image. The second set of parameters is derived from the evaluation of the Radon transform, as computed along eight axes. The results of the Radon transform are used to associate to each lesion a set of features, which are invariant to rotation and scaling of the image. In the final stage, a multilayer neural network has been used to assign each microcalcification to the classes introduced by Le Gal. The topology of the neural network is the same for both sets of descriptors, in order to allow comparison of the discriminative power of the two feature sets. Experimental results obtained with the proposed method from a set of digitized mammograms are reported and discussed.

“Hippocrates-mst”: a prototype for computer-aided microcalcification analysis and risk assessment for breast cancer

One of the most common cancer types among women is breast cancer. Regular mammographic examinations increase the possibility for early diagnosis and treatment and significantly improve the chance of survival for patients with breast cancer. Clustered microcalcifications have been considered as important indicators of the presence of breast cancer. We present "Hippocrates-mst", a prototype system for computer-aided risk assessment of breast cancer. Our research has been focused in developing software to locate microcalcifications on X-ray mammography images, quantify their critical features and classify them according to their probability of being cancerous. A total of 260 cases (187 benign and 73 malignant) have been examined and the performance of the prototype is presented through receiver operating characteristic (ROC) analysis. The system is showing high levels of sensitivity identifying correctly 98.63% of malignant cases.

A study on the computerized fractal analysis of architectural distortion in screening mammograms

Architectural distortion (AD) is a sign of malignancy often missed during mammographic interpretation. The purpose of this study was to explore the application of fractal analysis to the investigation of AD in screening mammograms. The study was performed using mammograms from the Digital Database for Screening Mammography (DDSM). The fractal dimension (FD) of mammographic regions of interest (ROIs) was calculated using the circular average power spectrum technique. Initially, the variability of the FD estimates depending on ROI location, mammographic view and breast side was studied on normal mammograms. Then, the estimated FD was evaluated using receiver operating characteristics (ROC) analysis to determine if it can discriminate ROIs depicting AD from those depicting normal breast parenchyma. The effect of several factors such as ROI size, image subsampling and breast density was studied in detail. Overall, the average FD of the normal ROIs was statistically significantly higher than that of the ROIs with AD. This result was consistent across all factors studied. For the studied set of implementation parameters, the best ROC performance achieved was 0.89 +/- 0.02. The generalizability of these conclusions across different digitizers was also demonstrated.