Neural network-based diagnostic and prognostic estimations in breast cancer microscopic instances

Image Analysis in Digital Pathology Utilizing Machine Learning and Deep Neural Networks

Detection of regions of interest (ROIs) in whole slide images (WSIs) in a clinical setting is a highly subjective and a labor-intensive task. In this work, recent developments in machine learning and computer vision algorithms are presented to assess their possible usage and performance to enhance and accelerate clinical pathology procedures, such as ROI detection in WSIs. In this context, a state-of-the-art deep learning framework (Detectron2) was trained on two cases linked to the TUPAC16 dataset for object detection and on the JPATHOL dataset for instance segmentation. The predictions were evaluated against competing models and further possible improvements are discussed.

Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search

Artificial Neural networks (ANNs) are often applied to data classification problems. However, training ANNs remains a challenging task due to the large and high dimensional nature of search space particularly in the process of fine-tuning the best set of control parameters in terms of weight and bias. Evolutionary algorithms are proved to be a reliable optimization method for training the parameters. While a number of conventional training algorithms have been proposed and applied to various applications, most of them share the common disadvantages of local optima stagnation and slow convergence. In this paper, we propose a new evolutionary training algorithm referred to as LPSONS, which combines the velocity operators in Particle Swarm Optimization (PSO) with Mantegna Lévy distribution to produce more diverse solutions by dividing the population and generation between different sections of the algorithm. It further combines Neighborhood Search with Mantegna Lévy distribution to mitigate premature convergence and avoid local minima. The proposed algorithm can find optimal results and at the same time avoid stagnation in local optimum solutions as well as prevent premature convergence in training Feedforward Multi-Layer Perceptron (MLP) ANNs. Experiments with fourteen standard datasets from UCI machine learning repository confirm that the LPSONS algorithm significantly outperforms a gradient-based approach as well as some well-known evolutionary algorithms that are also based on enhancing PSO.

An expert system design to diagnose cancer by using a new method reduced rule base

BACKGROUND AND OBJECTIVES

A Medical Expert System (MES) was developed which uses Reduced Rule Base to diagnose cancer risk according to the symptoms in an individual. A total of 13 symptoms were used. With the new MES, the reduced rules are controlled instead of all possibilities (2¹³= 8192 different possibilities occur). By controlling reduced rules, results are found more quickly. The method of two-level simplification of Boolean functions was used to obtain Reduced Rule Base. Thanks to the developed application with the number of dynamic inputs and outputs on different platforms, anyone can easily test their own cancer easily.

METHODS

More accurate results were obtained considering all the possibilities related to cancer. Thirteen different risk factors were determined to determine the type of cancer. The truth table produced in our study has 13 inputs and 4 outputs. The Boolean Function Minimization method is used to obtain less situations by simplifying logical functions. Diagnosis of cancer quickly thanks to control of the simplified 4 output functions.

RESULTS

Diagnosis made with the 4 output values obtained using Reduced Rule Base was found to be quicker than diagnosis made by screening all 2¹³= 8192 possibilities. With the improved MES, more probabilities were added to the process and more accurate diagnostic results were obtained. As a result of the simplification process in breast and renal cancer diagnosis 100% diagnosis speed gain, in cervical cancer and lung cancer diagnosis rate gain of 99% was obtained.

CONCLUSIONS

With Boolean function minimization, less number of rules is evaluated instead of evaluating a large number of rules. Reducing the number of rules allows the designed system to work more efficiently and to save time, and facilitates to transfer the rules to the designed Expert systems. Interfaces were developed in different software platforms to enable users to test the accuracy of the application. Any one is able to diagnose the cancer itself using determinative risk factors. Thereby likely to beat the cancer with early diagnosis.

Optimizing the Learning Process of Feedforward Neural Networks Using Lightning Search Algorithm

Evolutionary Neural Networks are proven to be beneficial in solving challenging datasets mainly due to the high local optima avoidance. Stochastic operators in such techniques reduce the probability of stagnation in local solutions and assist them to supersede conventional training algorithms such as Back Propagation (BP) and Levenberg-Marquardt (LM). According to the No-Free-Lunch (NFL), however, there is no optimization technique for solving all optimization problems. This means that a Neural Network trained by a new algorithm has the potential to solve a new set of problems or outperform the current techniques in solving existing problems. This motivates our attempts to investigate the efficiency of the recently proposed Evolutionary Algorithm called Lightning Search Algorithm (LSA) in training Neural Network for the first time in the literature. The LSA-based trainer is benchmarked on 16 popular medical diagnosis problems and compared to BP, LM, and 6 other evolutionary trainers. The quantitative and qualitative results show that the LSA algorithm is able to show not only better local solutions avoidance but also faster convergence speed compared to the other algorithms employed. In addition, the statistical test conducted proves that the LSA-based trainer is significantly superior in comparison with the current algorithms on the majority of datasets.

A neural network approach to multi-biomarker panel discovery by high-throughput plasma proteomics profiling of breast cancer

BACKGROUND

In the past several years, there has been increasing interest and enthusiasm in molecular biomarkers as tools for early detection of cancer. Liquid chromatography tandem mass spectrometry (LC/MS/MS) based plasma proteomics profiling technique is a promising technology platform to study candidate protein biomarkers for early detection of cancer. Factors such as inherent variability, protein detectability limitation, and peptide discovery biases among LC/MS/MS platforms have made the classification and prediction of proteomics profiles challenging. Developing proteomics data analysis methods to identify multi-protein biomarker panels for breast cancer diagnosis based on neural networks provides hope for improving both the sensitivity and the specificity of candidate cancer biomarkers for early detection.

RESULTS

In our previous method, we developed a Feed Forward Neural Network-based method to build the classifier for plasma samples of breast cancer and then applied the classifier to predict blind dataset of breast cancer. However, the optimal combination C* in our previous method was actually determined by applying the trained FFNN on the testing set with the combination. Therefore, in this paper, we applied a three way data split to the Feed Forward Neural Network for training, validation and testing based. We found that the prediction performance of the FFNN model based on the three way data split outperforms our previous method and the prediction performance is improved from (AUC = 0.8706, precision = 82.5%, accuracy = 82.5%, sensitivity = 82.5%, specificity = 82.5% for the testing set) to (AUC = 0.895, precision = 86.84%, accuracy = 85%, sensitivity = 82.5%, specificity = 87.5% for the testing set).

CONCLUSIONS

Further pathway analysis showed that the top three five-marker panels are associated with complement and coagulation cascades, signaling, activation, and hemostasis, which are consistent with previous findings. We believe the new approach is a better solution for multi-biomarker panel discovery and it can be applied to other clinical proteomics.

Fuzzy method for pre-diagnosis of breast cancer from the Fine Needle Aspirate analysis

Background

Across the globe, breast cancer is one of the leading causes of death among women and, currently, Fine Needle Aspirate (FNA) with visual interpretation is the easiest and fastest biopsy technique for the diagnosis of this deadly disease. Unfortunately, the ability of this method to diagnose cancer correctly when the disease is present varies greatly, from 65% to 98%. This article introduces a method to assist in the diagnosis and second opinion of breast cancer from the analysis of descriptors extracted from smears of breast mass obtained by FNA, with the use of computational intelligence resources - in this case, fuzzy logic.

Methods

For data acquisition of FNA, the Wisconsin Diagnostic Breast Cancer Data (WDBC), from the University of California at Irvine (UCI) Machine Learning Repository, available on the internet through the UCI domain was used. The knowledge acquisition process was carried out by the extraction and analysis of numerical data of the WDBC and by interviews and discussions with medical experts. The PDM-FNA-Fuzzy was developed in four steps: 1) Fuzzification Stage; 2) Rules Base; 3) Inference Stage; and 4) Defuzzification Stage. Performance cross-validation was used in the tests, with three databases with gold pattern clinical cases randomly extracted from the WDBC. The final validation was held by medical specialists in pathology, mastology and general practice, and with gold pattern clinical cases, i.e. with known and clinically confirmed diagnosis.

Results

The Fuzzy Method developed provides breast cancer pre-diagnosis with 98.59% sensitivity (correct pre-diagnosis of malignancies); and 85.43% specificity (correct pre-diagnosis of benign cases). Due to the high sensitivity presented, these results are considered satisfactory, both by the opinion of medical specialists in the aforementioned areas and by comparison with other studies involving breast cancer diagnosis using FNA.

Conclusions

This paper presents an intelligent method to assist in the diagnosis and second opinion of breast cancer, using a fuzzy method capable of processing and sorting data extracted from smears of breast mass obtained by FNA, with satisfactory levels of sensitivity and specificity. The main contribution of the proposed method is the reduction of the variation hit of malignant cases when compared to visual interpretation currently applied in the diagnosis by FNA. While the MPD-FNA-Fuzzy features stable sensitivity at 98.59%, visual interpretation diagnosis provides a sensitivity variation from 65% to 98% (this track showing sensitivity levels below those considered satisfactory by medical specialists). Note that this method will be used in an Intelligent Virtual Environment to assist the decision-making (IVEMI), which amplifies its contribution.

Data mining methods in Omics-based biomarker discovery

The advent of Omics technologies as genomics and proteomics has brought the hope of discovering novel biomarkers that can be used to diagnose, predict, and monitor the progress of disease. The importance of data mining to identify biological markers for the diagnostic classification and prognostic assessment in the context of microarray and proteomic data has been increasingly recognized. We present an overview of general data mining methods and their applications to biomarker discovery with particular focus on genomics and proteomics data. Two case studies are exemplarily presented, and relevant data mining terminology and techniques are explained.

Quantitative automated image analysis system with automated debris filtering for the detection of breast carcinoma cells

OBJECTIVE

To develop an intraoperative method for margin status evaluation during breast conservation therapy (BCT) using an automated analysis of imprint cytology specimens.

STUDY DESIGN

Imprint cytology samples were prospectively taken from 47 patients undergoing either BCT or breast reduction surgery. Touch preparations from BCT patients were taken on cut sections through the tumor to generate positive margin controls. For breast reduction patients, slide imprints were taken at cuts through the center of excised tissue. Analysis results from the presented technique were compared against standard pathologic diagnosis. Slides were stained with cytokeratin and Hoechst, imaged with an automated fluorescent microscope, and analyzed with a fast algorithm to automate discrimination between epithelial cells and noncellular debris.

RESULTS

The accuracy of the automated analysis was 95% for identifying invasive cancers compared against final pathologic diagnosis. The overall sensitivity was 87% while specificity was 100% (no false positives). This is comparable to the best reported results from manual examination of intraoperative imprint cytology slides while reducing the need for direct input from a cytopathologist.

CONCLUSION

This work demonstrates a proof of concept for developing a highly accurate and automated system for the intraoperative evaluation of margin status to guide surgical decisions and lower positive margin rates.

Assessment of gastric cancer survival: using an artificial hierarchical neural network

This study is designed to assess the application of neural networks in comparison to the Kaplan-Meier and Cox proportional hazards model in the survival analysis. Three hundred thirty gastric cancer patients admitted to and surgically treated were assessed and their post-surgical survival was determined. The observed baseline survival was determined with the three methods of Kaplan-Meier product limit estimator, Cox and the neural network and results were compared. Then the binary independent variables were entered into the model. Data were randomly divided into two groups of 165 each to test the models and assess the reproducibility. The Chi-square test and the multiple logistic model were used to ensure the groups were similar and the data was divided randomly. To compare subgroups, we used the log-rank test. In the next step, the probability of survival in different periods was computed based on the training group data using the Cox proportional hazards and a neural network and estimating Cox coefficient values and neural network weights (with 3 nodes in hidden layer). Results were used for predictions in the test group data and these predictions were compared using the Kaplan-Meier product limit estimator as the gold standard. Friedman and Kruskal-Wallis tests were used for comparisons as well. All statistical analyses were performed using SPSS version 11.5, Matlab version 7.2, Statistica version 6.0 and S_PLUS 2000. The significance level was considered 5% (alpha = 0.05). The three methods used showed no significance difference in base survival probabilities. Overall, there was no significant difference among the survival probabilities or the trend of changes in survival probabilities calculated with the three methods, but the 4 year (48th month) and 4.5 year (54th month) survival rates were significantly different with Cox compared to standard and estimated probabilities in the neural network (p < 0.05). Kaplan-Meier and Cox showed almost similar results for the baseline survival probabilities, but results with the neural network were different: higher probabilities up to the 4th year, then comparable with the other two methods. Estimates from Cox proportional hazards and the neural network with three nodes in hidden layer were compared with the estimate from the Kaplan-Meier estimator as the gold standard. Neither comparison showed statistically significant differences. The standard error ratio of the two estimate groups by Cox and the neural network to Kaplan-Meier were no significant differences, it indicated that the neural network was more accurate. Although we do not suggest neural network methods to estimate the baseline survival probability, it seems these models is more accurately estimated as compared with the Cox proportional hazards, especially with today's advanced computer sciences that allow complex calculations. These methods are preferable because they lack the limitations of conventional models and obviate the need for unnecessary assumptions including those related to the proportionality of hazards and linearity.