A neural network approach to breast cancer diagnosis as a constraint satisfaction problem

Breast cancer prediction using different machine learning methods applying multi factors

OBJECTIVE

Breast cancer (BC) is a multifactorial disease and is one of the most common cancers globally. This study aimed to compare different machine learning (ML) techniques to develop a comprehensive breast cancer risk prediction model based on features of various factors.

METHODS

The population sample contained 810 records (115 cancer patients and 695 healthy individuals). 45 attributes out of 85 were selected based on the opinion of experts. These selected attributes are in genetic, biochemical, biomarker, gender, demographic and pathological factors. 13 Machine learning models were trained with proposed attributes and coefficient of attributes and internal relationships were calculated.

RESULT

Compared to other methods random forest (RF) has higher performance (accuracy 99.26%, precision 99%, and area under the curve (AUC) 99%). The results of assessing the impact and correlation of variables using the RF method based on PCA indicated that pathology, biomarker, biochemistry, gene, and demographic factors with a coefficient of 0.35, 0.23, 0.15, 0.14, and 0.13 respectively, affected the risk of BC (r2 = 0.54).

CONCLUSION

Breast cancer has several risk factors. Medical experts use these risk factors for early diagnosis. Therefore, identifying related risk factors and their effect can increase the accuracy of diagnosis. Considering the broad features for predicting breast cancer leads to the development of a comprehensive prediction model. In this study, using RF technique a breast cancer prediction model with 99.3% accuracy was developed based on multifactorial features.

Global Research Trends of Artificial Intelligence on Histopathological Images: A 20-Year Bibliometric Analysis

Cancer has become a major threat to global health care. With the development of computer science, artificial intelligence (AI) has been widely applied in histopathological images (HI) analysis. This study analyzed the publications of AI in HI from 2001 to 2021 by bibliometrics, exploring the research status and the potential popular directions in the future. A total of 2844 publications from the Web of Science Core Collection were included in the bibliometric analysis. The country/region, institution, author, journal, keyword, and references were analyzed by using VOSviewer and CiteSpace. The results showed that the number of publications has grown rapidly in the last five years. The USA is the most productive and influential country with 937 publications and 23,010 citations, and most of the authors and institutions with higher numbers of publications and citations are from the USA. Keyword analysis showed that breast cancer, prostate cancer, colorectal cancer, and lung cancer are the tumor types of greatest concern. Co-citation analysis showed that classification and nucleus segmentation are the main research directions of AI-based HI studies. Transfer learning and self-supervised learning in HI is on the rise. This study performed the first bibliometric analysis of AI in HI from multiple indicators, providing insights for researchers to identify key cancer types and understand the research trends of AI application in HI.

Applications of Computational Methods in Biomedical Breast Cancer Imaging Diagnostics: A Review

With the exponential increase in new cases coupled with an increased mortality rate, cancer has ranked as the second most prevalent cause of death in the world. Early detection is paramount for suitable diagnosis and effective treatment of different kinds of cancers, but this is limited to the accuracy and sensitivity of available diagnostic imaging methods. Breast cancer is the most widely diagnosed cancer among women across the globe with a high percentage of total cancer deaths requiring an intensive, accurate, and sensitive imaging approach. Indeed, it is treatable when detected at an early stage. Hence, the use of state of the art computational approaches has been proposed as a potential alternative approach for the design and development of novel diagnostic imaging methods for breast cancer. Thus, this review provides a concise overview of past and present conventional diagnostics approaches in breast cancer detection. Further, we gave an account of several computational models (machine learning, deep learning, and robotics), which have been developed and can serve as alternative techniques for breast cancer diagnostics imaging. This review will be helpful to academia, medical practitioners, and others for further study in this area to improve the biomedical breast cancer imaging diagnosis.

Artificial neural networks in mammography interpretation and diagnostic decision making

Screening mammography is the most effective means for early detection of breast cancer. Although general rules for discriminating malignant and benign lesions exist, radiologists are unable to perfectly detect and classify all lesions as malignant and benign, for many reasons which include, but are not limited to, overlap of features that distinguish malignancy, difficulty in estimating disease risk, and variability in recommended management. When predictive variables are numerous and interact, ad hoc decision making strategies based on experience and memory may lead to systematic errors and variability in practice. The integration of computer models to help radiologists increase the accuracy of mammography examinations in diagnostic decision making has gained increasing attention in the last two decades. In this study, we provide an overview of one of the most commonly used models, artificial neural networks (ANNs), in mammography interpretation and diagnostic decision making and discuss important features in mammography interpretation. We conclude by discussing several common limitations of existing research on ANN-based detection and diagnostic models and provide possible future research directions.

Breast tissue image classification based on Semi-supervised Locality Discriminant Projection with Kernels

Breast tissue classification is an important and effective way for computer aided diagnosis of breast cancer. We present Semi-supervised Locality Discriminant Projections with Kernels for breast cancer classification. The contributions of this work lie in: 1) Semi-supervised learning is used into Locality Preserving Projections (LPP) to enhance its performance using side-information together with the unlabelled training samples, while current algorithms only consider the side-information but ignoring the unlabeled training samples. 2) Kernel trick is applied into Semi-supervised LPP to improve its ability in the nonlinear classification. 3) The framework of breast cancer classification with Semi-supervised LPP with kernels is presented. Many experiments are implemented on four breast tissue databases to testify and evaluate the feasibility and affectivity of the proposed scheme.

Bayesian networks of BI-RADStrade mark descriptors for breast lesion classification

We investigated Bayesian network structure learning and probability estimation from mammographic feature data in order to classify breast lesions into different pathological categories. We compared the learned networks to naive Bayes classifiers, which are similar to the expert systems previously investigated for breast lesion classification. The learned network structures reflect the difference in the classification of biopsy outcome and the invasiveness of malignant lesions for breast masses and microcalcifications. The difference between masses and microcalcifications should be taken into consideration when interpreting systems for automatic pathological classification of breast lesions. The difference may also affect use of these systems for tasks such as estimating the sampling error of biopsy.

Impact of missing data in evaluating artificial neural networks trained on complete data

This study investigated the impact of missing data in the evaluation of artificial neural network (ANN) models trained on complete data for the task of predicting whether breast lesions are benign or malignant from their mammographic Breast Imaging and Reporting Data System (BI-RADS) descriptors. A feed-forward, back-propagation ANN was tested with three methods for estimating the missing values. Similar results were achieved with a constraint satisfaction ANN, which can accommodate missing values without a separate estimation step. This empirical study highlights the need for additional research on developing robust clinical decision support systems for realistic environments in which key information may be unknown or inaccessible.

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

This paper deals with breast cancer diagnostic and prognostic estimations employing neural networks over the Wisconsin Breast Cancer datasets, which consist of measurements taken from breast cancer microscopic instances. A probabilistic approach is dedicated to solve the diagnosis problem, detecting malignancy among instances derived from the Fine Needle Aspirate test, while regression algorithms estimate the time interval that possibly correspond to the right end-point of the patients' disease-free survival time or the time where the tumour recurs (time-to-recur). For the diagnosis problem, the accuracy of the neural network in terms of sensitivity and specificity was measured at 98.6 and 97.5% respectively, using the leave-one-out test method. As far as the prognosis problem is concerned, the accuracy of the neural network was measured through a stratified tenfold cross-validation approach. Sensitivity ranged between 80.5 and 91.8%, while specificity ranged between 91.9 and 97.9%, depending on the tested fold and the partition of the predicted period. The prognostic recurrence predictions were then further evaluated using survival analysis and compared with other techniques found in literature.

Breast masses: computer-aided diagnosis with serial mammograms

PURPOSE

To retrospectively evaluate effects of computer-aided diagnosis (CAD) involving an interval change classifier (which uses interval change information extracted from prior and current mammograms and estimates a malignancy rating) on radiologists' accuracy in characterizing masses on two-view serial mammograms as malignant or benign.

MATERIALS AND METHODS

The data collection protocol had institutional review board approval. Patient informed consent was waived for this HIPAA-compliant retrospective study. Ninety temporal pairs of two-view serial mammograms (depicting 47 malignant and 43 benign biopsy-proved masses) were obtained from 68 patient files and were digitized. Biopsy was the reference standard. Eight Mammography Quality Standards Act of 1992-accredited radiologists and two breast imaging fellows assessed digitized two-view temporal pairs (in preselected regions of interest only) by estimating likelihood of malignancy and Breast Imaging Reporting and Data System (BI-RADS) category without and with CAD. Observers' rating data were analyzed with Dorfman-Berbaum-Metz (DBM) multireader multicase method. Statistical significance of differences was estimated with the DBM method and Student two-tailed paired t test.

RESULTS

Average area under the receiver operating characteristic curve for likelihood of malignancy across the 10 observers was 0.83 (range, 0.74-0.88) without CAD and improved to 0.87 (range, 0.80-0.92) with CAD (P < .05). The average partial area index above a sensitivity of 0.90 for likelihood of malignancy was 0.35 (range, 0.13-0.54) without CAD and 0.49 (range, 0.18-0.73) with CAD--a nonsignificant improvement (P = .11). For BI-RADS assessment, it was estimated that with CAD, six radiologists would correctly recommend additional biopsies for malignant masses (range, 4.3%-10.6%) and five would correctly recommend reduction of biopsy (ie, fewer biopsies) for benign masses (range, 2.3%-9.3%). However, five radiologists would incorrectly recommend additional biopsy for benign masses (range, 2.3%-14.0%), and one would incorrectly recommend reduction of biopsy (4.3%).

CONCLUSION

CAD involving interval change analysis of preselected regions of interest can significantly improve radiologists' accuracy in classifying masses on digitized screen-film mammograms as malignant or benign.

Improvement in Radiologists’ Characterization of Malignant and Benign Breast Masses on Serial Mammograms with Computer-aided Diagnosis: An ROC Study

PURPOSE

To evaluate the effects of computer-aided diagnosis (CAD) on radiologists' characterization of masses on serial mammograms.

MATERIALS AND METHODS

Two hundred fifty-three temporal image pairs (138 malignant and 115 benign) obtained from 96 patients who had masses on serial mammograms were evaluated. The temporal pairs were formed by matching masses of the same view from two different examinations. Eight radiologists and two breast imaging fellows assessed the temporal pairs with and without computer aid. The classification of accuracy was quantified by using the area under receiver operating characteristic curve (A(z)). The statistical significance of the difference in A(z) between the different reading conditions was estimated with the Dorfman-Berbaum-Metz method for analysis of multireader multicase data and with the Student paired t test for analysis of observer-specific paired data.

RESULTS

The average A(z) for radiologists' estimates of the likelihood of malignancy was 0.79 without CAD and improved to 0.84 with CAD. The improvement was statistically significant (P =.005). The corresponding average partial area index was 0.25 without CAD and improved to 0.37 with CAD. The improvement was also statistically significant (P =.005). On the basis of Breast Imaging Reporting and Data System assessments, it was estimated that with CAD, each radiologist, on average, reduced 0.7% (0.8 of 115) of unnecessary biopsies and correctly recommended 5.7% (7.8 of 138) of additional biopsies.

CONCLUSION

CAD based on analysis of interval changes can significantly increase radiologists' accuracy in classification of masses and thereby may be useful in improving correct biopsy recommendations.

Tolerance to missing data using a likelihood ratio based classifier for computer-aided classification of breast cancer

While mammography is a highly sensitive method for detecting breast tumours, its ability to differentiate between malignant and benign lesions is low, which may result in as many as 70% of unnecessary biopsies. The purpose of this study was to develop a highly specific computer-aided diagnosis algorithm to improve classification of mammographic masses. A classifier based on the likelihood ratio was developed to accommodate cases with missing data. Data for development included 671 biopsy cases (245 malignant), with biopsy-proved outcome. Sixteen features based on the BI-RADS lexicon and patient history had been recorded for the cases, with 1.3 +/- 1.1 missing feature values per case. Classifier evaluation methods included receiver operating characteristic and leave-one-out bootstrap sampling. The classifier achieved 32% specificity at 100% sensitivity on the 671 cases with 16 features that had missing values. Utilizing just the seven features present for all cases resulted in decreased performance at 100% sensitivity with average 19% specificity. No cases and no feature data were omitted during classifier development, showing that it is more beneficial to utilize cases with missing values than to discard incomplete cases that cannot be handled by many algorithms. Classification of mammographic masses was commendable at high sensitivity levels, indicating that benign cases could be potentially spared from biopsy.

Diagnostic abilities of three CAD methods for assessing microcalcifications in mammograms and an aspect of equivocal cases decisions by radiologists

Radiologists use an "Overall impression" rating to assess a suspicious region on a mammogram. The value ranges from 1 to 5. They will definitely send a patient for biopsy if the rating is 4 or 5. They will send the patient for core biopsy when a rating of 3 (indeterminate) is given. We have developed three methods to aid diagnosis of cases with microcalcifications. The first two methods, namely, Bayesian and multiple logistic regression (with a special "cutting score" technique), utilise six parameter ratings which minimise subjectivity in characterising the microcalcifications. The third method uses three parameters (age of patient, uniformity of size of microcalcification and their distribution) in a multiple stepwise regression. For both training set and test set, all three methods are as good as the two radiologists in terms of percentages of correct classification. Therefore, all three proposed methods potentially can be used as second readers.

Self-organizing map for cluster analysis of a breast cancer database

The purpose of this study was to identify and characterize clusters in a heterogeneous breast cancer computer-aided diagnosis database. Identification of subgroups within the database could help elucidate clinical trends and facilitate future model building. A self-organizing map (SOM) was used to identify clusters in a large (2258 cases), heterogeneous computer-aided diagnosis database based on mammographic findings (BI-RADS) and patient age. The resulting clusters were then characterized by their prototypes determined using a constraint satisfaction neural network (CSNN). The clusters showed logical separation of clinical subtypes such as architectural distortions, masses, and calcifications. Moreover, the broad categories of masses and calcifications were stratified into several clusters (seven for masses and three for calcifications). The percent of the cases that were malignant was notably different among the clusters (ranging from 6 to 83%). A feed-forward back-propagation artificial neural network (BP-ANN) was used to identify likely benign lesions that may be candidates for follow up rather than biopsy. The performance of the BP-ANN varied considerably across the clusters identified by the SOM. In particular, a cluster (#6) of mass cases (6% malignant) was identified that accounted for 79% of the recommendations for follow up that would have been made by the BP-ANN. A classification rule based on the profile of cluster #6 performed comparably to the BP-ANN, providing approximately 25% specificity at 98% sensitivity. This performance was demonstrated to generalize to a large (2177) set of cases held-out for model validation.

Differences between computer-aided diagnosis of breast masses and that of calcifications

PURPOSE

To compare the performance of a computer-aided diagnosis (CAD) system for diagnosis of previously detected lesions, based on radiologist-extracted findings on masses and calcifications.

MATERIALS AND METHODS

A feed-forward, back-propagation artificial neural network (BP-ANN) was trained in a round-robin (leave-one-out) manner to predict biopsy outcome from mammographic findings (according to the Breast Imaging Reporting and Data System) and patient age. The BP-ANN was trained by using a large (>1,000 cases) heterogeneous data set containing masses and microcalcifications. The performances of the BP-ANN on masses and microcalcifications were compared with use of receiver operating characteristic analysis and a z test for uncorrelated samples.

RESULTS

The BP-ANN performed significantly better on masses than microcalcifications in terms of both the area under the receiver operating characteristic curve and the partial receiver operating characteristic area index. A similar difference in performance was observed with a second model (linear discriminant analysis) and also with a second data set from a similar institution.

CONCLUSION

Masses and calcifications should be considered separately when evaluating CAD systems for breast cancer diagnosis.

Outcome analysis of patients with acute pancreatitis by using an artificial neural network

RATIONALE AND OBJECTIVES

The authors performed this study to evaluate the ability of an artificial neural network (ANN) that uses radiologic and laboratory data to predict the outcome in patients with acute pancreatitis.

MATERIALS AND METHODS

An ANN was constructed with data from 92 patients with acute pancreatitis who underwent computed tomography (CT). Input nodes included clinical, laboratory, and CT data. The ANN was trained and tested by using a round-robin technique, and the performance of the ANN was compared with that of linear discriminant analysis and Ranson and Balthazar grading systems by using receiver operating characteristic analysis. The length of hospital stay was used as an outcome measure.

RESULTS

Hospital stay ranged from 0 to 45 days, with a mean of 8.4 days. The hospital stay was shorter than the mean for 62 patients and longer than the mean for 30. The 23 input features were reduced by using stepwise linear discriminant analysis, and an ANN was developed with the six most statistically significant parameters (blood pressure, extent of inflammation, fluid aspiration, serum creatinine level, serum calcium level, and the presence of concurrent severe illness). With these features, the ANN successfully predicted whether the patient would exceed the mean length of stay (Az = 0.83 +/- 0.05). Although the Az performance of the ANN was statistically significantly better than that of the Ranson (Az = 0.68 +/- 0.06, P < .02) and Balthazar (Az = 0.62 +/- 0.06, P < .003) grades, it was not significantly better than that of linear discriminant analysis (Az = 0.82 +/- 0.05, P = .53).

CONCLUSION

An ANN may be useful for predicting outcome in patients with acute pancreatitis.