Abraham Pouliakis

BACK PROPAGATION NEURAL NETWORK IN THE DISCRIMINATION OF BENIGN FROM MALIGNANT LOWER URINARY TRACT LESIONS

PURPOSE We investigated the potential value of morphometry and artificial intelligence tools to discriminate between benign and malignant lower urinary tract lesions. MATERIALS AND METHODS The lesions included lithiasis in 50 cases, inflammation in 61, benign prostatic hyperplasia in 99, carcinoma in situ in 5, and grade I and grades II and III transitional cell carcinoma of the bladder in 71 and 184, respectively. Images of routine processed voided urine smears stained by the Giemsa technique were analyzed using a custom image analysis system, providing a data set of 45,452 cells. A neural net model of the back propagation type was used to discriminate benign from malignant cells based on the extracted morphometric and textural features. Data from 13,636 randomly selected cells (30% of the total data) were used as a training set and the data from the remaining 31,816 cells comprised the test set. In a similar attempt to discriminate at the patient level data on 30% of those randomly selected were used to train a back propagation neural net and data on the remaining 329 were used for testing. RESULTS Application of the back propagation neural net enabled the correct classification of 95.34% of benign and 86.71% of malignant cells with overall 90.57% accuracy. At the patient level the back propagation neural net enabled the correct classification of 100% of those with benign and 94.51% of those with malignant disease with overall 96.96% accuracy. CONCLUSIONS The use of neural nets and image morphometry may increase the speed of cytological diagnosis and the diagnostic accuracy of voided urine cytology.

An Intelligent Clinical Decision Support System for Patient-Specific Predictions to Improve Cervical Intraepithelial Neoplasia Detection

Nowadays, there are molecular biology techniques providing information related to cervical cancer and its cause: the human Papillomavirus (HPV), including DNA microarrays identifying HPV subtypes, mRNA techniques such as nucleic acid based amplification or flow cytometry identifying E6/E7 oncogenes, and immunocytochemistry techniques such as overexpression of p16. Each one of these techniques has its own performance, limitations and advantages, thus a combinatorial approach via computational intelligence methods could exploit the benefits of each method and produce more accurate results. In this article we propose a clinical decision support system (CDSS), composed by artificial neural networks, intelligently combining the results of classic and ancillary techniques for diagnostic accuracy improvement. We evaluated this method on 740 cases with complete series of cytological assessment, molecular tests, and colposcopy examination. The CDSS demonstrated high sensitivity (89.4%), high specificity (97.1%), high positive predictive value (89.4%), and high negative predictive value (97.1%), for detecting cervical intraepithelial neoplasia grade 2 or worse (CIN2+). In comparison to the tests involved in this study and their combinations, the CDSS produced the most balanced results in terms of sensitivity, specificity, PPV, and NPV. The proposed system may reduce the referral rate for colposcopy and guide personalised management and therapeutic interventions.

Identification of Women for Referral to Colposcopy by Neural Networks: A Preliminary Study Based on LBC and Molecular Biomarkers

Objective of this study is to investigate the potential of the learning vector quantizer neural network (LVQ-NN) classifier on various diagnostic variables used in the modern cytopathology laboratory and to build an algorithm that may facilitate the classification of individual cases. From all women included in the study, a liquid-based cytology sample was obtained; this was tested via HPV DNA test, E6/E7 HPV mRNA test, and p16 immunostaining. The data were classified by the LVQ-NN into two groups: CIN-2 or worse and CIN-1 or less. Half of the cases were used to train the LVQ-NN; the remaining cases (test set) were used for validation. Out of the 1258 cases, cytology identified correctly 72.90% of the CIN-2 or worst cases and 97.37% of the CIN-1 or less cases, with overall accuracy 94.36%. The application of the LVQ-NN on the test set allowed correct classification for 84.62% of the cases with CIN-2 or worse and 97.64% of the cases with CIN-1 or less, with overall accuracy of 96.03%. The use of the LVQ-NN with cytology and the proposed biomarkers improves significantly the correct classification of cervical precancerous lesions and/or cancer and may facilitate diagnosis and patient management.

Static Cytometry and Neural Networks in the Discrimination of Lower Urinary System Lesions

OBJECTIVES To investigate the potential of morphometry and artificial intelligence tools for the discrimination of benign and malignant lower urinary system lesions. METHODS The study group included 50 cases of lithiasis, 61 cases of inflammation, 99 cases of benign prostatic hyperplasia, 5 cases of in situ carcinoma, 71 cases of grade I transitional cell carcinoma of the bladder (TCCB), and 184 cases of grade II and grade III TCCB. Images of voided urine smears stained by the Giemsa technique were analyzed by a custom image analysis system. The analysis gave a data set of features from 45,452 cells. A learning vector quantizer (LVQ)-type neural network (NN) was used to discriminate benign from malignant cells on the basis of the extracted morphometric and textural features. The data from 13,636 randomly selected cells were used as a training set and the data from the remaining 31,816 cells made up the test set. Similarly, in an attempt to discriminate at the patient level, 30% of the cases randomly selected were used to train an LVQ NN and the remaining 329 cases were used for the test. RESULTS The application of the LVQ NN enabled the correct classification of 95.42% of the benign cells and 86.75% of the malignant cells, giving an overall accuracy rate of 90.63%. At the patient level, the LVQ NN enabled the correct classification of 100% of benign cases and 95.6% of malignant cases, giving an overall accuracy rate of 97.57%. CONCLUSIONS NNs combined with image analysis offer useful information in the discrimination of benign and malignant cells and lesions of the lower urinary system.

Artificial Intelligence in IVF: A Need

Predicting the outcome of in-vitro fertilization (IVF) treatment is an extremely semantic issue in reproductive medicine. Discrepancies in results among reproductive centres still exist making the construction of new systems capable to foresee the desired outcome a necessity. As such, artificial neural networks (ANNs) represent a combination of a learning, self-adapting, and predicting machine. In this review hypothesis paper we summarize the past efforts of the ANNs systems to predict IVF outcomes. This will be considered together with other statistical models, such as the ensemble techniques, Classification And Regression Tree (CART) and regression analysis techniques, discriminant analysis, and case based reasoning systems. We also summarize the various inputs that have been employed as parameters in these studies to predict the IVF outcome. Finally, we report our attempt to construct a new ANN architecture based on the Learning Vector Quantizer promising good generalization: a system filled by a complete data set of our IVF unit, formulated parameters most commonly used in similar studies, trained by a network expert, and evaluated in terms of predictive power.

Using classification and regression trees, liquid-based cytology and nuclear morphometry for the discrimination of endometrial lesions

‘The objective of this study is to investigate the potential of classification and regression trees (CARTs) in discriminating benign from malignant endometrial nuclei and lesions. The study was performed on 222 histologically confirmed liquid based cytological smears, specifically: 117 benign cases, 62 malignant cases and 43 hyperplasias with or without atypia. About 100 nuclei were measured from each case using an image analysis system; in total, we collected 22783 nuclei. The nuclei from 50% of the cases (the training set) were used to construct a CART model that was used for knowledge extraction. The nuclei from the remaining 50% of cases (test set) were used to evaluate the stability and performance of the CART on unknown data. Based on the results of the CART for nuclei classification, we propose two classification methods to discriminate benign from malignant cases. The CART model had an overall accuracy for the classification of endometrial nuclei equal to 85%, specificity 90.68%, and sensitivity 72.05%. Both methods for case classification had similar performance: overall accuracy in the range 94–95%, specificity 95%, and sensitivity 91–94%. The results of the proposed system outperform the standard cytological diagnosis of endometrial lesions. This study highlights interesting diagnostic features of endometrial nuclear morphology and provides a new classification approach for endometrial nuclei and cases. The proposed method can be a useful tool for the everyday practice of the cytological laboratory. Diagn. Cytopathol. 2014;42:582–591.

Artificial Neural Networks as Decision Support Tools in Cytopathology: Past, Present, and Future

Objective This study aims to analyze the role of artificial neural networks (ANNs) in cytopathology. More specifically, it aims to highlight the importance of employing ANNs in existing and future applications and in identifying unexplored or poorly explored research topics. Study Design A systematic search was conducted in scientific databases for articles related to cytopathology and ANNs with respect to anatomical places of the human body where cytopathology is performed. For each anatomic system/organ, the major outcomes described in the scientific literature are presented and the most important aspects are highlighted. Results The vast majority of ANN applications are related to cervical cytopathology, specifically for the ANN-based, semiautomated commercial diagnostic system PAPNET. For cervical cytopathology, there is a plethora of studies relevant to the diagnostic accuracy; in addition, there are also efforts evaluating cost-effectiveness and applications on primary, secondary, or hybrid screening. For the rest of the anatomical sites, such as the gastrointestinal system, thyroid gland, urinary tract, and breast, there are significantly less efforts relevant to the application of ANNs. Additionally, there are still anatomical systems for which ANNs have never been applied on their cytological material. Conclusions Cytopathology is an ideal discipline to apply ANNs. In general, diagnosis is performed by experts via the light microscope. However, this approach introduces subjectivity, because this is not a universal and objective measurement process. This has resulted in the existence of a gray zone between normal and pathological cases. From the analysis of related articles, it is obvious that there is a need to perform more thorough analyses, using extensive number of cases and particularly for the nonexplored organs. Efforts to apply such systems within the laboratory test environment are required for their future uptake.

Personalised management of women with cervical abnormalities using a clinical decision support scoring system

OBJECTIVES To develop a clinical decision support scoring system (DSSS) based on artificial neural networks (ANN) for personalised management of women with cervical abnormalities. METHODS We recruited women with cervical abnormalities and healthy controls that attended for opportunistic screening between 2006 and 2014 in 3 University Hospitals. We prospectively collected detailed patient characteristics, the colposcopic impression and performed a series of biomarkers using a liquid-based cytology sample. These included HPV DNA typing, E6&E7 mRNA by NASBA or flow cytometry and p16INK4a immunostaining. We used ANNs to combine the cytology and biomarker results and develop a clinical DSSS with the aim to improve the diagnostic accuracy of tests and quantify the individuals risk for different histological diagnoses. We used histology as the gold standard. RESULTS We analysed data from 2267 women that had complete or partial dataset of clinical and molecular data during their initial or followup visits (N=3565). Accuracy parameters (sensitivity, specificity, positive and negative predictive values) were assessed for the cytological result and/or HPV status and for the DSSS. The ANN predicted with higher accuracy the chances of high-grade (CIN2+), low grade (HPV/CIN1) and normal histology than cytology with or without HPV test. The sensitivity for prediction of CIN2 or worse was 93.0%, specificity 99.2% with high positive (93.3%) and negative (99.2%) predictive values. CONCLUSIONS The DSSS based on an ANN of multilayer perceptron (MLP) type, can predict with the highest accuracy the histological diagnosis in women with abnormalities at cytology when compared with the use of tests alone. A user-friendly software based on this technology could be used to guide clinician decision making towards a more personalised care.

Image analysis and multi-layer perceptron artificial neural networks for the discrimination between benign and malignant endometrial lesions

This study aims to investigate the efficacy of an Artificial Neural Network based on Multi‐Layer Perceptron (ANN–MPL) to discriminate between benign and malignant endometrial nuclei and lesions in cytological specimens.

The Application of Classification and Regression Trees for the Triage of Women for Referral to Colposcopy and the Estimation of Risk for Cervical Intraepithelial Neoplasia: A Study Based on 1625 Cases with Incomplete Data from Molecular Tests

Objective. Nowadays numerous ancillary techniques detecting HPV DNA and mRNA compete with cytology; however no perfect test exists; in this study we evaluated classification and regression trees (CARTs) for the production of triage rules and estimate the risk for cervical intraepithelial neoplasia (CIN) in cases with ASCUS+ in cytology. Study Design. We used 1625 cases. In contrast to other approaches we used missing data to increase the data volume, obtain more accurate results, and simulate real conditions in the everyday practice of gynecologic clinics and laboratories. The proposed CART was based on the cytological result, HPV DNA typing, HPV mRNA detection based on NASBA and flow cytometry, p16 immunocytochemical expression, and finally age and parous status. Results. Algorithms useful for the triage of women were produced; gynecologists could apply these in conjunction with available examination results and conclude to an estimation of the risk for a woman to harbor CIN expressed as a probability. Conclusions. The most important test was the cytological examination; however the CART handled cases with inadequate cytological outcome and increased the diagnostic accuracy by exploiting the results of ancillary techniques even if there were inadequate missing data. The CART performance was better than any other single test involved in this study.