A logistic regression model based on the national mammography database format to aid breast cancer diagnosis

Applying data mining techniques to predict vitamin D deficiency in diabetic patients

Vitamin D is among the vitamins necessary for both adults' and children's health. It plays a significant role in calcium absorption, the immune system, cell proliferation and differentiation, bone protection, skeletal health, rickets, muscle health, heart health, disease pathogenesis and severity, glucose metabolism, glucose intolerance, varying insulin secretion, and diabetes. Because the 25-hydroxyvitamin D (25OHD) test, which is used to measure vitamin D is expensive and may not be covered in healthcare benefits in many countries, this study aims to predict vitamin D deficiency in diabetic patients. The prediction method is based on data mining techniques combined with feature selection by using historical electronic health records. The results were compared with a filter-based feature selection algorithm, namely relief-F. Non-valuable features were eliminated effectively with the relief-F feature selection method without any performance loss in classification. The performances of the methods were evaluated using classification accuracy (ACC), sensitivity, specificity, F1-score, precision, kappa results, and receiver operating characteristic (ROC) curves. The analyses have been conducted on a vitamin D dataset of diabetic patients and the results show that the highest classification accuracy of 97.044% was obtained for the support vector machines (SVM) model using radial kernel that contains 18 features.

The impact of partner's behaviour on pregnancy related outcomes and safe child-birth in Pakistan

BACKGROUND

Pakistan is one of the nations with the worst statistics for pregnancy-related outcomes. Health programmes in underdeveloped nations frequently ignore the role of partners in maternal health, which is a crucial contributing factor in these worst situations. This research study aims to explore the role of husbands in maternity care and safe childbirth in Pakistan.

METHODS

The data for this study comes from the Pakistan Maternal Mortality Survey 2019. The k-Modes clustering algorithm was implemented to generate clusters from the dataset. Cluster profiling was used to identify the problems in pregnancy-related outcomes in cases where women live away from their partners. The chi-square test and logistic regression model were fitted to identify the significant factors associated with women's health and safe childbirth.

RESULTS

The finding of the study reveals that the partner's support during and after pregnancy plays a vital role in maternal health and safe child-birth. It was revealed that the women living away from their partners have certain health problems during pregnancy. These problems include Vaginal bleeding, Excessive vomiting, Chest pain, Cough, High B.P, Excessive weight gain, Body aches, Swelling of feet, and Swelling of the face. This also leads to complications and health problems in the postpartum period. Due to a lack of antenatal care from the spouse during pregnancy, the women who lived away from their partners lost their pregnancies.

CONCLUSION

The study concludes that the husband's emotional and financial support substantially impacts the overall health of expecting mothers and the safety of delivery in Pakistan. Given its potential advantages for mother and child health outcomes, male engagement in health education must be acknowledged and addressed. The finding of the study is of immense importance, as it guides the policymakers to arrange various awareness programs for the male partners to support their pregnant spouse and provide proper antenatal care.

TP53 Mutation Estimation Based on MRI Radiomics Analysis for Breast Cancer

BACKGROUND

Noninvasive detection of TP53 mutations is useful for the molecular stratification of breast cancer.

PURPOSE

To explore MRI radiomics features reflecting TP53 mutations in breast cancer and propose a classifier for detecting such mutations.

STUDY TYPE

Retrospective.

POPULATION/SUBJECTS

A total of 139 breast cancer patients with TP53 expression profiling (98 with TP53 mutations and 41 without TP53 mutations).

FIELD STRENGTH/SEQUENCE

1.5 T, T1-weighted (T1W) DCE-MRI.

ASSESSMENT

Lesions were manually segmented using subtracted T1WI. A total of 944 radiomics features (including 744 wavelet-related features) and 7 clinicopathological features were extracted from each lesion. Principal component analysis and Pearson's correlation analysis were used to preprocess the features. Linear discriminant analysis, logistic regression (LR), support vector machine (SVM), and random forest (RF) were used as the classifiers.

STATISTICAL TESTS

Analysis of variance, Kruskal-Wallis and recursive features elimination were used to select features. Receiver operating characteristic (ROC) analysis was performed to compare the diagnostic accuracy.

RESULTS

For the radiomics model, the validation cohorts AUCs of the four classifiers ranged from 0.69 (RF) to 0.74 (LR), and LR (0.74) attained the highest AUCs. For the clinicopathological-radiomics combined model, the validation AUCs of the four classifiers ranged from 0.68 (RF) to 0.86 (SVM), and SVM (0.86) attained highest AUCs. In the subgroup analysis of triple-negative (TN) and luminal type breast cancer, RF achieved the highest AUCs (0.83 and 0.94).

DATA CONCLUSION

Clinicopathological-radiomics combined model with SVM could be used as noninvasive biomarkers for predicting TP53 mutations. RF was recommended for the detection of TP53 mutations in TN and luminal type breast cancer.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Cardiovascular complications in a diabetes prediction model using machine learning: a systematic review

Prediction model has been the focus of studies since the last century in the diagnosis and prognosis of various diseases. With the advancement in computational technology, machine learning (ML) has become the widely used tool to develop a prediction model. This review is to investigate the current development of prediction model for the risk of cardiovascular disease (CVD) among type 2 diabetes (T2DM) patients using machine learning. A systematic search on Scopus and Web of Science (WoS) was conducted to look for relevant articles based on the research question. The risk of bias (ROB) for all articles were assessed based on the Prediction model Risk of Bias Assessment Tool (PROBAST) statement. Neural network with 76.6% precision, 88.06% sensitivity, and area under the curve (AUC) of 0.91 was found to be the most reliable algorithm in developing prediction model for cardiovascular disease among type 2 diabetes patients. The overall concern of applicability of all included studies is low. While two out of 10 studies were shown to have high ROB, another studies ROB are unknown due to the lack of information. The adherence to reporting standards was conducted based on the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) standard where the overall score is 53.75%. It is highly recommended that future model development should adhere to the PROBAST and TRIPOD assessment to reduce the risk of bias and ensure its applicability in clinical settings. Potential lipid peroxidation marker is also recommended in future cardiovascular disease prediction model to improve overall model applicability.

Ovarian cancer reporting lexicon for computed tomography (CT) and magnetic resonance (MR) imaging developed by the SAR Uterine and Ovarian Cancer Disease-Focused Panel and the ESUR Female Pelvic Imaging Working Group

OBJECTIVES

Imaging evaluation is an essential part of treatment planning for patients with ovarian cancer. Variation in the terminology used for describing ovarian cancer on computed tomography (CT) and magnetic resonance (MR) imaging can lead to ambiguity and inconsistency in clinical radiology reports. The aim of this collaborative project between Society of Abdominal Radiology (SAR) Uterine and Ovarian Cancer (UOC) Disease-focused Panel (DFP) and the European Society of Uroradiology (ESUR) Female Pelvic Imaging (FPI) Working Group was to develop an ovarian cancer reporting lexicon for CT and MR imaging.

METHODS

Twenty-one members of the SAR UOC DFP and ESUR FPI working group, one radiology clinical fellow, and two gynecologic oncology surgeons formed the Ovarian Cancer Reporting Lexicon Committee. Two attending radiologist members of the committee prepared a preliminary list of imaging terms that was sent as an online survey to 173 radiologists and gynecologic oncologic physicians, of whom 67 responded to the survey. The committee reviewed these responses to create a final consensus list of lexicon terms.

RESULTS

An ovarian cancer reporting lexicon was created for CT and MR Imaging. This consensus-based lexicon has 6 major categories of terms: general, adnexal lesion-specific, peritoneal carcinomatosis-specific, lymph node-specific, metastatic disease -specific, and fluid-specific.

CONCLUSIONS

This lexicon for CT and MR imaging evaluation of ovarian cancer patients has the capacity to improve the clarity and consistency of reporting disease sites seen on imaging.

KEY POINTS

• This reporting lexicon for CT and MR imaging provides a list of consensus-based, standardized terms and definitions for reporting sites of ovarian cancer on imaging at initial diagnosis or follow-up. • Use of standardized terms and morphologic imaging descriptors can help improve interdisciplinary communication of disease extent and facilitate optimal patient management. • The radiologists should identify and communicate areas of disease, including difficult to resect or potentially unresectable disease that may limit the ability to achieve optimal resection.

The Role of Artificial Intelligence in Early Cancer Diagnosis

Improving the proportion of patients diagnosed with early-stage cancer is a key priority of the World Health Organisation. In many tumour groups, screening programmes have led to improvements in survival, but patient selection and risk stratification are key challenges. In addition, there are concerns about limited diagnostic workforces, particularly in light of the COVID-19 pandemic, placing a strain on pathology and radiology services. In this review, we discuss how artificial intelligence algorithms could assist clinicians in (1) screening asymptomatic patients at risk of cancer, (2) investigating and triaging symptomatic patients, and (3) more effectively diagnosing cancer recurrence. We provide an overview of the main artificial intelligence approaches, including historical models such as logistic regression, as well as deep learning and neural networks, and highlight their early diagnosis applications. Many data types are suitable for computational analysis, including electronic healthcare records, diagnostic images, pathology slides and peripheral blood, and we provide examples of how these data can be utilised to diagnose cancer. We also discuss the potential clinical implications for artificial intelligence algorithms, including an overview of models currently used in clinical practice. Finally, we discuss the potential limitations and pitfalls, including ethical concerns, resource demands, data security and reporting standards.

Downgrade BI-RADS 4A Patients Using Nomogram Based on Breast Magnetic Resonance Imaging, Ultrasound, and Mammography

Objectives

To downgrade BI-RADS 4A patients by constructing a nomogram using R software.

Materials and Methods

A total of 1,717 patients were retrospectively analyzed who underwent preoperative ultrasound, mammography, and magnetic resonance examinations in our hospital from August 2019 to September 2020, and a total of 458 patients of category BI-RADS 4A (mean age, 47 years; range 18–84 years; all women) were included. Multivariable logistic regression was used to screen out the independent influencing parameters that affect the benign and malignant tumors, and the nomogram was constructed by R language to downgrade BI-RADS 4A patients to eligible category.

Results

Of 458 BI-RADS 4A patients, 273 (59.6%) were degraded to category 3. The malignancy rate of these 273 lesions is 1.5% (4/273) (<2%), and the sensitivity reduced to 99.6%, the specificity increased from 4.41% to 45.3%, and the accuracy increased from 63.4% to 78.8%.

Conclusion

By constructing a nomogram, some patients can be downgraded to avoid unnecessary biopsy.

A novel reliability-based regression model for medical modeling and forecasting

BACKGROUND AND AIMS

In recent decades, modeling and forecasting have played a significant role in the diagnosis and treatment of different diseases. Various forecasting models have been developed to improve data-based decision-making processes in medical systems. Although these models differ in many aspects, they all originate from the assumption that more generalizable results are achieved by more accurate models. This means that accuracy is considered as the only prominent feature to evaluate the generalizability of forecasting models. On the other side, due to the changeable medical situations and even changeable models' results, making stable and reliable performance is necessary to adopt appropriate medical decisions. Hence, reliability and stability of models' performance is another effective factor on the model's generalizability that should be taken into consideration in developing medical forecasting models.

METHODS

In this paper, a new reliability-based forecasting approach is developed to address this gap and achieve more consistent performance in making medical predictions. The proposed approach is implemented on the classic regression model which is a common accuracy-based statistical method in medical fields. To evaluate the effectiveness of the proposed model, it has been performed by using two medical benchmark datasets from UCI and obtained results are compared with the classic regression model.

RESULTS

Empirical results show that the proposed model has outperformed the classic regression model in terms of error criteria such as MSE and MAE. So, the presented model can be utilized as an appropriate alternative for the traditional regression model in making effective medical decisions.

CONCLUSIONS

Based on the obtained results, the proposed model can be an appropriate alternative for traditional multiple linear regression for modeling in real-world applications, especially when more generalization and/or more reliability is needed.

Transcriptome integration analysis and specific diagnosis model construction for Hodgkin's lymphoma, diffuse large B-cell lymphoma, and mantle cell lymphoma

Transcriptome differences between Hodgkin's lymphoma (HL), diffuse large B-cell lymphoma (DLBCL), and mantle cell lymphoma (MCL), which are all derived from B cell, remained unclear. This study aimed to construct lymphoma-specific diagnostic models by screening lymphoma marker genes. Transcriptome data of HL, DLBCL, and MCL were obtained from public databases. Lymphoma marker genes were screened by comparing cases and controls as well as the intergroup differences among lymphomas. A total of 9 HL marker genes, 7 DLBCL marker genes, and 4 MCL marker genes were screened in this study. Most HL marker genes were upregulated, whereas DLBCL and MCL marker genes were downregulated compared to controls. The optimal HL-specific diagnostic model contains one marker gene (MYH2) with an AUC of 0.901. The optimal DLBCL-specific diagnostic model contains 7 marker genes (LIPF, CCDC144B, PRO2964, PHF1, SFTPA2, NTS, and HP) with an AUC of 0.951. The optimal MCL-specific diagnostic model contains 3 marker genes (IGLV3-19, IGKV4-1, and PRB3) with an AUC of 0.843. The present study reveals the transcriptome data-based differences between HL, DLBCL, and MCL, when combined with other clinical markers, may help the clinical diagnosis and prognosis.

Machine Learning Models to Improve the Differentiation Between Benign and Malignant Breast Lesions on Ultrasound: A Multicenter External Validation Study

Purpose

This study aimed to establish and evaluate the usefulness of a simple, practical, and easy-to-promote machine learning model based on ultrasound imaging features for diagnosing breast cancer (BC).

Materials and Methods

Logistic regression, random forest, extra trees, support vector, multilayer perceptron, and XG Boost models were developed. The modeling data set of 1345 cases was from a tertiary class A hospital in China. The external validation data set of 1965 cases were from 3 tertiary class A hospitals and 2 primary hospitals. The area under the receiver operating characteristic curve (AUC) was used as the main evaluation index, and pathological biopsy was used as the gold standard for evaluating each model. Diagnostic capability was also compared with that of clinicians.

Results

Among the six models, the logistic model showed superior diagnostic efficiency, with an AUC of 0.771 and 0.906 and Brier scores of 0.181 and 0.165 in the test and validation sets, respectively. The AUCs of the clinician diagnosis and the logistic model were 0.913 and 0.906. Their AUCs in the tertiary class A hospitals were 0.915 and 0.915, respectively, and were 0.894 and 0.873 in primary hospitals, respectively.

Conclusion

The externally validated logical model can be used to distinguish between malignant and benign breast lesions in ultrasound images. Compared with clinician diagnosis, the logistic model has better diagnostic efficiency, making it potentially useful to assist in screening, particularly in lower level medical institutions.

Trial Registration

http://www.clinicaltrials.gov. ClinicalTrials.gov ID: NCT03080623.

Ovarian-Adnexal Reporting Lexicon for MRI: A White Paper of the ACR Ovarian-Adnexal Reporting and Data Systems MRI Committee

MRI is used in the evaluation of ovarian and adnexal lesions. MRI can further characterize lesions seen on ultrasound to help decrease the number of false-positive lesions and avoid unnecessary surgery in benign lesions. Currently, the reporting of ovarian and adnexal findings on MRI is inconsistent because of the lack of standardized descriptor terminology. The development of uniform reporting descriptors can lead to improved interpretation agreement and communication between radiologists and referring physicians. The Ovarian-Adnexal Reporting and Data Systems MRI Committee was formed under the direction of the ACR to create a standardized lexicon for adnexal lesions with the goal of improving the quality and consistency of imaging reports. This white paper describes the consensus process in the creation of a standardized lexicon for ovarian and adnexal lesions for MRI and the resultant lexicon.

Robust Biomarker Screening Using Spares Learning Approach for Liver Cancer Prognosis

LncRNAs, miRNAs, mRNAs, methylation, and proteins exert profound biological functions and are widely applied as prognostic features in liver cancer. This study aims to identify prognostic biomarkers' signature for liver cancer. Samples with inadequate tumor purity were filtered out and the expression data from different resources were retrieved. The Spares learning approach was applied to select lncRNAs, miRNAs, mRNAs, methylation, and proteins' features based on their differentially expressed groups. The LASSO boosting technique was employed for the predictive model construction. A total of 200 lncRNAs, 200 miRNAs, 371 mRNAs, 371 methylations, and 184 proteins were observed to be differentially expressed. Five lncRNAs, 11 miRNAs, 30 mRNAs, 4 methylations, and 3 proteins were selected for further evaluation using the feature elimination technique. The highest accuracy of 89.32% is achieved as a result of training and learning by Spares learning methodology. Final outcomes revealed that 5 lncRNA, 11 miRNA, 30 mRNA, 4 methylation, and 3 protein signatures could be potential biomarkers for the prognosis of liver cancer patients.

Methods Used in Computer-Aided Diagnosis for Breast Cancer Detection Using Mammograms: A Review

According to the American Cancer Society's forecasts for 2019, there will be about 268,600 new cases in the United States with invasive breast cancer in women, about 62,930 new noninvasive cases, and about 41,760 death cases from breast cancer. As a result, there is a high demand for breast imaging specialists as indicated in a recent report for the Institute of Medicine and National Research Council. One way to meet this demand is through developing Computer-Aided Diagnosis (CAD) systems for breast cancer detection and diagnosis using mammograms. This study aims to review recent advancements and developments in CAD systems for breast cancer detection and diagnosis using mammograms and to give an overview of the methods used in its steps starting from preprocessing and enhancement step and ending in classification step. The current level of performance for the CAD systems is encouraging but not enough to make CAD systems standalone detection and diagnose clinical systems. Unless the performance of CAD systems enhanced dramatically from its current level by enhancing the existing methods, exploiting new promising methods in pattern recognition like data augmentation in deep learning and exploiting the advances in computational power of computers, CAD systems will continue to be a second opinion clinical procedure.

Improving breast cancer risk prediction by using demographic risk factors, abnormality features on mammograms and genetic variants

The predictive capability of combining demographic risk factors, germline genetic variants, and mammogram abnormality features for breast cancer risk prediction is poorly understood. We evaluated the predictive performance of combinations of demographic risk factors, high risk single nucleotide polymorphisms (SNPs), and mammography features for women recommended for breast biopsy in a retrospective case-control study (n = 768) with four logistic regression models. The AUC of the baseline demographic features model was 0.580. Both genetic variants and mammography abnormality features augmented the performance of the baseline model: demographics + SNP (AUC =0.668), demographics + mammography (AUC =0.702). Finally, we found that the demographics + SNP + mammography model (AUC = 0.753) had the greatest predictive power, with a significant performance improvement over the other models. The combination of demographic risk factors, genetic variants and imaging features improves breast cancer risk prediction over prior methods utilizing only a subset of these features.

Preference-Sensitive Management of Post-Mammography Decisions in Breast Cancer Diagnosis

Decision models representing the clinical situations where treatment options entail a significant risk of morbidity or mortality should consider the variations in risk preferences of individuals. In this study, we develop a stochastic modeling framework that optimizes risk-sensitive diagnostic decisions after a mammography exam. For a given patient, our objective is to find the utility maximizing diagnostic decisions where we define the utility over quality-adjusted survival duration. We use real data from a private mammography database to numerically solve our model for various utility functions. Our choice of utility functions for the numerical analysis is driven by actual patient behavior encountered in clinical practice. We find that invasive diagnostic procedures such as biopsies are more aggressively used than what the optimal risk-neutral policy would suggest, implying a far-sighted (or equivalently risk-seeking) behavior. When risk preferences are incorporated into the clinical practice, policy makers should bear in mind that a welfare loss in terms of survival duration is inevitable as evidenced by our structural and empirical results.

Machine Learning Approach to Predicting Stem Cell Donor Availability

The success of unrelated donor stem cell transplants depends on not only finding genetically matched donors, but also donor availability. On average 50% of potential donors in the National Marrow Donor Program database are unavailable for a variety of reasons, after initially matching a patient, with significant variations in availability among subgroups (eg, by race or age). Several studies have established univariate donor characteristics associated with availability. Individual consideration of each applicable characteristic is laborious. Extrapolating group averages to the individual-donor level tends to be highly inaccurate. In the current environment with enhanced donor data collection, we can make better estimates of individual donor availability. We propose a machine learning based approach to predict availability of every registered donor, and evaluate the predictive power on a test cohort of 44,544 requests to be .77 based on the area under the receiver-operating characteristic curve. We propose that this predictor should be used during donor selection to reduce the time to transplant.

Minimization of annotation work: diagnosis of mammographic masses via active learning

The prerequisite for establishing an effective prediction system for mammographic diagnosis is the annotation of each mammographic image. The manual annotation work is time-consuming and laborious, which becomes a great hindrance for researchers. In this article, we propose a novel active learning algorithm that can adequately address this problem, leading to the minimization of the labeling costs on the premise of guaranteed performance. Our proposed method is different from the existing active learning methods designed for the general problem as it is specifically designed for mammographic images. Through its modified discriminant functions and improved sample query criteria, the proposed method can fully utilize the pairing of mammographic images and select the most valuable images from both the mediolateral and craniocaudal views. Moreover, in order to extend active learning to the ordinal regression problem, which has no precedent in existing studies, but is essential for mammographic diagnosis (mammographic diagnosis is not only a classification task, but also an ordinal regression task for predicting an ordinal variable, viz. the malignancy risk of lesions), multiple sample query criteria need to be taken into consideration simultaneously. We formulate it as a criteria integration problem and further present an algorithm based on self-adaptive weighted rank aggregation to achieve a good solution. The efficacy of the proposed method was demonstrated on thousands of mammographic images from the digital database for screening mammography. The labeling costs of obtaining optimal performance in the classification and ordinal regression task respectively fell to 33.8 and 19.8 percent of their original costs. The proposed method also generated 1228 wins, 369 ties and 47 losses for the classification task, and 1933 wins, 258 ties and 185 losses for the ordinal regression task compared to the other state-of-the-art active learning algorithms. By taking the particularities of mammographic images, the proposed AL method can indeed reduce the manual annotation work to a great extent without sacrificing the performance of the prediction system for mammographic diagnosis.

Assessing Breast Cancer Risk with an Artificial Neural Network

Objectives:

Radiologists face uncertainty in making decisions based on their judgment of breast cancer risk. Artificial intelligence and machine learning techniques have been widely applied in detection/recognition of cancer. This study aimed to establish a model to aid radiologists in breast cancer risk estimation. This incorporated imaging methods and fine needle aspiration biopsy (FNAB) for cyto-pathological diagnosis.

Methods:

An artificial neural network (ANN) technique was used on a retrospectively collected dataset including mammographic results, risk factors, and clinical findings to accurately predict the probability of breast cancer in individual patients. Area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values were used to evaluate discriminative performance.

Result:

The network incorporating the selected features performed best (AUC = 0.955). Sensitivity and specificity of the ANN were respectively calculated as 0.82 and 0.90. In addition, negative and positive predictive values were respectively computed as 0.90 and 0.80.

Conclusion:

ANN has potential applications as a decision-support tool to help underperforming practitioners to improve the positive predictive value of biopsy recommendations.

Quantifying predictive capability of electronic health records for the most harmful breast cancer

Improved prediction of the "most harmful" breast cancers that cause the most substantive morbidity and mortality would enable physicians to target more intense screening and preventive measures at those women who have the highest risk; however, such prediction models for the "most harmful" breast cancers have rarely been developed. Electronic health records (EHRs) represent an underused data source that has great research and clinical potential. Our goal was to quantify the value of EHR variables in the "most harmful" breast cancer risk prediction. We identified 794 subjects who had breast cancer with primary non-benign tumors with their earliest diagnosis on or after 1/1/2004 from an existing personalized medicine data repository, including 395 "most harmful" breast cancer cases and 399 "least harmful" breast cancer cases. For these subjects, we collected EHR data comprised of 6 components: demographics, diagnoses, symptoms, procedures, medications, and laboratory results. We developed two regularized prediction models, Ridge Logistic Regression (Ridge-LR) and Lasso Logistic Regression (Lasso-LR), to predict the "most harmful" breast cancer one year in advance. The area under the ROC curve (AUC) was used to assess model performance. We observed that the AUCs of Ridge-LR and Lasso-LR models were 0.818 and 0.839 respectively. For both the Ridge-LR and Lasso-LR models, the predictive performance of the whole EHR variables was significantly higher than that of each individual component (p<0.001). In conclusion, EHR variables can be used to predict the "most harmful" breast cancer, providing the possibility to personalize care for those women at the highest risk in clinical practice.

Logistic LASSO regression for the diagnosis of breast cancer using clinical demographic data and the BI-RADS lexicon for ultrasonography

Purpose

The aim of this study was to compare the performance of image analysis for predicting breast cancer using two distinct regression models and to evaluate the usefulness of incorporating clinical and demographic data (CDD) into the image analysis in order to improve the diagnosis of breast cancer.

Methods

This study included 139 solid masses from 139 patients who underwent a ultrasonography-guided core biopsy and had available CDD between June 2009 and April 2010. Three breast radiologists retrospectively reviewed 139 breast masses and described each lesion using the Breast Imaging Reporting and Data System (BI-RADS) lexicon. We applied and compared two regression methods-stepwise logistic (SL) regression and logistic least absolute shrinkage and selection operator (LASSO) regression-in which the BI-RADS descriptors and CDD were used as covariates. We investigated the performances of these regression methods and the agreement of radiologists in terms of test misclassification error and the area under the curve (AUC) of the tests.

Results

Logistic LASSO regression was superior (P<0.05) to SL regression, regardless of whether CDD was included in the covariates, in terms of test misclassification errors (0.234 vs. 0.253, without CDD; 0.196 vs. 0.258, with CDD) and AUC (0.785 vs. 0.759, without CDD; 0.873 vs. 0.735, with CDD). However, it was inferior (P<0.05) to the agreement of three radiologists in terms of test misclassification errors (0.234 vs. 0.168, without CDD; 0.196 vs. 0.088, with CDD) and the AUC without CDD (0.785 vs. 0.844, P<0.001), but was comparable to the AUC with CDD (0.873 vs. 0.880, P=0.141).

Conclusion

Logistic LASSO regression based on BI-RADS descriptors and CDD showed better performance than SL in predicting the presence of breast cancer. The use of CDD as a supplement to the BI-RADS descriptors significantly improved the prediction of breast cancer using logistic LASSO regression.

Assessment of Breast Cancer Risk in an Iranian Female Population Using Bayesian Networks with Varying Node Number

Objective:

As a source of information, medical data can feature hidden relationships. However, the high volume of datasets and complexity of decision-making in medicine introduce difficulties for analysis and interpretation and processing steps may be needed before the data can be used by clinicians in their work. This study focused on the use of Bayesian models with different numbers of nodes to aid clinicians in breast cancer risk estimation.

Methods:

Bayesian networks (BNs) with a retrospectively collected dataset including mammographic details, risk factor exposure, and clinical findings was assessed for prediction of the probability of breast cancer in individual patients. Area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values were used to evaluate discriminative performance.

Result:

A network incorporating selected features performed better (AUC = 0.94) than that incorporating all the features (AUC = 0.93). The results revealed no significant difference among 3 models regarding performance indices at the 5% significance level.

Conclusion:

BNs could effectively discriminate malignant from benign abnormalities and accurately predict the risk of breast cancer in individuals. Moreover, the overall performance of the 9-node BN was better, and due to the lower number of nodes it might be more readily be applied in clinical settings.

Integrative modeling of multi-omics data to identify cancer drivers and infer patient-specific gene activity

Background

High throughput technologies have been used to profile genes in multiple different dimensions, such as genetic variation, copy number, gene and protein expression, epigenetics, metabolomics. Computational analyses often treat these different data types as independent, leading to an explosion in the number of features making studies under-powered and more importantly do not provide a comprehensive view of the gene’s state. We sought to infer gene activity by integrating different dimensions using biological knowledge of oncogenes and tumor suppressors.

Results

This paper proposes an integrative model of oncogene and tumor suppressor activity in cells which is used to identify cancer drivers and compute patient-specific gene activity scores. We have developed a Fuzzy Logic Modeling (FLM) framework to incorporate biological knowledge with multi-omics data such as somatic mutation, gene expression and copy number measurements. The advantage of using a fuzzy logic approach is to abstract meaningful biological rules from low-level numerical data. Biological knowledge is often qualitative, thus combining it with quantitative numerical measurements may leverage new biological insights about a gene’s state. We show that the oncogenic and altered tumor suppressing state of a gene can be better characterized by integrating different molecular measurements with biological knowledge than by each data type alone. We validate the gene activity score using data from the Cancer Cell Line Encyclopedia and drug sensitivity data for five compounds: BYL719 (PIK3CA inhibitor), PLX4720 (BRAF inhibitor), AZD6244 (MEK inhibitor), Erlotinib (EGFR inhibitor), and Nutlin-3 (MDM2 inhibitor). The integrative score improves prediction of drug sensitivity for the known drug targets of these compounds compared to each data type alone. The gene activity scores are also used to cluster colorectal cancer cell lines. Two subtypes of CRCs were found and potential cancer drivers and therapeutic targets for each of the subtypes were identified.

Conclusions

We propose a fuzzy logic based approach to infer gene activity in cancer by integrating numerical data with descriptive biological knowledge. We compute general patient-specific gene-level scores useful to determine the oncogenic or tumor suppressor status of cancer gene drivers and to cluster or classify patients.

Electronic supplementary material

The online version of this article (doi:10.1186/s12918-016-0260-9) contains supplementary material, which is available to authorized users.

Comparing Mammography Abnormality Features to Genetic Variants in the Prediction of Breast Cancer in Women Recommended for Breast Biopsy

RATIONALE AND OBJECTIVES

The discovery of germline genetic variants associated with breast cancer has engendered interest in risk stratification for improved, targeted detection and diagnosis. However, there has yet to be a comparison of the predictive ability of these genetic variants with mammography abnormality descriptors.

MATERIALS AND METHODS

Our institutional review board-approved, Health Insurance Portability and Accountability Act-compliant study utilized a personalized medicine registry in which participants consented to provide a DNA sample and to participate in longitudinal follow-up. In our retrospective, age-matched, case-controlled study of 373 cases and 395 controls who underwent breast biopsy, we collected risk factors selected a priori based on the literature, including demographic variables based on the Gail model, common germline genetic variants, and diagnostic mammography findings according to Breast Imaging Reporting and Data System (BI-RADS). We developed predictive models using logistic regression to determine the predictive ability of (1) demographic variables, (2) 10 selected genetic variants, or (3) mammography BI-RADS features. We evaluated each model in turn by calculating a risk score for each patient using 10-fold cross-validation, used this risk estimate to construct Receiver Operator Characteristic Curve (ROC) curves, and compared the area under the ROC curve (AUC) of each using the DeLong method.

RESULTS

The performance of the regression model using demographic risk factors was not statistically different from the model using genetic variants (P = 0.9). The model using mammography features (AUC = 0.689) was superior to both the demographic model (AUC = .598; P < 0.001) and the genetic model (AUC = .601; P < 0.001).

CONCLUSIONS

BI-RADS features exceeded the ability of demographic and 10 selected germline genetic variants to predict breast cancer in women recommended for biopsy.

Breast Imaging in the Era of Big Data: Structured Reporting and Data Mining

OBJECTIVE

The purpose of this article is to describe structured reporting and the development of large databases for use in data mining in breast imaging.

CONCLUSION

The results of millions of breast imaging examinations are reported with structured tools based on the BI-RADS lexicon. Much of these data are stored in accessible media. Robust computing power creates great opportunity for data scientists and breast imagers to collaborate to improve breast cancer detection and optimize screening algorithms. Data mining can create knowledge, but the questions asked and their complexity require extremely powerful and agile databases. New data technologies can facilitate outcomes research and precision medicine.

Subcategorization of Suspicious Breast Lesions (BI-RADS Category 4) According to MRI Criteria: Role of Dynamic Contrast-Enhanced and Diffusion-Weighted Imaging

OBJECTIVE

The purposes of this study were to investigate whether dynamic contrast-enhanced MRI is adequate for subcategorization of suspicious lesions (BI-RADS category 4) and to evaluate whether use of DWI improves diagnostic performance.

MATERIALS AND METHODS

The study group was composed of 103 suspicious lesions found in 83 subjects. Patient ages and lesion sizes were compiled, and two radiologists reanalyzed the images; subcategorized the findings as BI-RADS 4A, 4B, or 4C; and calculated apparent diffusion coefficient (ADC) values. The stratified variables were tested by univariate analysis and inserted in two multivariate predictive models, which were used to generate ROC curves and compare AUCs. Positive predictive values (PPVs) for each subcategory and ADC level were calculated, and interobserver agreement was tested.

RESULTS

Forty-four (42.7%) suspicious findings proved malignant. Except for age (p = 0.08), all stratified predictor variables were significant in univariate analyses (p < 0.01). Logistic regression models did not differ substantially after comparison of the ROC curves (p = 0.09), but the one including ADC values was slightly better: AUC of 0.89 (95% CI, 0.82-0.95) against AUC of 0.85 (95% CI, 0.78-0.93). PPV increased progressively in each BI-RADS 4 subcategory (4A, 0.15; 4B, 0.37; 4C, 0.84). ADC values of 1.10 × 10(-3) mm(2)/s or less had the second highest PPV (0.77). Interobserver agreement was substantial at a kappa value of 0.80 (95% CI, 0.70-0.90; p < 0.01).

CONCLUSION

Risk stratification of suspicious lesions (BI-RADS category 4) can be satisfactorily performed with DCE-MRI and slightly improved when DWI is introduced.

External validation of a publicly available computer assisted diagnostic tool for mammographic mass lesions with two high prevalence research datasets

PURPOSE

Lesions detected at mammography are described with a highly standardized terminology: the breast imaging-reporting and data system (BI-RADS) lexicon. Up to now, no validated semantic computer assisted classification algorithm exists to interactively link combinations of morphological descriptors from the lexicon to a probabilistic risk estimate of malignancy. The authors therefore aim at the external validation of the mammographic mass diagnosis (MMassDx) algorithm. A classification algorithm like MMassDx must perform well in a variety of clinical circumstances and in datasets that were not used to generate the algorithm in order to ultimately become accepted in clinical routine.

METHODS

The MMassDx algorithm uses a naïve Bayes network and calculates post-test probabilities of malignancy based on two distinct sets of variables, (a) BI-RADS descriptors and age ("descriptor model") and (b) BI-RADS descriptors, age, and BI-RADS assessment categories ("inclusive model"). The authors evaluate both the MMassDx (descriptor) and MMassDx (inclusive) models using two large publicly available datasets of mammographic mass lesions: the digital database for screening mammography (DDSM) dataset, which contains two subsets from the same examinations-a medio-lateral oblique (MLO) view and cranio-caudal (CC) view dataset-and the mammographic mass (MM) dataset. The DDSM contains 1220 mass lesions and the MM dataset contains 961 mass lesions. The authors evaluate discriminative performance using area under the receiver-operating-characteristic curve (AUC) and compare this to the BI-RADS assessment categories alone (i.e., the clinical performance) using the DeLong method. The authors also evaluate whether assigned probabilistic risk estimates reflect the lesions' true risk of malignancy using calibration curves.

RESULTS

The authors demonstrate that the MMassDx algorithms show good discriminatory performance. AUC for the MMassDx (descriptor) model in the DDSM data is 0.876/0.895 (MLO/CC view) and AUC for the MMassDx (inclusive) model in the DDSM data is 0.891/0.900 (MLO/CC view). AUC for the MMassDx (descriptor) model in the MM data is 0.862 and AUC for the MMassDx (inclusive) model in the MM data is 0.900. In all scenarios, MMassDx performs significantly better than clinical performance, P < 0.05 each. The authors furthermore demonstrate that the MMassDx algorithm systematically underestimates the risk of malignancy in the DDSM and MM datasets, especially when low probabilities of malignancy are assigned.

CONCLUSIONS

The authors' results reveal that the MMassDx algorithms have good discriminatory performance but less accurate calibration when tested on two independent validation datasets. Improvement in calibration and testing in a prospective clinical population will be important steps in the pursuit of translation of these algorithms to the clinic.

A systematic approach for using DICOM structured reports in clinical processes: focus on breast cancer

This paper describes a methodology for redesigning the clinical processes to manage diagnosis, follow-up, and response to treatment episodes of breast cancer. This methodology includes three fundamental elements: (1) identification of similar and contrasting cases that may be of clinical relevance based upon a target study, (2) codification of reports with standard medical terminologies, and (3) linking and indexing the structured reports obtained with different techniques in a common system. The combination of these elements should lead to improvements in the clinical management of breast cancer patients. The motivation for this work is the adaptation of the clinical processes for breast cancer created by the Valencian Community health authorities to the new techniques available for data processing. To achieve this adaptation, it was necessary to design nine Digital Imaging and Communications in Medicine (DICOM) structured report templates: six diagnosis templates and three summary templates that combine reports from clinical episodes. A prototype system is also described that links the lesion to the reports. Preliminary tests of the prototype have shown that the interoperability among the report templates allows correlating parameters from different reports. Further work is in progress to improve the methodology in order that it can be applied to clinical practice.

Developing a comprehensive database management system for organization and evaluation of mammography datasets

We aimed to design and develop a comprehensive mammography database system (CMDB) to collect clinical datasets for outcome assessment and development of decision support tools. A Health Insurance Portability and Accountability Act (HIPAA) compliant CMDB was created to store multi-relational datasets of demographic risk factors and mammogram results using the Breast Imaging Reporting and Data System (BI-RADS) lexicon. The CMDB collected both biopsy pathology outcomes, in a breast pathology lexicon compiled by extending BI-RADS, and our institutional breast cancer registry. The audit results derived from the CMDB were in accordance with Mammography Quality Standards Act (MQSA) audits and national benchmarks. The CMDB has managed the challenges of multi-level organization demanded by the complexity of mammography practice and lexicon development in pathology. We foresee that the CMDB will be useful for efficient quality assurance audits and development of decision support tools to improve breast cancer diagnosis. Our procedure of developing the CMDB provides a framework to build a detailed data repository for breast imaging quality control and research, which has the potential to augment existing resources.

Construction the model on the breast cancer survival analysis use support vector machine, logistic regression and decision tree

The aim of the paper is to use data mining technology to establish a classification of breast cancer survival patterns, and offers a treatment decision-making reference for the survival ability of women diagnosed with breast cancer in Taiwan. We studied patients with breast cancer in a specific hospital in Central Taiwan to obtain 1,340 data sets. We employed a support vector machine, logistic regression, and a C5.0 decision tree to construct a classification model of breast cancer patients' survival rates, and used a 10-fold cross-validation approach to identify the model. The results show that the establishment of classification tools for the classification of the models yielded an average accuracy rate of more than 90% for both; the SVM provided the best method for constructing the three categories of the classification system for the survival mode. The results of the experiment show that the three methods used to create the classification system, established a high accuracy rate, predicted a more accurate survival ability of women diagnosed with breast cancer, and could be used as a reference when creating a medical decision-making frame.

A comprehensive methodology for determining the most informative mammographic features

This study aims to determine the most informative mammographic features for breast cancer diagnosis using mutual information (MI) analysis. Our Health Insurance Portability and Accountability Act-approved database consists of 44,397 consecutive structured mammography reports for 20,375 patients collected from 2005 to 2008. The reports include demographic risk factors (age, family and personal history of breast cancer, and use of hormone therapy) and mammographic features from the Breast Imaging Reporting and Data System lexicon. We calculated MI using Shannon's entropy measure for each feature with respect to the outcome (benign/malignant using a cancer registry match as reference standard). In order to evaluate the validity of the MI rankings of features, we trained and tested naïve Bayes classifiers on the feature with tenfold cross-validation, and measured the predictive ability using area under the ROC curve (AUC). We used a bootstrapping approach to assess the distributional properties of our estimates, and the DeLong method to compare AUC. Based on MI, we found that mass margins and mass shape were the most informative features for breast cancer diagnosis. Calcification morphology, mass density, and calcification distribution provided predictive information for distinguishing benign and malignant breast findings. Breast composition, associated findings, and special cases provided little information in this task. We also found that the rankings of mammographic features with MI and AUC were generally consistent. MI analysis provides a framework to determine the value of different mammographic features in the pursuit of optimal (i.e., accurate and efficient) breast cancer diagnosis.

A new hybrid case-based reasoning approach for medical diagnosis systems

Case-Based Reasoning (CBR) has been applied in many different medical applications. Due to the complexities and the diversities of this domain, most medical CBR systems become hybrid. Besides, the case adaptation process in CBR is often a challenging issue as it is traditionally carried out manually by domain experts. In this paper, a new hybrid case-based reasoning approach for medical diagnosis systems is proposed to improve the accuracy of the retrieval-only CBR systems. The approach integrates case-based reasoning and rule-based reasoning, and also applies the adaptation process automatically by exploiting adaptation rules. Both adaptation rules and reasoning rules are generated from the case-base. After solving a new case, the case-base is expanded, and both adaptation and reasoning rules are updated. To evaluate the proposed approach, a prototype was implemented and experimented to diagnose breast cancer and thyroid diseases. The final results show that the proposed approach increases the diagnosing accuracy of the retrieval-only CBR systems, and provides a reliable accuracy comparing to the current breast cancer and thyroid diagnosis systems.

Optimal Policies for Reducing Unnecessary Follow-up Mammography Exams in Breast Cancer Diagnosis

Mammography is the most effective screening tool for early diagnosis of breast cancer. Based on the mammography findings, radiologists need to choose from one of the following three alternatives: 1) take immediate diagnostic actions including prompt biopsy to confirm breast cancer; 2) recommend a follow-up mammogram; 3) recommend routine annual mammography. There are no validated structured guidelines based on a decision-analytical framework to aid radiologists in making such patient management decisions. Surprisingly, only 15-45% of the breast biopsies and less than 1% of short-interval follow-up recommendations are found to be malignant, resulting in unnecessary tests and patient-anxiety. We develop a finite-horizon discrete-time Markov decision process (MDP) model that may help radiologists make patient-management decisions to maximize a patient's total expected quality-adjusted life years. We use clinical data to find the policies recommended by the MDP model and also compare them to decisions made by radiologists at a large mammography practice. We also derive the structural properties of the MDP model, including sufficiency conditions that ensure the existence of a double control-limit type policy.

What is the optimal threshold at which to recommend breast biopsy?

Background

A 2% threshold, traditionally used as a level above which breast biopsy recommended, has been generalized to all patients from several specific situations analyzed in the literature. We use a sequential decision analytic model considering clinical and mammography features to determine the optimal general threshold for image guided breast biopsy and the sensitivity of this threshold to variation of these features.

Methodology/Principal Findings

We built a decision analytical model called a Markov Decision Process (MDP) model, which determines the optimal threshold of breast cancer risk to perform breast biopsy in order to maximize a patient’s total quality-adjusted life years (QALYs). The optimal biopsy threshold is determined based on a patient’s probability of breast cancer estimated by a logistic regression model (LRM) which uses demographic risk factors (age, family history, and hormone use) and mammographic findings (described using the established lexicon–BI-RADS). We estimate the MDP model's parameters using SEER data (prevalence of invasive vs. in situ disease, stage at diagnosis, and survival), US life tables (all cause mortality), and the medical literature (biopsy disutility and treatment efficacy) to determine the optimal “base case” risk threshold for breast biopsy and perform sensitivity analysis. The base case MDP model reveals that 2% is the optimal threshold for breast biopsy for patients between 42 and 75 however the thresholds below age 42 is lower (1%) and above age 75 is higher (range of 3–5%). Our sensitivity analysis reveals that the optimal biopsy threshold varies most notably with changes in age and disutility of biopsy.

Conclusions/Significance

Our MDP model validates the 2% threshold currently used for biopsy but shows this optimal threshold varies substantially with patient age and biopsy disutility.

Retrieval boosted computer-aided diagnosis of clustered microcalcifications for breast cancer

PURPOSE

The authors propose an image-retrieval based approach for case-adaptive classifier design in computer-aided diagnosis (CADx). The conventional approach in CADx is to first train a pattern-classifier based on a set of existing training samples and then apply this classifier to subsequent new cases. The purpose of this work is to improve the classification accuracy of a CADx classifier by making use of a set of known cases retrieved from a reference library that are similar to the case under consideration.

METHODS

In the proposed approach, the authors will first apply image-retrieval to obtain a set of lesion images from a library of known cases that have similar image features to a case being diagnosed (i.e., query). These retrieved cases are then used to optimize a pattern-classifier toward boosting its classification accuracy on the query case. The basic idea is to put more emphasis on those cases that are similar to the query. The proposed approach is demonstrated first using a linear classifier and then extended to a nonlinear classifier induced by kernel principal component analysis.

RESULTS

The proposed retrieval-driven approach was tested on a library of mammogram images from 1006 cases (646 benign and 360 malignant) obtained from multiple institutions and was demonstrated to yield significant improvement in classification performance. Measured by the area under the receiver operating characteristic curve (AUC), the case-adaptive approach could boost the classification performance of a linear classifier from AUC = 0.7415 to AUC = 0.7807; similar improvement was also obtained for a nonlinear classifier, with AUC boosted from 0.7527 to 0.7838.

CONCLUSIONS

Use of additional cases from a reference library that have similar image features can improve the classification accuracy of a CADx classifier on a query case. It can even outperform retraining the classifier with all the cases from the entire reference library. This implies that cases with similar image features are more relevant in defining the local decision boundary of the CADx classifier around the query.

The Effect of Budgetary Restrictions on Breast Cancer Diagnostic Decisions

We develop a finite-horizon discrete-time constrained Markov decision process (MDP) to model diagnostic decisions after mammography where we maximize the total expected quality-adjusted life years (QALYs) of a patient under resource constraints. We use clinical data to estimate the parameters of the MDP model and solve it as a mixed-integer program. By repeating optimization for a sequence of budget levels, we calculate incremental cost-effectiveness ratios attributable to consecutive levels of funding and compare actual clinical practice with optimal decisions. We prove that the optimal value function is concave in the allocated budget. Comparing to actual clinical practice, using optimal thresholds for decision making may result in approximately 22% cost savings without sacrificing QALYs. Our analysis indicates short-term follow-ups are the immediate target for elimination when budget becomes a concern. Policy change is more drastic in the older age group with the increasing budget, yet the gains in total expected QALYs related to larger budgets are predominantly seen in younger women along with modest gains for older women.

Optimal Breast Biopsy Decision-Making Based on Mammographic Features and Demographic Factors

Breast cancer is the most common non-skin cancer affecting women in the United States, where every year more than 20 million mammograms are performed. Breast biopsy is commonly performed on the suspicious findings on mammograms to confirm the presence of cancer. Currently, 700,000 biopsies are performed annually in the U.S.; 55%-85% of these biopsies ultimately are found to be benign breast lesions, resulting in unnecessary treatments, patient anxiety, and expenditures. This paper addresses the decision problem faced by radiologists: When should a woman be sent for biopsy based on her mammographic features and demographic factors? This problem is formulated as a finite-horizon discrete-time Markov decision process. The optimal policy of our model shows that the decision to biopsy should take the age of patient into account; particularly, an older patient's risk threshold for biopsy should be higher than that of a younger patient. When applied to the clinical data, our model outperforms radiologists in the biopsy decision-making problem. This study also derives structural properties of the model, including sufficiency conditions that ensure the existence of a control-limit type policy and nondecreasing control-limits with age.

Breast cancer risk estimation with artificial neural networks revisited: discrimination and calibration

BACKGROUND

Discriminating malignant breast lesions from benign ones and accurately predicting the risk of breast cancer for individual patients are crucial to successful clinical decisions. In the past, several artificial neural network (ANN) models have been developed for breast cancer-risk prediction. All studies have reported discrimination performance, but not one has assessed calibration, which is an equivalently important measure for accurate risk prediction. In this study, the authors have evaluated whether an artificial neural network (ANN) trained on a large prospectively collected dataset of consecutive mammography findings can discriminate between benign and malignant disease and accurately predict the probability of breast cancer for individual patients.

METHODS

Our dataset consisted of 62,219 consecutively collected mammography findings matched with the Wisconsin State Cancer Reporting System. The authors built a 3-layer feedforward ANN with 1000 hidden-layer nodes. The authors trained and tested their ANN by using 10-fold cross-validation to predict the risk of breast cancer. The authors used area the under the receiver-operating characteristic curve (AUC), sensitivity, and specificity to evaluate discriminative performance of the radiologists and their ANN. The authors assessed the accuracy of risk prediction (ie, calibration) of their ANN by using the Hosmer-Lemeshow (H-L) goodness-of-fit test.

RESULTS

Their ANN demonstrated superior discrimination (AUC, 0.965) compared with the radiologists (AUC, 0.939; P<.001). The authors' ANN was also well calibrated as shown by an H-L goodness of fit P-value of .13.

CONCLUSIONS

The authors' ANN can effectively discriminate malignant abnormalities from benign ones and accurately predict the risk of breast cancer for individual abnormalities.

Computer-aided diagnostic models in breast cancer screening

Mammography is the most common modality for breast cancer detection and diagnosis and is often complemented by ultrasound and MRI. However, similarities between early signs of breast cancer and normal structures in these images make detection and diagnosis of breast cancer a difficult task. To aid physicians in detection and diagnosis, computer-aided detection and computer-aided diagnostic (CADx) models have been proposed. A large number of studies have been published for both computer-aided detection and CADx models in the last 20 years. The purpose of this article is to provide a comprehensive survey of the CADx models that have been proposed to aid in mammography, ultrasound and MRI interpretation. We summarize the noteworthy studies according to the screening modality they consider and describe the type of computer model, input data size, feature selection method, input feature type, reference standard and performance measures for each study. We also list the limitations of the existing CADx models and provide several possible future research directions.

Quantitative methodology using CT for predicting survival in patients with metastatic colorectal carcinoma: a pilot study

OBJECTIVE

To develop a methodology which quantifies multiple changing lesion features resulting in an optimized computed tomography (CT) response score (CRS) for prediction of overall survival (OS) in response to treatment for metastatic colorectal carcinoma (MCRC).

SUBJECTS AND METHODS

This Health Insurance Portability and Accountability Act-compliant, institutional review board-approved retrospective study evaluated multiple changing imaging findings and their correlation with OS with a new methodology comparing the baseline and first post-treatment CT scans in 38 MCRC patients on last-line chemotherapy (cetuximab and irinotecan). Tumor size/enhancement changes and interval development of new lesions were quantified with either Likert-type scales (all parameters) or Response Evaluation Criteria in Solid Tumors (RECIST) (size change only). The most predictive parameters for OS were used to generate the CRS with an overall range of -3 (complete disappearance) to +2 (definite tumor increase). The Cox Hazard Ratio was used to assess prediction of survival. Reader agreement was evaluated by the kappa statistic.

RESULTS

Tumor size was the best predictor of OS using the Likert-type scale or RECIST. The CRS was not improved combining size change with other parameters. Use of the Likert-type scale resulted in predicting OS with a Cox hazard ratio of 1.697 (P=.0004) and good agreement (kappa=0.73, 95% CI=0.41-1.10) between observers with no significant difference using RECIST.

CONCLUSION

The methodology produces a CRS for MCRC predicting OS resulting from therapy which expands standard RECIST guidelines to allow critical evaluation of multiple additional imaging parameters. Size change alone was found to be the best parameter of those considered in terms of maximizing agreement and prediction of OS.

Informatics in radiology: comparison of logistic regression and artificial neural network models in breast cancer risk estimation

Computer models in medical diagnosis are being developed to help physicians differentiate between healthy patients and patients with disease. These models can aid in successful decision making by allowing calculation of disease likelihood on the basis of known patient characteristics and clinical test results. Two of the most frequently used computer models in clinical risk estimation are logistic regression and an artificial neural network. A study was conducted to review and compare these two models, elucidate the advantages and disadvantages of each, and provide criteria for model selection. The two models were used for estimation of breast cancer risk on the basis of mammographic descriptors and demographic risk factors. Although they demonstrated similar performance, the two models have unique characteristics-strengths as well as limitations-that must be considered and may prove complementary in contributing to improved clinical decision making.

Information Extraction for Clinical Data Mining: A Mammography Case Study

Breast cancer is the leading cause of cancer mortality in women between the ages of 15 and 54. During mammography screening, radiologists use a strict lexicon (BI-RADS) to describe and report their findings. Mammography records are then stored in a well-defined database format (NMD). Lately, researchers have applied data mining and machine learning techniques to these databases. They successfully built breast cancer classifiers that can help in early detection of malignancy. However, the validity of these models depends on the quality of the underlying databases. Unfortunately, most databases suffer from inconsistencies, missing data, inter-observer variability and inappropriate term usage. In addition, many databases are not compliant with the NMD format and/or solely consist of text reports. BI-RADS feature extraction from free text and consistency checks between recorded predictive variables and text reports are crucial to addressing this problem. We describe a general scheme for concept information retrieval from free text given a lexicon, and present a BI-RADS features extraction algorithm for clinical data mining. It consists of a syntax analyzer, a concept finder and a negation detector. The syntax analyzer preprocesses the input into individual sentences. The concept finder uses a semantic grammar based on the BI-RADS lexicon and the experts' input. It parses sentences detecting BI-RADS concepts. Once a concept is located, a lexical scanner checks for negation. Our method can handle multiple latent concepts within the text, filtering out ultrasound concepts. On our dataset, our algorithm achieves 97.7% precision, 95.5% recall and an F1-score of 0.97. It outperforms manual feature extraction at the 5% statistical significance level.