A Logistic Regression Model Based on the National Mammography Database Format to Aid Breast Cancer Diagnosis

Chhatwal, Jagpreet; Alagöz, Oğuzhan; Lindstrom, Mary J.; Kahn, Charles Η.; Shaffer, Katherine A.; Burnside, Elizabeth S.

doi:10.2214/ajr.07.3345

Cited by 70 publications

(56 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past, the breast cancer diagnostic problem has been one of the main application areas of classification problems [19][20][21][22][23]. Many modeling, like statistical methods [10][11][12][13][14] are becoming a very popular alternative in handling breast cancer diagnostic tasks. Over the last few years, many studies have shown that data mining techniques such as Artificial Neural Network [19][20][21] and Support Vector Machine [22,23] achieved better performance than did statistical methods.…”

Section: Discussionmentioning

confidence: 99%

“…Some researchers have developed a variety of statistical methods for mammographic diagnosis of breast cancer [10][11][12][13][14]. Rakowski and Clark utilized multiple logistic regression to select significant correlates of screening mammogram and used classification-tree (CHAID) to combine the significant correlates into exclusive and exhaustive subgroups [13].…”

Section: Introductionmentioning

confidence: 99%

“…Rakowski and Clark utilized multiple logistic regression to select significant correlates of screening mammogram and used classification-tree (CHAID) to combine the significant correlates into exclusive and exhaustive subgroups [13]. In addition, Chhatwal et al reported that logistic regression model can discriminate between benign and malignant in decision making for the early detection of breast cancer and identify the most important features associated with breast cancer [14]. Moreover, Heine and colleagues show how parametric statistical methods can be useful for in identifying normal tissue in mammograms [12].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Diagnosing Breast Masses in Digital Mammography Using Feature Selection and Ensemble Methods

Luo

Cheng

2010

J Med Syst

View full text Add to dashboard Cite

Methods that can accurately predict breast cancer are greatly needed and good prediction techniques can help to predict breast cancer more accurately. In this study, we used two feature selection methods, forward selection (FS) and backward selection (BS), to remove irrelevant features for improving the results of breast cancer prediction. The results show that feature reduction is useful for improving the predictive accuracy and density is irrelevant feature in the dataset where the data had been identified on full field digital mammograms collected at the Institute of Radiology of the University of Erlangen-Nuremberg between 2003 and 2006. In addition, decision tree (DT), support vector machine-sequential minimal optimization (SVM-SMO) and their ensembles were applied to solve the breast cancer diagnostic problem in an attempt to predict results with better performance. The results demonstrate that ensemble classifiers are more accurate than a single classifier.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Diagnosing Breast Masses in Digital Mammography Using Feature Selection and Ensemble Methods

Luo

Cheng

2010

J Med Syst

View full text Add to dashboard Cite

show abstract

“…In other words, in our experience, the careful selection of terminologies and ontologies that fit the requirements of the radiologists is a key to correlate the results acquired with different techniques, possibly in different hospitals. This should help in creating new models that improve the accuracy of computer-assisted breast cancer diagnosis [50].…”

Section: Lessons Learned From Redesigning a Clinical Processmentioning

confidence: 99%

A Systematic Approach for Using DICOM Structured Reports in Clinical Processes: Focus on Breast Cancer

et al. 2014

View full text Add to dashboard Cite

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.

show abstract

“…1 Many promising semantic CADx algorithms with good to very good diagnostic performance have been proposed; the statistical techniques employed include artificial neural networks, 2,3 Bayesian networks, [4][5][6] decision trees, 7 and logistic regression. 8,9 However, before it is acceptable to actually apply a semantic CADx algorithm in clinical routine, an external validation of the algorithm's diagnostic performance is mandatory. 10,11 External validation is defined as evaluation of the performance of a classification algorithm on data that were not used to generate the algorithm.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2015

Self Cite

View full text Add to dashboard Cite

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-operatingcharacteristic 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. C 2015 American Association of Physicists in Medicine. [http://dx

show abstract

A Logistic Regression Model Based on the National Mammography Database Format to Aid Breast Cancer Diagnosis

Cited by 70 publications

References 38 publications

Diagnosing Breast Masses in Digital Mammography Using Feature Selection and Ensemble Methods

Diagnosing Breast Masses in Digital Mammography Using Feature Selection and Ensemble Methods

A Systematic Approach for Using DICOM Structured Reports in Clinical Processes: Focus on Breast Cancer

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

Contact Info

Product

Resources

About