Perceptron error surface analysis: a case study in breast cancer diagnosis

Markey, Mia K.; Lo, Joseph Y.; Vargas-Voracek, Rene; Tourassi, Georgia D.; Floyd, Carey E.

doi:10.1016/s0010-4825(01)00035-x

Cited by 12 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A learning rate of 0.05 (this constant regulates the speed of learning. A lower learning constant improves the classification model at the expense of the time it takes to process the variable) was used 31. This algorithm was used to distinguish between localized tumors and the corresponding metastases.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Predicting neuroendocrine tumor (carcinoid) neoplasia using gene expression profiling and supervised machine learning

Drozdov

Kidd

Nadler

et al. 2009

Cancer

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

“…This algorithm was used to distinguish between localized tumors and the corresponding metastases. This methodology has previously been shown to be effective in predicting malignancy of breast cancer 31.…”

Section: Methodsmentioning

confidence: 99%

Predicting neuroendocrine tumor (carcinoid) neoplasia using gene expression profiling and supervised machine learning

Drozdov

Kidd

Nadler

et al. 2009

Cancer

View full text Add to dashboard Cite

show abstract

“…In general, BI-RADS attributes are collected by different physicians trained at different radiology centres providing values for a given BI-RADS attribute such as the mass shape, to a suspicious region seen in a mammogram. An artificial neural networks approach was proposed to deduce the diagnosis from BI-RADS descriptions [6,7]. Alternative approaches based on case-based reasoning and Bayesian networks were later proposed [8]- [12].…”

Section: Introductionmentioning

confidence: 99%

Prediction of breast cancer biopsy outcomes using a distributed genetic programming approach

Ludwig

2010

Proceedings of the 1st ACM International Health Informatics Symposium

View full text Add to dashboard Cite

Worldwide, breast cancer is the second most common type of cancer after lung cancer and the fifth most common cause of cancer death accounting for 519,000 deaths worldwide in 2004. The most effective method for breast cancer screening today is mammography. However, presently predictions of breast biopsies resulting from mammogram interpretation lead to approximately 70 % biopsies with benign outcomes, which are preventable. Therefore, an automatic method is necessary to aid physicians in the prognosis of mammography interpretations. The data set used for this investigation is based on BI-RADS findings. Previous work has achieved good results using a decision tree, an artificial neural networks and a case-based reasoning approach to develop predictive classifiers. This paper uses a distributed genetic programming approach to predict the outcomes of the mammography achieving even better prediction results.

show abstract

“…In these approaches, the BI-RADS™ descriptors of abnormalities (assigned by radiologists) are used to classify abnormalities as malignant or benign and have shown to be quite accurate [9][10][11][12][13][14][15][16][17][18].…”

mentioning

confidence: 99%

Classification of mammographic lesions into BI-RADS shape categories using the beamlet transform

2005

Self Cite

View full text Add to dashboard Cite

We present a new algorithm and preliminary results for classifying lesions into BI-RADS shape categories: round, oval, lobulated, or irregular. By classifying masses into one of these categories, computer aided detection (CAD) systems will be able to provide additional information to radiologists. Thus, such a tool could potentially be used in conjunction with a CAD system to enable greater interaction and personalization. For this classification task, we have developed a new set of features using the Beamlet transform, which is a recently developed multi-scale image analysis transform. We trained a k-Nearest Neighbor classifier using images from the Digital Database for Digital Mammography (DDSM). The method was tested on a set of 25 images of each type and we obtained a classification accuracy of 78% for classifying masses as oval or round and an accuracy of 72% for classifying masses as lobulated or round.

show abstract

Perceptron error surface analysis: a case study in breast cancer diagnosis

Cited by 12 publications

References 22 publications

Predicting neuroendocrine tumor (carcinoid) neoplasia using gene expression profiling and supervised machine learning

Predicting neuroendocrine tumor (carcinoid) neoplasia using gene expression profiling and supervised machine learning

Prediction of breast cancer biopsy outcomes using a distributed genetic programming approach

Classification of mammographic lesions into BI-RADS shape categories using the beamlet transform

Contact Info

Product

Resources

About