Breast Cancer Classification Using Statistical Features and Fuzzy Classification of Thermograms

Schaefer, Gerald; Nakashima, Tomoharu; Zavisek, M.; Yokota, Yasuyuki; Drastich, Aleš; Ishibuchi, Hisao

doi:10.1109/fuzzy.2007.4295520

Cited by 22 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The improvement of classification parameters when fuzzy-neural networks are selected in place of single neural networks was also confirmed by another author's research [19,20]. Schaefer et al studied the number of ideal partitions in a fuzzy-rule based classification system for breast cancer, reaching ACC, SN and SP values of 97.95%, 93.10% and 99.15%, respectively, as the number of partitions increased [21,22]. A fuzzy model based on C-means clustering by Lashkari et al showed accuracy values of 75% for the screening of suspicious breast areas, a lower performance when compared to the supervised AdaBoost algorithm developed in their previous work (88%) [23,24].…”

Section: Breast Cancermentioning

confidence: 76%

Meta-Analysis and Systematic Review of the Application of Machine Learning Classifiers in Biomedical Applications of Infrared Thermography

2021

View full text Add to dashboard Cite

Atypical body temperature values can be an indication of abnormal physiological processes associated with several health conditions. Infrared thermal (IRT) imaging is an innocuous imaging modality capable of capturing the natural thermal radiation emitted by the skin surface, which is connected to physiology-related pathological states. The implementation of artificial intelligence (AI) methods for interpretation of thermal data can be an interesting solution to supply a second opinion to physicians in a diagnostic/therapeutic assessment scenario. The aim of this work was to perform a systematic review and meta-analysis concerning different biomedical thermal applications in conjunction with machine learning strategies. The bibliographic search yielded 68 records for a qualitative synthesis and 34 for quantitative analysis. The results show potential for the implementation of IRT imaging with AI, but more work is needed to retrieve significant features and improve classification metrics.

show abstract

Section: Breast Cancermentioning

confidence: 76%

Meta-Analysis and Systematic Review of the Application of Machine Learning Classifiers in Biomedical Applications of Infrared Thermography

2021

View full text Add to dashboard Cite

show abstract

“…The study made by Johra & Shuvo (2017) shows that the fuzzy logic model’s accuracy is 94.26% when applied with histopathology image dataset to classify benign and malignant cells in breast cancer tumours. Result of breast cancer thermogram classification by Schaefer et al (2007) that also implemented the fuzzy method had achieved the diagnostic accuracy rate of 80%. High accuracies result based on the previous studies show the efficiency of the method in solving classification problems.…”

Section: Methodsmentioning

confidence: 99%

Breast cancer disease classification using fuzzy-ID3 algorithm with FUZZYDBD method: automatic fuzzy database definition

Idris¹,

Ismail²

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Breast cancer becomes the second major cause of death among women cancer patients worldwide. Based on research conducted in 2019, there are approximately 250,000 women across the United States diagnosed with invasive breast cancer each year. The prevention of breast cancer remains a challenge in the current world as the growth of breast cancer cells is a multistep process that involves multiple cell types. Early diagnosis and detection of breast cancer are among the greatest approaches to preventing cancer from spreading and increasing the survival rate. For more accurate and fast detection of breast cancer disease, automatic diagnostic methods are applied to conduct the breast cancer diagnosis. This paper proposed the fuzzy-ID3 (FID3) algorithm, a fuzzy decision tree as the classification method in breast cancer detection. This study aims to resolve the limitation of an existing method, ID3 algorithm that unable to classify the continuous-valued data and increase the classification accuracy of the decision tree. FID3 algorithm combined the fuzzy system and decision tree techniques with ID3 algorithm as the decision tree learning. FUZZYDBD method, an automatic fuzzy database definition method, would be used to design the fuzzy database for fuzzification of data in the FID3 algorithm. It was used to generate a predefined fuzzy database before the generation of the fuzzy rule base. The fuzzified dataset was applied in FID3 algorithm, which is the fuzzy version of the ID3 algorithm. The inference system of FID3 algorithm is simple with direct extraction of rules from generated tree to determine the classes for the new input instances. This study also analysed the results using three breast cancer datasets: WBCD (Original), WDBC (Diagnostic) and Coimbra. Furthermore, the comparison of FID3 algorithm with the existing methods is conducted to verify the proposed method’s capability and performance. This study identified that the combination of FID3 algorithm with FUZZYDBD method is reliable, robust and managed to perform well in breast cancer classification.

show abstract

“…Schaefer et al [13] used a set of statistical features derived from the comparison between left and right breast regions. Then, these features are passed to a diagnosis system that depends on fuzzy rules.…”

Section: Related Workmentioning

confidence: 99%

Bio-inspired Based Techniques for Thermogram Breast Cancer Classification

Ahmed¹,

Ali²,

Selim³

2019

IJIES

View full text Add to dashboard Cite

Nowadays, breast cancer considered a main cause of death for women all over the world. It is defined as a group of cells that grow rapidly and causes the formation of a lump in breast tissue which leads to tumor formation which can be categorized either malignant (cancerous) or benign (non-cancerous). On the other side, mammography as a screening and diagnostic tool suffers from some limitations, especially with young women who have dense breasts. Therefore, there was a need to develop more effective tools. Thermography is an imaging tool used to record the thermal pattern. The main contribution of this paper is proposing a unique method for classifying the breast thermography images into one of three classes: normal, benign, or malignant. Additionally, bio-inspired algorithms namely, ant colony optimization (ACO) and particle swarm optimization (PSO) are used for feature selection. The proposed method contains four phases: Image preprocessing, feature extraction, feature selection, and classification. The proposed method is assessed using a benchmark thermography dataset. The experimental results show that our method has a promising performance.

show abstract

Breast Cancer Classification Using Statistical Features and Fuzzy Classification of Thermograms

Cited by 22 publications

References 15 publications

Meta-Analysis and Systematic Review of the Application of Machine Learning Classifiers in Biomedical Applications of Infrared Thermography

Meta-Analysis and Systematic Review of the Application of Machine Learning Classifiers in Biomedical Applications of Infrared Thermography

Breast cancer disease classification using fuzzy-ID3 algorithm with FUZZYDBD method: automatic fuzzy database definition

Bio-inspired Based Techniques for Thermogram Breast Cancer Classification

Contact Info

Product

Resources

About