Sequential minimal optimization for support vector machine with feature selection in breast cancer diagnosis

Urmaliya, Ajay; Singhai, Jyoti

doi:10.1109/iciip.2013.6707638

Cited by 10 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Early works have focused on image processing and classification techniques to extract features of the image and predict the outcome (i.e., whether benign or malignant) in the image [12]- [20]. A neural network-based algorithm [14] and a linear discriminant approach [2] are proposed to solve the diagnosis problem.…”

Section: A Computer-aided Detection and Diagnosis System For Breast mentioning

confidence: 99%

Using Contextual Learning to Improve Diagnostic Accuracy: Application in Breast Cancer Screening

Song

Hsu

et al. 2016

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Clinicians need to routinely make management decisions about patients who are at risk for a disease such as breast cancer. This paper presents a novel clinical decision support tool that is capable of helping physicians make diagnostic decisions. We apply this support system to improve the specificity of breast cancer screening and diagnosis. The system utilizes clinical context (e.g., demographics, medical history) to minimize the false positive rates while avoiding false negatives. An online contextual learning algorithm is used to update the diagnostic strategy presented to the physicians over time. We analytically evaluate the diagnostic performance loss of the proposed algorithm, in which the true patient distribution is not known and needs to be learned, as compared with the optimal strategy where all information is assumed known, and prove that the false positive rate of the proposed learning algorithm asymptotically converges to the optimum. In addition, our algorithm also has the important merit that it can provide individualized confidence estimates about the accuracy of the diagnosis recommendation. Moreover, the relevancy of contextual features is assessed, enabling the approach to identify specific contextual features that provide the most value of information in reducing diagnostic errors. Experiments were conducted using patient data collected at a large academic medical center. Our proposed approach outperforms the current clinical practice by 36% in terms of false positive rate given a 2% false negative rate.

show abstract

Section: A Computer-aided Detection and Diagnosis System For Breast mentioning

confidence: 99%

Using Contextual Learning to Improve Diagnostic Accuracy: Application in Breast Cancer Screening

Song

Hsu

et al. 2016

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…Wahyuni [3] menguji uji akurasi diagnosis kanker payudara menggunakan algoritma SMO, MLP, C4.5 dan Naive Bayes pada dataset WBCD dan menunjukkan bahwa SMO memperoleh akurasi diagnosis tertinggi sebesar 97.6574%. Hasil uji akurasi SMO memiliki akurasi tertinggi didukung oleh Urmaliya dan Singhai [20] yang menyatakan bahwa. akurasi diagnosis kanker payudara tertinggi adalah menggunakan algoritma SMO.…”

Section: Pendahuluanunclassified

“…[9] serta Safutra dan Prabowo [18] yang menggunakan metode naive bayes, namun lebih akurat daripada [7], [8], [10]- [13] dan [15] yang menggunakan fuzzy, regresi logistik dan SVM, serta Dempster Shafer. Untuk mendapatkan akurasi yang lebih baik lagi, seleksi fitur dapat ditambahkan dalam aplikasi seperti dalam [20]. Dihasilkannya aplikasi diagnosis kanker payudara yang akurat dan cepat dengan waktu rerata 1,04 detik ini dapat membantu dokter atau analis kesehatan untuk mendiagnosis kanker payudara dengan lebih cepat.…”

Section: Hasil Dan Pembahasanunclassified

Aplikasi Diagnosis Penyakit Kanker Payudara Menggunakan Algoritma Sequential Minimal Optimization

Wibowo

2017

J. Teknol. dan Sist. Komput.

View full text Add to dashboard Cite

-Various methods for the diagnosis of breast cancer exist, but not many have been implemented as an application. This study aims to develop an application using SMO algorithm assisted by Weka to diagnose breast cancer. The application was webbased application and developed using Javascript. [14]. Penelitian tersebut menggunakan algoritma fuzzy dan certainty factor. Penelitian ini bertujuan menerapkan model diagnosis algoritma SMO menjadi sebuah aplikasi diagnosis kanker payudara. Aplikasi ini diterapkan untuk mendeteksi kanker payudara dengan lebih akurat. Model yang dihasilkan dari tahap sebelumnya diterjemahkan ke dalam kode program. Aplikasi dikembangkan berbasis web menggunakan bahasa Javascript agar bersifat multiplatform. II. METODE PENELITIANPengujian akurasi dilakukan dengan cara membandingkan luaran diagnosis aplikasi dengan nilai hasil diagnosis dari setiap record pada dataset. Akurasi diagnosis aplikasi juga dibandingkan dengan hasil diagnosis model pada dataset WEKA.Aplikasi yang dikembangkan dalam artikel ini menggunakan tiga aspek dari hasil uji model, yaitu model machine learning, simpulan, dan matrik galat bersama. Model machine learning digunakan untuk membentuk algoritma program. Simpulan digunakan sebagai dasar akurasi model dan bersama matrik galat digunakan sebagai uji akurasi aplikasi sehingga dapat dilihat apakah aplikasi yang dibangun memiliki peningkatan akurasi atau tidak.Model machine learning dari hasil pengujian algoritma SMO akan memberikan bobot dari setiap atribut yang digunakan untuk klasifikasi. Bobot dari setiap atribut pada model diagnosis adalah seperti dinyatakan dalam Persamaan 1.

show abstract

“…6,7 Multiple studies have been reported focusing on the use of mp-MRI data for the characterization of breast tumors. [8][9][10] Different machine learning (ML) classifiers based upon features from mp-MRI data have been reported, including logistic regression, 11 linear discriminant analysis, 12 artificial neural networks (ANN), 13 support vector machine (SVM), [13][14][15] and deep learning. 16 In these studies, different types of features, such as texture, morphology, semiquantitative, tracer kinetic, and apparent diffusion coefficient (ADC), were used.…”

Section: Introductionmentioning

confidence: 99%

Characterization of breast tumors using machine learning based upon multiparametric magnetic resonance imaging features

2021

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is playing an important role in the classification of breast tumors. MRI can be used to obtain multiparametric (mp) information, such as structural, hemodynamic, and physiological information. Quantitative analysis of mp‐MRI data has shown potential in improving the accuracy of breast tumor classification. In general, a large set of quantitative and texture features can be generated depending upon the type of methodology used. A suitable combination of selected quantitative and texture features can further improve the accuracy of tumor classification. Machine learning (ML) classifiers based upon features derived from MRI data have shown potential in tumor classification. There is a need for further research studies on selecting an appropriate combination of features and evaluating the performance of different ML classifiers for accurate classification of breast tumors. The objective of the current study was to develop and optimize an ML framework based upon mp‐MRI features for the characterization of breast tumors (malignant vs. benign and low‐ vs. high‐grade). This study included the breast mp‐MRI data of 60 female patients with histopathology results. A total of 128 features were extracted from the mp‐MRI tumor data followed by features selection. Five ML classifiers were evaluated for tumor classification using 10‐fold crossvalidation with 10 repetitions. The support vector machine (SVM) classifier based on optimum features selected using a wrapper method with an adaptive boosting (AdaBoost) technique provided the highest sensitivity (0.96 ± 0.03), specificity (0.92 ± 0.09), and accuracy (94% ± 2.91%) in the classification of malignant versus benign tumors. This method also provided the highest sensitivity (0.94 ± 0.07), specificity (0.80 ± 0.05), and accuracy (90% ± 5.48%) in the classification of low‐ versus high‐grade tumors. These findings suggest that the SVM classifier outperformed other ML methods in the binary classification of breast tumors.

show abstract

Sequential minimal optimization for support vector machine with feature selection in breast cancer diagnosis

Cited by 10 publications

References 11 publications

Using Contextual Learning to Improve Diagnostic Accuracy: Application in Breast Cancer Screening

Using Contextual Learning to Improve Diagnostic Accuracy: Application in Breast Cancer Screening

Aplikasi Diagnosis Penyakit Kanker Payudara Menggunakan Algoritma Sequential Minimal Optimization

Characterization of breast tumors using machine learning based upon multiparametric magnetic resonance imaging features

Contact Info

Product

Resources

About