Adaptive Gradient Descent Backpropagation for Classification of Breast Tumors in Ultrasound Imaging

Singh, Bikesh Kumar; Verma, Kesari; Thoke, A. S.

doi:10.1016/j.procs.2015.02.091

Cited by 46 publications

(27 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Using a vector product between the masks of the same sizes, different spatial domain filters or kernels of size 3×3, 5×5 and 7×7 were generated by Laws. Laws texture energy measures have been used in filtering input medical images for texture analysis in many applications 39,129–140 . Another example of a specially designed kernel is the fractal dimension kernel designed by Al Kadi et al 141 .…”

Section: Morphological Featuresmentioning

confidence: 99%

“…Wavelets have been extensively used in multiresolution texture analysis of medical images 5,38,50,58–63,70,73,77,88,140,146 . The use of multiresolution can decompose the data into different frequency components, thereby facilitating the study of each component with a resolution matched to its scale.…”

Section: Morphological Featuresmentioning

confidence: 99%

“…The best features identified in this study were GLCM based contrast with θ = 45° and GLCM based correlation with θ = 0°. Numerous studies have since used texture analysis to differentiate between benign and malignant breast lesions using ultrasound 83,140,146,169 .…”

Section: Radiomics Applicationsmentioning

confidence: 99%

See 2 more Smart Citations

Radiomics: a new application from established techniques

Parekh

Jacobs

2016

Expert Review of Precision Medicine and Drug Development

280

230

View full text Add to dashboard Cite

The increasing use of biomarkers in cancer have led to the concept of personalized medicine for patients. Personalized medicine provides better diagnosis and treatment options available to clinicians. Radiological imaging techniques provide an opportunity to deliver unique data on different types of tissue. However, obtaining useful information from all radiological data is challenging in the era of “big data”. Recent advances in computational power and the use of genomics have generated a new area of research termed Radiomics. Radiomics is defined as the high throughput extraction of quantitative imaging features or texture (radiomics) from imaging to decode tissue pathology and creating a high dimensional data set for feature extraction. Radiomic features provide information about the gray-scale patterns, inter-pixel relationships. In addition, shape and spectral properties can be extracted within the same regions of interest on radiological images. Moreover, these features can be further used to develop computational models using advanced machine learning algorithms that may serve as a tool for personalized diagnosis and treatment guidance.

show abstract

Section: Morphological Featuresmentioning

confidence: 99%

Section: Morphological Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Radiomics: a new application from established techniques

Parekh

Jacobs

2016

Expert Review of Precision Medicine and Drug Development

280

230

View full text Add to dashboard Cite

show abstract

“…Dalam penelitian ini Gradient Descent With Momentum & Adaptive LR digunakan untuk prediksi tingkat partisipasi sekolah. Hasilnya dibandingkan dengan algoritma gradient descent standar, Gradient Descent With Momentum & Adaptive LR lebih baik [39].…”

Section: B Gradient Descentunclassified

Prediksi Angka Partisipasi Sekolah dengan Fungsi Pelatihan Gradient Descent With Momentum & Adaptive LR

Wanto

2019

Algoritma

View full text Add to dashboard Cite

School Participation Rate (APS) is known as one of the indicators of the success of the development of educational services in regions both Province, Regency or City in Indonesia. The higher the value of the School Participation Rate, then the area is considered successful in providing access to education services. The purpose of this study is to predict School Participation Rates based on Provinces in Indonesia from Aceh to Papua. The prediction algorithm used is the backpropagation algorithm using the gradient descent with momentum & adaptive LR (traingdx) training function. Traingdx is a network training function that updates weight values and biases based on gradient descent momentum and adaptive learning levels. Usually, the backpropagation algorithm uses the gradient descent backpropagation (traingd) function, but in this study, the training function used is using gradient descent with momentum & adaptive LR (traingdx). The data used in this study data on School Participation Figures for each province in Indonesia in 2011-2017 aged 19-24 years were taken from the Indonesian Central Bureau of Statistics (BPS). The reason for choosing this age range is because at this age is one of the factors that determine the success of education in a country, especially Indonesia. This study uses 3 network architecture models, namely: 5-5-1, 5-15-1 and 5-25-1. Of the 3 models, the best model is 5-5-1 with an iteration of 130, the accuracy of 94% and MSE 0,0008708473. This model is then used to predict School Participation Rates in each province in Indonesia over the next 3 years (2018-2020). These results are expected to help the Indonesian government to further increase scholarships and improve the quality of education in the future.. Keywords: Prediction, APS, Backpropagation, Traingdx.

show abstract

“…In a research to classify breast tumors [5] an accuracy of 84.6% was reported using BPNN. Another research [6], which combined BPNN and fuzzy analytical hierarchy process (Fuzzy_AHP) to predict the risk of heart failure, achieved a prediction accuracy of 91.10%.…”

Section: Introductionmentioning

confidence: 99%

Indonesia Scholarship Selection Model Using a Combination of Back-Propagation Neural Network and Fuzzy Inference System Approaches

Latumakulita¹,

Usagawa²

2018

IJIES

View full text Add to dashboard Cite

"Bidik Misi" (BM) is a famous scholarship offered by Indonesia Government which has two main qualification aspects: economic needs and academic performance. Since BM scholarship was initiated in 2010, the number of candidates has increased year by year despite limited quota, causing difficulties in selecting the most qualified candidates. This research is proposing a new selection model by combining Back-Propagation Neural Network (BPNN) as candidate's predictor and Fuzzy Inference System (FIS) as candidate's selector. BPNN is used to classify candidates into two, and three recommendation classes then perform FIS on priority set of candidates which is derived from the intersection of classification's result of two and three recommendation classes to make candidate's ranking. Closed test results show that for assuming quota of 50% from total 625 candidates or quota = 312, system can choose 267 highly recommended and reject 268 non-recommended candidates while 45 are identified as moderate recommended, and 45 other are identified as candidates of lower priority with selection accuracy of 85.6% better than five previous similar works. The open test results provide accuracy average of 86.88% and the lowest accuracy of 84% which is close enough to the closed test's accuracy of 85.6% with the difference around 1%, and a small standard deviation value of 2.37 indicates stability of system performance in the selection process. The lowest and highest accuracies of the open test results indicate the proposed system can predict and select BM scholarship's candidates in the future with satisfactory accuracies from 84% up to 90%; thus the proposed system can be trusted as a proper model for BM scholarship selection process.

show abstract

Adaptive Gradient Descent Backpropagation for Classification of Breast Tumors in Ultrasound Imaging

Cited by 46 publications

References 25 publications

Radiomics: a new application from established techniques

Radiomics: a new application from established techniques

Prediksi Angka Partisipasi Sekolah dengan Fungsi Pelatihan Gradient Descent With Momentum & Adaptive LR

Indonesia Scholarship Selection Model Using a Combination of Back-Propagation Neural Network and Fuzzy Inference System Approaches

Contact Info

Product

Resources

About