Performance of neural network architectures: Cascaded MLP versus extreme learning machine on cervical cell image classification

Yusoff, Intan Aidha; Isa, Nor Ashidi Mat; Othman, Nor Hayati; Sulaiman, Siti Noraini; Jusman, Yessi

doi:10.1109/isspa.2010.5605463

Cited by 14 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Kedua fitur ini direpresentasikan dalam fitur intensitas dan fitur bentuk. Fitur tersebut dapat mengindikasikan jika terdapat ciri abnormal pada sel serviks, karena sel terinfeksi Human Papilloma Virus (HPV) yang bisa berkembang menjadi tahap kanker akan menunjukkan perubahan biologis tertentu seperti ukuran nukleus yang membesar dan warna nukleus sel abnormal yang lebih gelap dibandingkan dengan sel normal (Yusoff, 2010). Selain fitur bentuk dan intensitas, fitur tekstur dapat direpresentasikan sebagai ciri sel untuk mengukur pola chromatin sel dalam citra pap smear.…”

Section: Pendahuluanunclassified

Penggabungan Fitur Bentuk dan Fitur Tekstur yang Invariant terhadap Rotasi untuk Klasifikasi Citra Pap Smear

Pasrun

Fatichah

Suciati

2016

JBI

View full text Add to dashboard Cite

Abstract. Pap test is a cervical cancer screening manually and requires a long time that it needs an exact cell classification system based computers. Features determination by observation in characteristic differences between the datasets visually betweenclass will help a cell classification results which has relevant characteristics between classes. In addition, the change in orientation of the cells at the time of the acquisition will affect the value of the generated feature so extraction method that is rotation invariant is needed to overcome that problem. This research proposes the combination of simple shapes feature and the texture feature from extraction Local Binary Pattern Histogram Fourier (LBP-HF) that invariant to rotation as additional features to classify pap smear images. The result show that the proposed feature combination yield good performance with accuracy 92.44% for two category cell and 70.06% for seven class cell.Keywords: classification, lbp-hf, Â pap smear image, shape feature.Â Abstrak. Pap test adalah pemeriksaan kanker serviks secara manual yang membutuhkan waktu yang lama sehingga dibutuhkan sistem klasifikasi sel berbasis komputer yang tepat. Penentuan fitur melalui observasi pada perbedaan ciri antarkelas secara visual pada dataset akan membantu hasil klasifikasi sel untuk mendapatkan ciri yang relevan antarkelas. Selain itu, adanya perubahan orientasi sel pada saat akuisisi akan mempengaruhi nilai fitur yang dihasilkan sehingga dibutuhkan metode ekstraksi fitur yang invariant terhadap rotasi. Penelitian ini mengusulkan penggabungan fitur bentuk sederhana dan fitur tekstur dengan ekstraksi fitur Local Binary Pattern â€“Histogram Fourier yang invariant terhadap rotasi sebagai ciri tambahan dalam mengklasifikasikan citra pap smear. Hasilnya menunjukkan bahwa kombinasi fitur menghasilkan performa yang baik dengan akurai 92,44% untuk dua kategori sel dan 70,06% untuk tujuh kelas sel.Kata Kunci: klasifikasi, lbp-hf, citra pap smear, fitur bentuk.

show abstract

Section: Pendahuluanunclassified

Penggabungan Fitur Bentuk dan Fitur Tekstur yang Invariant terhadap Rotasi untuk Klasifikasi Citra Pap Smear

Pasrun

Fatichah

Suciati

2016

JBI

View full text Add to dashboard Cite

show abstract

“…Learning Machines Differential evolution proposed by Storn and Price is a global searching optimization method which obtains more compact network than the original ELM, as they require a large number of hidden units and long time for responding to new input patterns [9]. The network archi- tecture comprises of three layers such as input, hidden and output each consisting of one layer and is trained with K hidden neurons to learn N distinct samples.…”

Section: Differential Evolutionary Extremementioning

confidence: 99%

“…The ELM algorithm overcomes many issues in traditional gradient algorithms such as stopping criterion, learning rate, number of epochs and local minima. On account of these advantages, DE-ELM has been effectively used in the field of medical diagnosis [8,9].…”

Section: Introductionmentioning

confidence: 99%

Automated Decision Support System for Tuberculosis Digital Images Using Evolutionary Learning Machines

Priya¹,

Srinivasan

2013

ejbi

View full text Add to dashboard Cite

Background: Tuberculosis (TB) is a major cause of illness and death in many countries, especially in Asia and Africa. Repeated tests of microscopic examination are needed to be performed for early detection of the disease. Hence there is a need to automate the diagnostic process for improvement in the sensitivity and accuracy of the test. Objective: To automate the decision support system for tuberculosis digital images using histogram based statistical features and evolutionary based extreme learning machines. Materials and methods: The sputum smear positive and negative images recorded under standard image acquisition protocol are subjected to histogram based feature extraction technique. Most significant features are selected using student 't' test.These significant features are further used as input to the differential evolutionary extreme learning machine classifier.Results: Results demonstrate that the histogram based significant features are able to differentiate TB positive and negative images with a higher specificity and accuracy. Conclusion: The methodology used in this work seems to be useful for the automated analysis of TB sputum smear images in mass screening disorders such as pulmonary tuberculosis.

show abstract

“…In regard to the acquirement of cell features, most of the researchers used multidimensional features to classify the cells [ 12 , 14 – 16 ]. Some authors analyzed four parameters: area, integrated optical density (IOD), eccentricity, and Fourier coefficients [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

“…Some authors analyzed four parameters: area, integrated optical density (IOD), eccentricity, and Fourier coefficients [ 12 ]. Other authors used 16 features: area of nucleus, area of cytoplasm, nuclear gray level, cytoplasm's gray level, and so forth [ 14 ]. Some authors acquired nine parameters: mean intensity, variance, number of concave points, area, area ratio, perimeter, roundness, entropy, and intensity ratio [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

Automatic Detection of Cervical Cancer Cells by a Two-Level Cascade Classification System

et al. 2016

Analytical Cellular Pathology

View full text Add to dashboard Cite

We proposed a method for automatic detection of cervical cancer cells in images captured from thin liquid based cytology slides. We selected 20,000 cells in images derived from 120 different thin liquid based cytology slides, which include 5000 epithelial cells (normal 2500, abnormal 2500), lymphoid cells, neutrophils, and junk cells. We first proposed 28 features, including 20 morphologic features and 8 texture features, based on the characteristics of each cell type. We then used a two-level cascade integration system of two classifiers to classify the cervical cells into normal and abnormal epithelial cells. The results showed that the recognition rates for abnormal cervical epithelial cells were 92.7% and 93.2%, respectively, when C4.5 classifier or LR (LR: logical regression) classifier was used individually; while the recognition rate was significantly higher (95.642%) when our two-level cascade integrated classifier system was used. The false negative rate and false positive rate (both 1.44%) of the proposed automatic two-level cascade classification system are also much lower than those of traditional Pap smear review.

show abstract

Performance of neural network architectures: Cascaded MLP versus extreme learning machine on cervical cell image classification

Cited by 14 publications

References 7 publications

Penggabungan Fitur Bentuk dan Fitur Tekstur yang Invariant terhadap Rotasi untuk Klasifikasi Citra Pap Smear

Penggabungan Fitur Bentuk dan Fitur Tekstur yang Invariant terhadap Rotasi untuk Klasifikasi Citra Pap Smear

Automated Decision Support System for Tuberculosis Digital Images Using Evolutionary Learning Machines

Automatic Detection of Cervical Cancer Cells by a Two-Level Cascade Classification System

Contact Info

Product

Resources

About