Classification of Dermoscopic Image of Skin Cancer Using the GLCM Method and Multi-SVM Algorithm

Hasanah, Riyan Latifahul; Riana, Dwiza

doi:10.21107/rekayasa.v14i3.12213

Cited by 5 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hasanah et al [8] classified melanoma in dermoscopic images depending on whether they show Common Nevus, Atypical Nevus, or Melanoma using Mendonca et al database [9]. The RGB is converted to grayscale.…”

Section: Literature Reviewmentioning

confidence: 99%

“…When comparing Murugan et al [3], Kavitha et al [5], and Hasanah et al [8] for dermoscopic images with the study from Ramezani et al [6], Pillay et al [10], Oliveira et al [11], and Hurtado et al [16] for macroscopic images, it is known whether the classification performance of macroscopic images is better than dermoscopic images. Murugan et al [3] using the SVM for melanoma detection in dermoscopic images produced the best accuracy, but it was not implemented on macroscopic images.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The specificity calculation formula is shown in (8). A recall is determined by dividing the TP by the sum of the TP and FN.…”

Section: Dmentioning

confidence: 99%

See 2 more Smart Citations

Melanoma Detection using Convolutional Neural Network with Transfer Learning on Dermoscopic and Macroscopic Images

Millenia

Naufal²,

Siswantoro³

2022

J. Inf. Syst. Eng. Bus. Intell.

View full text Add to dashboard Cite

Background: Melanoma is a skin cancer that starts when the melanocytes that produce the skin color pigment start to grow out of control and form a cancer. Detecting melanoma early before it spreads to the lymph nodes and other parts of the body is very important because it makes a big difference to the patient's 5-year life expectancy. Screening is the process of conducting a skin examination to suspect a mole is melanoma using dermoscopic or macroscopic images. However, manual screening takes a long time. Therefore, automatic melanoma detection is needed to speed up the melanoma detection process. The previous studies still have weakness because it has low precision or recall, which means the model cannot predict melanoma accurately. The distribution of melanoma and moles datasets is imbalanced where the number of melanomas is less than moles. In addition, in previous study, comparisons of several CNN transfer learning architectures have not been carried out on dermoscopic and macroscopic images. Objective: This study aims to detect melanoma using the Convolutional Neural Network (CNN) with transfer learning on dermoscopic and macroscopic melanoma images. CNN with Transfer learning is a popular method for classifying digital images with high accuracy. Methods: This study compares four CNN with transfer learning architectures, namely MobileNet, Xception, VGG16, and ResNet50 on dermoscopic and macroscopic image. This research also uses black-hat filtering and inpainting at the preprocessing stage to remove hair from the skin image. Results: MobileNet is the best model for classifying melanomas or moles in this experiment which has 83.86% of F1 score and 11 second of training time per epoch. Conclusion: MobileNet and Xception have high average F1 scores of 84.42% and 80.00%, so they can detect melanoma accurately even though the number of melanoma datasets is less than moles. Therefore, it can be concluded that MobileNet and Xception are suitable models for classifying melanomas and moles. However, MobileNet has the fastest training time per epoch which is 11 seconds. In the future, oversampling method can be implemented to balance the number of datasets to improve the performance of the classification model.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Melanoma Detection using Convolutional Neural Network with Transfer Learning on Dermoscopic and Macroscopic Images

Millenia

Naufal²,

Siswantoro³

2022

J. Inf. Syst. Eng. Bus. Intell.

View full text Add to dashboard Cite

show abstract

“…Recently, various applications and software using computers have been developed, such as image processing, artificial intelligence in cancer imaging [6] , a validated open-source deeplearning algorithm (Sybil) from a single low-dose chest CT [7] , machine learning approaches [8] , or other ways using GLCM (Gray Level Co-Occurrence Matrix) [9] so that medical image analysis diagnosis can perform more practically and automatically. The segmentation process on CT-Scan images is a stage to separate normal and abnormal lung areas of objects for analysis.…”

Section: Introductionmentioning

confidence: 99%

Volume Estimation of Lung Cancer using Image-J For CT-Scan Image

Nurjannah,

Zainura,

Iswardy

et al. 2024

Indonesian J Appl Phys

View full text Add to dashboard Cite

ABSTRACTLung cancer is a malignant tumor that develops in the lower respiratory system, including cells in the walls of the bronchi and bronchioles. Lung cancer originates from genetic changes in cells in the lungs. Improper treatment of lung cancer can cause the cancer to spread to other nearby tissues around the lungs. By conducting early detection of lung cancer, it will help patients to get appropriate treatment. One of the medical instruments used to detect lung cancer is the CT-Scan. This instrument’s examination can provide information about the location, size, characteristics of the tumor, lymph node spread, and tissue infiltration into the surroundings, thus helping to determine the clinical stage of lung cancer. Organ size determination is one of the analysis of pulmonary image for diagnostic and therapeutic purposes. The purpose of this study was to obtain information on the volume of lung cancer based on the results of CT Scan images using Image J software. Information on the edges of the lungs affected by cancer was carried out by the edge detection method. The results of this study show that Image-J software can provide a clear picture of the edges of the cancer and obtain accurate cancer volume at each image slice. Based on calculations obtained in the 1st patient, it was calculated to have a volume of 128 cm3, in the 2nd patient of 447 cm3 and in the 3rd patient of 335 cm3, respectively.Keywords: Ct Scan image; lung cancer; edge detection; volume analysis; Image JABSTRAKKanker paru merupakan tumor ganas yang berkembang pada sistem pernapasan bagian bawah, termasuk sel-sel di dinding bronkus dan bronkiolus. Kanker paru berawal dari perubahan genetik sel di dalam paru-paru. Penanganan kanker paru yang tidak tepat dapat menyebabkan kanker menyebar ke jaringan lain yang terdekat di sekitar paru-paru. Dengan dilakukan pendeteksian dini kanker paru, maka akan sangat membantu penderita agar mendapatkan penanganan yang cepat dan tepat. Salah satu instrumen medis yang digunakan untuk mendeteksi kanker paru adalah pesawat CT-Scan. Pemeriksaan CT-Scan dapat memberikan informasi tentang lokasi, ukuran, karakteristik tumor, penyebaran kelenjar getah bening, dan infiltrasi jaringan ke sekitarnya sehingga membantu penetapan stadium klinis kanker paru. Penentuan ukuran organ merupakan salah satu analisa terhadap citra paru untuk keperluan diagnosa dan terapi. Tujuan penelitian ini adalah memperoleh informasi volume kanker paru berdasarkan hasil citra CT Scan menggunakan Image J. Informasi gambaran tepi paru yang terkena kanker dilakukan dengan metode deteksi tepi. Hasil dari penelitian ini menunjukan bahwa software Image-J dapat memberikan gambaran tepi kanker yang jelas dan diperoleh volume kanker yang akurat pada setiap irisan citra. Berdasarkan perhitungan didapatkan pada pasien ke-1 terhitung memiliki volume sebesar 128 cm3, pada pasien ke-2 sebesar 447 cm3 dan pada pasien ke-3 sebesar 335 cm3.Kata kunci: CT Scan; Kanker paru; deteksi tepi; analisis volume; Image J

show abstract