Klasifikasi Kanker dan Artery pada Citra Computed Tomography Menggunakan Deep Learning Convolution Neural Network
Abstract
Abstract
Detection of lung cancer can significantly reduce the average death rate from lung cancer. Research on detection of lung cancer has been done. Most research on lung cancer detection always begins with image preprocessing, lung segmentation, lung candidate segmentation and lung cancer detection. These steps can cause the detection process to take a long time. The proposed research is to classify cancer and arterial images on CT-Scan using Convolution Neural Network (CNN). This research consists of two main points. Starting with the process of determining the region of interest (ROI) from the image of cancer and artery. The second is cancer classification and artery using CNN deep learning. The accuracy obtained from testing is 95%.
Keyword: CNN, CtScan, Deep Learning, Lung Cancer, ROI
Abstrak
Deteksi awal kanker paru dapat menurunkan rata-rata angka kematian akibat kanker paru secara signifikan. Penelitian tentang deteksi awal kanker paru sudah banyak dilakukan. Sebagian besar studi mengenai deteksi kanker paru pada CT-Scan selalu diawali dengan preprosesing citra, segmentasi paru, segmentasi kandidat paru dan deteksi kanker paru. Langkah-langkah tersebut dapat menyebabkan proses deteksi membutuhkan waktu yang lama. Penelitian yang dilakukan adalah melakukan klasifikasi kanker dan arteri pada gambar Computed Tomography menggunakan Convolution Neural Network (CNN). Penelitian ini terdiri dari dua hal pokok. Pertama adalah preprosesing dari citra kanker dan artery. Kedua adalah klasifikasi kanker dan artery menggunakan deep learning CNN. Akurasi tertinggi yang didapatkan dari ujicoba adalah 95%.
Kata Kunci: CNN, CtScan, Deep Learning, Lung Cancer, ROI
Keywords
Full Text:
PDFReferences
Association AL. State of Lung Cancer [Internet]. 2018. Available from: https://www.lung.org/our-initiatives/research/monitoring-trends-in-lung-disease/state-of-lung-cancer/
Patil BG, Jain SN. Cancer Cells Detection Using Digital Image Processing Methods. Int J Latest Trends Eng Technol. 2014;3(4):45–9.
A.Gajdhane MV, L.M PD. Detection of Lung Cancer Stages on CT scan Images by Using Various Image Processing Techniques. IOSR J Comput Eng. 2014;16(5):28–35.
Sharma D, Gagandeep J. Identifying Lung Cancer Using Image Processing Techniques. Int Conf Comput Tech Artif Intell.
Mahersia H, Zaroug M, Gabralla L. Lung Cancer Detection on CT Scan Images: A Review on the Analysis Techniques. Int J Adv Res Artif Intell [Internet]. 2015;4(4). Available from: http://thesai.org/Publications/ViewPaper?Volume=4&Issue=4&Code=ijarai&SerialNo=6
Sahni P, Mittal N. Breast Cancer Detection Using Image Processing Techniques. Lect Notes Mech Eng. 2019;(March):813–23.
Tiwari L, Awasthi V, Patra RK, Miri R, Raja H, Bhaskar N. Lung Cancer Detection Using Deep Convolutional Neural Networks. In 2022. p. 373–85. Available from: https://link.springer.com/10.1007/978-981-19-1559-8_37
Hatuwal BK, Thapa HC. Lung Cancer Detection Using Convolutional Neural Network on Histopathological Images. Int J Comput Trends Technol [Internet]. 2020 Oct 25;68(10):21–4. Available from: http://ijcttjournal.org/archives/ijctt-v68i10p104
Al-Yasriy HF, AL-Husieny MS, Mohsen FY, Khalil EA, Hassan ZS. Diagnosis of Lung Cancer Based on CT Scans Using CNN. IOP Conf Ser Mater Sci Eng [Internet]. 2020 Nov 1;928(2):022035. Available from: https://iopscience.iop.org/article/10.1088/1757-899X/928/2/022035
Kalaivani N, Manimaran N, Sophia S, D. Devi D. Deep Learning Based Lung Cancer Detection and Classification. IOP Conf Ser Mater Sci Eng. 2020;994(1).
Widodo S, Wijiyanto. Software Development for Three Dimensional Visualization of Lung on Computed Tomography Scans Using Active Shape Model and Volume Rendering. J Theor Appl Inf Technol. 2014;65(1):154–60.
Widodo S, Rohmah RN, Handaga B, Arini LDD. Lung Diseases Detection Caused by Smoking Using Support Vector Machine. Telkomnika (Telecommunication Comput Electron Control. 2019;17(3):1256–66.
Widodo S, Rohmah RN, Handaga B. Classification of Lung Nodules and Arteries in Computed Tomography Scan Image Using Principle Component Analysis. Proc - 2017 2nd Int Conf Inf Technol Inf Syst Electr Eng ICITISEE 2017. 2018;2018-January(November):153–8.
Widodo S, Rosyid I, Faizuddin Bin Noor M, Bin Ismail R. Texture Feature Extraction To Improve Accuracy of Malignant and Benign Cancer Detection on Ct-Scan Images. Int J Psychosoc Rehabil. 2020;24(09):3540–54.
Widodo S, Duta U, Surakarta B. Improved Accuracy in Detection of Lung Cancer Using Self Organizing Map. J Crit Rev. 2020;7(14).
DOI: https://doi.org/10.47007/inohim.v10i2.444
Refbacks
- There are currently no refbacks.
Lembaga Penerbitan Universitas Esa Unggul
Jl Arjuna Utara No 9. Tol Tomang, Kebon Jeruk, Jakarta. 11510
Email : inohim.ueu@esaunggul.ac.id
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
View My Stats