Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Journal of Information Technology and Cyber Security
Mufti, Abdul Latief
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Classification Techniques in Finding Malignant Breast Cancer Detection Whardana, Adithya Kusuma; Mufti, Abdul Latief; Hermawan, Hendar; Aziz, Umar Alfaruq Abdul
Journal of Information Technology and Cyber Security Vol. 2 No. 1 (2024): January
Publisher : Department of Information Systems and Technology, Faculty of Intelligent Electrical and Informatics Technology, Universitas 17 Agustus 1945 Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30996/jitcs.8829

Abstract

The most fundamental aspect of cancer is that it is marked by abnormal and uncontrolled cell growth, allowing it to spread to the surrounding areas of existing tissues. One of the most common cancers experienced by people in Indonesia, according to the Indonesian Ministry of Health, is breast cancer. The diagnosis of diseases, especially cancer, also requires a visual form that is later used as an image to determine the condition within the patient's organs. The use of mammography images is one implementation of X-rays aimed at revealing the structure of human bones and tissues. The use of images is also recognized in information technology in the field of digital image processing, which is useful for analyzing, enhancing, compressing, and reconstructing images using a collection of computational techniques. One application of digital image processing techniques for breast mammography images is recognizing the possibility of breast cancer through computer automation using classification methods supported by googlepredict.net architectures. The results obtained in this study use a dataset sourced from King Abdul Aziz University, totaling 2378 images. The method used in this research is Convolutional Neural Network (CNN), with the addition of the GoogleNet architecture. The convolution extraction method runs with the GoogleNet architecture, enhancing deep learning for optimal breast cancer recognition. The overall results of this study found an average precision value of 90%, recall of 92%, F-1 Score of 91.49%, and accuracy of 91.49%.
Early Breast Cancer Detection Using Gabor Filter and Convolutional Neural Network for Microcalcification Identification Mufti, Abdul Latief; Whardana, Adithya Kusuma
Journal of Information Technology and Cyber Security Vol. 3 No. 2 (2025): July
Publisher : Department of Information Systems and Technology, Faculty of Intelligent Electrical and Informatics Technology, Universitas 17 Agustus 1945 Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30996/jitcs.132037

Abstract

Breast cancer poses a considerable challenge in Indonesia, resulting in numerous fatalities. This study aims to improve the accuracy and efficiency of early breast cancer diagnosis by leveraging modern image processing and artificial intelligence. The dataset used is the Mini-DDSM (Mini Digital Database for Screening Mammography), taken from Kaggle and vetted by radiologists into a Region of Interest (ROI) consisting of three categories: Benign, Cancer, and Normal. The methodology encompasses comprehensive image preprocessing, which includes resizing, cropping, RGB-to-grayscale conversion, Laplacian of Gaussian (LoG) filtering, Gabor filtering, global threshold segmentation, and image enhancement. A Convolutional Neural Network (CNN) is employed for classification purposes. Ninety percent of the images are allocated for training, while 10% are designated for testing, with critical parameters such as learning rate, batch size, and epochs being tuned throughout the training process. The CNN architecture was assessed based on recognition rate, error rate, epoch count, and training duration. The results provide a flawless validation accuracy of 100% over 32 trials. The findings demonstrate that the suggested method markedly enhances early breast cancer identification using microcalcification analysis in mammography images, assisting medical professionals in early diagnosis and potentially elevating patient recovery rates through prompt detection and treatment.
Co-Authors Aziz, Umar Alfaruq Abdul Hermawan, Hendar Whardana, Adithya Kusuma