Claim Missing Document
Check
Articles

Found 3 Documents
Search

Views on Deep Learning for Medical Image Diagnosis Irohito Nozomi; Febri Aldi; Rio Bayu Sentosa
Journal of Applied Engineering and Technological Science (JAETS) Vol. 4 No. 1 (2022): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v4i1.1367

Abstract

Deep learning models are more often used in the medical field as a result of the rapid development of machine learning, graphics processing technologies, and accessibility of medical imaging data. The convolutional neural network (CNN)-based design, adopted by the medical imaging community to assist doctors in identifying the disease, has exacerbated this situation. This research uses a qualitative methodology. The information used in this study, which explores the ideas of deep learning and convolutional neural networks (CNN), taken from publications or papers on artificial intelligent (AI) Convolutional neural networks has been used in recent years for the analysis of medical image data. CNN's development of its machine learning roots is traced in this study. We also provide a brief mathematical description of CNN as well as the pre-processing process required for medical images before inserting them into CNN. Using CNN in many medical domains, including classification, segmentation, detection, and localization, we evaluate relevant research in the field of medical imaging analysis. It can be concluded that CNN's deep learning view of medical imaging is very helpful for medical parties in their work
Teknik Segmentasi untuk Mengidentifikasi Kelainan Jantung pada Citra Rontgen Dada Febri Aldi; Sumijan
Jurnal KomtekInfo Vol. 9 No. 3 (2022): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v9i3.307

Abstract

The annual death toll from heart disease is 17.5 million people. Currently, heart disease is a prevalent condition that kills a lot of people and shortens people's lives. Life is based on the work of the heart, since the heart is a much-needed part of our body where life is impossible. Heart disease affects heart function and can lead to death or annoy the patient before deathThe use of contemporary medical imaging methods like computed tomography (CT), ultrasound, and magnetic resonance imaging (MRI), as well as X-rays, is now commonplace. These methods enable non-invasive qualitative and quantitative assessment of the anatomical structure and function of the heart and support diagnosis, disease monitoring, treatment planning, and prognosis. The purpose of this study is to find heart problems in patients. The data used in this study were chest X-rays of patients with normal heart conditions and chest X-rays of abnormal heart patients obtained from the kaggle website. Segmentation techniques are used to process these cardiac images. Segmentation is the process of separating between an object and another object or between objects and the background contained in an image. Then the calculation of the area of the heart area is carried out using the extraction of morpological and regional features method characteristics with an algorithm that has been developed. The results of this study can identify heart defects through the process of measuring the area of the heart normal and abnormal. So that it produces a good accuracy rate of 85%. This segmentation technique is proven to be very good so that it can be a medical reference to perform further medical actions against abnormalities in the heart.
Standardscaler's Potential in Enhancing Breast Cancer Accuracy Using Machine Learning Febri Aldi; Febri Hadi; Nadya Alinda Rahmi; Sarjon Defit
Journal of Applied Engineering and Technological Science (JAETS) Vol. 5 No. 1 (2023): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v5i1.3080

Abstract

The major consequence of breast cancer is death. It has been proven in many studies that machine learning techniques are more efficient in diagnosing breast cancer. These algorithms have also been used to estimate a person's likelihood of surviving breast cancer. In this study, we employed machine learning algorithms to predict breast cancer. A total of 569 breast cancer datasets were obtained from kaggle sites. Some of the machine learning algorithms that we use are K-Nearest Neighbor (KNN), besides Random Forest (RF), there is also Gradient Boosting (GB), then Gaussian Naive Bayes (GNB), Vector Support Machine (SVM), and then Logistic Regression (LR). Before algorithms were used to train and test breast cancer datasets, StandardScaler was leveraged to transform training datasets and test datasets for improved algorithm performance. As a result of this utilization, the performance measurement carried out succeeded in producing high accuracy. The highest results were obtained from the Logistic Regression algorithm with an accuracy value of 99%. The value of precison is 99% benign, and 100% malignant. The recall results are 100% benign, and 98% malignant. The F1-Score results show 99% benign, and 99% malignant. It is hoped that this research can help the medical party to determine the next step in dealing with breast cancer.