According to data reported by the Global Burden of Disease (GBD) study in 2018, lung disease is among the top 20 diseases causing Disability-Adjusted Life Years (DALY). DALY is a measure used to describe the burden of disease by combining the burden of death and the burden of disease living with disability. Lung disease can cause decreased lung function, disability, and affect an individual's quality of life. Prevention, early diagnosis, treatment, and management of lung disease are essential to reduce the burden of this disease in society and improve overall lung health.The importance of computer-aided diagnosis (CAD) in chest X-Ray (CXR) is very significant in the field of radiology. This technology utilizes artificial intelligence (AI) in the form of Deep Learning (DL) with artificial neural networks (ANN) to analyze radiological images and assist doctors in making diagnoses. The ANN model has the ability to learn complex patterns in lung radiology images that are difficult for humans to recognize, so it can recognize the typical characteristics of various lung diseases if trained on CXR data. CAD using ANN can improve the accuracy of diagnosis, as well as reduce the subjectivity of doctors when making a diagnosis. However, it is important to note that CAD does not replace the role of doctors, but rather acts as a tool that provides initial recommendations. The final interpretation and decision on diagnosis remain in the hands of the doctor. One of the main obstacles in the development of ANN for CAD is data limitations. In the medical field, the available datasets tend to have a small amount of data, or have a large imbalance between the amount of data for each diagnostic category (data imbalance) due to limitations that exist during the data collection process. To overcome the problem of limited data, Transfer Learning (TL) can be used. To overcome data imbalance, the Self-Supervised Learning method is one solution that can be used. In our previous research, SSL methods such as Swapping Assignments between Views (SwAV) have been proven to be able to make ANN models achieve better accuracy, even in conditions where there is severe data imbalance, but the model can only achieve an Area Under Curve (AUC) value of 0.952 and an F1 score of 0.821. Further development of this method allows the ANN model to achieve a higher level of accuracy, and can improve the effectiveness of early screening for lung disease. With proper use, this can save research costs from hospitals and provide efficient solutions in healthcare. As a further development of previous research, we use a new algorithm that is known to be more accurate to handle data imbalance. This new ANN model is then implemented as a web application.

InDRY

The development of AI-based early screening and Computer-Aided Diagnosis (CAD) systems is very important for the field of radiology

During the COVID-19 pandemic, the implementations of maximum room capacity monitoring systems were considered critical. However, such systems tend to naively count all humans detected from the CCTV footage, including people outside the rooms that are visible through glass. By using a novel method named the Gap Regularizer, the AI model became capable of distinguishing people inside and outside the rooms even when they are only divided by glass.

Maximum Room Capacity Limit Violation Detector System Using CSRNet and Gap Regularizer

To monitor the compliance to room capacity limitations, this system can count people inside glass-surrounded rooms or other regions-of-interest by using CSRNet and Gap Regularizer. 

The lack of data transparency in Indonesia's stunting research ecosystem requires specialized data that covered the profile, background, and anthropometry measurement&nbsp;data of children is necessary. StuntingDB was designed to assist the public health workforce in collecting anthropometric measurements of stunted children. This can greatly benefit public health sectors to obtain such data in a more accurate, standardized, and accountable manner. Stunting validation process validated StuntingDB has complied with PERMENKES No. 2/2020 and developed in the form of a website application to allow users&nbsp;to access them from personal computers, tablets, and smartphones without installation.

StuntingDB

StuntingDB is a database designed to collect anthropometric measurements of stunted children in a more accurate, standardized, and accountable manner

Computer-Aided Diagnosis systems can greatly benefit medical personnel. By using a Convolutional Neural Network trained using the SwAV algorithm, the application can display diagnoses and locations of anomalies from chest X-ray images uploaded by users. The AI model itself was accurate even while being trained on an imbalanced dataset,

Lung Disease Detection System Using SwAV in A Web-based Application

This application allows medical personnel to perform early screenings of lung diseases and locating anomalies. By using the SwAV algorithm, the AI model achieved high accuracy under imbalanced data.

Prof. Bens Pardamean, B.Sc., M.Sc., Ph.D.

Prof. Dr. Bens Pardamean has over thirty years of global experience in information technology, bioinformatics, and education. His professional experience includes being a practitioner, researcher, consultant, entrepreneur, and lecturer.&nbsp;He currently holds a dual appointment as Director of Bioinformatics &amp; Data Science Research Center (BDSRC) | AI Research &amp; Development Center (AIRDC) and Professor of Computer Science at Bina Nusantara (BINUS) University in Jakarta, Indonesia. He earned a doctoral degree in informatics research from University of Southern California (USC), as well as a master’s degree in computer education and a bachelor’s degree in computer science from California State University at Los Angeles (USA).

Prof. Bens Pardamean, B.Sc., M.Sc., Ph.D.

Faculty Member Computer Science

Join Us Now!