Early Lung Cancer Detection Using Artificial Neural Network

Pandiangan, Tumpal; Bali, Ika; Silalahi, Alexander R. J.

doi:10.17146/aij.2019.860

Cited by 15 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, other solutions focus on detecting misbehaving nodes in cITSs. These solutions aim to protect the system against threats carried out by legitimate yet compromised nodes, which is more challenging as those nodes are trusted and thus less suspicious [18]. Nonetheless, most of these solutions assume that the cITS is stationary.…”

Section: Related Workmentioning

confidence: 99%

Adaptive IDS for Cooperative Intelligent Transportation Systems Using Deep Belief Networks

2022

View full text Add to dashboard Cite

The adoption of cooperative intelligent transportation systems (cITSs) improves road safety and traffic efficiency. Vehicles connected to cITS form vehicular ad hoc networks (VANET) to exchange messages. Like other networks and systems, cITSs are targeted by attackers intent on compromising and disrupting system integrity and availability. They can repeatedly spoof false information causing bottlenecks, traffic jams and even road accidents. The existing security infrastructure assumes that the network topology and/or attack behavior is static. However, the cITS is inherently dynamic in nature. Moreover, attackers may have the ability and resources to change their behavior continuously. Assuming a static IDS security model for VANETs is not suitable and can lead to low detection accuracy and high false alarms. Therefore, this paper proposes an adaptive security solution based on deep learning and contextual references that can cope with the dynamic nature of the cITS topologies and increasingly common attack behaviors. In this study, deep belief networks (DBN) modeling was used to train the detection model. Binary cross entropy was used as a loss function to measure the prediction error. Two activation functions were used, Relu and Softmax, for input–output mapping. The Relu was used in the hidden layers, while the Sigmoid was used in the last layer to map the real vector to output between 0 and 1. The adaptation mechanism was incorporated into the detection model using a moving average that monitors predicted values within a time window. In this way, the model can readjust the classification thresholds on-the-fly as appropriate. The proposed model was evaluated using the Next Generation Simulation (NGSIM) dataset, which is commonly used in such related works. The result is improved accuracy, demonstrating that the adaptation mechanism used in this study was effective.

show abstract

Section: Related Workmentioning

confidence: 99%

Adaptive IDS for Cooperative Intelligent Transportation Systems Using Deep Belief Networks

2022

View full text Add to dashboard Cite

show abstract

“…Regarding the screening and early risk prediction of whether a patient has lung cancer, Cheng et al [ 30 ] proposed a new clinical decision support system for screening chest CT images for the presence or absence of lung nodules. Pandiangan et al [ 31 ] used a feedforward neural network to train an artificial neural network model with patients’ physical symptoms as binary data labels. This detects the presence of lung cancer in the patient’s body with an accuracy of 96.67%.…”

Section: Related Workmentioning

confidence: 99%

A Convolutional Neural Network-Based Intelligent Medical System with Sensors for Assistive Diagnosis and Decision-Making in Non-Small Cell Lung Cancer

Zhan

Long

Gou

et al. 2021

Sensors

View full text Add to dashboard Cite

In many regions of the world, early diagnosis of non-small cell lung cancer (NSCLC) is a major challenge due to the large population and lack of medical resources, which is difficult toeffectively address via limited physician manpower alone. Therefore, we developed a convolutional neural network (CNN)-based assisted diagnosis and decision-making intelligent medical system with sensors. This system analyzes NSCLC patients’ medical records using sensors to assist staging a diagnosis and provides recommended treatment plans to physicians. To address the problem of unbalanced case samples across pathological stages, we used transfer learning and dynamic sampling techniques to reconstruct and iteratively train the model to improve the accuracy of the prediction system. In this paper, all data for training and testing the system were obtained from the medical records of 2,789,675 patients with NSCLC, which were recorded in three hospitals in China over a five-year period. When the number of case samples reached 8000, the system achieved an accuracy rate of 0.84, which is already close to that of the doctors (accuracy: 0.86). The experimental results proved that the system can quickly and accurately analyze patient data and provide decision information support for physicians.

show abstract

“…Pemantauan dosis radiasi yang diterima oleh organ tubuh manusia selama pemeriksaan dengan alat medis radiasi seperti metode bracytherapy payudara (Skowronek, 2017) tidak dapat diabaikan, bahkan merupakan suatu keharusan agar dapat memastikan dampak radiasi terhadap keselamatan pasien dan pekerja radiasi. Setiap perlakuan paparan radiasi pada pasien harus menerapkan prinsip proteksi radiasi, yaitu menerapkan radiasi serendah mungkin dengan kualitas diagnostik sebaik mungkin bagi pasien (Pandiangan et al, 2019). Beberapa perangkat lunak pemantauan dosis telah dikembangkan guna memantau dan mengontrol distribusi dosis sebelum (Pandiangan et al, 2020) dan selama pemeriksaan pasien menggunakan alat medis radiasi pengion.…”

Section: Pendahuluanunclassified

Analisis Dosis Radiasi Pada Jaringan Tumor Dengan Simulasi Program McNp-5

Pandiangan¹,

Bali²

2021

JMSTKIK

View full text Add to dashboard Cite

Direct measurement of each radiation dose to the patient's organs is not possible. In general, to estimate the dose absorbed by human organs is approached by measurements in human phantoms, but this approach is still too rough because the composition of phantoms is not easily made the same as the actual organ composition. Currently, for important matters such as the accuracy of determining the absorption dose by human organs, the Monte Carlo simulation method (MCNP) with special software is used. This has led to a growing desire for scientists to make the transition from using phantoms to computing software for medical physics applications. However, until now no comprehensive document has been written to introduce the use of the MCNP program to simulate its application in medical physics. The purpose of this study was to analyze the absorbed dose of gamma radiation in tumor tissue in the breast by simulating changes in distance and tumor size using the MCNP-5 program. This can be useful in ensuring the application of radiation protection to the patient and the environment in which the patient is located. The results showed that the radiation dose in cell 1 (tumor tissue) with a change in the distance between the radiation source and cell 1 was getting bigger, resulting in a decrease in the dose in cell 1, while the effect of cell volume 1 was greater, the greater the dose received by cell 1. In addition, through this simulation it can be seen that for each addition of 1 cm3 the volume of cell 1 for tumor tissue can increase the absorption energy by 3.5x10e-12 Gray. Keywords: MCNP-5; simulation; radiation dose; tumor tissue AbstrakPengukuran setiap dosis radiasi pada organ pasien tidak dimungkinkan secara langsung. Pada umumnya untuk memperkirakan dosis yang diserap oleh organ tubuh manusia didekati dengan pengukuran pada phantom manusia, namun pendekatan ini juga masih terlalu kasar karena komposisi phantom tidak mudah dibuat sama dengan komposisi organ yang sebenarnya. Sehingga saat ini, untuk hal-hal yang penting seperti ketepatan penentuan dosis serap oleh organ tubuh manusia, digunakan metode simulasi Monte Carlo (MCNP) dengan perangkat lunak khusus. Hal ini mendorong meningkatnya keinginan para ilmuwan melakukan transisi dari penggunaan phantom ke penggunaan komputasi perangkat lunak untuk aplikasi fisika medis. Namun sampai saat ini belum tersedia dokumen komprehensif yang ditulis untuk memperkenalkan penggunaan program MCNP guna mensimulasikan aplikasinya dalam fisika medis. Tujuan penelitian ini adalah menganalisis dosis serap radiasi gamma pada jaringan tumor di payudara melalui simulasi perubahan jarak dan besar tumor menggunakan program MCNP-5. Hal ini dapat berguna dalam memastikan penerapan proteksi radiasi pada pasien dan lingkungan tempat pasien. Hasil penelitian menunjukkan dosis radiasi pada sel 1 (jaringan tumor) dengan perubahan jarak antara sumber radiasi dengan sel 1 semakin besar, mengakibatkan besar dosis di sel 1 semakin menurun, sedangkan pengaruh volume sel 1 yang semakin besar maka dosis yang diterima sel 1 semakin besar juga. Selain itu, melalui simulasi ini dapat diketahui untuk setiap penambahan 1 cm3 volume sel 1 jaringan tumor dapat meningkatkan energi serap sebesar 3,5x10e-12 Gray.

show abstract

Early Lung Cancer Detection Using Artificial Neural Network

Cited by 15 publications

References 7 publications

Adaptive IDS for Cooperative Intelligent Transportation Systems Using Deep Belief Networks

Adaptive IDS for Cooperative Intelligent Transportation Systems Using Deep Belief Networks

A Convolutional Neural Network-Based Intelligent Medical System with Sensors for Assistive Diagnosis and Decision-Making in Non-Small Cell Lung Cancer

Analisis Dosis Radiasi Pada Jaringan Tumor Dengan Simulasi Program McNp-5

Contact Info

Product

Resources

About