Hasil Pencarian  ::  Simpan CSV :: Kembali

"Pada umumnya, dosis pasien kanker terapi radionuklida diberikan secara fixed dose, namun diperoleh eror yang besar. Untuk menjamin keakurasian, maka diperlukan perhitungan dosimetri internal. Penelitian bertujuan mengembangkan software in-house perhitungan dosimetri internal terapi radionuklida dengan menggabungkan software peneliti sebelumnya terkait kuantifikasi aktivitas organ citra planar kamera gamma dan perhitungan AUC. Software tersebut bernama Absorbed Dose Calculator of Lu-177 dalam bentuk tampilan GUI (graphical user interface) yang dikembangkan melalui software MATLAB versi 2020a. Terdapat 3 tahap perhitungan yaitu tahap kuantifikasi akivitas berdasarkan perhitungan aktivitas conjugate view, tahap perhitungan AUC dan dosis serap. Perhitungan dilakukan terhadap 7 pasien RrDTC pada organ ginjal kanan, ginjal kiri, hati dan limfa. Nilai tertinggi untuk aktivitas diperoleh pada organ hati sebesar 20,02 MBq, sedangkan untuk dosis serap pada organ limfa sebesar 554,46 mGy atau 0,55 Gy. Nilai dosis yang diperoleh tidak melebihi nilai batas dosis yang ditoleransikan. Hasil validasi menunjukan eror (relative deviation, %RD) kurang dari 10%. Software peneliti dapat melakukan perhitungan dosimetri internal dengan hasil yang baik.

---

In general, the dose of radionuclide therapy cancer patients is given in a fixed dose, but a large error is obtained. To ensure accuracy, it is necessary to calculate the internal dosimetry. This study aims to develop an in-house software for calculating the internal dosimetry of radionuclide therapy by combining the software of previous researchers related to the quantification of organ activity in gamma camera planar images and AUC calculations. The software is called Absorbed Dose Calculator of Lu-177 in the form of a GUI (graphical user interface) display which was developed through the MATLAB software version 2020a. There are 3 calculation stages, namely the activity quantification stage based on the conjugate view activity calculation, the AUC calculation stage and the absorbed dose. Calculations were performed on 7 RrDTC patients in the right kidney, left kidney, liver and spleen. The highest value for activity was obtained in the liver at 20,02 MBq, while the absorbed dose in the spleen was 554,46 mGy or 0,55 MBq. The dose value obtained does not exceed the tolerable dose limit value. The validation results show the error (relative deviation, %RD) is less than 10%. Research software can perform internal dosimetry calculations with good results."

"Identifikasi radionuklida berguna untuk keamanan nuklir, monitor lingkungan, serta diagnosa kesehatan, di mana keandalan identifikasi radionuklida di berbagai kondisi merupakan hal yang penting. Data spektrum gamma biasanya rentan terhadap gangguan noise. Penelitian ini menyelidiki performa machine learning dalam mengenali radionuklida di bawah pengaruh gangguan adversarial attack, yang dirancang untuk melatih ketangguhannya terhadap gangguan luar. Pada penelitian ini, digunakan data spektrum gamma dari Co-60, Cs-134, dan Cs-137 yang di-preprocessing dengan background subtraction, adversarial attack, dan logarithmic normalization, kemudian lebih lanjut dengan zero padding dan 2D mapping dengan Hilbert curve. Data ini digunakan untuk training model Convolutional Neural Network (CNN). Terdapat 4 model yang dibuat: model 1D, model 1D dengan adversarial attack, model 2D, dan model 2D dengan adversarial attack. Model 1D dan 2D menunjukkan akurasi yang tinggi (98% untuk keduanya) dengan konvergensi loss yang cepat saat training. Dengan adversarial attack, proses training dan identifikasi radionuklida menunjukkan performa yang lebih buruk, yakni 77% untuk model 1D dan 71% untuk model 2D. Ini menunjukkan bahwa mentode adversarial learning menggunakan adversarial attack cenderung menurunkan performa model terhadap noise yang tak kasat mata, dan model tidak dapat memiliki performa yang lebih baik maupun sebaik model tanpa adversarial attack.

---

Radionuclide identification finds its use in nuclear safety, environmental monitoring, and health diagnosis, where identification performance under noisy conditions is of utmost importance. Gamma-ray spectrum data are typically vulnerable against external noise. This research investigates the performance of machine learning in identifying radionuclides under the influence of adversarial attacks, which are designed to train the robustness of the model against external perturbations. In this research, the gamma-ray spectrum data of Co-60, Cs-134, and Cs-137 are preprocessed with background subtraction, adversarial attack, and logarithmic normalization, and additionally with zero padding and 2D mapping using the Hilbert curve. The data is then used to train the Convolutional Neural Network (CNN) model. Four models are constructed: the 1D model, the 1D model with adversarial attack, the 2D model, and the 2D model with adversarial attack. The 1D model and the 2D model exhibits high accuracy (98% for both) with fast loss convergence during the training process. With the adversarial attack, the training and radionuclide identification decline in performance, with 77% accuracy for the 1D model and 71% for the 2D model. This demonstrates how adversarial attaqcks can decrease the model’s robustness against external perturbations, and that the models’ performances are significantly worse compared to those without the adversarial attacks."