Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
Given the rapid evolution of radiological imaging in the past four decades, medical image processing nowadays is an essential tool for clinical research. Applications range from research in neuroscience, biomechanics and biomedical engineering to clinical routine tasks such as the visualization of huge datasets provided by modern computed tomography systems in radiology, the manufacturing of patient-specific prostheses for orthopedic surgery, the precise planning of dose distributions in radiation oncology, the fusion of multimodal image data for therapymonitoring in internal medicine, and computer-aided neurosurgical interventions.

Abstrak :
Conveys the essential knowledge needed to understand the clinical application of imaging technologies. Suitable for radiology residents and students, this title covers various subspecialty areas and imaging modalities as utilized in neuroradiology, chest, breast, abdominal, musculoskeletal imaging, ultrasound, and nuclear radiology

Abstrak :
Optimize diagnostic accuracy in the emergency department with Problem Solving in Radiology: Emergency Radiology, a new addition to the popular Problem Solving in Radiology series. Published in association with the American Society of Emergency Radiology, the medical reference book is designed to help experienced radiologists, residents, or emergency medicine practitioners accurately address problematic conditions and reach the most accurate diagnosis. Consult this title on your favorite e-reader, conduct rapid searches, and adjust font sizes for optimal readability.Access problem-oriented con.

Abstrak :
Pada penelitian ini bertujuan untuk merancang dan membuat perangkat lunak simulasi penyinaran radiografi dengan metode ray tracing menggunakan bahasa pemrograman Python. Metode ray tracing dilakukan dengan menghitung intensitas yang diterima detektor setelah melewati suatu materi dan mengalami atenuasi. Penelitian ini dimulai dengan memodelkan fantom TOR 18FG sebagai objek penyinaran. Merancang dan membuat modul simulasi penyinaran monoenergi pada energi 50 keV dan melakukan validitas terhadap perangkat lunak dengan membandingkan citra hasil simulasi dengan citra referensi kemudian menghitung persentase kesalahannya pada geometri dengan perhitungan statistik Mean Absolute Error (MAPE) dan nilai kontras citra dengan perhitungan statistik Mean Absolute Percentage Error (MAE). Pada validasi geometri, persentase kesalahan absolut perangkat lunak sebesar 4,082%. Sedangkan pada validasi nilai kontras, besar kesalahan absolut perangkat lunak sebesar 27,5%. Hasil dari penelitian ini, didapatkan perangkat lunak sederhana yang menyajikan pemodelan penyinaran dengan metode ray tracing dalam bentuk GUI yang dapat menginput nilai intensitas awal berupa jumlah foton dan menghasilkan output berupa citra fantom dengan tingkat akurasi yang tinggi secara geometri, tetapi tingkat akurasi secara nilai kontras masih rendah. ......In this study aims to design and manufacture radiographic irradiation simulation software using the ray tracing method using the Python programming language. The ray tracing method is performed by calculating the intensity received by the detector after passing through a material and experiencing attenuation. This research begins by modeling the TOR 18FG phantom as an irradiating object. Designing and manufacturing a monoenergy irradiation simulation module at 50 keV energy and validating the software by comparing the simulated image with a reference image and then calculating the percentage error in the geometry by calculating the Mean Absolute Error (MAPE) and the contrast value of the image by calculating the Mean Absolute Percentage Errors (MAE). In geometry validation, the software absolute error percentage is 4.082%. Whereas in the validation of contrast values, the software absolute error is 27.5%. The results of this study, obtained simple software that presents irradiation modeling with the ray tracing method in the form of a GUI that can input the initial intensity value in the form of the number of photons and produces an output in the form of a phantom image with a high degree of accuracy in terms of geometry, but the level of accuracy in terms of contrast value is still low.

Abstrak :
Dalam mendapatkan hasil pencitraan Kedokteran Nuklir yang baik adalah didukung dengan instrumen dengan performa yang baik yaitu sesuai dengan standar mutu alat tersebut. Untuk menjaga agar performa instrumen tetap bekerja secara optimal harus dilakukan uji secara berkala dengan protokol uji yang tepat. Penelitian ini dilakukan untuk menguji kualitas citra kamera gamma dengan fantom IEC 61675-2 dan membuat protokol pengujianya meliputi pengujian resolusi radial, resolusi tangensial dan scatter fraction. Pengujian resolusi radial dan resolusi tangensial dilakukan menggunakan sumber titik sedangkan untuk pengujian scatter fraction menggunakan sumber garis. Dari penelitian ini didapatkan hasil rerata FWHM untuk resolusi radial 14,08, pada resolusi tangensial 10,21 mm. Untuk pengujian scatter fraction didapatkan hasil 0,042 dengan prosentase hamburan 4,2%.

---

In order to achieve an optimal scanned image of nuclear medicine device, a good instrument with proper performance which is consistent with its standard quality is required. Furthermore, suitable and periodic protocol test is also a good requirement so that the instrument can extend its maximum performance.In order to Achieve an optimal scanned image of nuclear medicine devices, a good instrument with proper roomates performance is consistent with its standard quality is required. This research was conducted to test the image quality of gamma cameras with phantom IEC 61675-2 and make protocol includes testing radial resolution, tangential resolution and scatter fraction. Test of tangential and radial resolution made using a point source, while for test Scatter fraction using a line source. From this research, the results of the mean FWHM for the radial resolution 14.08 mm and 10.21 mm in tangential resolution. test Scatter fraction obtained scattering percentage of 4.2%.

Abstrak :
Penyakit mata berat yang telat tertangani seperti katarak, glaukoma, serta retinopati diabetik merupakan salah satu penyebab utama gangguan penglihatan dan kebutaan. Pencegahan dapat dilakukan dengan melakukan pendektesian dini melalui citra fundus. Untuk mengatasi minimnya dokter mata dan persebarannya yang masih belum merata, dilakukan pendektesian penyakit mata secara otomatis melalui gambar mata dengan pendekatan deep learning. Dalam penelitian ini, digunakan metode Transfer Learning U-Net dengan VGG16 sebagai pretrained model (V-Unet) yang telah dilatih pada online database, ImageNet. Data yang digunakan dalam penelitian ini merupakan data citra fundus yang diperoleh dari platform Kaggle. Preprocessing data pada citra fundus yang dilakukan untuk meningkatkan kinerja model adalah centered crop, resize, dan rescale. Fungsi optimasi Adam digunakan untuk meminimalkan fungsi loss ketika melatih model. Pada penelitian ini, dilakukan pemisahan data training, validasi, testing dengan 3 rasio berbeda, yaitu kasus I dengan rasio 60:20:20, kasus II dengan rasio 70:20:10, dan kasus III dengan rasio 80:10:10. Hasil penelitian ini menunjukkan bahwa V-Unet memiliki kinerja paling baik pada kasus II berdasarkan skor AUC dan running time dengan nilai rata-rata skor AUC 0,8622 dan rata-rata running time 3,7079 detik sedangkan berdasarkan nilai akurasinya V-Unet memiliki kinerja paling baik pada kasus III dengan rata-rata nilai akurasi sebesar 66,34%. ......Untreated severe eye diseases such as cataracts, glaucoma, and diabetic retinopathy is one of the main causes of visual impairment and blindness. Prevention can be done by doing early detection through fundus images. To overcome the lack of ophthalmologists and their uneven distribution, an automatic detection of eye diseases is carried out through eye images using a deep learning approach. In this study, Transfer Learning U-Net method was used with VGG16 as a pre-trained model (V-Unet) which had been trained on the online database, ImageNet . The data used in this study is fundus image data that obtained from the Kaggle platform. Preprocessing data on the fundus image that is carried out to improve model performance is centered crop, resize, and rescale. Adam's optimization function used to minimize the loss function when training the model. In this study, the training, validation, testing data was separated with 3 different ratios, namely case I with a ratio of 60:20:20, case II with a ratio of 70:20:10, and case III with a ratio of 80:10:10. The results of this study indicate that V-Unet has the best performance in case II based on the AUC score and running time with an average AUC score of 0.8622 and an average running time of 3.7079 seconds while based on accuracy value the best case is case III with an average accuracy value of 66.34%.