Article Per Year (5 Year)
p-Index From 2021 - 2026
3.249
P-Index
This Author published in this journals
All Journal Mutiara Medika: Jurnal Kedokteran dan Kesehatan Jurnal Imejing Diagnostik Jurnal Manajemen Kesehatan Yayasan RS.Dr. Soetomo Proceedings of the International Conference on Applied Science and Health Journal of Applied Health Management and Technology MAHESA : Malahayati Health Student Journal Jurnal Multidisiplin Madani (MUDIMA) JMMR (Jurnal Medicoeticolegal dan Manajemen Rumah Sakit)
Gatot Murti Wibowo, Gatot Murti
Technic of Radiodiagnostic and Radiotherapy Department, Polytechnic Health Ministry of Semarang
Civil Engineering, Building, Construction & Architecture Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Education Health Professions Industrial & Manufacturing Engineering Medicine & Pharmacology Nursing Public Health Social Sciences

Published : 23 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 23 Documents
Search

 1   2   3 
Model Deteksi Parkinson Disease Berbasis Deep Learning Menggunakan Arsitektur VGG Lestari, Deva; Wibowo, Gatot Murti; Setiawan, Agung Nugroho; Suwondo, Ari; Susanto, Edy
Jurnal Imejing Diagnostik (JImeD) Vol. 12 No. 1 (2026): JANUARY 2026
Publisher : Poltekkes Kemenkes Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31983/jimed.v12i1.14284

Abstract

Background: Parkinsons Disease (PD) is a progressive neurodegenerative disorder characterized by the loss of dopaminergic neurons in the substantia nigra, resulting in motor and non-motor impairments. Early diagnosis remains challenging due to subtle initial symptoms and the relatively low accuracy of clinical assessment during early disease stages. Magnetic Resonance Imaging (MRI) provides high-resolution anatomical visualization and has the potential to detect early morphological changes. Advances in deep learning offer opportunities for automated PD detection through MRI analysis. This study aims to develop a PD detection model using the VGG architecture and evaluate its performance on MRI images. Methods: This study employed a Research and Development (R&D) approach to construct a deep learning–based PD detection model. The dataset consisted of 2,000 brain MRI images (1,000 PD and 1,000 healthy controls) obtained from the open-source Kaggle platform. Preprocessing included image normalization and resizing to 256×256 pixels. The dataset was divided into 80% training data and 20% testing data. The model was developed using the VGG architecture and trained for 15 epochs with a batch size of 16. Model performance was evaluated using accuracy, precision, sensitivity, and specificity metrics. Results: The VGG model demonstrated excellent classification performance on the test dataset. Evaluation results showed an accuracy of 0.99, precision of 0.99, sensitivity of 0.98, and specificity of 0.99. The confusion matrix indicated that the model correctly classified 198 healthy control images and 196 PD images, with minimal misclassification. Visualization of MRI comparisons showed that the model was able to detect morphological changes in the substantia nigra, including loss of the normal curvature of the crus cerebri, as an early indicator of PD. Conclusions: The VGG-based PD detection model achieved very high performance in distinguishing PD from healthy controls using MRI images. These findings highlight the potential of deep learning as a tool for early PD detection. However, the use of Kaggle data as the primary dataset represents a limitation due to unverified acquisition standards and clinical quality. Therefore, further validation using multicenter clinical datasets is required to ensure the model’s generalizability to broader patient populations.
Efektivitas Nilai PSNR dan Informasi Citra terhadap Kombinasi Teknik Bilateral Filter dan Non-Local Means sebagai Denoising pada Verifikasi Radioterapi Regio Pelvis Sukmasari, Nyoman Indah; Wibowo, Gatot Murti; Handoko, Bagus Dwi; Santoso, Bedjo; Masrochah, Siti
MAHESA : Malahayati Health Student Journal Vol 6, No 4 (2026): Volume 6 Nomor 4 (2026)
Publisher : Universitas Malahayati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33024/mahesa.v6i4.22131

Abstract

ABSTRACT The quality of radiotherapy verification images on a 6 MeV Linear Accelerator (Linac) often decreases due to noise generated by high energy, potentially reducing the accuracy of irradiation positioning and endangering surrounding healthy tissues. The combination of Bilateral Filter and Non-Local Means techniques is a denoising method designed to reduce noise while preserving important image details. This study aims to evaluate the effectiveness of combining these two techniques in improving the quality of pelvis region verification images, focusing on the quantitative parameter Peak Signal-to-Noise Ratio (PSNR) and the qualitative parameter of image information. The research design used was Research and Development (RD) with 20 samples of anteroposterior (AP) and lateral projection verification images obtained from the Electronic Portal Imaging Device (EPID) of a 6 MeV Linac at the Radiotherapy Unit of RSUD Dr. Moewardi. The denoising process was performed using Python–OpenCV. PSNR values were measured before and after denoising, while image information was assessed by four expert evaluators using a 1–5 scale checklist. Statistical analysis employed paired t-test or Wilcoxon test for PSNR, and Wilcoxon test as well as Cohen’s Kappa for image information. The results showed a significant increase in PSNR values in both projections (p 0.05) with an N-gain score of 59%–64%. Image information assessment also showed a significant improvement (p 0.05), with Cohen’s Kappa indicating moderate to strong agreement among evaluators. Therefore, the combination of Bilateral Filter and Non-Local Means has been proven effective in improving the quality of pelvis region radiotherapy verification images, potentially enhancing irradiation accuracy and patient safety. Keywords: PSNR, Bilateral Filter, Non Local Means, Radiotherapy.  ABSTRAK Kualitas citra verifikasi radioterapi pada Linear Accelerator (Linac) 6 MeV sering menurun akibat noise yang dihasilkan oleh energi tinggi, sehingga berpotensi mengurangi akurasi penentuan posisi penyinaran dan membahayakan jaringan sehat di sekitarnya. Kombinasi teknik Bilateral Filter dan Non-Local Means merupakan metode denoising yang dirancang untuk mengurangi noise sekaligus mempertahankan detail penting citra. Penelitian ini bertujuan mengevaluasi efektivitas kombinasi kedua teknik tersebut dalam meningkatkan kualitas citra verifikasi regio pelvis, dengan fokus pada parameter kuantitatif Peak Signal to Noise Ratio (PSNR) dan parameter kualitatif informasi citra. Desain penelitian yang digunakan Adalah Research and Development (RnD) dengan 20 sampel citra verifikasi proyeksi AP dan lateral yang diambil dari Electronic Portal Imaging Device (EPID) Linac 6 MeV di Instalasi Radioterapi RSUD Dr. Moewardi. Proses denoising dilakukan menggunakan Python–OpenCV. Nilai PSNR diukur sebelum dan sesudah denoising, sedangkan informasi citra dinilai oleh empat penilai ahli menggunakan lembar checklist skala 1–5. Analisis statistik menggunakan uji paired t-test atau Wilcoxon untuk PSNR, dan uji Wilcoxon serta Cohen’s Kappa untuk informasi citra. Hasil penelitian menunjukkan adanya peningkatan signifikan nilai PSNR pada kedua proyeksi (p0,05) dengan N-gain skor 59%–64%. Penilaian informasi citra juga meningkat signifikan (p0,05), dengan nilai Cohen’s Kappa menunjukkan kesepakatan moderat hingga kuat antar penilai. Dengan demikian, kombinasi Bilateral Filter dan Non-Local Means terbukti efektif meningkatkan kualitas citra verifikasi radioterapi regio pelvis, yang berpotensi meningkatkan akurasi penyinaran dan keselamatan pasien. Kata Kunci: PSNR, Bilateral Filter, Non Local Means, Radioterapi.
Evaluasi Efektivitas Model U-Net untuk Segmentasi Citra Renal Scintigraphy pada Penilaian Fungsi Ginjal Gitawiarsa, I Putu Pande Wahyu; Guruh, Bambang; Dartini, Dartini; Mulyantoro, Donny Kristanto; Masrochah, Siti; Wibowo, Gatot Murti
MAHESA : Malahayati Health Student Journal Vol 6, No 4 (2026): Volume 6 Nomor 4 (2026)
Publisher : Universitas Malahayati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33024/mahesa.v6i4.22074

Abstract

ABSTRACT Renal scintigraphy is a nuclear medicine procedure commonly used to quantitatively assess kidney function and monitor various clinical conditions. Image analysis requires segmentation of the kidney’s region of interest (ROI), which is typically performed manually by experienced operators. This manual approach is time-consuming and prone to inter-observer variability. This study develops and evaluates a Convolutional Neural Network (CNN) U-Net model to perform automated ROI segmentation of the kidneys in Tc-99m DTPA–based renal scintigraphy images. The image dataset underwent preprocessing, normalization, and data augmentation, and was then split into training, validation, and testing sets. Model performance was evaluated using the Dice Coefficient on both validation and testing datasets. The results showed an average Dice Coefficient of 0.900 on the validation set and 0.889 on thetesting set. Frame-by-frame analysis demonstrated stable model performance across all acquisition phases, with Dice Coefficient values ≥ 0.87. These findings demonstrate that the U-Net model can accurately and consistently segment kidney ROIs, and has the potential to be integrated into clinical decision-support systems to enhance the efficiency and consistency of renal scintigraphy interpretation. Keywords: U-Net, Medical Image Segmentation, Renal Scintigraphy, Nuclear Medicine, Deep Learning.  ABSTRAK Renal scintigraphy merupakan prosedur kedokteran nuklir yang umum digunakan untuk menilai fungsi ginjal secara kuantitatif dan memantau berbagai kondisi klinis. Proses analisis citra memerlukan segmentasi region of interest (ROI) ginjal, yang umumnya dilakukan secara manual oleh operator berpengalaman. Metode manual ini memakan waktu dan rentan terhadap variabilitas antar- pengamat. Penelitian ini mengembangkan dan mengevaluasi model Convolutional Neural Network (CNN) U-Net untuk melakukan segmentasi otomatis ROI ginjal pada citra renal scintigraphy berbasis radiofarmaka Tc-99m DTPA. Dataset citra yang digunakan melalui proses pra-pemrosesan, normalisasi, dan data augmentation, kemudian dibagi menjadi data latih, validasi, dan uji. Evaluasi kinerja model menggunakan metrik Dice Coefficient pada dataset validasi dan uji. Hasil menunjukkan nilai rata-rata Dice Coefficient sebesar 0,900 pada data validasi dan 0,889 pada data uji. Analisis per frame menunjukkan stabilitas performa model di seluruh faseperekaman, dengan Dice Coefficient ≥0,87. Temuan ini membuktikan bahwa model U-Net mampu melakukan segmentasi ROI ginjal secara akurat dan konsisten, serta berpotensi diintegrasikan dalam sistem pendukung keputusan klinis untuk meningkatkan efisiensi dan konsistensi interpretasi citra renal scintigraphy. Kata Kunci: U-Net, Segmentasi Citra Medis, Renal Scintigraphy, Kedokteran Nuklir, Deep Learning.
Co-Authors Agung Nugroho Setiawan Agustina Dwi Prastanti, Agustina Dwi Ari Suwondo Bagus Dwi Handoko, Bagus Dwi Bambang Satoto, Bambang Bedjo Santoso Kadri Budiati, Tri Asih Darmini Darmini Dartini Dartini, Dartini Donny Kristanto Mulyantoro Dwi Rochmayanti edy susanto Fajriyah, Ayu Yuliana Fatimah fatimah Fatimah Gitawiarsa, I Putu Pande Wahyu Guruh, Bambang Hanifan, Arinal Hanifan Hari Santoso Hariri, Ahmad Harnanto, Rudy Hidayatullah, Mohamad I Made Lana Prasetya Izzudin, Muhammad Jeffri Ardiyanto Kurniawan Saputra Kusworo Adi Leny Latifah Lestari, Deva Lokatara, Sista Lokatara M. Choiroel Anwar M.Pd S.T. S.Pd. I Gde Wawan Sudatha . MAIZZA NADIA PUTR MUSLIMAH PUTRI UTAMI Muzhaffar, Muhammad Isfan Nuha, M. Dzawin Nur Hayati Pranandya, Brian Ilham Puspita, Mega Indah Rasyid Rasyid, Rasyid Rini, Regi Kusuma Romadhoni, Efriza Nur Setjadiningra, Rr. Lydia Purna Widyastuti Siti Daryati, Siti Siti Masrochah Sri Mulyati Suan, Kesita Grace Natalia Sudiyono Sudiyono SUGIYANTO Sukmasari, Nyoman Indah Suryono Suryono Ummah, Sylvia Ishlahul Wahyuni, Wilda Yeti Kartikasari, Yeti