DSDjarwani Soeharso Soejoko

Djarwani Soeharso Soejoko

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Djarwani Soeharso Soejoko has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Artificial neural network for cervical abnormalities detection on computed tomography images

    by Erlinda Ratnasari Putri, Ahmad Zarkasi, Prawito Prajitno, Djarwani Soeharso Soejoko

    Cervical cancer is the second deadliest after breast cancer in Indonesia. Sundry diagnostic imaging modalities had been used to decide the location and severity of cervical cancer, one among those is computed tomography (CT) Scan. This study handles a CT image dataset consisting of two categories, abnormal cervical images of cervical cancer patients and normal cervix images of patients with other diseases. It focuses on the ability of segmentation and classification programs to localize cervical cancer areas and classify images into normal and abnormal categories based on the features contained in them. We conferred a novel methodology for the contour detection round the cervical organ classified with artificial neural network (ANN) which was employed to categorize the image data. The segmentation algorithm used was a region-based snake model. The texture features of the cervical image area were arranged in the form of gray level co-occurrence matrix (GLCM). Support vector machine (SVM) had been added to determine which algorithm was better for comparison. Experimental results show that ANN model has better receiver operating characteristic (ROC) parameter values than SVM model’s and existing approach’s regarding 96.2% of sensitivity, 95.32% of specificity, and 95.75% of accuracy.


  • Open Access

    Effects of Ovariectomy and Dieting with Nano Calcium Phosphate on Bone Quality in White Rats Rattus norvegicus

    by Neng Nenden Mulyaningsih, Ariadne Lakshmidevi Juwono, Djarwani Soeharso Soejoko, Dewi Apri Astuti

    Calcium supplements are widely used to prevent osteopenia and osteoporosis and can be used as a treatment along with other drugs. The effect of this supplement can be seen from the improved bone quality. The focus in this study was to analyze the quality of femur bone based on the mineral maturity and the degree of crystallinity from ovariectomized Rattus norvegicus where the treatment of various nano calcium phosphate diets (1.0×; 1.5× and 2.0× normal needs, respectively called A, B and C diets) also given. In the amount of 40 white female rats age 12 weeks were ovariectomized and 5 sham rats were nurtured. The group of sham was given euthanasia treatment at age 13 weeks, while ovariectomized group was treated euthanasia at age 17 and 21 weeks. At the age of 25 weeks after ovariectomy, the rats were treated with a nano calcium phosphate diet where analysis was performed when they were 31 and 40 weeks old. In each harvest, proximal femur part was collected and characterized by using FTIR Spectroscopy. Rat bone quality shows osteoporosis trait for the first time at age 21 weeks or after 9 weeks of ovariectomy with the mineral maturity and degree of crystallinity decreased in the amount of 1.16 and 2.27 %, respectively compared to femur bone from sham rat group. The dietary treatment study conducted showed that the group of rats fed the A diet had not a significant changes (p < 0.05) in the mineral maturity and the degree of crystallinity, while giving B or C diet had a significant increase in the mineral maturity at 40 weeks of age or after 15 weeks on a diet. The increase in the degree of crystallinity of the rats fed B diet (6 weeks) was faster than the group fed C diet (15 weeks). Therefore, diet B is recommended because it is more efficient and effective based on the time it increases the degree of crystallinity and the cost of producing the diet. HIGHLIGHTS GRAPHICAL ABSTRACT

  • Open Access

    Evaluation and Implementation of Otsu and Active Contour Segmentation in Contrast-Enhanced Cardiac CT Images

    by Arvi Razanata, Prawito Prajitno, Djarwani Soeharso Soejoko

    The CT cardiac acquisition process is usually conducted by using an additional image with contrast medium that is injected inside the body and reconstructed by a radiologist using an integrated CT Scan software with the aim to find the morphology and volume dimension of the heart and coronary arteries. In fact, the data obtained from the hospital are raw data without segmented contour from a radiologist. For the purpose of automation, dataset is needed to be used as input data for further program development. This study is focused on the evaluation of the segmentation results of CT cardiac images using Otsu threshold and active contour algorithm with the aim to make a dataset for the heart volume quantification that can be used interactively as an alternative to integrated CT scan software. 2D contrast enhanced cardiac CT from 6 patients using image processing techniques was run on Matlab software. Of the 689 slices that was used, as many as (73.75 ± 19.41)%of CT cardiac slices have been segmented properly, (19.15 ± 19.61)%of the slices that were segmented included the spine bone, (1.36 ± 0.98)%of the slices did not include all region of the heart, (16.58 ± 15.26)%of the slices included other organs with the consistency from the measurement proven from inter-observer variability to produce r = 0,9941.The result is due to the geometry influence from the diameter of the patient’s body thickness that tends to be thin.

  • Open Access

    Noise reduction of three-dimensional rotational angiography (3DRA) images using residual encoder-decoder convolutional neural network (RED-CNN)

    by L. E. Lubis, H. B. Cokrokusumo, R A. Basith, I. Lestariningsih, P. Prajitno, D. S. Soejoko

    Compared to computed tomography (CT), three-dimensional rotational angiography (3DRA) presents tomographic images with relatively higher noise due to a lack of imaging projections and a more considerable scatter volume. This paper extends the use of the residual encoder-decoder convolutional neural network (RED-CNN) to denoise 3DRA images with a specific mode of training, where an in-house algorithm was trained using CT images of homogeneity water phantom as target noise level for 3DRA images to refer to. The algorithm was applied to 3DRA images obtained using GE Optima CL323i with CT images from a Siemens Somatom 16 as benchmarks. All 3DRA images were also denoised using the standard block-matching and 3D filtering (BM3D) method as a preliminary comparison. Noise levels were quantified in Hounsfield unit using ImQuest software, while the limiting spatial resolution (10% modulation transfer function, MTF) was determined using Spice-CT plugin of the ImageJ tool. Whereas resulting 3DRA images denoised using BM3D had an average of 22,6% decrease in noise level (from 29,6 HU to 22,9 HU), our method presents an average of 49,0% decrease in noise level (29,6 HU to 15,1 HU) for the same images. The 3DRA images denoised using RED-CNN underwent an increase of spatial resolution (8,2%), while BM3D-denoised images had their 10% MTF reduced by an average of 8,7%. These preliminary results had indicated a potential use of RED-CNN based method to denoise 3DRA images without compromising the spatial resolution.


  • Morphology of Proximal Cortical Epiphysis Bone of Ovariectomized Rattus Norvegicus

    by Neng Nenden Mulyaningsih, Ariadne Lakshmidevi Juwono, Djarwani Soeharso Soejoko, Dewi Apri Astuti


  • Medical Physics Education and Training in South East Asia

    by A. Krisanachinda, N. V. Hoa, J. C. L. Lee, K. H. Ng, A. P. Peralta, D. Soejoko, T. J. Wong