Abstrak: Di Indonesia kanker paru menjadi penyebab kematian kedua setelah kanker payudara. Angka mortalitas yang cukup tinggi, maka penentuan diagnosis lebih awal memegang peranan yang sangat penting dalam manajemen terapi. Kelemahan CT-Scan dalam mendiagnosa kanker paru-paru disebabkan oleh kontras citra yang rendah dan derau pada citra. Pada penelitian ini akan membandingkan metode contrast enhancement berbasis histogram equalization dan contrast limited adaptive histogram equalization untuk meningkatkan kualitas citra dengan menggunakan software Matlab. Namun, sebelumnya dilakukan reduksi noise dengan menggunakan metode median filter. Kinerja dari setiap metode dihitung dengan mencari nilai MSE (Mean Square Error) dan PSNR (Peak Signal to Noise Ratio) citra. Dari nilai MSE dan PSNR yang di dapatkan diperoleh nilai MSE dan PSNR terbaik pada metode contrast limited adaptive histogram equalization dengan nilai 653,434 dB dan 245,547 dB.

Kinship face synthesis is an increasingly popular topic within the computer vision community, particularly the task of predicting the child appearance using parental images. Previous work has been limited in terms of model capacity and inadequate training data, which comprised of low-resolution and tightly cropped images, leading to lower synthesis quality. In this paper, we propose ChildNet, a method for kinship face synthesis that leverages the facial image generation capabilities of a state-of-the-art Generative Adversarial Network (GAN), and resolves the aforementioned problems. ChildNet is designed within the GAN latent space and is able to predict a child appearance that bears high resemblance to real parents' children. To ensure fine-grained control, we propose an age and gender manipulation module that allows precise manipulation of the child synthesis result. ChildNet is capable of generating multiple child images per parent pair input, while providing a way to control the image generation variability. Additionally, we introduce a mechanism to control the dominant parent image. Finally, to facilitate the task of kinship face synthesis, we introduce a new kinship dataset, called Next of Kin. This dataset contains 3690 high-resolution face images with a diverse range of ethnicities and ages. We evaluate ChildNet in comprehensive experiments against three competing kinship face synthesis models, using two kinship datasets. The experiments demonstrate the superior performance of ChildNet in terms of identity similarity, while exhibiting high perceptual image quality. The source code for the model is publicly available at: https://github.com/MartinPernus/ChildNet.

No abstract

Magnetic Resonance Imaging (MRI) is an imaging technique for the human body cross-section, which utilizes electromagnetic radiations in the form of radio frequency. The MRI imaging technique is relatively complex, since the resulted images depend on many parameters, including Time Repetition (TR) and Time Echo (TE). This research is aimed to analyze the selection of TR and TE parameters, as well as to analyze the differences of signal intensity on White Matter (WM) tissue, Gray Matter (GM) tissue, and Cerebrospinal Fluid (CSF) of T1 MEMP and DWI images in the human brain. The obtained results showed that T1 MEMP images had short TR value (400–500 ms) and short TE value (13 ms), while DWI images had a b-value = 1,000 s/mm2 with long TR value (7,000 ms) and long TE value (80–90 ms). The resulted signal intensity on WM tissue, GM tissue, and CSF was measured based on gray value distribution using RadiAnt DICOM Viewer version 2.2.9.10728 (64 bit) and ENVI version 4.5 software. The results showed that the average of gray value distribution on T1 MEMP images were 46.5–66.5 for GM tissue, 67.5–94 for WM tissue, and 18.9–45.5 for CSF, while the average of gray value distribution on DWI images were 178–255 for GM tissue, 92.1–177 for WM tissue, and 31.5–91.1 for CSF. Hence, the WM tissue appeared clearer by using T1 MEMP images and the GM tissue appeared clearer by using DWI images.

A natural distillation process as an atmospheric machine in producing fresh water from seawater is of importance to be relearned. This study aims to scrutinize a thermodynamic cycle involving evaporation on sea surface and condensation at a possible height to occur in lower temperature and pressure by comparing reversible and irreversible process. The main stratification of pressure and temperature are obtained from local radiosonde record. The result of this study will give an explanation about how the diabatic process restores the energy to maintain the system equilibrium.