Hasil Pencarian  ::  Simpan CSV :: Kembali

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%.

Abstrak :
ABSTRAK
Dalam beberapa dekade terakhir, pencitraan sinar-X menggunakan film-screen mulai digantikan oleh digital radiography. Sistem pencitraan digital salah satunya adalah computed radiography (CR). Sejauh ini di Indonesia, perkembangan yang pesat dari CR belum dibarengi dengan penelitian untuk memperoleh kondisi optimum dalam aplikasinya.

Telah dilakukan penelitian di RS X menggunakan CR Agfa tipe PSP MD 4.0 dan fantom Rando Man untuk menentukan optimasi pembentukan citra. Juga dilakukan pengukuran Entrance Surface Dose (ESD) menggunakan thermoluminescent dosimeter (TLD) dengan berbagai variasi nilai kV. Pemeriksaan yang dipilih adalah kepala PA, thorax PA, dan abdomen AP. Citra fantom dievaluasi berdasarkan panduan dari European Commission dibantu oleh dokter spesialis radiologi. Optimasi citra didasarkan pada nilai kV dengan nilai ESD yang rendah dan hasil evaluasi citra.

Hasil penelitian menunjukkan bahwa untuk pemeriksaan kepala PA optimasi terjadi pada ESD 3,580 mGy dan 3,834 mGy untuk kondisi 80 kV dan 83 kV dengan 0,224 ? 0,274 mGy/mAs. Untuk pemeriksaan thorax PA teknik kV standar optimasi terjadi pada ESD 1,341 mGy dan 2,378 mGy untuk kondisi 50 kV dan 55 kV dengan 0,134 ? 0,297 mGy/mAs. Sedangkan untuk teknik kV tinggi yang menggunakan 100 kV, optimasi terjadi pada ESD 2,960 mGy dengan 0,947 mGy/mAs. Dan untuk pemeriksaan abdomen AP optimasi terjadi pada ESD 4,090 mGy dan 4,268 mGy untuk kondisi 70 kV dan 80 kV dengan 0,204 ? 0,267 mGy/mAs. Selain nilai kV, optimasi juga mengikutsertakan nilai kontras tinggi dan rendah, serta karakter CR Agfa yang diwakili oleh nilai lgM (log Median).

---

Abstract
For the last few decades, X-ray imaging using film screen has been replaced by digital radiography. One of digital imaging systems is computed radiography (CR). So far in Indonesia, the rapid development of CR is not ensued with research to obtain optimum condition in its application.

Has been performed a research in hospital X using Agfa CR Type PSP MD 4.0 and Rando Man phantom to determine optimization of image development. Also conducted measurement of Entrance Surface Dose (ESD) using thermoluminescent dosimeter (TLD) for various kV values. The examinations were selected for skull PA, thorax PA, and abdomen AP. Image phantom assessment was carried out using guideliness from European Commission with assistance of radiologist. Optimization of image was done based on kV value with low ESD value and image assessment.

The results showed that for skull PA examination, optimization occured on ESD 3.580 mGy and 3.834 mGy for exposure condition of 80 kV and 83 kV with 0.224 to 0.274 mGy/mAs. For standard kV technique thorax PA examination, optimization occured on ESD 1.341 mGy and 2.378 mGy at 50 kV and 55 kV with 0.134 to 0.297 mGy/mAs. As for the high kV technique of which used a 100 kV, ESD optimization occured at 2.960 mGy with 0.947 mGy/mAs. While for abdomen AP examination, optimization occured on ESD 4.090 mGy and 4.268 mGy for 70 kV and 80 kV with 0.204 to 0.267 mGy/mAs. In addition to values of kV, optimization also included high and low contrast values as consideration and Agfa CR character that was represented by the lgM (log Median) value.

Abstrak :
This book constitutes the refereed proceedings of the International Workshop on Mesh Processing in Medical Image Analysis, MeshMed 2012, held in Nice, France, in October 2012 in conjunction with MICCAI 2012, the 15th International Conference on Medical Image Computing and Computer Assisted Intervention. The book includes 16 submissions, 8 were selected for presentation along with the 3 plenary talks representative of the meshing, and 8 were selected for poster presentations. The papers cover a broad range of topics, including statistical shape analysis and atlas construction, novel meshing approaches, soft tissue simulation, quad dominant meshing and mesh based shape descriptors. The described techniques were applied to a variety of medical data including cortical bones, ear canals, cerebral aneurysms and vascular structures.

Abstrak :
The three-volume set LNCS 7510, 7511, and 7512 constitutes the refereed proceedings of the 15th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2012, held in Nice, France, in October 2012. Based on rigorous peer reviews, the program committee carefully selected 252 revised papers from 781 submissions for presentation in three volumes. The first volume includes 91 papers organized in topical sections on abdominal imaging, computer-assisted interventions and robotics, computer-aided diagnosis and planning, image reconstruction and enhancement, analysis of microscopic and optical images, computer-assisted interventions and robotics, image segmentation, cardiovascular imaging, and brain imaging, structure, function and disease evolution.

Abstrak :
Creating new medical ontologies for image annotation focuses on the problem of the medical images automatic annotation process, which is solved in an original manner by the authors. All the steps of this process are described in detail with algorithms, experiments and results. In addition, the authors treat the problem of creating ontologies in an automatic way, starting from Medical Subject Headings (MESH). They have presented some efficient and relevant annotation models and also the basics of the annotation model used by the proposed system, cross media relevance models. Based on a text query the system will retrieve the images that contain objects described by the keywords.

Abstrak :
This book is a compendium of the ICCMIA 2018 proceedings, which provides an ideal reference for all medical imaging researchers and professionals to explore innovative methods and analyses on imaging technologies for better prospective patient care. This work serves as an exclusive source for new computer assisted clinical and medical developments in imaging diagnosis, intervention and analysis. It includes articles on computer assisted medical scanning techniques, computer-aided diagnosis, robotic surgery and imaging, imaging genomics, clinically-oriented imaging physics and informatics, augmented-reality medical visualization, imaging modalities, computerized radiology, oncology, and surgery. Moreover, information on non-medical imaging that has medical applications such as multi-photon microscopy and confocal, photoacoustic imaging, optical microendoscope, infra-red radiation, and other imaging modalities is also represented.

Abstrak :
This book presents a comprehensive overview of medical image analysis. Practical in approach, the text is uniquely structured by potential applications. Features : presents learning objectives, exercises and concluding remarks in each chapter, in addition to a glossary of abbreviations; describes a range of common imaging techniques, reconstruction techniques and image artefacts, discusses the archival and transfer of images, including the HL7 and DICOM standards, presents a selection of techniques for the enhancement of contrast and edges, for noise reduction and for edge-preserving smoothing, examines various feature detection and segmentation techniques, together with methods for computing a registration or normalisation transformation, explores object detection, as well as classification based on segment attributes such as shape and appearance, reviews the validation of an analysis method, includes appendices on Markov random field optimization, variational calculus and principal component analysis.

Abstrak :
This book constitutes the refereed proceedings of the Second International Workshop on Spatio-temporal Image Analysis for Longitudinal and Time-Series Image Data, STIA 2012, held in conjunction with MICCAI 2012 in Nice, France, in October 2012. The 13 papers presented in this volume were carefully reviewed and selected from 22 submissions. They are organized in topical sections named, longitudinal registration and transport, spatio-temporal analysis for shapes, spatio-temporal analysis under appearance changes, and spatio-temporal analysis for biology.

Abstrak :
The three-volume set LNCS 7510, 7511, and 7512 constitutes the refereed proceedings of the 15th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2012, held in Nice, France, in October 2012. Based on rigorous peer reviews, the program committee carefully selected 252 revised papers from 781 submissions for presentation in three volumes. The third volume includes 79 papers organized in topical sections on diffusion imaging, from acquisition to tractography, image acquisition, segmentation and recognition, image registration, neuroimage analysis, analysis of microscopic and optical images, image segmentation, diffusion weighted imaging, computer-aided diagnosis and planning, and microscopic image analysis.

Abstrak :
The 33 revised full papers presented were carefully reviewed and selected from 67 submissions. The main aim of this workshop is to help advance the scientific research within the broad field of machine learning in medical imaging. It focuses on major trends and challenges in this area, and it presents work aimed to identify new cutting-edge techniques and their use in medical imaging.