{"title":"3D Binary Lesion Mask Parsing","authors":"Yi-Qing Wang, G. Palma","doi":"10.1145/3576938.3576940","DOIUrl":"https://doi.org/10.1145/3576938.3576940","url":null,"abstract":"Liver lesion segmentation is a key module for an automated liver disease diagnosis system. Numerous methods have been developed recently to produce accurate 3D binary lesion masks for CT scans. From the clinical perspective, it is thus important to be able to correctly parse these masks into separate lesion instances in order to enable downstream applications such as lesion tracking and characterization. For the lack of a better alternative, 3D connected component analysis is often used for this task, though it does not always work, especially in the presence of confluent lesions. In this paper, we propose a new method for parsing 3D binary lesion masks and an approach to evaluating its performance. We show that our method outperforms 3D connected component analysis on a large collection of annotated portal-venous phase studies.","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114789696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evaluating the Accuracy of 128-Section Multi-Detector Computed Tomography (MDCT) in Detecting Coronary Artery Stenosis","authors":"Mutasem Kmail, Muntaser S. Ahmad, M. Hjouj","doi":"10.1145/3576938.3576948","DOIUrl":"https://doi.org/10.1145/3576938.3576948","url":null,"abstract":"Catheter-Based Coronary Angiography (CCA) and computed tomography coronary angiography (CTCA) are both used in the diagnosis of coronary artery disease (CAD). The current study aims to evaluate the accuracy of CTCA compared to CCA as a gold standard to find an alternative method to CCA in diagnosing CAD. 65 patients with suspected coronary heart disease underwent CCA and CTCA procedures using 128-section computed tomography (MDCT). The CT images were analyzed by three consultant radiologists with more than 10 years of experience. CCA and CTCA reports were compared, and sensitivity, specificity, positive expected value (PPV) and negative expected value (NPV) were analyzed. These values were found for the 'per artery' and 'per patient' criteria. The results showed that the sensitivity, specificity of PPV, and NPV for accuracy measures of 'per patient' analyzes were 96.8%, 97%, 96.8%, and 97%, respectively. For left main coronary artery (LM), left anterior Descending (LAD), Circumflex artery (CX), and Right Coronary Artery (RCA), the results were 100%, 98.40%, 75%, 100%, 90.6%, 97%, 96.6 %, 91.4% and 61.1%, 100%, 100%, 87% and 73.70%, 97.8%, 93.3%, 90%, respectively with p<.001. The study concluded that it is possible to use MDCT as an alternative part of CCA, which can be used to reduce CCA pain, procedure time, and at a lower cost.","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129798408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Neural Rendering of Confocal Microscopy Images","authors":"Daniel Li","doi":"10.1145/3576938.3576941","DOIUrl":"https://doi.org/10.1145/3576938.3576941","url":null,"abstract":"We present a novel application of neural rendering methods to confocal microscopy. Neural rendering and implicit neural representations have developed at a remarkable pace, and are prevalent in modern 3D computer vision literature. However, they have not yet been applied to optical microscopy, an important imaging field where 3D volume information may be heavily sought after. In this paper, we employ neural rendering on confocal microscopy focus stack data and share the results. We highlight the benefits and potential of adding neural rendering to the toolkit of microscopy image processing techniques.","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128450571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Hjouj, Deema Budeiri, Abrar Rajabi, Sara Abu Khalaf, Deana Jghama
{"title":"Assessment of peak voltage accuracy and reproducibility of conventional X-radiography units in Palestine","authors":"M. Hjouj, Deema Budeiri, Abrar Rajabi, Sara Abu Khalaf, Deana Jghama","doi":"10.1145/3576938.3576947","DOIUrl":"https://doi.org/10.1145/3576938.3576947","url":null,"abstract":"Introduction: All components of diagnostic X-ray system must be committed to a periodic quality control program, in order to achieve accurate and quick diagnosis and low radiation dose to patients, which is the real purpose of medical imaging. Aim and objectives: the main objective of this study is to determine voltage (V) accuracy and reproducibility for the individual diagnostic X-ray units, as well as evaluate if the X-ray units age and average daily load have significant correlation on mean kVp accuracy. Materials and methods: In this experimental study, kVp accuracy and reproducibility tests were performed on 12 conventional X-radiography units (A-1_H-1) in 3 cities in Palestine, which, the tests were conducted according to the relevant acceptance limits recommended by the American Association of Physicists in Medicine (AAPM), using the multiple-purpose analyzer the Radcal Accu pro (model: 9096). Results: The findings revealed that 11 of X-ray units passed the kVp accuracy test (91%), and all the evaluated X-ray units passed the kVp reproducibility test, and there was a weak statistically significant relationship between X-ray unit age and mean kVp accuracy p-value = 0.008, while there was no significant relationship between the Average daily load and the mean kVp accuracy p-value = 0.238 Conclusion: kVp accuracy and reproducibility test are not performed in most of the evaluated X-ray units, while enhancement the performance of quality control programs will lead to a higher degree of professionalism, However Machine age appears to have a major impact on kVp accuracy.","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126492599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An Improved Binary Tomography Reconstruction","authors":"F. Hjouj","doi":"10.1145/3576938.3576944","DOIUrl":"https://doi.org/10.1145/3576938.3576944","url":null,"abstract":"In this paper, the binary tomographic reconstruction problem is considered. Binary tomography aims to reconstruct binary images from their projections. Possible applications can be the field of human X-ray angiography, where the aim is to reconstruct images representing blood vessels or heart chambers, using X-ray tomography methods. Injecting a contrast agent with high linear attenuation coefficient into the part of the body being examined and seek for the presence or absence of the contrast agent in certain positions. Other common applications of this field are electron tomography and industrial non-destructive testing. To reconstruct a binary image from their projections, an improved algebraic approach is proposed in this paper. An energy-minimization reconstruction model is used; this model employs a loss function to be minimized. This loss function combines three features that can be extracted from the given projections. First, data fitting term based on the given projections; second, the first two image moments that are extracted from the given projections; and third, a term that enforces the binary solution. The first two terms are expressed in terms of a linear system and the third is expressed as anon linear cost function. The projected gradient descent algorithm is then employed for this minimization process. Experimental evaluations show that reasonable results can be obtained from minimal number of projections.","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114875229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Detection of Iron in Liver and Myocardial by Magnetic Resonance Imaging","authors":"Bassam Abuarqoub, M. Hjouj","doi":"10.1145/3576938.3576945","DOIUrl":"https://doi.org/10.1145/3576938.3576945","url":null,"abstract":"Background: Magnetic Resonance Imaging (MRI) is a non-invasive modality used to detect the iron overload in the liver and myocardial . The aim of the current study was to assess both Liver Iron Concentration (LIC) and Myocardium Iron Concentration (MIC) for thalassemia major patients using MRI. Methods and sample: The current study dealt with 70 thalassemia patients aged 11-31y. 20 of them, do not suffer from heart disease and do not have a satisfactory history of blood transfusion. cardiac and liver T2* MRI and Serum Ferritin estimation was done for all subjects. Measurements were obtained using (a 1.5T MRI Philips Ingenia ), at the Radiology Department in Hebron Governmental Hospital. Results: The mean Serum Ferritin (SF) among participants was 2150 ng/ml (SD 2179ng/ml). Significant correlation was found in participants between LIC, mean 15mg/g, (dry weight), and SF levels (r = 0.522; p < 0.001), and also significant but weaker correlation was found in patients between MIC, mean 1.3mg/g. (dry weight), and SF levels (r=0.483; p<0.001). Seventeen participants (34%) had a SF of <1000 ng/ml. Of them, 11 and 3 participants respectively had LIC and MIC more than normal range. Conclusions: The relaxation rates R2 (1/T2) and R2* (1/T2*) measured by MRI is a valuable non-invasive tool for quantification of liver and myocardium iron deposition in patients with thalassemia major","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122193209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ahmed. M. AbuAli, Mosab Maree, Ahmed F. Ghanem, Jihad Hamaida, R. Odeh, Husam Salameh, M. Hjouj
{"title":"A Quantitative Prospective Study for Whole Body- Diffusion MRI and PET-CT in Detection of Primary and Metastatic Malignant Lesions","authors":"Ahmed. M. AbuAli, Mosab Maree, Ahmed F. Ghanem, Jihad Hamaida, R. Odeh, Husam Salameh, M. Hjouj","doi":"10.1145/3576938.3576949","DOIUrl":"https://doi.org/10.1145/3576938.3576949","url":null,"abstract":"The idea of an integrated nuclear medicine unit consisting of a PET-CT scanner with a practical source of radioisotopes such as a cyclotron to operate efficiently in Palestinian health system is almost impossible due to several reasons, mainly political and financial issues. The goal of this study is to find a safe, valid, and widely available modality as an alternative to help oncologists and patients; we proposed a whole-body diffusion MRI protocol (WB-DWI MRI) A 33 oncological patients, 60% male (n = 20) and 40% female (n = 13), age 18-74 years with a mean age of 48 years old participated in our study for a PET-CT and WB-DWI MRI scan. Participants already diagnosed to have primary tumors including non-Hodgkin's lymphoma (NHL), Hodgkin's lymphoma, endometrial cancer, prostate cancer, pancreatic cancer, gastric cancer, thyroid cancer, idiopathic pathological fractures and skin lesions suspected to be melanoma. Our results shows that PET-CT demonstrated 181 hypermetabolic lesion distributed in the four zones ( head-neck, chest, abdomen-pelvis and musculoskeletal), was detected by WB-DWI MRI which shows most of the same lesions restricted in diffusion with extra small sub centimeter lesions totally 251 lesions in count with a comparison between standard uptake volume (SUV) and apparent diffusion coefficient ADC) which shows most high SUV( SUV>2.5) have ADC < 1.1 x10-3 mm2/S. Statistical quantitative analysis shows a significant positive correlation between number of detected lesions in the same zone for each patient at p value < 0.05 (p=0.00004) and R-value = 0.5335, a comparative correlation between ADC and SUV shows a significant negative correlation between SUV and ADC at p value < 0.05 and R-value= -0.3073. WB-DWI MRI can replace PET-CT scan in lymphoma cases and tumors follow up to monitor the response for treatment after chemotherapy or radiotherapy either post-surgical resection.","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126308929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Alzubaidi, Marco Agus, Khaled A. Althelaya, M. Makhlouf, Khalid Alyafei, Mowafa J Househ
{"title":"A Composite Image Processing Technique to Enhance Segmentation of Ultrasound Images","authors":"M. Alzubaidi, Marco Agus, Khaled A. Althelaya, M. Makhlouf, Khalid Alyafei, Mowafa J Househ","doi":"10.1145/3576938.3576939","DOIUrl":"https://doi.org/10.1145/3576938.3576939","url":null,"abstract":"In ultrasound images, the speckle noise phenomenon is a typical issue that limits the accuracy of the images obtained from any quantitative measurement. Noise elimination in ultrasound images in the pre-processing stage is an important step to make the image fit for the following steps involved in image segmentation. However, various noises produce a range of significant impacts on the quality of the image and thus tend to affect the interpretation of neural networks. In this study, 35 different image processing techniques, including denoising, feature descriptor, edge detection, miscellaneous, clustering, morphological, sharpening, and composite techniques were used to determine the most optimal ultrasound image in order to improve the segmentation of ultrasound images. The performance of image processing techniques was compared using a statistical parameter, peak signal-to-noise ratio (PSNR). All techniques were examined on deep learning segmentation approach. The segmentation performance was evaluated using mean intersection over union (mIoU) and mean pixel accuracy (mPA). The results showed that the composite image technique (FancyPCA + Bilateral + Gabor) slightly enhanced the segmentation performance, with the most ideal mIoU 0.96893%, mPA 0.97831%, and average PSNR 53.034 dB.","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116393959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Real-time, Visualization and Cloud-Linked Health Monitoring System for Disabled Elderly: Elderly Health Monitoring System","authors":"Liqing Yang, Lin Chen, Lu Liu, Haibo Chen","doi":"10.1145/3576938.3576950","DOIUrl":"https://doi.org/10.1145/3576938.3576950","url":null,"abstract":"With the aging process, the prevalence of chronic diseases and the incidence of disability among the elderly has also increased rapidly. The disabled elderly who are in bed for a long time need long-term monitoring of physiological parameters because of the serious decline of physical function. At the same time, it is also necessary to monitor the surface contact pressure between patients and nursing beds to prevent pressure ulcers. In traditional systems, physiological and stress monitoring are kept separate and are expensive and difficult to operate. Therefore, this paper proposes a real-time, visualization, and cloud-linked disabled elderly monitoring system based on WiFi technology. It can not only monitor physiological parameters in real-time but also monitor surface contact pressure. This system consists of four levels: (1) The sensor terminal nodes collect electrocardiogram (ECG), heart rate (HR), oxygen saturation (SpO2), and collect interface pressure in real-time. (2) The network transport layer adopts WIFI (IEEE 802.11b) protocol. (3) The application layer designs a visual sever written by Qt software. (4) Cloud layer is deployed in the Ali-Cloud IoT server to connect to other cloud medical services. Six subjects took participated in the test and each subject was tested five times. The experimental results demonstrate that the system has a good performance to acquire data, visualize real-time, to connect clouds with a small delay.","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"212 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122648151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Improving Diagnostic Accuracy of Rheumatoid Arthritic by Image Generation Utilizing GAN","authors":"Reo Kojima, T. Goto","doi":"10.1145/3576938.3576946","DOIUrl":"https://doi.org/10.1145/3576938.3576946","url":null,"abstract":"Rheumatoid arthritis is a disease that causes inflammation of joints, destruction of cartilage and bone, loss of joint function, and joint deformation if left untreated. Therefore, this paper proposes a system for detecting abnormalities in rheumatoid arthritis using X-ray images of joints. In addition, we aim to solve the problem that X-ray images of joints, which are medical images, are difficult to obtain, and to improve the accuracy of the diagnosis system and the validity of our system by generating images using GANs.","PeriodicalId":191094,"journal":{"name":"Proceedings of the 2022 5th International Conference on Digital Medicine and Image Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126648634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}