Wyniki wyszukiwania - BazTech

1

Fast Segmentation of Convex Cyst-like Structures in Gelatin Soft Tissue Phantoms under Ultrasound Imaging with Artifacts and Limited Training Samples

Drozd Dalia, Ciszkiewicz Adam

Advances in Science and Technology. Research Journal

|

2024

|

Vol. 18, no 4

89--96

EN

Ultrasound imaging is common for surgical training and development of medical robotics systems. Recent advancements in surgical training often utilize soft-tissue phantoms based on gelatin, with additional objects inserted to represent different, typically fluid-based pathologies. Segmenting these objects from the images is an important step in the development of training and robotic systems. The current study proposes a simple and fast algorithm for segmenting convex cyst-like structures from phantoms under very low training sample scenarios. The algorithm is based on a custom two-step thresholding procedure with additional post-processing with two trainable parameters. Two large phantoms with convex cysts are created and used to train the algorithm and evaluate its performance. The train/test procedure are repeated 60 times with different dataset splits and prove the viability of the solution with only 4 training images. The DICE coefficients were on average at 0.92, while in the best cases exceeded 0.95, all with fast performance in single-thread operation. The algorithm might be useful for development of surgical training systems and medical robotic systems in general.

2

Common path optical coherence tomography with electronic feedback for improved sensitivity

Alsnaie Khalid

Optica Applicata

|

2023

|

Vol. 53, nr 3

495--504

EN

Optical coherence tomography (OCT) imaging has become a useful tool in medical diagnosis over the past 25 years, because of its ability to visualize intracellular structures at high resolution. The main objective of this work is to add electronic feedback to the optical coherence tomography setup to increase its sensitivity. Noise added to the measured interferogram obscures some details of examined tissue layered structure. Adjusting signal power level in such a way to improve signal-to-noise ratio can help to enhance image quality. Electronic feedback is added to enhance system sensitivity. A logarithmic amplifier is included in the OCT setup to automatically adapt signal level. Moreover, the resolution of the optical spectrum analyzer is controlled according to the farthest layer detected in the A-scan. These techniques are tested showing an improvement in obtained image of a human nail.

3

Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification

Fedoruk Oleksandr, Klimaszewski Konrad, Ogonowski Aleksander, Kruk Michał

Machine Graphics and Vision

|

2023

|

Vol. 32, No. 3/4

107--124

EN

Data augmentation is a popular approach to overcome the insufficiency of training data for medical imaging. Classical augmentation is based on modification (rotations, shears, brightness changes, etc.) of the images from the original dataset. Another possible approach is the usage of Generative Adversarial Networks (GAN). This work is a continuation of the previous research where we trained StyleGAN2-ADA by Nvidia on the limited COVID-19 chest X-ray image dataset. In this paper, we study the dependence of the GAN-based augmentation performance on dataset size with a focus on small samples. Two datasets are considered, one with 1000 images per class (4000 images in total) and the second with 500 images per class (2000 images in total). We train StyleGAN2-ADA with both sets and then, after validating the quality of generated images, we use trained GANs as one of the augmentations approaches in multi-class classification problems. We compare the quality of the GAN-based augmentation approach to two different approaches (classical augmentation and no augmentation at all) by employing transfer learning-based classification of COVID-19 chest X-ray images. The results are quantified using different classification quality metrics and compared to the results from the previous article and literature. The GAN-based augmentation approach is found to be comparable with classical augmentation in the case of medium and large datasets but underperforms in the case of smaller datasets. The correlation between the size of the original dataset and the quality of classification is visible independently from the augmentation approach.

4

Improving Quality of Watermarked Medical Images Using Symmetric Dilated Convolution Neural Networks

Pulgam Namita D., Shinde Subhash K.

Journal of Telecommunications and Information Technology

|

2023

|

nr 2

46--52

EN

Rapid development of online medical technologies raises questions about the security of the patient’s medical data.When patient records are encrypted and labeled with a watermark, they may be exchanged securely online. In order to avoid geometrical attacks aiming to steal the information, image quality must be maintained and patient data must be appropriately extracted from the encoded image. To ensure that watermarked images are more resistant to attacks (e.g. additive noise or geometric attacks), diﬀerent watermarking methods have been invented in the past. Additive noise causes visual distortion and render the potentially harmful diseases more diﬃcult to diagnose and analyze. Consequently, denoising is an important pre-processing method for obtaining superior outcomes in terms of clarity and noise reduction and allows to improve the quality of damaged medical images. Therefore, various publications have been studied to understand the denoising methods used to improve image quality. The ﬁndings indicate that deep learning and neural networks have recently contributed considerably to the advancement of image processing techniques. Consequently, a system has been created that makes use of machine learning to enhance the quality of damaged images and to facilitate the process of identifying speciﬁc diseases. Images, damaged in the course of an assault, are denoised using the suggested technique relying on a symmetric dilated convolution neural network. This improves the system’s resilience and establishes a secure environment for the exchange of data while maintaining secrecy.

5

Melanoma skin cancer and nevus mole classification using intensity value estimation with convolutional neural network

Ashafuddula N. I. Md., Islam Rafiqul

Computer Science

|

2023

|

T. 24 (3)

277--296

EN

Melanoma skin cancer is one of the most dangerous and life-threatening cancer. Exposure to ultraviolet rays may damage the skin cell's DNA, which can causes melanoma skin cancer. However, detecting and classifying melanoma and nevus moles at their immature stages is difficult. In this work, an automatic deep-learning system has been developed based on intensity value estimation with a convolutional neural network model (CNN) for detecting and classifying melanoma and nevus moles more accurately. Since intensity levels are the most distinctive features for identifying objects or regions of interest, high-intensity pixel values have been selected from extracted lesion images. Incorporating those high-intensity features into CNN improves the overall performance of the proposed model than the state-of-the-art methods for detecting melanoma skin cancer. To evaluate the system, we used five-fold cross-validation. The experimental results showed that superior percentages of accuracy (92.58%), sensitivity (93.76%), specificity (91.56%), and precision (90.68%) were achieved.

6

Soft computing techniques-based digital video forensics for fraud medical anomaly detection

Nanda Sunpreet Kaur, Ghai Deepika, Ingole P.V., Pande Sagar

Computer Assisted Methods in Engineering and Science

|

2023

|

Vol. 30, no. 2

111--130

EN

The current pandemic situation has made it important for everyone to wear masks. Digital image forensics plays an important role in preventing medical fraud and in object detection. It is helpful in avoiding the high-risk situations related to the health and security of the individuals or the society, including getting the proper evidence for identifying the people who are not wearing masks. A smart system can be developed based on the proposed soft computing technique, which can be helpful to detect precisely and quickly whether a person wears a mask or not and whether he/she is carrying a gun. The proposed method gave 100% accurate results in videos used to test such situations. The system was able to precisely differentiate between those wearing a mask and those not wearing a mask. It also effectively detects guns, which can be used in many applications where security plays an important role, such as the military, banks, etc.

7

Optimization of the WLS design for positron emission mammography and Total-Body J-PET systems

Georgadze Anzori, Shivani Shivani, Ardebili Keyvan Tayefi, Moskal Paweł

Bio-Algorithms and Med-Systems

|

2023

|

Vol. 19, no. 1

114--123

EN

Total-body positron emission tomography (PET) instruments are medical imaging devices that detect and visualize metabolic activity in the entire body. The PET scanner has a ring-shaped detector that surrounds the patient and detects the gamma rays emitted by the tracer as it decays. Usually these detectors are made up of scintillation crystals coupled to photodetectors that convert the light produced by the scintillation crystal into electrical signals. Jagiellonian Positron Emission Mammograph (J-PEM) is the first J-PET prototype module based on a novel idea with a plastic scintillator and wavelength shifter (WLS). At the same time, it is a prototype module for the Total-Body J-PET system. J-PEM can be an effective system for the detection and diagnosis of breast cancer in its early stage by improving sensitivity. This can be achieved using the superior timing properties of plastic scintillators combined with the WLS sheets readout. In this paper we present an application of the Geant4 program for simulating optical photon transport in the J-PEM module. We aim to study light transport within scintillator bars and WLS sheets to optimize gamma-ray hit position resolution. We simulated a pencil beam of 511 keV photons impinging the scintillator bar at different locations. For each condition we calculated the value of the pulse height centroid and the spread of the photon distribution. Some free parameters of the simulation, like reflectivity and the effective attenuation length in the sheet, were determined from a comparison to experimental data. Finally, we estimated the influence of the application of WLS layer in the Total-Body J-PET on the scatter fraction. To optimize the performance of the J-PEM module we compared geometry WLS strips 50 and 83. It was found that spatial resolution was 2.7 mm and 3.5 mm FWHM for 50 and 83 WLS strips, respectively. Despite the better granularity, the 83-strip WLS geometry exhibited poorer resolution due to fewer photons being transmitted to the strip, resulting in large fluctuations of signal.

8

Exploration of simultaneous dual-isotope imaging with multiphoton modular J-PET scanner

Beyene Ermias Y., Das Manish, Durak-Kozica Martyna, Korcyl Grzegorz, Mryka Wiktor, Niedźwiecki Szymon, Parzych Szymon, Tayefi Keyvan, Walczak Rafał, Wawrowicz Kamil, Stępien Ewa, Moskal Pawel

Bio-Algorithms and Med-Systems

|

2023

|

Vol. 19, no. 1

101--108

EN

The modular J-PET scanner, comprising 24 compact and versatile modules, each consisting of 13 plastic strips with four SiPM detectors at the ends, represents a powerful tool for clinical applications in nuclear medical imaging. This study presents preliminary results from the exploration of simultaneous dual-isotope imaging using the modular J-PET system. Our approach involved two isotopes: 68Ge, characterized by a ringlike shape, and 22Na, exhibiting a point-like shape. The imaging was based on double-coincidence and triple-coincidence events. In the double coincidence case, both isotopes contributed comparably, whereas in the triple coincidence case 22Na dominated due to the prompt gamma being emitted with 100% of positron emissions, unlike 68Ga, where the prompt gamma was emitted in only 1.3% of cases after positron emission. In this work we present direct 2γ images determined for two-signal events and images for three-signal events, with two signals from annihilation photons and one from a prompt gamma. These results showcase the preliminary findings from simultaneous dual-isotope imaging of 68Ga and 22Na isotopes using the modular J-PET scanner, which will be presented and discussed.

9

Evaluation of Modular J-PET sensitivity

Tayefi Ardebili Faranak, Niedźwiecki Szymon, Moskal Paweł

Bio-Algorithms and Med-Systems

|

2023

|

Vol. 19, no. 1

132--138

EN

The Modular J-PET represents the latest advancement in the Jagiellonian-PET series, utilizing extended plastic scintillator strips. This prototype's modular design enables cost-effective imaging of multi-photon annihilation and positronium, allowing for easy assembly, portability, and versatility. Additionally, its lightweight construction facilitates static bed examinations with a mobile detection system that can be positioned conveniently alongside the patient, negating the requirement for spacious clinical settings. Comprising 24 modules arranged in regular 24-sided polygons circumscribing a 73.9 cm diameter circle, each module integrates 13 scintillator strips, measuring 50 cm in length and 6 mm × 24 mm in cross-section. Scintillation light is captured at both ends through analog Silicon Photomultipliers (SiPMs). This research presents Sensitivity of the Modular J-PET tomograph, adhering to the NEMA_NU 2-2018 standards. Sensitivity measurement was performed with 68Ge line source inside the 5 sleeves aluminium phantom placed at center of the detector`s field-of-view (FOV) and 10 cm offset from the center of detector. Analyzing the gathered data involved employing the specialized J-PET Framework software, developed within the C++ architecture. To validate the experimental findings, comparisons were made with GATE simulations, wherein the source and phantom were emulated in the same configuration as employed in the actual experiment. The system sensitivity of the Modular J-PET was assessed to be 1.03 ± 0.02 cps/kBq in the center of the detector`s FOV with the peak sensitivity of 2.1 cps/kBq. However, the simulations indicate that at the center of the detector's FOV, the Modular J-PET achieves a system sensitivity of 1.32 ± 0.03 cps/kBq, with a peak sensitivity of 2.9 cps/kBq.

10

Estimating the efficiency and purity for detecting annihilation and prompt photons for positronium imaging with J-PET using toy Monte Carlo simulation

Das Manish, Mryka Wiktor, Beyene Ermias Y., Parzych Szymon, Sharma Sushil, Stępień Ewa, Moskal Paweł

Bio-Algorithms and Med-Systems

|

2023

|

Vol. 19, no. 1

87--95

EN

The positronium imaging technique represents a potential enhancement of the PET imaging method. Its core principle involves employing a β+ radiation source that emits additional gamma (γ) quanta referred to as prompt gamma. Our aim is to evaluate the capability to differentiate between annihilation and prompt gamma emissions, a vital aspect of positronium imaging. For this purpose, the selected isotopes should enable high efficiency and purity in detecting both prompt gamma and annihilation gamma. The assessment of the efficiency in identifying prompt and annihilation photons for various isotopes, which are potentially superior candidates for β++ γ emitters, is conducted through toy Monte-Carlo simulation utilizing the cross-section formula for photon-electron scattering. In this article, we have performed calculations for efficiency and purity values across different isotopes under ideal conditions and examined how these values evolve as we incorporate the fractional energy resolution into the analysis. Ultimately, the primary goal is to determine the energy threshold that optimizes both efficiency and purity, striking a balance between accurately identifying and recording events of interest while minimizing contamination from undesired events.

11

Efficiency analysis and promising applications of silicon drift detectors

Khreptak Aleksander, Skurzok Magdalena

Bio-Algorithms and Med-Systems

|

2023

|

Vol. 19, no. 1

74--79

EN

Silicon drift detectors (SDDs) stand as a groundbreaking technology with a diverse range of applications, particularly in the fields of physics and medical imaging. This paper provides an analysis of the performance of SDDs as detectors for X-ray radiation measurement, shedding light on their exceptional capabilities and potential in medical imaging. Compared to conventional detectors, SDDs have several notable advantages. Their high efficiency in capturing X-rays allows them to provide outstanding sensitivity and accuracy in detecting even low-energy X-rays. In addition, SDDs exhibit significantly low electronic-noise levels, contributing to better signal-to-noise ratio and better data quality. Furthermore, their high resolution enables exact spatial localization of radiation sources, which is essential for accurate diagnosis. This research is devoted to the evaluation of efficiency and potential application of SDDs in X-ray spectroscopy, with particular emphasis on their application in medical imaging. We focus on evaluating the performance characteristics of SDDs, such as their linearity, stability and sensitivity in detecting X-rays. The aim is to highlight the suitability of SDDs for a wide range of applications.

12

A cross-staged gantry for total-body PET and CT imaging

Kaplanoğlu Muhammed Tevfik, Moskal Paweł

Bio-Algorithms and Med-Systems

|

2023

|

Vol. 19, no. 1

109--113

EN

Total-body Positron Emission Tomography (PET) scanning is a promising new method for rapidly acquiring comprehensive wide-volume metabolic data with a lower radiation dosage compared to discrete whole-body PET imaging. PET scanners are generally used with Computed Tomography (CT) scanners to precisely understand tumor location and composition with the help of anatomical images. However, PET/CT sequential imaging methods for simultaneous total-body imaging are impractical for claustrophobic patients due to the enclosed gantry design and require large examination rooms because of the need for an exceptionally long patient table. To address this challenge, the Jagiellonian-PET Tomography (J-PET) Total-body scanner employs an innovative approach: utilizing both PET and CT devices on the same patient table but from different axes. The motion system of the J-PET Total Body scanner requires custom linear stages to move both PET and CT gantries. In this study, a novel cross-staged linear guiding solution is proposed by combining scanners on intersecting separable stages. The proposed sliding system is a combination of different machine elements and will be produced for the J-PET Total-body PET/CT Scanner. Concept designs are shown, and the proposed system is described. The application of the system for the J-PET total-body PET/CT scanner is discussed. The proposed solution is still in the development phase. The system holds the potential to achieve combining CT and PET scanners from different axes and enables motion artifact-free imaging for total-body imaging.

13

Aplikacja do przetwarzania obrazów medycznych z wizualizacją przestrzenną

Krzyżanowski Andrzej, Poczekajło Paweł

Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej

|

2022

|

Nr 75

23--26

PL

W pracy przedstawiono opracowanie prototypu aplikacji umożliwiającej przegląd i przetwarzanie trójwymiarowych (3D) obrazów medycznych. Aplikacja umożliwia płynne wyświetlanie przekrojów 2D obiektu wzdłuż każdej z osi (x,y,z) oraz za pomocą algorytmu renderingu wolumetrycznego pozwala na wyświetlenie obiektu w 3D. Dodatkowo poprzez wykorzystanie efektu odbicia na ścianach bryły o kształcie ściętego ostrosłupa aplikacja umożliwia uzyskanie obrazu 3D, jako wizualizacji przestrzennej. Praca zawiera dokładny opis algorytmu generującego tekstury 2D i 3D pozwalające na wyświetlenie obiektu, omówienie funkcjonalności wraz z instrukcją użytkowania, a także na przykładzie wykorzystania zestawu deweloperskiego Jetson Nano 2GB propozycję konfiguracji zestawu prototypowego do wyświetlania obrazów medycznych. W podsumowaniu pracy omówiono pomysł wykorzystania aplikacji w celach edukacyjnych oraz możliwości dalszego jej rozwoju.

EN

The article presents the development of a prototype of an application enabling the review and processing of medical images. The application enables the smooth display of 2D sections of an object along each axis (x, y, z) and, using the volumetric rendering algorithm, it enables the object to be displayed in 3D. In addition, by using the reflection effect on the walls of a solid in the shape of a truncated pyramid, the application allows you to obtain a 3D image as a 3D visualization. The work contains a detailed description of the algorithm that generates 2D and 3D textures that allow displaying the object, discusses the functionality with the instructions for use, and uses the Jetson Nano 2GB development kit as an example, a proposal to configure a prototype set for displaying medical images. The summary of the work presents the idea of using the application for educational purposes and the possibility of its further development.

14

Związki kompleksowe na bazie Gd(III), W(IV), Mn(II), Eu(III) i 99mTc wykorzystywane w diagnostyce medycznej

Pobłocki Kacper, Drzeżdżon Joanna, Jacewicz Dagmara Elżbieta

Wiadomości Chemiczne

|

2022

|

[Z] 76, 9-10

803--823

EN

Recently, hospitals have undergone major changes. Minimally invasive surgery is becoming more common, and numerous innovations are emerging, such as interventional radiology (IVR) and hybrid surgery. In order to keep pace with changes in this extremely dynamic field, scientist keep working on the development of imaging technology and the improvement of image display devices and new compounds acting as contrast agent (CA). In medicine, metals are used for diagnostic and therapeutic purposes. Inorganic elements are increasingly used as contrast agents in medical imaging due to their unique physicochemical properties. In this review, we would like to focus on the latest literature reports that contain information on Gd(III), W(IV), Mn(II), Eu(III) and 99mTc used in medical diagnostics.

15

Image reconstruction for lung monitoring in wearable electrical impedance tomography

Wójcik Dariusz, Stefaniak Barbara, Woś Michał, Kiczek bartłomiej, Rymarczyk Tomasz

Przegląd Elektrotechniczny

|

2022

|

R. 98, nr 3

106--109

EN

This work presents a method for measuring and reconstructing human lungs using a waistcoat with an integrated impedance tomograph. The reconstructions obtained make it possible to follow the patient's breathing and, in the case of a 3D model, to determine whether there is fluid in the patient's lungs. The numerical model involves minimising the functional, determining the simulation and the form of the sensitivity matrix. In order to perform the tests, a portable impedance tomography system for biomedical applications was constructed, consisting of a measuring belt and a portable device made of flexible material with 32 round electrodes installed. This solution allows imaging of lung lesions by defining a model and solving the inverse problem using the finite element method.

PL

Praca przedstawia metodę pomiaru i rekonstrukcji ludzkich płuc przy użyciu kamizelki z wbudowanym tomografem impedancyjnym. Uzyskane rekonstrukcje pozwalają na śledzenie oddychania pacjenta a w przypadku 3D model pozwala stwierdzić czy w płucach pacjenta znajduje się płyn. Model numeryczny polega na minimalizacji funkcjonału, wyznaczaniu symulacji i postaci macierzy wrażliwości. W celu wykonania badań skonstruowano przenośny system tomografii impedancyjnej do zastosowań biomedycznych składający się z pasa pomiarowego oraz przenośnego urządzenia wykonane z elastycznego materiału z zainstalowanymi 32 okrągłymi elektrodami. Takie rozwiązanie umożliwia obrazowanie zmian w płucach poprzez zdefiniowanie modelu i rozwiązując problem odwrotny z wykorzystaniem metody elementów skończonych.

16

3D lung segmentation of the CT series based on 2D Chan-Vese

Maciura Łukasz, Rosa Wojciech, Wójcik Dariusz, Rymarczyk Tomasz, Maj Michał, Kozłowski Edward

Przegląd Elektrotechniczny

|

2022

|

R. 98, nr 5

165--168

EN

This paper presents a new 3D segmentation algorithm for lung segmentation tasks on CT series. The algorithm consists of a 2D stage (for each slice) which is performed parallelly and 3D postprocessing after merging to 3D. The 2D stage consists of 2D preprocessing, Chan - Vese segmentation, and 2D postprocessing. This algorithm was tested on the set of 60 CT series containing labelled data enable to its assessment. The results of the algorithm are close to deep learning approaches. This algorithm will be an element of a commercial expert system for medical applications where some patient assessment will be necessary based on segmented human organs.

PL

Ten artykuł prezentuje nowy algorytm segmentacji 3D do zadań segmentacji płuc na seriach z tomografii komputerowej. Ten algorytm składa się z etapu 2D (dla każdego przekroju) który jest wykonywany równolegle i post-processingu 3D po scaleniu wyników do 3D. Etap 2D składa się z pre-processingu 2D, segmentacji Chan – Vese I post-processingu 2D. Algorytm był przetestowany na zbiorze 60 serii obtazów z tomografii komputerowej zawierających zaetykietowane dane co umożliwiło jego ocenę. Wyniki algorytmu są przybliżonej dokładności do rozwiązań deep learning. Algorytm ten będzie elementem komercyjnego system ekspertowego do zastosowań medycznych, gdzie niezbędna będzie ocena pacienta bazując na segmentowanych organach człowieka.

17

Detection of pneumonia using convolutional neural networks and deep learning

Szepesi Patrik, Szilágyi László

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

1012--1022

EN

The objective and automated detection of pneumonia represents a serious challenge in medical imaging, because the signs of the illness are not obvious in CT or X-ray scans. Further on, it is also an important task, since millions of people die of pneumonia every year. The main goal of this paper is to propose a solution for the above mentioned problem, using a novel deep neural network architecture. The proposed novelty consists in the use of dropout in the convolutional part of the network. The proposed method was trained and tested on a set of 5856 labeled images available at one of Kaggle’s many medical imaging challenges. The chest X-ray images (anterior-posterior) were selected from retrospective cohorts of pediatric patients, aged between one and five years, from Guangzhou Women and Children’s Medical Center, Guangzhou, China. Results achieved by our network would have placed first in the Kaggle competition with the following metrics: 97.2% accuracy, 97.3% recall, 97.4% precision and AUC ₌ 0:982, and they are competitive with current state-of-the-art solutions.

18

Automated diagnosis of COVID stages from lung CT images using statistical features in 2-dimensional flexible analytic wavelet transform

Patel Rajneesh Kumar, Kashyap Manish

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

829--841

EN

TheCOVID-19 epidemic has been causing a global problem since December 2019.COVID-19 is highly contagious and spreads rapidly throughout the world. Thus, early detection is essential. The progression of COVID-19 lung illness has been demonstrated to be aided by chest imaging. The respiratory system is the most vulnerable component of the human body to the COVID virus. COVID can be diagnosed promptly and accurately using images from a chest X-ray and a computed tomography scan. CT scans are preferred over X-rays to rule out other pulmonary illnesses, assist venous entry, and pinpoint any new heart problems. The traditional and trending tools are physical, time-inefficient, and not more accurate. Many techniques for detecting COVID utilizing CT scan images have recently been developed, yet none of them can efficiently detect COVID at an early stage. We proposed a two-dimensional Flexible analytical wavelet transform (FAWT) based on a novel technique in this work. This method is decomposed pre-processed images into sub-bands. Then statistical-based relevant features are extracted, and principal component analysis (PCA) is used to identify robust features. After that, robust features are ranked with the help of the Student’s t-value algorithm. Finally, features are applied to Least Square-SVM (RBF) for classification. According to the experimental outcomes, our model beat state-of-the-art approaches for COVID classification. This model attained better classification accuracy of 93.47%, specificity 93.34%, sensitivity 93.6% and F1-score 0.93 using tenfold cross-validation.

19

Multi-photon time-of-flight MLEM application for the positronium imaging in J-PET

Shopa Roman Y., Dulski Kamil

Bio-Algorithms and Med-Systems

|

2022

|

Vol. 18, no. 1

135--143

EN

We develop a positronium imaging method for the Jagiellonian PET (J-PET) scanners based on the timeof-flight maximum likelihood expectation maximisation (TOF MLEM). The system matrix elements are calculated on-the-fly for the coincidences comprising two annihilation and one de-excitation photons that originate from the ortho-positronium (o-Ps) decay. Using the Geant4 library, a Monte Carlo simulation was conducted for four cylindrical 22Na sources of β+ decay with diverse o-Ps mean lifetimes, placed symmetrically inside the two JPET prototypes. The estimated time differences between the annihilation and the positron emission were aggregated into histograms (one per voxel), updated by the weights of the activities reconstructed by TOF MLEM. The simulations were restricted to include only the o-Ps decays into back-to-back photons, allowing a linear fitting model to be employed for the estimation of the mean lifetime from each histogram built in the log scale. To suppress the noise, the exclusion of voxels with activity below 2% - 10% of the peak was studied. The estimated o-Ps mean lifetimes were consistent with the simulation and distributed quasi-uniformly at high MLEM iterations. The proposed positronium imaging technique can be further upgraded to include various correction factors, as well as be modified according to realistic o-Ps decay models.

20

Multi-molecule imaging and inter-molecular imaging in nuclear medicine

Shimazoe Kenji, Uenomachi Mizuki

Bio-Algorithms and Med-Systems

|

2022

|

Vol. 18, no. 1

127--134

EN

Multi-molecule imaging and inter-molecular imaging are not fully implemented yet, however, can become an alternative in nuclear medicine. In this review article, we present arguments demonstrating that the advent of the Compton positron emission tomography (Compton-PET) system and the invention of the quantum chemical sensing method with double photon emission imaging (DPEI) provide realistic perspectives for visualizing inter-molecular and multi-molecule in nuclear medicine with MeV photon. In particular, the pH change of InCl3 solutions can be detected and visualized in a three-dimensional image by combining the hyperfine electric quadrupole interaction sensing and DPEI. Moreover, chemical states, such as chelating, can be detected through angular correlation sensing. We argue that multi-molecule and chemical sensing could be a realistic stream of research in future nuclear medicine.