Current image reconstruction techniques in computed tomography (CT) such as filtered back-projection (FBP) and iterative reconstruction (IR) have limited use in low-dose CT imaging due to poor image quality and reconstruction times not fit for clinical implementation. Hence, with the increasing need for radiation dose reductions in CT, the use of artificial intelligence (AI) in image reconstruction has been an area of growing interest.
The aim of this review is to examine the use of AI in CT image reconstruction and its effectiveness in enabling further dose reductions through improvements in image quality of low-dose CT images.
A review of the literature from 2016 to 2020 was conducted using the databases Scopus, Ovid MEDLINE, and PubMed. A subsequent search of several well-known journals was performed to obtain additional information. After careful assessment, articles were excluded if they were not obtainable from the databases or not available in English.
This review found that deep learning-based algorithms demonstrate promising results in improving the image quality of low-dose images through noise suppression, artefact reduction, and structure preservation in addition to optimising IR methods.
In conclusion, with the two AI-based CT systems currently in clinical use showing favourable benefits, it is expected that AI algorithms will continue to proliferate and enable significant dose reductions in CT imaging.
Computed tomography (CT); Artificial Intelligence (AI); Image reconstruction (IN); Machine learning (ML); Deep learning (DL); Dose reduction.
AI: Artificial intelligence; CT: Computed tomography; ML: Machine learning; DL: Deep learning; FBP: Filtered back-projection; IR: Iterative reconstruction; MBIR: Model-based iterative reconstruction; LDCT: Low-dose computed tomography; FDA: U.S Food and Drug Administration; ANN: Artificial neural network; DNN: Deep neural network; CNN: Convolutional neural network; CNR: Contrast-to-noise ratio; SNR: Signal-to-noise ratio.
This study analysed the sensitivity of the field size from variations in the target volume dimensions, depth, and position. The variations in the target volume analysis were used to determine the width of the field size. Thus, the quality control of the radiation beam can be obtained.
Materials and Methods
The computed tomography (CT) image of the IBA Dose 1 type of water phantom consists of 350 slices. Variations in the dimension of the target volume were modelled in 10×10×10 cm3, 10×12×10 cm3, 10.2×10×10.2 cm3, and 15×15×15 cm3. Beam parameters use one beam of irradiation on the central axis 0°, 6 MV energy, 100 cm source-skin distance (SSD), beamlet delta x, and y set to 0.1 cm. Dose distribution in the form of the XZ isodose curve and dose profile was used to observe the field size.
In this study, the isodose curve was successfully displayed in the XZ isodose curve. The field size’s sensitivity has been successfully reviewed from variations of the target volume, depth, and position. The target X and Z direction analysis is used in determining the width and length of the field size.
The analysis related to the field size sensitivity study was obtained from a relatively valid calculation. The field size was evaluated with variations in depth of 1.5 cm, 5 cm, 10 cm, and variations in positions of 10 cm, 12 cm, 14 cm, 18 cm, and 20 cm. This study will be used as a reference to validate the distribution of computational environment for radiotherapy research (CERR) dose in the future. Thus, the accuracy of the dose calculation can be obtained.
2D Dose Distribution; Sensitivity; Quality control; Treatment planning system; Radiation therapy dosimetry.
To read the digital imaging and communications in medicine (DICOM) images of brain and extract intensity values and build a three dimensional model for Monte Carlo n-particle transport (MCNP) code input file in purpose to study the average particle flux and deposited energy of X-Ray photons resulting at 120 kVp and 1 mAs (form point source) as function to DICOM pixel numbers in the brain tissues for a 29-year-old female patient using MCNP code and Matlab program to read the DICOM images.
The matrix laboratory (MATLAB) program was used to read the DICOM images and extract the intensity values in each pixel of the DICOM image corresponding to certain slice of the brain. These color levels are characteristic of different tissue, and have been relied upon to create the specific material in each volume element in MCNP input file.
Values of the deposited energy at surface of skin are high, so it is always necessary to be cautious when performing the examination to obtain acceptable images from the first time and without having to repeat the imaging again for the same case unless there are necessities for it.
Computed tomography (CT); X-ray; Voxel phantom; MCNP Code; Average particle flux; Matlab.
The Breast Imaging-Reporting and Data System (BI-RADS) is a classification system aimed at standardizing risk assessment during breast ultrasound to ensure patient safety. BI-RADS is currently used in Uganda so as to standardize breast ultrasound reporting and enhance patient management.
This study aimed at exploring staff perceptions towards the use of the BI-RADS ultrasound characterization of breast masses.
It was an exploratory qualitative study that involved staff who perform breast ultrasound at Mulago Hospital in Uganda. Focus group discussions and individual interviews were conducted.
All staff used the BI-RADS system, however, some of them had a negative attitude towards BI-RADS. The three major themes that emerged were: standardization of breast ultrasound reporting for patient safety; need for more Continuous Professional Development (CPD) and challenges with the BI-RADS system.
The study demonstrated that the staff generally had positive perceptions and attitude of the BI-RADS system and felt that it was an efficient system for ensuring patient safety and further reduce mortality from breast cancer.
Breast imaging-reporting and data system (BI-RADS); Breast; Ultrasound; Staff perceptions.
Breast cancer is among the most common cancers affecting women worldwide, including Egypt. Age is a well-known determinant of breast cancer risk; however, more data is needed to better understand the importance of age on incidence of breast cancer in the Middle East. Being overweight or obese are also known risk factors—especially for post-menopausal women–however, these data are not available for women in developing countries.
The purpose of this study was to qualitatively explore the association between age, breast density, and demographic factors of breast cancer patients, across a spectrum of radiological breast diagnoses at a large Breast Imaging Clinic in Cairo, Egypt.
We explored the association between age, demographic factors, and Breast cancer incidence among 6,711 women undergoing mammographic screening over a consecutive period of 6-years. Data was collected from March 2007 until March 2013 and extracted
from an electronic data base system.
A total of 6,711 participants were included in this study. The median age of all patients was 46.1. Mean body mass index (BMI) of 28.5, where 34% of the patients were overweight and 32.4% were obese. Older women were more likely to be obese compared to younger women (38.4% vs 18.1%, p<0.001). Older females were more likely to have less dense breasts (ACR: A) compared to younger females (18.1% vs 8.7%, p<0.001). Women older than 40 had a higher confirmed number of breast cancer diagnoses compared with the younger age group (10.7% vs 3.5%, p<0.001). Women with breast cancer were more obese (p<0.001), had denser breasts (p<0.001), were post-menopausal (p=0.002), and more likely to be Muslim (p=0.0021). In the multivariate analysis, aforementioned factors were significant predictors for confirmed diagnosis.
To our knowledge this is the largest study to examine the association of radiological breast assessments on breast cancer incidence, obesity and demographic factors in Egypt. Although data shows the global burden of breast cancer is shifting to the developing world and affecting younger women at alarming rates, our data demonstrated a very low occurrence of breast cancer in both age groups.
Breast cancer; Breast radiological diagnoses; Phenotypic variations; Breast imaging-reporting and data system (BI-RADS).
A 21-year-old male underwent screening for a positive family history of colloid cyst with an MRI scan. This suggested a lesion in the region of the roof of his 3rd ventricle which was confirmed on a computerized tomography (CT) scan as a colloid cyst measuring 6 mm. Seven-years before his evaluation, the patient’s father was found to have an approximately 20 mm colloid cyst with acute hydrocephalus for which he underwent excision. His sister suffered a sudden death at the age of 25. The cause of death was confirmed on autopsy as a colloid cyst which was undiagnosed and associated with acute hydrocephalus. At the time of evaluation, the patient was asymptomatic. On serial imaging in 1-year, there was a definite increase in size of the colloid cyst which now measured 8 mm along its maximum dimension. The colloid cyst also changed in signal intensity appearing more hyperintense on T2-weighted images and fluid-attenuated inversion recovery (FLAIR) sequence. A serial magnetic resonance imaging (MRI) was performed in 18-months as a part of ongoing surveillance with neuroimaging following the first presentation. This demonstrated a decrease in size and change in the shape of the colloid cyst, measuring 5 mm in maximum dimension, with associated decrease in ventricular size and resolution of hydrocephalus suggesting some spontaneous rupture of the colloid cyst. A CT head with unenhanced volume acquisition of the head demonstrated residual partially international organization for standardization (ISO), partially hyperdense colloid cyst seen at the foramen of Monro. This confirmed the findings of MRI with a decrease in size of residual colloid cyst measuring approximately 5 mm in maximal diameter with no residual hydrocephalus.
Neuroradiology; Central nervous system cysts; Colloid cyst; Magnetic resonance imaging; Third ventricle; Foramen of Monro.
Point of care ultrasound (POCUS) has been adopted across many countries as a way of addressing the human resource gap of radiologists and sonographers. It involves providing basic and focused ultrasound skills to non-radiology health care providers to enhance their routine clinical work.
The purpose of this study was to explore the perceptions of radiology professionals about POCUS training.
The study was qualitative, involving radiologists and sonographers who perform ultrasound examinations. Purposive sampling was used to select the participants. Purposive sampling is a type of sampling where participants are selected because they have the knowledge and experience needed to answer the research objective. Focus group discussions and individual interviews were used to collect data and thematic analysis employed.
Participants generally held negative perceptions towards POCUS training. These were reflected in four major themes: 1) Absence of standardized training curriculum; 2) Limited consultations with radiology professionals; 3) Fear of loss of professional identity and 4) Challenges with POCUS training.
The participants felt negatively about POCUS training. For future acceptability, we recommend involvement of radiology professionals in designing a POCUS curriculum as well as having a regulatory mechanism for monitoring the trainees.
Point of care ultrasound (POCUS); Training; Perceptions; Radiology professionals.
Digital tomosynthesis (DT) is a novel imaging modality that has yet to be adopted widespread in Australia, but has potential to enhance patient outcomes both in diagnosis and reducing radiation dose. A review of the literature was performed to develop an introduction to digital tomosynthesis, and identify its uses and viability in general radiography.
Scopus, Ovid, MEDLINE and PubMed were utilised initially to identify literature published within 5-years, using several search terms linked with AND and OR. Articles were assessed according to specific guidelines, and categorised. Journal databases, medical imaging vendor websites, and article references were also evaluated for relevant information.
Based on tomography, digital tomosynthesis is offered as an add-on to general radiographic equipment from general electric (GE), ShimadzuTM and Fujifilm. It’s technology involves a sweep of the X-ray tube over a limited angle onto a stationary flat panel detector. The data is reconstructed to produce multiple slices in the acquisition plane, providing limited depth resolution in a radiographic setting, at a substantially lower dose to computerized tomography (CT) examinations. It’s use has been highlighted in orthopaedic imaging, in detecting occult fractures when radiography has ambiguous results. Additional uses are mainly in surveillance; digital tomosynthesis has higher sensitivity and similar specificity to radiography, and thus can be used to monitor solid lung nodules, nephrolithiasis and deterioration of arthritic conditions.
At a lower cost to CT, digital tomosynthesis has the potential to become a bridging modality from radiography to both save patient dose and reduce their overall waiting times. However, more large-scale studies are required to confirm this.
Digital tomosynthesis (DT); Radiography; Medical imaging; Emerging imaging; Whole body imaging; Tomosynthesis; Future prospects.
Senior MSK Specialty Radiologist
Department of Diagnostic Imaging
Kings College Hospital
Brixton, London SE5 9RS, UK
Departments of Biomedical Science and Morphological and Functional Images
University of Messina, Messina, Italy
Honorary Senior Lecturer
Department of Radiology
University of Sydney
New South Wales 2006, Australia