Africa's readiness for artificial intelligence in clinical radiotherapy delivery: Medical physicists to lead the way.

BACKGROUND: There have been several proposals by researchers for the introduction of Artificial Intelligence (AI) technology due to its promising role in radiotherapy practice. However, prior to the introduction of the technology, there are certain general recommendations that must be achieved. Also, the current challenges of AI must be addressed. In this review, we assess how Africa is prepared for the integration of AI technology into radiotherapy service delivery. METHODS: To assess the readiness of Africa for integration of AI in radiotherapy services delivery, a narrative review of the available literature from PubMed, Science Direct, Google Scholar, and Scopus was conducted in the English language using search terms such as Artificial Intelligence, Radiotherapy in Africa, Machine Learning, Deep Learning, and Quality Assurance. RESULTS: We identified a number of issues that could limit the successful integration of AI technology into radiotherapy practice. The major issues include insufficient data for training and validation of AI models, lack of educational curriculum for AI radiotherapy-related courses, no/limited AI teaching professionals, funding, and lack of AI technology and resources. Solutions identified to facilitate smooth implementation of the technology into radiotherapy practices within the region include: creating an accessible national data bank, integrating AI radiotherapy training programs into Africa's educational curriculum, investing in AI technology and resources such as electronic health records and cloud storage, and creation of legal laws and policies to support the use of the technology. These identified solutions need to be implemented on the background of creating awareness among health workers within the radiotherapy space. CONCLUSION: The challenges identified in this review are common among all the geographical regions in the African continent. Therefore, all institutions offering radiotherapy education and training programs, management of the medical centers for radiotherapy and oncology, national and regional professional bodies for medical physics, ministries of health, governments, and relevant stakeholders must take keen interest and work together to achieve this goal.

A GATE Monte Carlo framework for dosimetric evaluation in mammography in an Algerian hospital.

A framework has been developed for dosimetric evaluation in mammography, using the GATE Monte Carlo (MC) platform, to simulate a MAMMOMAT 3000 Nova mammograph (Siemens) available at the University Hospital Center "1st November 1954" of Oran (EHU Oran 1er Novembre, 1954), Algeria. Calculated quantities such half-value layer (HVL), Entrance Surface Dose (ESD) and Mean Glandular Dose (MGD) have been compared to experimental data in order to validate the modeling of mammography examinations. Results are consistent with previous studies and show a good agreement between measurements and Monte Carlo calculations. By varying the tube voltage from 25 to 35 kV, we have estimated an increasing of a factor of 2.4 in ESD, and a factor of 2.75 for the MGD in a breast phantom. Furthermore, the current intensity of 100 mAs used for a beam quality combination (Mo/Mo) Anode/filter was found suitable for the tube voltages of 25-29 keV since the MGD does not exceed the limits set by the different quality insurance protocols. This GATE dose calculation framework thus provides a very useful tool for the optimization of mammography examinations at Oran hospital by allowing a better estimation of the dose delivered to patients according to the parameters of the examination.

ADULT CT EXAMINATIONS IN ALGERIA: TOWARDS UPDATING NATIONAL DIAGNOSTIC REFERENCE LEVELS.

A pilot study has concerned the most frequent computed tomography examinations (CT). This represents the first results based on actual survey for diagnostic reference levels (DRLs) establishment in Algeria. A total number of 2540 patients underwent this survey that has included the recording of CT parameters, computed tomography dose index (CTDIvol) and dose-length product of the head, thorax, abdomen, abdomen-pelvis (AP), lumbar spine (LS) and thorax-abdomen-pelvis (TAP) performed on standard patients. The proposed DRLs are 71 mGy/1282 mGy.cm for head, 16 mGy/555 mGy.cm for thorax, 18 mGy/671 mGy.cm for abdomen, 21 mGy/950 mGy.cm for AP, 36 mGy/957 mGy.cm for LS and 18 mGy/994 mGy.cm for TAP. The rounded 75th percentile seems to be higher in some examinations compared to the literature. Our findings confirm the need to optimise our practice. These results provide a starting point for institutional evaluation of CT radiation doses.

IAEA survey of paediatric computed tomography practice in 40 countries in Asia, Europe, Latin America and Africa: procedures and protocols.

OBJECTIVE: To survey procedures and protocols in paediatric computed tomography (CT) in 40 less resourced countries. METHODS: Under a project of the International Atomic Energy Agency, 146 CT facilities in 40 countries of Africa, Asia, Europe and Latin America responded to an electronic survey of CT technology, exposure parameters, CT protocols and doses. RESULTS: Modern MDCT systems are available in 77 % of the facilities surveyed with dedicated paediatric CT protocols available in 94 %. However, protocols for some age groups were unavailable in around 50 % of the facilities surveyed. Indication-based protocols were used in 57 % of facilities. Estimates of radiation dose using CTDI or DLP from standard CT protocols demonstrated wide variation up to a factor of 100. CTDI(vol) values for the head and chest were between two and five times those for an adult at some sites. Sedation and use of shielding were frequently reported; immobilisation was not. Records of exposure factors were kept at 49 % of sites. CONCLUSION: There is significant potential for improvement in CT practice and protocol use for children in less resourced countries. Dose estimates for young children varied widely. This survey provides critical baseline data for ongoing quality improvement efforts by the IAEA.

IAEA survey of pediatric CT practice in 40 countries in Asia, Europe, Latin America, and Africa: Part 1, frequency and appropriateness.

OBJECTIVE: The purpose of this study was to assess the frequency of pediatric CT in 40 less-resourced countries and to determine the level of appropriateness in CT use. MATERIALS AND METHODS: Data on the increase in the number of CT examinations during 2007 and 2009 and appropriate use of CT examinations were collected, using standard forms, from 146 CT facilities at 126 hospitals. RESULTS: The lowest frequency of pediatric CT examinations in 2009 was in European facilities (4.3%), and frequencies in Asia (12.2%) and Africa (7.8%) were twice as high. Head CT is the most common CT examination in children, amounting to nearly 75% of all pediatric CT examinations. Although regulations in many countries assign radiologists with the main responsibility of deciding whether a radiologic examination should be performed, in fact, radiologists alone were responsible for only 6.3% of situations. Written referral guidelines for imaging were not available in almost one half of the CT facilities. Appropriateness criteria for CT examinations in children did not always follow guidelines set by agencies, in particular, for patients with accidental head trauma, infants with congenital torticollis, children with possible ventriculoperitoneal shunt malfunction, and young children (< 5 years old) with acute sinusitis. In about one third of situations, nonavailability of previous images and records on previously received patient doses have the potential to lead to unnecessary examinations and radiation doses. CONCLUSION: With increasing use of CT in children and a lack of use of appropriateness criteria, there is a strong need to implement guidelines to avoid unnecessary radiation doses to children.

Radiation exposure to patients during interventional procedures in 20 countries: initial IAEA project results.

OBJECTIVE: The purpose of our study was to investigate the level of radiation protection of patients and staff during interventional procedures in 20 countries of Africa, Asia, and Europe. SUBJECTS AND METHODS: In a multinational prospective study, information on radiation protection tools, peak skin dose (PSD), and kerma-area product (KAP) was provided by 55 hospitals in 20 mainly developing countries (nine mostly in Eastern Europe, five in Africa, and six in Asia). RESULTS: Nearly 40% of the interventional rooms had an annual workload of more than 2,000 patients. It is remarkable that the workload of pediatric interventional procedures can reach the levels of adult procedures even in developing countries. About 30% of participating countries have shown a 100% increase in workload in 3 years. Lead aprons are used in all participating rooms. Even though KAP was available in almost half of the facilities, none had experience in its use. One hundred of 505 patients monitored for PSD (20%) were above the 2-Gy threshold for deterministic effects. CONCLUSION: Interventional procedures are increasing in developing countries, not only for adults but also for pediatric patients. The situation with respect to staff protection is considered generally acceptable, but this is not the case for patient protection. Many patients exceeded the dose threshold for erythema. A substantial number (62%) of percutaneous transluminal coronary angioplasty procedures performed in developing countries in this study are above the currently known dose reference level and thus could be optimized. Therefore, this study has significance in introducing the concept of patient dose estimation and dose management.

Effects of energy spectrum on dose distribution calculations for high energy electron beams.

In an early work we have demonstrated the possibility of using Monte Carlo generated pencil beams for 3D electron beam dose calculations. However, in this model the electron beam was considered as monoenergetic and the effects of the energy spectrum were taken into account by correction factors, derived from measuring central-axis depth dose curves. In the present model, the electron beam is considered as polyenergetic and the pencil beam distribution of a clinical electron beam, of a given nominal energy, is represented as a linear combination of Monte Carlo monoenergetic pencil beams. The coefficients of the linear combination describe the energy spectrum of the clinical electron beam, and are chosen to provide the best-fit between the calculated and measured central axis depth dose, in water. The energy spectrum is determined by the constrained least square method. The angular distribution of the clinical electron beam is determined by in-air penumbra measurements. The predictions of this algorithm agree very well with the measurements in the region near the surface, and the discrepancies between the measured and calculated dose distributions, behind 3D heterogeneities, are reduced to less than 10%. We have demonstrated a new algorithm for 3D electron beam dose calculations, which takes into account the energy spectra. Results indicate that the use of this algorithm leads to a better modeling of dose distributions downstream, from complex heterogeneities.