Is deep learning-enabled real-time personalized CT dosimetry feasible using only patient images as input?

PURPOSE: To propose a novel deep-learning based dosimetry method that allows quick and accurate estimation of organ doses for individual patients, using only their computed tomography (CT) images as input. METHODS: Despite recent advances in medical dosimetry, personalized CT dosimetry remains a labour-intensive process. Current state-of-the-art methods utilize time-consuming Monte Carlo (MC) based simulations for individual organ dose estimation in CT. The proposed method uses conditional generative adversarial networks (cGANs) to substitute MC simulations with fast dose image generation, based on image-to-image translation. The pix2pix architecture in conjunction with a regression model was utilized for the generation of the synthetic dose images. The lungs, heart, breast, bone and skin were manually segmented to estimate and compare organ doses calculated using both the original and synthetic dose images, respectively. RESULTS: The average organ dose estimation error for the proposed method was 8.3% and did not exceed 20% for any of the organs considered. The performance of the method in the clinical environment was also assessed. Using segmentation tools developed in-house, an automatic organ dose calculation pipeline was set up. Calculation of organ doses for heart and lung for each CT slice took about 2 s. CONCLUSIONS: This work shows that deep learning-enabled personalized CT dosimetry is feasible in real-time, using only patient CT images as input.

Nuclear and radiological emergencies: Building capacity in medical physics to support response.

Medical physicists represent a valuable asset at the disposal of a structured and planned response to nuclear or radiological emergencies (NREs), especially in the hospital environment. The recognition of this fact led the International Atomic Energy Agency (IAEA) and the International Organization for Medical Physics (IOMP) to start a fruitful collaboration aiming to improve education and training of medical physicists so that they may support response efforts in case of NREs. Existing shortcomings in specific technical areas were identified through international consultations supported by the IAEA and led to the development of a project aiming at preparing a specific and standardized training package for medical physicists in support to NREs. The Project was funded through extra-budgetary contribution from Japan within the IAEA Nuclear Safety Action Plan. This paper presents the work accomplished through that project and describes the current steps and future direction for enabling medical physicists to better support response to NREs.

Survey on impact of regulations on radiation safety and development of radiation safety culture in 25 countries.

The purpose of this work was to assess the: (a) impact of regulations on radiation safety and development of radiation safety culture, (b) perceived safety level in the participating facilities, (c) future needs regarding strengthening of regulations, patient dose consideration, and exposure tracking, in different countries around the world. Appropriate questionnaires probing the above-mentioned themes were sent to radiologic professionals working in healthcare facilities. A total of 257 responses from 25 countries were received and analyzed. Average scores for the three different sections/themes of the questionnaire ranged from 64.6% to 74.9%. Higher scores indicated stronger agreement of the survey participants with the theme in question. Statistical comparisons among different professional groups revealed that professionals in developing countries perceived regulations to be significantly more important for improving safety than their counterparts in developed countries did. Radiologic professionals believe that regulation enhances radiation safety and the development of safety culture. However, there is still room for improvement regarding the implementation of regulatory tools. Safety levels were perceived to be satisfactory, and future needs point toward strengthening of regulations regarding patient dose control, patient dose consideration, and patient exposure tracking. The results of this study should be interpreted keeping possible selection bias in view.

Out-of-field organ doses and associated radiogenic risks from para-aortic radiotherapy for testicular seminoma.

PURPOSE: The aims of this study were to (a) calculate the radiation dose to out-of-field organs from radiotherapy for stage I testicular seminoma and (b) estimate the associated radiogenic risks. METHODS: Monte Carlo methodology was employed to model radiation therapy with typical anteroposterior and posteroanterior para-aortic fields on an anthropomorphic phantom simulating an average adult. The radiation dose received by all main and remaining organs that defined by the ICRP publication 103 and excluded from the treatment volume was calculated. The effect of field dimensions on each organ dose was determined. Additional therapy simulations were generated by introducing shielding blocks to protect the kidneys from primary radiation. The gonadal dose was employed to assess the risk of heritable effects for irradiated male patients of reproductive potential. The lifetime attributable risks (LAR) of radiotherapy-induced cancer were estimated using gender- and organ-specific risk coefficients for patient ages of 20, 30, 40, and 50 years old. The risk values were compared with the respective nominal risks. RESULTS: Para-aortic irradiation to 20 Gy resulted in out-of-field organ doses of 5.0-538.6 mGy. Blocked field treatment led to a dose change up to 28%. The mean organ dose variation by increasing or decreasing the applied field dimensions was 18.7% ± 3.9% and 20.8% ± 4.5%, respectively. The out-of-field photon doses increased the lifetime intrinsic risk of developing thyroid, lung, bladder, prostate, and esophageal cancer by (0.1-1.4)%, (0.4-1.1)%, (2.5-5.4)%, (0.2-0.4)%, and (6.4-9.2)%, respectively, depending upon the patient age at exposure and the field size employed. A low risk for heritable effects of less than 0.029% was found compared with the natural incidence of these defects. CONCLUSIONS: Testicular cancer survivors are subjected to an increased risk for the induction of bladder and esophageal cancer following para-aortic radiotherapy. The probability for the appearance of any other malignant disease to out-of-field organs was slightly elevated in respect to the nominal cancer incidence rates.

Peripheral organ doses from radiotherapy for heterotopic ossification of non-hip joints: is there a risk for radiation-induced malignancies?

Radiotherapy, used for heterotopic ossification (HO) management, may increase radiation risk to patients. This study aimed to determine the peripheral dose to radiosensitive organs and the associated cancer risks due to radiotherapy of HO in common non-hip joints. A Monte Carlo model of a medical linear accelerator combined with a mathematical phantom representing an average adult patient were employed to simulate radiotherapy for HO with standard AP and PA fields in the regions of shoulder, elbow and knee. Radiation dose to all out-of-field radiosensitive organs defined by the International Commission on Radiological Protection was calculated. Cancer induction risk was estimated using organ-specific risk coefficients. Organ dose change with increased field dimensions was also evaluated. Radiation therapy for HO with a 7 Gy target dose in the sites of shoulder, elbow and knee, resulted in the following equivalent organ dose ranges of 0.85-62 mSv, 0.28-1.6 mSv and 0.04-1.6 mSv, respectively. Respective ranges for cancer risk were 0-5.1, 0-0.6 and 0-1.3 cases per 10(4) persons. Increasing the field size caused an average increase of peripheral doses by 15-20%. Individual organ dose increase depends upon the primary treatment site and the distance between organ of interest and treatment volume. Relatively increased risks of more than 1 case per 10,000 patients were found for skin, breast and thyroid malignancies after treatment in the region of shoulder and for skin cancer following elbow irradiation. The estimated risk for inducing any other malignant disease ranges from negligible to low.

Templates and existing elements and models for implementation of patient exposure tracking.

There is wide interest currently in patient exposure tracking. This paper provides templates for implementation of tracking at the practice (hospital) level, multi-practice level, national level and international level. It provides suggestions for implementation in less-resourced countries. It includes elements such as patient identifier, dose quantities that should be covered and how to make sense from dose figures, availability of digital imaging and communications in medicine files with dose information or structured dose reports and capabilities of picture archiving and communication system (PACS). While tracking at several hospitals in a country connected by PACS and nationwide PACS is also a reality, tracking at the international level is currently a challenge. Guidance provided in this paper will facilitate its implementation at all levels.

Radiation dose from cone-beam CT in neuroradiology applications.

OBJECTIVE: In view of increasing concern about radiation dose, this article aims to provide a summary of radiation doses in neuroradiologic applications of cone-beam CT. CONCLUSION: The conventional wisdom that cone-beam CT incurs a much lower radiation dose than MDCT may not be uniformly true, especially in intraoperative use if operators are tempted to overuse the 3D imaging capabilities. The emerging nature of cone-beam CT warrants extra caution to avoid overexposure of patients.

Radiation exposure tracking: survey of unique patient identification number in 40 countries.

OBJECTIVE: The purposes of this study were to survey in 40 countries the availability and use of unique patient identification numbers for radiologic examinations to facilitate radiation exposure tracking and to address plans for nationwide use of PACS networks and regulations in support of tracking. MATERIALS AND METHODS: The survey was conducted with a web-based questionnaire sent to contacts and counterparts of the International Atomic Energy Agency medical exposure projects unit. RESULTS: A unique patient identification number was available in 33 of 40 countries (82.5%) that participated in the survey and is used in the medical record and for tracking of imaging examinations in 18 of the 33 (54.5%). PACS infrastructures connecting a few hospitals within a country are fairly widespread (32 of 40 countries [80%]), and a very good infrastructure connecting most hospitals in a country was available in 15% (6 of 40 countries). Approximately one half of the participating countries (21 of 40) have plans for establishing a national PACS. Regulations regarding tracking of patient x-ray radiation exposures were found to exist in 30% of the countries. CONCLUSION: It is highly encouraging to note that most of the countries in which the survey was administered already have unique identification numbers for citizens and that nearly one half of these countries are using the number whenever a patient undergoes a medical imaging examination. Furthermore, nearly one half of respondents indicated that lack of technology rather than confidentiality was the reason for not using a patient identifier. That nearly one third of the countries-all 12 in Europe-support regulations requiring the tracking of patient radiation exposure is an important finding.

Calculation of organ doses from breast cancer radiotherapy: a Monte Carlo study.

The current study aimed to: a) utilize Monte Carlo simulation methods for the assessment of radiation doses imparted to all organs at risk to develop secondary radiation induced cancer, for patients undergoing radiotherapy for breast cancer; and b) evaluate the effect of breast size on dose to organs outside the irradiation field. A simulated linear accelerator model was generated. The in-field accuracy of the simulated photon beam properties was verified against percentage depth dose (PDD) and dose profile measurements on an actual water phantom. Off-axis dose calculations were verified with thermoluminescent dosimetry (TLD) measurements on a humanoid physical phantom. An anthropomorphic mathematical phantom was used to simulate breast cancer radiotherapy with medial and lateral fields. The effect of breast size on the calculated organ dose was investigated. Local differences between measured and calculated PDDs and dose profiles did not exceed 2% for the points at depths beyond the depth of maximum dose and the plateau region of the profile, respectively. For the penumbral regions of the dose profiles, the distance to agreement (DTA) did not exceed 2 mm. The mean difference between calculated out-of-field doses and TLD measurements was 11.4% ± 5.9%. The calculated doses to peripheral organs ranged from 2.32 cGy up to 161.41 cGy depending on breast size and thus the field dimensions applied, as well as the proximity of the organs to the primary beam. An increase to the therapeutic field area by 50% to account for the large breast led to a mean organ dose elevation by up to 85.2% for lateral exposure. The contralateral breast dose ranged between 1.4% and 1.6% of the prescribed dose to the tumor. Breast size affects dose deposition substantially.

Comparison of methods for assessing geometric efficiency on multi-detector CT scanners.

The aim of the current study was to compare the film method against the method based on a new CT slice detector in assessing geometric efficiency (GE) of x-ray beams utilized by a multi-detector CT (MDCT) scanner. Measurements of GE were performed using radiographic films and a solid state CT slice detector for all beam qualities, collimations and focal spot sizes available on an MDCT scanner. Repeatability of GE measurements was assessed. The radiographic film and the solid state detector methods were compared to each other in regard to efficacy in measuring free-in-air GE. The values of GE determined using the radiographic film method were found to range between 48.5% and 90.6%. Differences between values obtained with the radiographic film method and corresponding values obtained with the solid state detector were less than 10% exceeding 5% for only one case. Both methods show that wide beams have higher GE values compared to thin ones. The use of large instead of small focal spot was found to deteriorate GE values by up to 23.1%. Beam quality did not seem to influence GE of the various collimations. When thin beam collimations are employed, a considerable amount of the radiation is wasted for non-imaging purposes. Both film and solid state probe methods are capable of measuring GE of thin as well as wide collimations. The solid state detector is the easiest to use, however its usefulness is reduced by the fact that it cannot measure dose profiles of beam collimations available for step-and-shoot mode of operation.

International Atomic Energy Agency study with referring physicians on patient radiation exposure and its tracking: a prospective survey using a web-based questionnaire.

OBJECTIVES: To assess the following themes among referring physicians: (A) importance of acquiring information about previous diagnostic exposures; (B) knowledge about radiation doses involved, familiarity with radiation units and, age-related radiosensitivity; (C) opinion on whether patients should be provided information about radiation dose and (D) self-assessment of appropriateness of referrals. DESIGN: A prospective survey using a web-based questionnaire. SETTING: International survey among referring physicians. PARTICIPANTS: Referring physicians from 28 countries. MAIN OUTCOME MEASURES: Knowledge, opinion and practice of the four themes of the survey. RESULTS: All 728 responses from 28 countries (52.3% from developed and 47.7% from developing countries) indicated that while the vast majority (71.7%) of physicians feel that being aware of history of CT scans would always or mostly lead them to a better decision on referring patients for CT scans, only 43.4% often enquire about it. The majority of referring physicians (60.5%) stated that having a system that provides quick information about patient exposure history would be useful. The knowledge about radiation doses involved is poor, as only one-third (34.7%) of respondents chose the correct option of the number of chest x-rays with equivalence of a CT scan. In total, 70.9% of physicians stated that they do not feel uncomfortable when patients ask about radiation risk from CT scans they prescribe. Most physicians (85.6%) assessed that they have rarely prescribed CT scans of no clinical use in patient management. CONCLUSIONS: This first ever multinational survey among referring physicians from 28 countries indicates support for a system that provides radiation exposure history of the patient, demonstrates poor knowledge about radiation doses, supports radiation risk communication with patients and mandatory provisions for justification of a CT examination.

Patient radiation exposure tracking: worldwide programs and needs--results from the first IAEA survey.

The purpose of this study was to assess the current status of patient radiation exposure tracking internationally, gauge interest and develop recommendations for implementation. A survey questionnaire was distributed to representatives of countries to obtain information, including the existence of a patient exposure tracking program currently available in the country, plans for future programs, perceived needs and goals of future programs, which examinations will be tracked, whether procedure tracking alone or dose tracking is planned, and which dose quantities will be tracked. Responses from 76 countries, including all of the six most populous countries and 16 of the 20 most populous, showed that although no country has yet implemented a patient exposure tracking program at a national level, there is increased interest in this issue. Eight countries (11%) indicated that such a program is actively being planned and 3 (4%) stated that they have a program for tracking procedures only, but not for dose. Twenty-two (29%) feel that such a program will be "extremely useful", 46 (60%) "very useful" and 8 (11%) "moderately useful", with no respondents stating "Mildly useful" or "Not useful". Ninety-nine percent of countries indicated an interest in developing and promoting such a program. In a first global survey covering 76 countries, it is clear that no country has yet achieved exposure tracking at a national level, although there are successful examples at sub-national level. Almost all have indicated interest and some have plans to achieve dose tracking in the near future.