Expanding the medical physicist curricular and professional programme to include Artificial Intelligence

Opportunities for Artificial Intelligence in Oncology: From the Lens of Clinicians and Patients

Much work has been published on artificial intelligence (AI) and oncology, with many focusing on an algorithm perspective. However, very few perspective articles have explicitly discussed the role of AI in oncology from the perspectives of the stakeholders-the clinicians and the patients. In this article, we delve into the opportunities of AI in oncology from the clinician's and patient's lens. From the clinician's perspective, we discuss reducing burnout, enhancing decision making, and leveraging vast data sets to provide evidence-based recommendations, eventually affecting diagnostic accuracy and treatment planning. From the patient's perspective, we discuss AI virtual concierge, which could improve the cancer care journey by facilitating patient education, mental health support, and personalized lifestyle wellness recommendations promoting a holistic approach to care. We aim to highlight the stakeholders' unmet needs and guide institutions to create innovative AI solutions in oncology. By addressing these perspectives, our article aims to bridge the gap between technological research advancements and their real-world AI-focused clinical applications in cancer care. Understanding and prioritizing the needs of the stakeholders will foster the development of impactful AI tools and intentional utilization of such technology, with an aim for clinical implementation and integration into workflows.

European Federation of Organisations for medical physics (EFOMP) policy statement no 20: The role of medical physicists and medical physics experts in physiological measurement and related therapies

The role of medical physics professionals (MPPs) (medical physicists and medical physics experts) in physiological measurement and related therapies (PM&T) applied in e.g., critical care, neurophysiology, neurology, physiology, audiology, and neurotology has long been acknowledged. Given that the exact role and medical specialty fields in which MPP are involved vary between countries, this policy statement aims to provide direction towards improved definition, harmonisation, and development of the role. This policy statement considers the surveyed experiences from several European countries, state-of-the-art of PM&T, and anticipated future developments. We also present an inventory of competences, and associated knowledge and skills expected of MPPs working in these areas.

Artificial Intelligence for Radiation Treatment Planning: Bridging Gaps From Retrospective Promise to Clinical Reality

Artificial intelligence (AI) radiation therapy (RT) planning holds promise for enhancing the consistency and efficiency of the RT planning process. Despite technical advancements, the widespread integration of AI into RT treatment planning faces challenges. The transition from controlled retrospective environments to real-world clinical settings introduces heightened scrutiny from clinical end users, potentially leading to decreased clinical acceptance. Key considerations for implementing AI RT planning include ensuring the AI model performance aligns with clinical standards, using high-quality training data, and incorporating sufficient data variation through meticulous curation by clinical experts. Beyond technical aspects, factors such as potential biases and the level of trust clinical end users place in AI may present unforeseen obstacles for real-world clinical use. Addressing these challenges requires bridging education and expertise gaps among clinical end users, enabling them to confidently embrace and utilize AI for routine RT planning. By fostering a better understanding of AI capabilities, building trust, and providing comprehensive training, the promises of AI RT planning can be a reality in the clinical setting. This article assesses the current clinical use of AI RT planning and explores challenges and considerations for bridging gaps in knowledge and expertise for AI operationalization, with focus on training data curation, workflow integration, explainability, bias, and domain knowledge. Remaining challenges in clinical implementation of AI RT treatment planning are examined in the context of trust building approaches.

Robust machine learning challenge: An AIFM multicentric competition to spread knowledge, identify common pitfalls and recommend best practice

PURPOSE

A novel and unconventional approach to a machine learning challenge was designed to spread knowledge, identify robust methods and highlight potential pitfalls about machine learning within the Medical Physics community.

METHODS

A public dataset comprising 41 radiomic features and 535 patients was employed to assess the potential of radiomics in distinguishing between primary lung tumors and metastases. Each participant developed two classification models using: (i) all features (base model); (ii) only robust features (robust model). Both models were validated with cross-validation and on unseen data. The population stability index (PSI) was used as diagnostic metric for implementation issues. Performance was compared to reference. Base and robust models were compared in terms of performance and stability (coefficient of variation (CoV) of prediction probabilities).

RESULTS

PSI detected potential implementation errors in 70 % of models. The dataset exhibited strong imbalance. The average Gmean (i.e. an appropriate metric for imbalance) among all participants was 0.67 ± 0.01, significantly higher than reference Gmean of 0.50 ± 0.04. Robust models performances were slightly worse than base models (p < 0.05). Regarding stability, robust models exhibited lower median CoV on training set only.

CONCLUSION

AI4MP-Challenge models overperformed the reference, significantly improving the Gmean. Exclusion of less-robust features did not improve model robustness and it should be avoided when confounding effects are absent. Other methods, like harmonization or data augmentation, should be evaluated. This study demonstrated how the collaborative effort to foster knowledge on machine learning among medical physicists, through interactive sessions and exchange of information among participants, can result in improved models.

Artificial intelligence and radiotherapy: Evolution or revolution?

The integration of artificial intelligence, particularly deep learning algorithms, into radiotherapy represents a transformative shift in the field, enhancing accuracy, efficiency, and personalized care. This paper explores the multifaceted impact of artificial intelligence on radiotherapy, the evolution of the roles of radiation oncologists and medical physicists, and the associated practical challenges. The adoption of artificial intelligence promises to revolutionize the profession by automating repetitive tasks, improving diagnostic precision, and enabling adaptive radiotherapy. However, it also introduces significant risks, such as automation bias, verification failures, and the potential erosion of clinical skills. Ethical considerations, such as maintaining patient autonomy and addressing biases in artificial intelligence systems, are critical to ensuring the responsible use of artificial intelligence. Continuous training and development of robust quality assurance programs are required to mitigate these risks and maximize the benefits of artificial intelligence in radiotherapy.

Machine learning and lean six sigma for targeted patient-specific quality assurance of volumetric modulated arc therapy plans

Background and purpose

Radiotherapy plans with excessive complexity exhibit higher uncertainties and worse patient-specific quality assurance (PSQA) results, while the workload of measurement-based PSQA can impact the efficiency of the radiotherapy workflow. Machine Learning (ML) and Lean Six Sigma, a process optimization method, were implemented to adopt a targeted PSQA approach, aiming to reduce workload, risk of failures, and monitor complexity.

Materials and methods

Lean Six Sigma was applied using DMAIC (define, measure, analyze, improve, and control) steps. Ten complexity metrics were computed for 69,811 volumetric modulated arc therapy (VMAT) arcs from 28,612 plans delivered in our Institute (2013-2021). Outlier complexities were defined as >95th-percentile of the historical distributions, stratified by treatment. An ML model was trained to predict the gamma passing rate (GPR-3 %/1mm) of an arc given its complexity. A decision support system was developed to monitor the complexity and expected GPR. Plans at risk of PSQA failure, either extremely complex or with average GPR <90 %, were identified. The tool's impact was assessed after nine months of clinical use.

Results

Among 1722 VMAT plans monitored prospectively, 29 (1.7 %) were found at risk of failure. Planners reacted by performing PSQA measurement and re-optimizing the plan. Occurrences of outlier complexities remained stable within 5 %. The expected GPR increased from a median of 97.4 % to 98.2 % (Mann-Whitney p < 0.05) due to plan re-optimization.

Conclusions

ML and Lean Six Sigma have been implemented in clinical practice enabling a targeted measurement-based PSQA approach for plans at risk of failure to improve overall quality and patient safety.

Automation and artificial intelligence in radiation therapy treatment planning

Automation and artificial intelligence (AI) is already possible for many radiation therapy planning and treatment processes with the aim of improving workflows and increasing efficiency in radiation oncology departments. Currently, AI technology is advancing at an exponential rate, as are its applications in radiation oncology. This commentary highlights the way AI has begun to impact radiation therapy treatment planning and looks ahead to potential future developments in this space. Historically, radiation therapist's (RT's) role has evolved alongside the adoption of new technology. In Australia, RTs have key clinical roles in both planning and treatment delivery and have been integral in the implementation of automated solutions for both areas. They will need to continue to be informed, to adapt and to transform with AI technologies implemented into clinical practice in radiation oncology departments. RTs will play an important role in how AI-based automation is implemented into practice in Australia, ensuring its application can truly enable personalised and higher-quality treatment for patients. To inform and optimise utilisation of AI, research should not only focus on clinical outcomes but also AI's impact on professional roles, responsibilities and service delivery. Increased efficiencies in the radiation therapy workflow and workforce need to maintain safe improvements in practice and should not come at the cost of creativity, innovation, oversight and safety.

A markerless beam's eye view tumor tracking algorithm based on unsupervised deformable registration learning framework of VoxelMorph in medical image with partial data

PURPOSE

To propose an unsupervised deformable registration learning framework-based markerless beam's eye view (BEV) tumor tracking algorithm for the inferior quality megavolt (MV) images with occlusion and deformation.

METHODS

Quality assurance (QA) plans for thorax phantom were delivered to the linear accelerator with artificially treatment offsets. Electronic portal imaging device (EPID) images (682 in total) and corresponding digitally reconstructed radiograph (DRR) were gathered as the moving and fixed image pairs, which were randomly divided into training and testing set in a ratio of 0.7:0.3 to train a non-rigid registration model with Voxelmorph. Simultaneously, 533 pairs of patient images from 21 lung tumor plans were acquired for tumor tracking investigation to offer quantifiable tumor motion data. Tracking error and image similarity measures were employed to evaluate the algorithm's accuracy.

RESULTS

The tracking algorithm can handle image registration with non-rigid deformation and losses ranging from 10 % to 80 %. The tracking errors in the phantom study were below 3 mm in about 86.8 % of cases, and below 2 mm in about 80 % of cases. The normalized mutual information (NMI) changes from 1.182 ± 0.024 to 1.198 ± 0.024 (p < 0.005). The patient target had an average translation of 3.784 mm and a maximum comprehensive displacement value of 7.455 mm. NMI of patient images changes from 1.209 ± 0.027 to 1.217 ± 0.026 (p < 0.005), indicating the presence of non-negligible non-rigid deformation.

CONCLUSIONS

The study provides a robust markerless tumor tracking algorithm for multi-modal, partial data and inferior quality image processing.

Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency

The interest in machine learning (ML) has grown tremendously in recent years, partly due to the performance leap that occurred with new techniques of deep learning, convolutional neural networks for images, increased computational power, and wider availability of large datasets. Most fields of medicine follow that popular trend and, notably, radiation oncology is one of those that are at the forefront, with already a long tradition in using digital images and fully computerized workflows. ML models are driven by data, and in contrast with many statistical or physical models, they can be very large and complex, with countless generic parameters. This inevitably raises two questions, namely, the tight dependence between the models and the datasets that feed them, and the interpretability of the models, which scales with its complexity. Any problems in the data used to train the model will be later reflected in their performance. This, together with the low interpretability of ML models, makes their implementation into the clinical workflow particularly difficult. Building tools for risk assessment and quality assurance of ML models must involve then two main points: interpretability and data-model dependency. After a joint introduction of both radiation oncology and ML, this paper reviews the main risks and current solutions when applying the latter to workflows in the former. Risks associated with data and models, as well as their interaction, are detailed. Next, the core concepts of interpretability, explainability, and data-model dependency are formally defined and illustrated with examples. Afterwards, a broad discussion goes through key applications of ML in workflows of radiation oncology as well as vendors' perspectives for the clinical implementation of ML.

Recent Applications of Artificial Intelligence in Radiotherapy: Where We Are and Beyond

In recent decades, artificial intelligence (AI) tools have been applied in many medical fields, opening the possibility of finding novel solutions for managing very complex and multifactorial problems, such as those commonly encountered in radiotherapy (RT). We conducted a PubMed and Scopus search to identify the AI application field in RT limited to the last four years. In total, 1824 original papers were identified, and 921 were analyzed by considering the phase of the RT workflow according to the applied AI approaches. AI permits the processing of large quantities of information, data, and images stored in RT oncology information systems, a process that is not manageable for individuals or groups. AI allows the iterative application of complex tasks in large datasets (e.g., delineating normal tissues or finding optimal planning solutions) and might support the entire community working in the various sectors of RT, as summarized in this overview. AI-based tools are now on the roadmap for RT and have been applied to the entire workflow, mainly for segmentation, the generation of synthetic images, and outcome prediction. Several concerns were raised, including the need for harmonization while overcoming ethical, legal, and skill barriers.

Artificial Intelligence Assists the Construction of Quantitative Model for the High-Quality Development of Modern Enterprises

Artificial intelligence companies are different from traditional labor-intensive and capital-intensive companies in that their core competitiveness lies in technology, knowledge, and manpower. Enterprises show the characteristics of a high proportion of intangible assets, strong profitability, and rapid growth. At the same time, there are also the characteristics of high risk and high uncertainty. In addition to the existing value brought by existing profitability, corporate value should also consider the potential value brought by potential profitability. Enterprise value is affected by many factors such as profitability, growth ability, innovation ability, and external environment. Traditional valuation techniques are often utilised to value artificial intelligence businesses in the present market. Traditional valuation methods ignore the dynamics and uncertainties of artificial intelligence enterprise value evaluation, make static and single predictions of future earnings, ignore the value of enterprise management flexibility, and are unable to assess the intrinsic value of artificial intelligence businesses. Based on the projection pursuit method, this paper constructs a modern high-quality development enterprise high-quality development evaluation model, uses real-code accelerated genetic algorithm to optimize the projection objective function, and calculates the best projection direction vector and projection value. The collected sample data can be imported into the evaluation model to calculate the comprehensive evaluation value of the high-quality development of modern high-quality development enterprises and the weights of various indicators included. By comparing the size of the comprehensive evaluation value, each sample can be calculated Evaluation of the level of high-quality development. The results show that the high-quality development level of China's overall economy is on the rise, but the level of development is still low, and there is a large gap between the development level of the eastern region and the central and western regions. Using the systematic generalized moment estimation method, empirically, we analyse the impact of artificial intelligence on the high-quality economic development. The results show that artificial intelligence at the national level and in the central and western regions will significantly promote high-quality economic development, while artificial intelligence in the eastern region has a significant inhibitory effect on high-quality economic development.

Big Data for Biomedical Education with a Focus on the COVID-19 Era: An Integrative Review of the Literature

Medical education refers to education and training delivered to medical students in order to become a practitioner. In recent decades, medicine has been radically transformed by scientific and computational/digital advances-including the introduction of new information and communication technologies, the discovery of DNA, and the birth of genomics and post-genomics super-specialties (transcriptomics, proteomics, interactomics, and metabolomics/metabonomics, among others)-which contribute to the generation of an unprecedented amount of data, so-called 'big data'. While these are well-studied in fields such as medical research and methodology, translational medicine, and clinical practice, they remain overlooked and understudied in the field of medical education. For this purpose, we carried out an integrative review of the literature. Twenty-nine studies were retrieved and synthesized in the present review. Included studies were published between 2012 and 2021. Eleven studies were performed in North America: specifically, nine were conducted in the USA and two studies in Canada. Six studies were carried out in Europe: two in France, two in Germany, one in Italy, and one in several European countries. One additional study was conducted in China. Eight papers were commentaries/theoretical or perspective articles, while five were designed as a case study. Five investigations exploited large databases and datasets, while five additional studies were surveys. Two papers employed visual data analytical/data mining techniques. Finally, other two papers were technical papers, describing the development of software, computational tools and/or learning environments/platforms, while two additional studies were literature reviews (one of which being systematic and bibliometric).The following nine sub-topics could be identified: (I) knowledge and awareness of big data among medical students; (II) difficulties and challenges in integrating and implementing big data teaching into the medical syllabus; (III) exploiting big data to review, improve and enhance medical school curriculum; (IV) exploiting big data to monitor the effectiveness of web-based learning environments among medical students; (V) exploiting big data to capture the determinants and signatures of successful academic performance and counteract/prevent drop-out; (VI) exploiting big data to promote equity, inclusion, and diversity; (VII) exploiting big data to enhance integrity and ethics, avoiding plagiarism and duplication rate; (VIII) empowering medical students, improving and enhancing medical practice; and, (IX) exploiting big data in continuous medical education and learning. These sub-themes were subsequently grouped in the following four major themes/topics: namely, (I) big data and medical curricula; (II) big data and medical academic performance; (III) big data and societal/bioethical issues in biomedical education; and (IV) big data and medical career. Despite the increasing importance of big data in biomedicine, current medical curricula and syllabuses appear inadequate to prepare future medical professionals and practitioners that can leverage on big data in their daily clinical practice. Challenges in integrating, incorporating, and implementing big data teaching into medical school need to be overcome to facilitate the training of the next generation of medical professionals. Finally, in the present integrative review, state-of-art and future potential uses of big data in the field of biomedical discussion are envisaged, with a focus on the still ongoing "Coronavirus Disease 2019" (COVID-19) pandemic, which has been acting as a catalyst for innovation and digitalization.

Artificial intelligence and the medical physics profession - A Swedish perspective

BACKGROUND

There is a continuous and dynamic discussion on artificial intelligence (AI) in present-day society. AI is expected to impact on healthcare processes and could contribute to a more sustainable use of resources allocated to healthcare in the future. The aim for this work was to establish a foundation for a Swedish perspective on the potential effect of AI on the medical physics profession.

MATERIALS AND METHODS

We designed a survey to gauge viewpoints regarding AI in the Swedish medical physics community. Based on the survey results and present-day situation in Sweden, a SWOT analysis was performed on the implications of AI for the medical physics profession.

RESULTS

Out of 411 survey recipients, 163 responded (40%). The Swedish medical physicists with a professional license believed (90%) that AI would change the practice of medical physics but did not foresee (81%) that AI would pose a risk to their practice and career. The respondents were largely positive to the inclusion of AI in educational programmes. According to self-assessment, the respondents' knowledge of and workplace preparedness for AI was generally low.

CONCLUSIONS

From the survey and SWOT analysis we conclude that AI will change the medical physics profession and that there are opportunities for the profession associated with the adoption of AI in healthcare. To overcome the weakness of limited AI knowledge, potentially threatening the role of medical physicists, and build upon the strong position in Swedish healthcare, medical physics education and training should include learning objectives on AI.

The perceptions of medical physicists towards relevance and impact of artificial intelligence

Artificial intelligence (AI) is an innovative tool with the potential to impact medical physicists' clinical practices, research, and the profession. The relevance of AI and its impact on the clinical practice and routine of professionals in medical physics were evaluated by medical physicists and researchers in this field. An online survey questionnaire was designed for distribution to professionals and students in medical physics around the world. In addition to demographics questions, we surveyed opinions on the role of AI in medical physicists' practices, the possibility of AI threatening/disrupting the medical physicists' practices and career, the need for medical physicists to acquire knowledge on AI, and the need for teaching AI in postgraduate medical physics programmes. The level of knowledge of medical physicists on AI was also consulted. A total of 1019 respondents from 94 countries participated. More than 85% of the respondents agreed that AI would play an essential role in medical physicists' practices. AI should be taught in the postgraduate medical physics programmes, and that more applications such as quality control (QC), treatment planning would be performed by AI. Half of the respondents thought AI would not threaten/disrupt the medical physicists' practices. AI knowledge was mainly acquired through self-taught and work-related activities. Nonetheless, many (40%) reported that they have no skill in AI. The general perception of medical physicists was that AI is here to stay, influencing our practices. Medical physicists should be prepared with education and training for this new reality.

Artificial intelligence for quality assurance in radiotherapy

In radiotherapy, patient-specific quality assurance is very time-consuming and causes machine downtime. It consists of testing (using measurement with a phantom and detector) if a modulated plan is correctly delivered by a treatment unit. Artificial intelligence and in particular machine learning algorithms were mentioned in recent reports as promising solutions to reduce or eliminate the patient-specific quality assurance workload. Several teams successfully experienced a virtual patient-specific quality assurance by training a machine learning tool to predict the results. Training data are generally composed of previous treatment plans and associated patient-specific quality assurance results. However, other training data types were recently introduced such as actual positions and velocities of multileaf collimators, metrics of the plan's complexity, and gravity vectors. Different types of machine learning algorithms were investigated (Poisson regression algorithms, convolutional neural networks, support vector classifiers) with sometimes promising results. These tools are being used for treatment units' quality assurance as well, in particular to analyse the results of imaging devices. Most of these reports were feasibility studies. Using machine learning in clinical routines as a tool that could fully replace quality assurance tests conducted by physics teams has yet to be implemented.

Automation in radiotherapy treatment planning: Examples of use in clinical practice and future trends for a complete automated workflow

Modern radiotherapy treatment planning is a complex and time-consuming process that requires the skills of experienced users to obtain quality plans. Since the early 2000s, the automation of this planning process has become an important research topic in radiotherapy. Today, the first commercial automated treatment planning solutions are available and implemented in a growing number of clinical radiotherapy departments. It should be noted that these various commercial solutions are based on very different methods, implying a daily practice that varies from one center to another. It is likely that this change in planning practices is still in its infancy. Indeed, the rise of artificial intelligence methods, based in particular on deep learning, has recently revived research interest in this subject. The numerous articles currently being published announce a lasting and profound transformation of radiotherapy planning practices in the years to come. From this perspective, an evolution of initial training for clinical teams and the drafting of new quality assurance recommendations is desirable.