Advances in Auto-Segmentation.

Manual image segmentation is a time-consuming task routinely performed in radiotherapy to identify each patient's targets and anatomical structures. The efficacy and safety of the radiotherapy plan requires accurate segmentations as these regions of interest are generally used to optimize and assess the quality of the plan. However, reports have shown that this process can be subject to significant inter- and intraobserver variability. Furthermore, the quality of the radiotherapy treatment, and subsequent analyses (ie, radiomics, dosimetric), can be subject to the accuracy of these manual segmentations. Automatic segmentation (or auto-segmentation) of targets and normal tissues is, therefore, preferable as it would address these challenges. Previously, auto-segmentation techniques have been clustered into 3 generations of algorithms, with multiatlas based and hybrid techniques (third generation) being considered the state-of-the-art. More recently, however, the field of medical image segmentation has seen accelerated growth driven by advances in computer vision, particularly through the application of deep learning algorithms, suggesting we have entered the fourth generation of auto-segmentation algorithm development. In this paper, the authors review traditional (nondeep learning) algorithms particularly relevant for applications in radiotherapy. Concepts from deep learning are introduced focusing on convolutional neural networks and fully-convolutional networks which are generally used for segmentation tasks. Furthermore, the authors provide a summary of deep learning auto-segmentation radiotherapy applications reported in the literature. Lastly, considerations for clinical deployment (commissioning and QA) of auto-segmentation software are provided.

Technology for Innovation in Radiation Oncology.

Radiation therapy is an effective, personalized cancer treatment that has benefited from technological advances associated with the growing ability to identify and target tumors with accuracy and precision. Given that these advances have played a central role in the success of radiation therapy as a major component of comprehensive cancer care, the American Society for Radiation Oncology (ASTRO), the American Association of Physicists in Medicine (AAPM), and the National Cancer Institute (NCI) sponsored a workshop entitled "Technology for Innovation in Radiation Oncology," which took place at the National Institutes of Health (NIH) in Bethesda, Maryland, on June 13 and 14, 2013. The purpose of this workshop was to discuss emerging technology for the field and to recognize areas for greater research investment. Expert clinicians and scientists discussed innovative technology in radiation oncology, in particular as to how these technologies are being developed and translated to clinical practice in the face of current and future challenges and opportunities. Technologies encompassed topics in functional imaging, treatment devices, nanotechnology, and information technology. The technical, quality, and safety performance of these technologies were also considered. A major theme of the workshop was the growing importance of innovation in the domain of process automation and oncology informatics. The technologically advanced nature of radiation therapy treatments predisposes radiation oncology research teams to take on informatics research initiatives. In addition, the discussion on technology development was balanced with a parallel conversation regarding the need for evidence of efficacy and effectiveness. The linkage between the need for evidence and the efforts in informatics research was clearly identified as synergistic.

Fifty years of progress in radiation therapy for breast cancer.

Fifty years ago, radiation therapy (RT) was only used after mastectomy in patients with high-risk disease. The equipment, treatment planning, and treatment delivery were rudimentary compared to what is available today. In retrospect, the deleterious effects of the RT back then negated its benefits. The strategy of combining lesser surgery with RT (and adjuvant systemic therapy) has been successfully employed in breast-conserving therapy (BCT) and in avoiding axillary lymph node dissection in patients with 1 or 2 involved sentinel nodes. Local recurrence rates at 10 years following BCT are now similar to those following mastectomy. RT after breast-conserving surgery and after mastectomy has been demonstrated to not only decrease local-regional recurrence but also decrease distant metastases and improve long-term survival. The development of effective adjuvant systemic therapy has made RT not only more effective but also arguably more important. If systemic therapy is effective at addressing micro-metastatic disease, then obtaining local tumor control becomes even more important. Moderately hypofractionated RT (2.66 Gy per day) is just as safe and effective as conventional fractionation shortening BCT from 6 weeks to 3-4 weeks. Treatment is now given with multiple-energy linear accelerators, CT-based simulation, 3-dimensional beam modulation for much greater dose homogeneity, on-board imaging for greater daily accuracy, and various techniques to reduce cardiac dose.

Critical review, with an optimistic outlook, on Boron Neutron Capture Therapy (BNCT).

The first BNCT trials took place in the USA in the early 1960's, yet BNCT is still far from mainstream medicine. Nonetheless, in recent years, reported results in the treatment of head and neck cancer and recurrent glioma, coupled with the progress in developing linear accelerators specifically for BNCT applications, have given some optimism to the future of BNCT. This article provides a brief reminder on the ups and downs of the history of BNCT and supports the view that controlled and prospective clinical trials with a modern design will make BNCT an evidence-based treatment modality within the coming decade.

[Innovation and the next generation radiotherapy system].

Innovation is the key to future success for Japan that is slowly falling behind. Industries targeted by the "Abenomics" growth strategy include healthcare and medicine. Since cancer is the leading cause of death in Japan, the development of a system that can detect and treat early stage cancers will be very valuable for patient QOL and reducing health care costs. Although the effectiveness of radiation therapy for treating early stage cancer is widely recognized, there has been no system to treat small, moving tumors with sub millimeter accuracy. A project supported by NEDO develops a "Next-Generation Radiation Therapy System" that uses high energy, narrow X-rays beams that can be accurately pinpointed deep inside the body. Performance testing of a prototype system is currently underway at the National Center for Global Health and Medicine in Tokyo.

Technological advances in radiotherapy for esophageal cancer.

Radiotherapy with concurrent chemotherapy and surgery represent the main treatment modalities in esophageal cancer. The goal of modern radiotherapy approaches, based on recent technological advances, is to minimize post-treatment complications by improving the gross tumor volume definition (positron emission tomography-based planning), reducing interfraction motion (image-guided radiotherapy) and intrafraction motion (respiratory-gated radiotherapy), and by better dose delivery to the precisely defined planning target volume (intensity-modulated radiotherapy and proton therapy). Reduction of radiotherapy-related toxicity is fundamental to the improvement of clinical results in esophageal cancer, although the dose escalation concept is controversial.

[Past, present and near future of techniques in radiation oncology]. / Histoire de l'évolution des techniques de radiothérapie.

Since the discovery of X-rays, the goal of radiotherapy has been to deliver an optimal dose in the target volume and the lowest possible dose in the normal tissues. The history of radiotherapy can be divided in three periods. The Kilovoltage era (1900-1939) where only superficial and radiosensitive tumours could be controlled, the Megavoltage era (1950-1995) where Telecobalt and linear accelerators could deliver high doses in all parts of the body. Radiotherapy has since been playing an important curative and conservative role for most cancers. The Computer-Assisted Radiotherapy era (1995-2010) now provides the capacity to optimise the dose distribution in three dimensions. Dose is better conformed to the target volume and organ at risk are better preserved. intensity modulated radio-therapy (IMRT) allows to "shape" concave isodoses and to spare the parotids when irradiating oropharyngeal tumours. Moving targets (lung, liver etc.) are efficiently irradiated using "on-line tracking" and "image-guided radiotherapy". Stereotactic irradiation, first initiated for brain lesions, is now performed for extra-cranial tumours and due to its millimetric precision opens the way back to hypo-fractionated treatments. The next period, already ongoing, is Hadrontherapy with protons and soon helium or carbon ions techniques. In a multidisciplinary strategy, progress in radiotherapy is based on a global approach of the patient and tailored/personalized well targeted treatment of the tumour.

Respiratory motion management in particle therapy.

Clinical outcomes of charged particle therapy are very promising. Currently, several dedicated centers that use scanning beam technology are either close to clinical use or under construction. Since scanned beam treatments of targets that move with respiration most likely result in marked local over- and underdosage due to interplay of target motion and dynamic beam application, dedicated motion mitigation techniques have to be employed. To date, the motion mitigation techniques, rescanning, beam gating, and beam tracking, have been proposed and tested in experimental studies. Rescanning relies on repeated irradiations of the target with the number of particles reduced accordingly per scan to statistically average local misdosage. Specific developments to prohibit temporal correlation between beam scanning and target motion will be required to guarantee adequate averaging. For beam gating, residual target motion within gating windows has to be mitigated in order to avoid local misdosage. Possibly the most promising strategy is to increase the overlap of adjacent particle pencil beams laterally as well as longitudinally to effectively reduce the sensitivity against small residual target motion. The most conformal and potentially most precise motion mitigation technique is beam tracking. Individual particle pencil beams have to be adapted laterally as well as longitudinally according to the target motion. Within the next several years, it can be anticipated that rescanning as well as beam gating will be ready for clinical use. For rescanning, treatment planning margins that incorporate the full extent of target motion as well as motion induced density variations in the beam paths will result in reduced target conformity of the applied dose distributions. Due to the limited precision of motion monitoring devices, it seems likely that beam gating will be used initially to mitigate interplay effects only but not to considerably decrease treatment planning margins. Then, in the next step, beam gating, based on more accurate motion monitoring systems, provides the possibility to restore target conformity as well as steep dose gradients due to reduced treatment planning margins. Accurate motion monitoring systems will be required for beam tracking. Even though beam tracking has already been successfully tested experimentally, full clinical implementation requires direct feedback of the actual target position in quasireal time to the treatment control system and can be anticipated to be several more years ahead.

[Help for delineation: what kind of tools?]. / Aide à la délinéation: quels outils pratiques?

The planning of radiotherapy has known major developments during the last years. With the emergence of news techniques such as conformational radiotherapy, intensity modulated radiation therapy or stereotactic radiation therapy, the definition of target volumes was of great importance. The recommendations for the target volumes definition have been defined in the ICRU 50 and 62 reports, without any guidelines for volume delineation. Among the uncertainties that may influence the outcome after irradiation, the intra- and interobservers variations in delineation are the most important. Many teams have offered guidelines or atlases to homogenize these volumes and reduce these variations related to medical intervention. The aim of this paper is to present the main recommendations.

Advances in SPECT imaging with respect to radionuclide therapy.

Radionuclide therapy is gradually becoming more important as a therapy option in various diseases. Nuclear medicine imaging plays an important role in this, before, during and after the therapy. Single photon emission computed tomography (SPECT) imaging can be used to predict therapy response, calculate doses delivered to the tumour and the surrounding organ, check radiopharmaceutical distribution and follow-up this distribution in time. On a technological level, radionuclide imaging in a therapy setting shows some particularities and issues to be resolved. Accurate quantification is important but is hampered by attenuation, scatter from different energy peaks and from bremsstrahlung photons, septal penetration, partial volume effects etc. Some of these issues are discussed in this paper. A technique specific for therapy imaging is bremsstrahlung imaging, which can be used if the therapeutical agent is a pure beta emitter. Quantitative bremsstrahlung imaging is particularly challenging due to the complicated nature of the energy spectrum of these photons. Some work towards quantitative bremsstrahlung imaging is discussed here. Finally, some recent technical advances relevant to this field are pointed out. On the software side, Monte Carlo simulations seem to have a great potential for accurate quantitative SPECT reconstruction and subsequent patient specific image based dose calculations. Concerning hardware, the availability of SPECT-CT technology may have a large impact in imaging in radionuclide therapy. Novel detector technologies such as solid-state detectors may also prove to have significant advantages in this field.

Technological advances in radiation oncology for central nervous system tumors.

Advances in computer software technology have led to enormous progress that has enabled increasing levels of complexity to be incorporated into radiotherapy treatment planning systems. Because of these changes, the delivery of radiotherapy evolved from therapy designed primarily on plain 2-dimensional X-ray images and hand calculations to therapy based on 3-dimensional images incorporating increasingly complex computer algorithms in the planning process. In addition, challenges in treatment planning and radiation delivery, such as problems with setup error and organ movement, have begun to be systematically addressed, ushering in an era of so-called 4-dimensional radiotherapy. This review article discusses how these advances have changed the way in which many common neoplasms of the central nervous system are being treated at present.

Robotic brachytherapy of the prostate.

Recent applications of robotics in the field of prostate brachytherapy are seeding the future and could potentially lead to a fully automated prostate brachytherapy surgery. Currently, a typical prostate brachytherapy surgery involves the implantation of upwards of 100 radioactive I-125 seeds by a surgeon. This review supplies background information on prostate biology, brachytherapy of the prostate, robotic brachytherapy, and transrectal ultrasound. Subsequently, it examines the physics involved in ultrasound, radiation from an I-125 source, dosimetry, and robotics. A current semi-automated robotic brachytherapy system is examined in detail and a discussion on future improvements is outlined. Finally, future work to improve prostate brachytherapy is postulated, most notably, phantom optimization using polyvinyl alcohol cryogel. The future of robotic brachytherapy lies in the advent of more sophisticated robotics. This review will give the reader a superior understanding of brachytherapy and its recent robotic advancements. Hopefully, this review will generate new ideas needed to advance prostate brachytherapy procedures leading to more accurate dosimetry, faster procedure time, less ionizing radiation received by surgery staff, more rapid patient recovery, and an overall safer procedure.

Technological approaches to in-room CBCT imaging.

The use of Cone-Beam Computed Tomography (CBCT) in Image-Guided Radiation Therapy (IGRT) has become increasingly feasible and popular in recent years. Advances and developments in Flat-Panel Imager (FPI) technology and image reconstruction software allow for linac-mounted 3D CBCT imaging. Taking CBCT images on a daily/weekly basis, offers the possibility to guide the treatment beam according to tumour motion and to apply changes to the treatment plan if necessary. This however raises the issue of additional imaging dose and thus increases in secondary cancer risk. The performance characteristics of kV-CBCT and MV-CBCT solutions currently offered by Elekta, Siemens and Varian are compared in this paper in terms of additional imaging dose and image quality. The review also outlines applications of CBCT for IGRT and Adaptive Radiotherapy (ART). As CBCT is not the only in-room IGRT platform, helical MV-CT (Tomotherapy) and in-room CT designs are also presented.

[What is the impact of new radiotherapy techniques?]. / Was leisten die neuen Bestrahlungstechniken?

Radiation oncology, along with surgery and chemotherapy, is one of the cornerstones in the treatment of head and neck tumors. Within the last years, this field has experienced a remarkable evolution of new technical possibilities. New imaging modalities have been introduced into radiation planning and into linear accelerators themselves. In addition, new techniques enable the tailor-made conformation of radiation beams and dose distributions to complex tumor geometries. At the same time, organs at risk can be spared, and long-term toxicities are considerably reduced. This report presents the new techniques in radiation oncology and describes the effects on new treatment options and patients' quality of life.

Current external beam radiation therapy quality assurance guidance: does it meet the challenges of emerging image-guided technologies?

The traditional prescriptive quality assurance (QA) programs that attempt to ensure the safety and reliability of traditional external beam radiation therapy are limited in their applicability to such advanced radiation therapy techniques as three-dimensional conformal radiation therapy, intensity-modulated radiation therapy, inverse treatment planning, stereotactic radiosurgery/radiotherapy, and image-guided radiation therapy. The conventional QA paradigm, illustrated by the American Association of Physicists in Medicine Radiation Therapy Committee Task Group 40 (TG-40) report, consists of developing a consensus menu of tests and device performance specifications from a generic process model that is assumed to apply to all clinical applications of the device. The complexity, variation in practice patterns, and level of automation of high-technology radiotherapy renders this "one-size-fits-all" prescriptive QA paradigm ineffective or cost prohibitive if the high-probability error pathways of all possible clinical applications of the device are to be covered. The current approaches to developing comprehensive prescriptive QA protocols can be prohibitively time consuming and cost ineffective and may sometimes fail to adequately safeguard patients. It therefore is important to evaluate more formal error mitigation and process analysis methods of industrial engineering to more optimally focus available QA resources on process components that have a significant likelihood of compromising patient safety or treatment outcomes.

Image-guided radiation therapy for non-small cell lung cancer.

Recent developments in image-guided radiotherapy are ushering in a new era of radiotherapy for lung cancer. Positron emission tomography/computed tomography (PET/CT) has been shown to improve targeting accuracy in 25 to 50% of cases, and four-dimensional CT scanning helps to individualize radiotherapy by accounting for tumor motion. Daily on-board imaging reduces treatment set-up uncertainty and provides information about daily organ motion and variations in anatomy. Image-guided intensity-modulated radiotherapy may allow for the escalation of radiotherapy dose with no increase in toxicity. More importantly, treatment adaptations based on anatomic changes during the course of radiotherapy and dose painting within involved lesions using functional imaging such as PET may further improve clinical outcomes of lung cancer patients and potentially lead to new clinical trials. Image-guided stereotactic radiotherapy can achieve local control rates exceeding 90% through the use of focused, hypofractionated, highly biologically effective doses. These novel approaches were considered experimental just a few years ago, but accumulating evidence of their potential for significantly improving clinical outcomes is leading to their inclusion in standard treatments for lung cancer at major cancer centers. In this review article, we focus on novel image-guided radiotherapy approaches, particularly PET/CT and four-dimensional CT-based radiotherapy planning and on-board image-guided delivery, stereotactic radiotherapy, and intensity-modulated radiotherapy for mobile nonsmall cell lung cancer.