Explore the vast range of titles available.

Convolutional neural network (CNN), a class of artificial neural networks that has become dominant in various computer vision tasks, is attracting interest across a variety of domains, including radiology. CNN is designed to automatically and adaptively learn spatial hierarchies of features through backpropagation by using multiple building blocks, such as convolution layers, pooling layers, and fully connected layers. This review article offers a perspective on the basic concepts of CNN and its application to various radiological tasks, and discusses its challenges and future directions in the field of radiology. Two challenges in applying CNN to radiological tasks, small dataset and overfitting, will also be covered in this article, as well as techniques to minimize them. Being familiar with the concepts and advantages, as well as limitations, of CNN is essential to leverage its potential in diagnostic radiology, with the goal of augmenting the performance of radiologists and improving patient care.Key Points• Convolutional neural network is a class of deep learning methods which has become dominant in various computer vision tasks and is attracting interest across a variety of domains, including radiology.• Convolutional neural network is composed of multiple building blocks, such as convolution layers, pooling layers, and fully connected layers, and is designed to automatically and adaptively learn spatial hierarchies of features through a backpropagation algorithm.• Familiarity with the concepts and advantages, as well as limitations, of convolutional neural network is essential to leverage its potential to improve radiologist performance and, eventually, patient care.

Pancreatic ductal adenocarcinoma (PDAC) is a highly devastating disease with poor prognosis and rising incidence. Late detection and a particularly aggressive biology are the major challenges which determine therapeutic failure. In this review, we present the current status and the recent advances in PDAC treatment together with the biological and immunological hallmarks of this cancer entity. On this basis, we discuss new concepts combining distinct treatment modalities in order to improve therapeutic efficacy and clinical outcome – with a specific focus on protocols involving radio(chemo)therapeutic approaches.

Lung, breast, and esophageal cancer represent three common malignancies with high incidence and mortality worldwide. The management of these tumors critically relies on radiotherapy as a major part of multi-modality care, and treatment-related toxicities, such as radiation-induced pneumonitis and/or lung fibrosis, are important dose limiting factors with direct impact on patient outcomes and quality of life. In this review, we summarize the current understanding of radiation-induced pneumonitis and pulmonary fibrosis, present predictive factors as well as recent diagnostic and therapeutic advances. Novel candidates for molecularly targeted approaches to prevent and/or treat radiation-induced pneumonitis and pulmonary fibrosis are discussed.

Despite aggressive management consisting of maximal safe surgical resection followed by external beam radiation therapy (60 Gy/30 fractions) with concomitant and adjuvant temozolomide, approximately 90% of WHO grade IV gliomas (glioblastomas, GBM) will recur locally within 2 years. For patients with recurrent GBM, no standard of care exists. Thanks to the continuous improvement in radiation science and technology, reirradiation has emerged as feasible approach for patients with brain tumors. Using stereotactic radiosurgery (SRS) or stereotactic radiotherapy (SRT), either hypofractionated or conventionally fractionated schedules, several studies have suggested survival benefits following reirradiation of patients with recurrent GBM; however, there are still questions to be answered about the efficacy and toxicity associated with a second course of radiation. We provide a clinical overview on current status and recent advances in reirradiation of GBM, addressing relevant clinical questions such as the appropriate patient selection and radiation technique, optimal dose fractionation, reirradiation tolerance of the brain and the risk of radiation necrosis.

Background The targeting accuracy of proton therapy (PT) for moving soft-tissue tumours is expected to greatly improve by real-time magnetic resonance imaging (MRI) guidance. The integration of MRI and PT at the treatment isocenter would offer the opportunity of combining the unparalleled soft-tissue contrast and real-time imaging capabilities of MRI with the most conformal dose distribution and best dose steering capability provided by modern PT. However, hybrid systems for MR-integrated PT (MRiPT) have not been realized so far due to a number of hitherto open technological challenges. In recent years, various research groups have started addressing these challenges and exploring the technical feasibility and clinical potential of MRiPT. The aim of this contribution is to review the different aspects of MRiPT, to report on the status quo and to identify important future research topics. Methods Four aspects currently under study and their future directions are discussed: modelling and experimental investigations of electromagnetic interactions between the MRI and PT systems, integration of MRiPT workflows in clinical facilities, proton dose calculation algorithms in magnetic fields, and MRI-only based proton treatment planning approaches. Conclusions Although MRiPT is still in its infancy, significant progress on all four aspects has been made, showing promising results that justify further efforts for research and development to be undertaken. First non-clinical research solutions have recently been realized and are being thoroughly characterized. The prospect that first prototype MRiPT systems for clinical use will likely exist within the next 5 to 10 years seems realistic, but requires significant work to be performed by collaborative efforts of research groups and industrial partners.

Radiation therapy is an integral part of the multidisciplinary management of breast cancer. Regional lymph node irradiation in younger trials seems to provide superior target coverage as well as a reduction in long-term toxicity resulting in a small benefit in the overall survival rate. For partial breast irradiation there are now two large trials available which support the role of partial breast irradiation in low risk breast cancer patients. Multiple randomized trials have established that a sequentially applied dose to the tumor bed improves local control with the cost of worse cosmetic results.

Radiation nephropathy (RN) is a kidney injury induced by ionizing radiation. In a clinical setting, ionizing radiation is used in radiotherapy (RT). The use and the intensity of radiation therapy is limited by normal-tissue damage including kidney toxicity. Different thresholds for kidney toxicity exist for different entities of RT. Histopathologic features of RN include vascular, glomerular and tubulointerstitial damage. The different molecular and cellular pathomechanisms involved in RN are not fully understood. Ionizing radiation causes double-stranded breaks in the DNA, followed by cell death including apoptosis and necrosis of renal endothelial, tubular and glomerular cells. Especially in the latent phase of RN oxidative stress and inflammation have been proposed as putative pathomechanisms, but so far no clear evidence was found. Cellular senescence, activation of the renin–angiotensin–aldosterone-system and vascular dysfunction might contribute to RN, but only limited data is available. Several signalling pathways have been identified in animal models of RN and different approaches to mitigate RN have been investigated. Drugs that attenuate cell death and inflammation or reduce oxidative stress and renal fibrosis were tested. Renin–angiotensin–aldosterone-system blockade, anti-apoptotic drugs, statins, and antioxidants have been shown to reduce the severity of RN. These results provide a rationale for the development of new strategies to prevent or reduce radiation-induced kidney toxicity.

The integration of magnetic resonance imaging (MRI) for guidance in external beam radiotherapy has faced significant research and development efforts in recent years. The current availability of linear accelerators with an embedded MRI unit, providing volumetric imaging at excellent soft tissue contrast, is expected to provide novel possibilities in the implementation of image-guided adaptive radiotherapy (IGART) protocols. This study reviews open medical physics issues in MR-guided radiotherapy (MRgRT) implementation, with a focus on current approaches and on the potential for innovation in IGART. Daily imaging in MRgRT provides the ability to visualize the static anatomy, to capture internal tumor motion and to extract quantitative image features for treatment verification and monitoring. Those capabilities enable the use of treatment adaptation, with potential benefits in terms of personalized medicine. The use of online MRI requires dedicated efforts to perform accurate dose measurements and calculations, due to the presence of magnetic fields. Likewise, MRgRT requires dedicated quality assurance (QA) protocols for safe clinical implementation. Reaction to anatomical changes in MRgRT, as visualized on daily images, demands for treatment adaptation concepts, with stringent requirements in terms of fast and accurate validation before the treatment fraction can be delivered. This entails specific challenges in terms of treatment workflow optimization, QA, and verification of the expected delivered dose while the patient is in treatment position. Those challenges require specialized medical physics developments towards the aim of fully exploiting MRI capabilities. Conversely, the use of MRgRT allows for higher confidence in tumor targeting and organs-at-risk (OAR) sparing. The systematic use of MRgRT brings the possibility of leveraging IGART methods for the optimization of tumor targeting and quantitative treatment verification. Although several challenges exist, the intrinsic benefits of MRgRT will provide a deeper understanding of dose delivery effects on an individual basis, with the potential for further treatment personalization.

Background Linac-based stereotactic radiosurgery or fractionated stereotactic radiotherapy (SRS/FSRT) of multiple brain lesions using volumetric modulated arc therapy (VMAT) is typically performed by a multiple-isocenter approach, i.e. one isocenter per lesion, which is time-demanding for the need of independent setup verifications of each isocenter. Here, we present our initial experience with a new dedicated mono-isocenter technique with multiple non-coplanar arcs (HyperArc™, Varian Inc.) in terms of a plan comparison with a multiple-isocenter VMAT approach. Methods From August 2017 to October 2017, 20 patients with multiple brain metastases (mean 5, range 2–10) have been treated by HyperArc in 1–3 fractions. The prescribed doses (Dp) were 18–25 Gy in single-fraction, and 21–27 Gy in three-fractions. Planning Target Volume (PTV), defined by a 2 mm isotropic margin from each lesion, had mean dimension of 9.6 cm 3 (range 0.5–27.9 cm 3 ). Mono-isocenter HyperArc VMAT plans (HA) with 5 non-coplanar 180°-arcs (couch at 0°, ±45°, ±90°) were generated and compared to multiple-isocenter VMAT plans (RA) with 2 coplanar 360°-arcs per isocenter. A dose normalization of 100%Dp at 98%PTV was adopted, while D 2% (PTV) < 150%D p was accepted. All plans had to respect the constraints on maximum dose to the brainstem (D 0.5cm3  < 18 Gy) as well as to the optical nerves/chiasm, eyes and lenses (D 0.5cm3  < 15 Gy). HA and RA plans were compared in terms of dose-volume metrics, by Paddick conformity (CI) and gradient (GI) index and by V 12 and mean dose to the brain-minus-PTV, and in terms of MU and overall treatment time (OTT) per fraction. OTT was measured for HA treatments, whereas for RA plans OTT was estimated by assuming 3 min. For initial patient setup plus 5 min. For each CBCT-guided setup correction per isocenter. Results Significant variations in favour of HA plans were computed for both target dose indexes, CI ( p  < .01) and GI ( p  < .01). The lower GI in HA plans was the likely cause of the significant reduction in V 12 to the brain-minus-PTV ( p  = .023). Although at low doses, below 2–5 Gy, the sparing of the brain-minus-PTV was in favour of RA plans, no significant difference in terms of mean doses to the brain-minus-PTV was observed between the two groups ( p  = .31). Finally, both MU ( p  < .01) and OTT ( p  < .01) were significantly reduced by HyperArc plans. Conclusions For linac-based SRS/FSRT of multiple brain lesions, HyperArc plans assured a higher CI and a lower GI than standard multiple-isocenter VMAT plans. This is consistent with the computed reduction in V 12 to the brain-minus-PTV. Finally, HyperArc treatments were completed within a typical 20 min. time slot, with a significant time reduction with respect to the expected duration of multiple-isocenters VMAT.

Purpose The HyperArc VMAT (HA-VMAT) planning approach was newly developed to fulfill the demands of dose delivery for brain metastases stereotactic radiosurgery. We compared the dosimetric parameters of the HA-VMAT plan with those of the conventional VMAT (C-VMAT). Material and methods For 23 patients (1–4 brain metastases), C-VMAT and HA-VMAT plans with a prescription dose of 20–24 Gy were retrospectively generated, and dosimetric parameters for PTV (homogeneity index, HI; conformity index, CI; gradient index, GI) and brain tissue (V 2Gy -V 16Gy ) were evaluated. Subsequently, the physical characteristics (modulation complexity score for VMAT, MCSV; Monitor unit, MU) of both treatment approaches were compared. Results HA-VMAT provided higher HI (1.41 ± 0.07 vs. 1.24 ± 0.07, p  < 0.01), CI (0.93 ± 0.02 vs. 0.90 ± 0.05, p  = 0.01) and lower GI (3.06 ± 0.42 vs. 3.91 ± 0.55, p  < 0.01) values. Moderate-to-low dose spreads (V 4Gy -V 16Gy ) were significantly reduced ( p  < 0.01) in the HA-VMAT plan over that of C-VMAT. HA-VMAT plans resulted in more complex MLC patterns (lower MCSV, p  < 0.01) and higher MU ( p  < 0.01). Conclusions HA-VMAT plans provided significantly higher conformity and rapid dose falloff with respect to the C-VMAT plans.