What information can we gain from performing adaptive radiotherapy of head and neck cancer patients from the past 10 years?

The aim of the review was to present the current literature status about replanning regarding anatomical and dosimetric changes in the target and OARs in the head and neck region during radiotherapy, to discuss and to analyze factors influencing the decision for adaptive radiotherapy of head and neck cancer patients. Significant progress has been made in head and neck patients’ evaluation and qualification for adapted radiotherapy over the past ten years. Many factors leading to anatomical and dosimetric changes during treatment have been identified. Based on the literature, the most common factors triggering re-plan are weight loss, tumor and nodal changes, and parotid glands shrinkage. The fluctuations in dose distribution in the clinical area are significant predictive factors for patients’ quality of life and the possibility of recovery. It has been shown that re-planning influence clinical outcomes: local control, disease free survival and overall survival. Regarding literature studies, it seems that adaptive radiotherapy would be the most beneficial for tumors of immense volume or those in the nearest proximity of the OARs. All researchers agree that the timing of re-planning is a crucial challenge, and there are still no clear consensus guidelines for time or criteria of re-planning. Nowadays, thanks to significant technological progress, the decision is mostly made based on observation and supported with IGRT verification. Although further research is still needed, adaptive strategies are evolving and now became the state of the art of modern radiotherapy.     

Feasibility of a method for low contrast CT image quality assessment using difference detail curves for abdominal scans

This work describes a measurement method for assessing dose-related image-quality of CT scans based on the difference detail curve (DDC) method, and showcases its use in a low contrast setting. The method is based on a phantom consisting of elliptical slices of different sizes into which contrast object modules can be inserted. These modules contain contrast objects based on (synthetic) resin mixtures with sucrose (native) or sodium iodine (contrast medium). Mixing ratios are provided to achieve a range of clinically relevant CT-numbers with these materials. The phantom is characterized in terms of contrast accuracy, energy dependency and long-term drift with satisfying results. Contrast accuracy and energy dependency are similar to that of water or soft tissue. Image quality of 655 scans of the phantom acquired at 30 different clinical institutions and with 16 different CT scanner models from 4 manufacturers was assessed by calculating a difference detail curve (DDC) from evaluation of up to 5 human observers using a custom-made software (RadiVates) described in this work. Based on these measurements, inter-observer variability was quantified using a bootstrap method and was shown to be a large contributor to the overall variability. This work demonstrates that assessment of CT image quality is feasible with the aforementioned phantom and DDC method.     

Automatic segmentation of thoracic CT images using three deep learning models

PurposeDeep learning (DL) techniques are widely used in medical imaging and in particular for segmentation. Indeed, manual segmentation of organs at risk (OARs) is time-consuming and suffers from inter- and intra-observer segmentation variability. Image segmentation using DL has given very promising results. In this work, we present and compare the results of segmentation of OARs and a clinical target volume (CTV) in thoracic CT images using three DL models.Materials and methodsWe used CT images of 52 patients with breast cancer from a public dataset. Automatic segmentation of the lungs, the heart and a CTV was performed using three models based on the U-Net architecture. Three metrics were used to quantify and compare the segmentation results obtained with these models: the Dice similarity coefficient (DSC), the Jaccard coefficient (J) and the Hausdorff distance (HD).ResultsThe obtained values of DSC, J and HD were presented for each segmented organ and for the three models. Examples of automatic segmentation were presented and compared to the corresponding ground truth delineations. Our values were also compared to recent results obtained by other authors.ConclusionThe performance of three DL models was evaluated for the delineation of the lungs, the heart and a CTV. This study showed clearly that these 2D models based on the U-Net architecture can be used to delineate organs in CT images with a good performance compared to other models. Generally, the three models present similar performances. Using a dataset with more CT images, the three models should give better results.     

Ultrasound-guided Brachytherapy for Cervix Cancer

Radiotherapy and brachytherapy are the definitive treatments for locally advanced cervix cancer. The use of soft-tissue imaging, particularly magnetic resonance imaging, has enhanced their effectiveness and improved clinical outcomes. However, the use of magnetic resonance imaging is largely restricted to well-resourced centres in both the first and developing world and remains elusive to many less advantaged centres, particularly those in areas with a high burden of cervix cancer. Ultrasound is an accessible, affordable and accurate imaging modality that can be used throughout the brachytherapy procedure. Ultrasound is primarily used to ensure safe insertion of the applicator but can also be used to guide planning. The methods used to utilise ultrasound images for planning are described. Ultrasound is particularly useful as a verification aid to confirm applicator placement after patients are moved and transferred around the radiotherapy department. It can also be used to verify the dimensions of treatment volumes over the course of brachytherapy. There is a crucial unmet need for an accessible economical soft-tissue imaging modality in cervical brachytherapy. Ultrasound has the potential to meet this need.     

Digital surface scanning in flap perfusion

Monitoring vascular perfusion of transferred tissue is essential in reconstructive surgery to recognize early flap failure. The aim of this study was to evaluate the ability of a digital surface scanner to detect vascular perfusion disorders through the monitoring of skin colour changes. A total of 160 surface scans of the forearm skin were performed with a TRIOS 3D scanner. Vascular compromise was simulated at different time-points by intermittent occlusion of the blood supply to the forearm skin (first the arterial blood supply and then the venous blood supply). Skin colour changes were examined according to the hue, saturation, and value colour scale. Colour differences were analysed with a paired t-test. Significant differences were observed between the colour of the normal skin and that of the vascular compromised skin (P < 0.01). The surface scanner could distinguish between arterial occlusion and venous congestion (P < 0.01). A digital surface scan is an objective, non-invasive tool to detect early vascular perfusion disorders of the skin.     

基于自动勾画和快速蒙特卡罗计算的放射治疗全身器官剂量数据库平台的可行性研究

目的:探讨建立一种放射治疗全身器官剂量数据库平台的可行性。方法:使用基于深度学习的自动勾画软件DeepViewer?1例食管癌患者的全身CT上勾画全身器官，然后利用基于GPU加速的蒙特卡罗软件ARCHER计算相应的器官剂量分布，最后利用Lyman-Kutcher-Burman（LKB）模型评估放疗患者正常组织并发症概率（NTCP）。结果:针对该病例，成功建立基于DeepViewer?ARCHER和LKB模型的全身器官剂量数据库，发现距离靶区越近的器官剂量越大，其中心脏与靶区间距离最小，剂量为14.11 Gy，但因其模型参数特殊，通过LKB模型计算的NTCP为0.00%；左、右肺的剂量分别为3.19和1.16 Gy，但是NTCP值却很大，分别为2.13%和1.60%。对于距离靶区较远的头颈部器官（视交叉、视神经和眼）和腹部器官（直肠、膀胱和股骨头）剂量分别约为9和2 mGy，并且NTCP均近似为0.00%。结论:研究结果证明通过自动勾画软件DeepViewer?蒙特卡罗软件ARCHER和LKB模型建立全身器官剂量数据库的可行性。     

DEep learning-based rapid Spiral Image REconstruction (DESIRE) for high-resolution spiral first-pass myocardial perfusion imaging

The objective of the current study was to develop and evaluate a DEep learning-based rapid Spiral Image REconstruction (DESIRE) technique for high-resolution spiral first-pass myocardial perfusion imaging with whole-heart coverage, to provide fast and accurate image reconstruction for both single-slice (SS) and simultaneous multislice (SMS) acquisitions. Three-dimensional U-Net–based image enhancement architectures were evaluated for high-resolution spiral perfusion imaging at 3 T. The SS and SMS MB = 2 networks were trained on SS perfusion images from 156 slices from 20 subjects. Structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and normalized root mean square error (NRMSE) were assessed, and prospective images were blindly graded by two experienced cardiologists (5: excellent; 1: poor). Excellent performance was demonstrated for the proposed technique. For SS, SSIM, PSNR, and NRMSE were 0.977 [0.972, 0.982], 42.113 [40.174, 43.493] dB, and 0.102 [0.080, 0.125], respectively, for the best network. For SMS MB = 2 retrospective data, SSIM, PSNR, and NRMSE were 0.961 [0.950, 0.969], 40.834 [39.619, 42.004] dB, and 0.107 [0.086, 0.133], respectively, for the best network. The image quality scores were 4.5 [4.1, 4.8], 4.5 [4.3, 4.6], 3.5 [3.3, 4], and 3.5 [3.3, 3.8] for SS DESIRE, SS L1-SPIRiT, MB = 2 DESIRE, and MB = 2 SMS-slice-L1-SPIRiT, respectively, showing no statistically significant difference (p = 1 and p = 1 for SS and SMS, respectively) between L1-SPIRiT and the proposed DESIRE technique. The network inference time was ~100 ms per dynamic perfusion series with DESIRE, while the reconstruction time of L1-SPIRiT with GPU acceleration was ~ 30 min. It was concluded that DESIRE enabled fast and high-quality image reconstruction for both SS and SMS MB = 2 whole-heart high-resolution spiral perfusion imaging.