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.     

A comparison of mobilization and mobilization with movement on pain and range of motion in people with lateral ankle sprain: A randomized clinical trial

BackgroundMaitland and Mulligan mobilization techniques are two manual therapy methods to increase the range of motion following immobility treatment. The present study was conducted to compare two therapeutic methods, namely mobilization and mobilization with movement (MWM), on the pain and range of motion in people with lateral ankle sprain.MethodsA total of 40 individuals with grade two lateral ankle sprain were randomly divided into two groups, including the Maitland's mobilization intervention group, and the Mulligan's mobilization intervention group. Both groups underwent treatment every other day for two consecutive weeks. The pain intensity was measured using the Visual Analogue Scale (VAS), and the ankle dorsiflexion movement range using the Weight Bearing Lunge Test (WBLT) before and one day after the intervention.ResultsThere were no significant differences between the two groups in terms of pain (P = 0.297) and range of motion (P = 0.294) before the intervention. Meanwhile, after the intervention, a significant change was observed in both groups in terms of these variables, which indicates the effectiveness of both interventions (P < 0.001) and the greater effect of the mobilization with movement in reducing pain (P = 0.037) and increasing the range of motion (P = 0.021).ConclusionsBoth techniques significantly improved the range of motion and reduced pain in people with lateral ankle sprain, but Mulligan's technique was significantly more effective among the two, perhaps due to joining active and passive mobilizing tensile forces as well as interaction of afferents and efferents in the reflex arc.     

Effects of manual therapy on body posture: Systematic review and meta-analysis

BackgroundSeveral clinical trials investigated the effectiveness of MT on body posture, but a systematic review grouping the results of these studies was not found in the literature.Research questionDoes manual therapy (MT) cause postural changes?MethodsInclusion criteria were: randomized controlled trials in any population; studies in which the primary intervention was the use of any MT technique; studies that evaluated the immediate, short, medium, or long-term effects of interventions on body posture; and studies published in peer-reviewed scientific journals in any year and language. In March 2022, we conducted a search in the PUBMED, Cinahl, Embase, PEDro, and Cochrane Central databases that yielded 6627 articles, of which 38 including 1597 participants were eligible; of these, 35 could be grouped into 12 meta-analyses. The risk of bias was assessed using the PEDro scale and the certainty in the scientific evidence rated through the GRADE system.ResultsThe results allowed us to conclude with moderate certainty in the evidence that, when compared to no intervention or sham, in the short and medium term, MT reduced the forward head posture (14 studies, 584 individuals, 95%CI 0.38, 1.06), reduced thoracic kyphosis (5 studies, 217 individuals, 95%CI 0.37, 0.94), improved lateral pelvic tilt (5 studies, 211 individuals, 95%CI 0.11, 0.67) and pelvic torsion (2 studies, 120 individuals, 95%CI 0.44, 1.19) and increased plantar area (3 studies, 134 individuals, 95%CI 0.04, 0.74). With moderate certainty, there was no significant effect on shoulder protrusion (5 studies, 176 individuals, 95%CI −0.11, 0.61), shoulder alignment in the frontal plane (3 studies, 160 individuals, 95%CI −0.15, 0.52), scoliosis (2 studies, 26 individuals, 95%CI −1.57, 2.19), and pelvic anteversion (5 studies, 233 individuals, 95%CI −0.02, 0.51). With low certainty, MT had no effect on scapular upward rotation (2 studies, 74 individuals, 95%CI −0.76, 2.17). With low to very low certainty, it is possible to conclude that MT was not superior to other interventions in the short or medium term regarding the improvement of forward head posture (5 studies, 170 individuals, 95%CI −1.39, 0.67) and shoulder protrusion (3 studies, 94 individuals, 95%CI −4.04, 0.97).SignificanceMT can be recommended to improve forward head posture, thoracic kyphosis and pelvic alignment in the short and medium term, but not shoulder posture and scoliosis. MT reduces the height of the plantar arch and this must be taken into account in physical therapy planning. PROSPERO registration number: CRD42021244423.     

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。     

舌象分割技术的文献计量学分析

[目的]了解舌象分割技术的研究现况及发展趋势,为舌象客观化提供参考。[方法]基于中国知网、维普、万方及Pubmed数据库检索建库至2018年公开发表的舌象分割技术文献,利用Note Express 3.20、Excel 2016、SATI3.2、UCINET 6.0软件进行文献计量学及关键词共现网络分析。[结果]舌象分割技术文献研究整体呈上升趋势,北京工业大学居首位。主要基金资助为国家自然科学基金。根据普赖斯定律的要求,基本形成"核心作者群"。舌象分割以Snake模型和基于阈值的分割技术为主。关键词集中分布在"舌诊""图像分割""舌诊客观化"等方面。[结论]舌象分割技术研究仍需受到重视,国家政府应加大资助力度,加强研究机构间合作,尚存在一些舌象分割评价标准问题,需待改进。     

基于机器学习的脑胶质瘤多模态影像分析

脑部胶质瘤是临床中常见的一种原发性脑肿瘤，具有复发率高、死亡率高以及治愈率低的特点。常规临床诊断主要依靠计算机断层扫描(CT)和磁共振成像(MRI)检查技术进行鉴别。随着成像技术和机器学习方法的不断发展，多模态影像智能分析技术已经逐步成为研究热点，在脑胶质瘤的病灶分割测量、肿瘤分级、预后生存周期预测和基因型辨别等方面具有重要的应用前景。本文重点介绍基于机器学习和多模态影像在脑胶质瘤临床辅助诊断和预后评估中的应用进展。     

Spinal manual therapy and exercises for chronic hamstring injuries in a sprinter: A case report

IntroductionHamstring injuries tend to be chronic in nature and thus require considerable recovery time in athletes. Although some rehabilitation protocols have been previously advocated, there is no consensus in terms of the treatment protocol for chronic hamstring injuries.MethodsWe present the case of a 15-year-old male sprinter who was successfully treated with a combination of manual therapy targeting the lumbosacral region and hamstring-specific exercises. The patient presented with hamstring pain which persisted for 7 weeks.ResultsManual therapy immediately reduced pain and increased muscle strength. The patient was able to run satisfactorily without pain 30 days after the initial intervention.ConclusionsThis case report suggests that the use of manual therapy targeting the lumbosacral region, along with hamstring exercises, may be beneficial in chronic hamstring pain management.     

An electronic travel guide for visually impaired – vehicle board recognition system through computer vision techniques

Abstract

Purpose: In the context of assistive technology, mobility takes the meaning of “moving safely, gracefully, and comfortably”.The aim of this article is to provide a system which will be a convenient means of navigation for the Visually Impaired people, in the public transport system.

Method: A blind regular commuter who travels by public transport facility finds difficulty in identifying the vehicle that is nearing the stop. Hence, a real-time system that dynamically identifies the nearing vehicle and informs the commuters is necessary. This paper proposes such a system namely the “Vehicle Board Recognition System” (VBRS). Computer Vision techniques such as segmentation, object recognition, text detection and optical character recognition are utilized to build the system, which will detect, analyze, derive and communicate the information to the passengers.

Results: Thanks to the rapid development in technology, there are several navigation systems both hand held and wearable, available to help visually impaired (VI) people move comfortably both indoor and outdoor. Many blind people are not comfortable in using these devices or they are not affordable for them. Thus the proposed system gives them the comfort of navigation.

Conclusion: This system can be installed in the bus stop to assist the Visually Impaired, from externally rather than their hand held or wearable assistive devices.

• Implications for rehabilitation

• This proposed system will help the visually impaired to

• ensure secure navigation

• be independent of the others

• develop self confidence.

• overcome the training, affordability of wearable/ handheld devices.