姑息医学在大肠癌治疗中的地位和应用策略

大肠癌的治疗应采用一种无缝的连接方式将姑息治疗与抗肿瘤治疗整合在一起。姑息医学的采用应贯穿肿瘤治疗的始终,以期更好地提高生命质量,尊重生命价值,体现医学本质和人文关怀。     

乳腺癌手术患者术前心理危机的原因剖析与应对策略

乳腺癌手术患者术前严重的心理危机对其极为不利,笔者从多方面剖析了患者术前心理危机产生的原因,同时针对乳腺癌手术患者术前心理危机如何有效应对提出了诸多策略,最后就目前临床工作中存在的一些不足进行了必要的思考。     

对宫颈癌中前哨淋巴结检测的认识

广泛子宫切除+盆腔淋巴结清扫是治疗早期宫颈癌的标准术式。但对无盆腔淋巴结转移患者,淋巴结清扫并无治疗意义,且伴随多种并发症。前哨淋巴结检测有望解决这一问题,其在宫颈癌中的应用有较大可行性,亦存在局限性。只有正确认识并应用之,才能造福患者。     

非小细胞肺癌术后化疗循证医学证据引发的思考

肺癌是目前对人类生命威胁最大的恶性肿瘤之一.对非小细胞肺癌术后化疗的循证医学证据及由此引发的思考:对循证医学的局限性及认识真理的曲折性进行了阐述.     

与癌共存安享欢乐生活

癌症是现代社会人群意外死亡的致命杀手,目前医学科学还没有完美预防和治疗它的措施和办法,恐惧、悲观、失望、焦虑是有害的,过度治疗也不可取,与癌共存,安享生活是值得提倡的理念。     

乳腺癌术式的演变及其最佳选择

乳腺癌作为女性常见的恶性肿瘤之一,一直是肿瘤学界研究的热点和焦点。手术作为其基本的治疗手段,术式几经改变。通过对乳腺癌术式演变的历史回顾,认为正是由于对乳腺癌生物学行为研究的不断深入,使得乳腺癌手术切除范围更趋于规范和科学。而由生物医学模式向生物—心理—社会医学模式的转变,以及循证医学(EBM)研究的开展,更促进了乳腺癌术式的不断改进,以最大程度减少并发症,获得更为满意的疗效。     

食管癌诊断方法研究进展及面临的问题

食管癌诊断方法研究,涵盖流行病学、生物化学、病理学、肿瘤学、分子生物学等多学科。临床需求是医学科学进步的原动力,科技进步推动了医学发展,食管癌诊断方法的研究和正确的科研思路在控制食管癌发病率和死亡率中起重要作用。     

循证医学与卵巢癌的治疗

循证医学(EBM)是在临床实践中通过科学的方法获得最充分的证据,并对病人做出最佳诊治决策的一门科学。目前卵巢癌的治疗还存在很多不规范的问题,利用循证医学观点来指导卵巢癌治疗方案的选择,对保留患者的生育功能、生理功能、提高生活质量有着重要的指导意义。     

Processing speed in children treated for brain tumors: effects of radiation therapy and age

The current study examined processing speed in children two years post-treatment for brain tumors (BT) with radiation therapy (RT) compared to those treated with without RT. Participants included 59 children (4–17 years) with BT assessed as part of the Brain Radiation Investigative Study Consortium (BRISC). Processing speed was assessed at two time points: Time1 (3–9 months post-surgery) for 26 children who received whole brain or focal RT (RT group) and 33 treated without RT (no-RT group), and again two years later (Time2) for 42 participants (17 RT, 25 no-RT). Linear mixed effects (LME) regression analyses examined differences in cognitive and motor speed between groups and across visits, with age at Time1 (age1) treated as a moderating variable, and sex and primary tumor size as covariates. No effects for treatment group or visit were found for motor speed (Pegboard) or mean reaction time (Attention Network Task). On the Wechsler Processing Speed Index (PSI), the no-RT group performed better than the RT group, with a group-by-age interaction such that across visits, the difference between the no-RT and RT groups was larger among children who were older at initial treatment (≥10 years) than among those who were younger (<10 years). Cumulative brain injury earlier in life (tumor, surgery, plus RT) may result in greater impact on more complex tasks of cognitive efficiency. Children receiving RT showed reduced processing speed over time, with a larger group difference among those who were over 10 years at treatment.     

A performance comparison between shallow and deeper neural networks supervised classification of tomosynthesis breast lesions images

Computer Aided Decision (CAD) systems, based on 3D tomosynthesis imaging, could support radiologists in classifying different kinds of breast lesions and then improve the diagnosis of breast cancer (BC) with a lower X-ray dose than in Computer Tomography (CT) systems.In previous work, several Convolutional Neural Network (CNN) architectures were evaluated to discriminate four different classes of lesions considering high-resolution images automatically segmented: (a) irregular opacity lesions, (b) regular opacity lesions, (c) stellar opacity lesions and (d) no-lesions. In this paper, instead, we use the same previously extracted relevant Regions of Interest (ROIs) containing the lesions, but we propose and evaluate two different approaches to better discriminate among the four classes.In this work, we evaluate and compare the performance of two different frameworks both considering supervised classifiers topologies. The first framework is feature-based, and consider morphological and textural hand-crafted features, extracted from each ROI, as input to optimised Artificial Neural Network (ANN) classifiers. The second framework, instead, considers non-neural classifiers based on automatically computed features evaluating the classification performance extracting several sets of features using different Convolutional Neural Network models.Final results show that the second framework, based on features computed automatically by CNN architectures performs better than the first approach, in terms of accuracy, specificity, and sensitivity.