Computer-aided diagnosis tool for cervical cancer screening with weakly supervised localization and detection of abnormalities using adaptable and explainable classifier

While pap test is the most common diagnosis methods for cervical cancer, their results are highly dependent on the ability of the cytotechnicians to detect abnormal cells on the smears using brightfield microscopy. In this paper, we propose an explainable region classifier in whole slide images that could be used by cyto-pathologists to handle efficiently these big images (100,000x100,000 pixels). We create a dataset that simulates pap smears regions and uses a loss, we call classification under regression constraint, to train an efficient region classifier (about 66.8% accuracy on severity classification, 95.2% accuracy on normal/abnormal classification and 0.870 KAPPA score). We explain how we benefit from this loss to obtain a model focused on sensitivity and, then, we show that it can be used to perform weakly supervised localization (accuracy of 80.4%) of the cell that is mostly responsible for the malignancy of regions of whole slide images. We extend our method to perform a more general detection of abnormal cells (66.1% accuracy) and ensure that at least one abnormal cell will be detected if malignancy is present. Finally, we experiment our solution on a small real clinical slide dataset, highlighting the relevance of our proposed solution, adapting it to be as easily integrated in a pathology laboratory workflow as possible, and extending it to make a slide-level prediction.     

Work-related injuries in the Australian education sector: A retrospective cohort study

IntroductionEducators are exposed to several work-related hazards. Evidence suggests musculoskeletal pain, psychological distress, and student-inflicted violence-related injuries are common. However, there is little evidence on the burden of workplace injury among Australian educators.AimTo compare incidence of injury claims and duration of compensated time off work between educators and non-educators, and associated factors.MethodsRetrospective cohort study of 1,559,676 Australian workers’ compensation claims, including 84,915 educator claims, lodged between July 2009 to June 2015, from the National Dataset for Compensation-based Statistics. Cases were included if aged 18+ years and working in the education sector less than 100 h per week. Negative binomial regression models estimated the relative risk of making a compensation claim and survival analyses calculated disability duration within educators by sex, age, injury type and mechanism, socioeconomic area, remoteness, and jurisdiction.ResultsCompared to non-educators, educators had lower rates of injury claims and shorter disability durations. However, educators had a higher rate of claims for mental health conditions and assault, with the highest risk being among those in special education and education aides. Among educators, injury claim rates were highest among special educators, education aides, and secondary educators.Discussion and ConclusionThough surveys indicate Australians in the education sector have higher incidences of work-related injuries, this study found lower incidence of injury claims and shorter disability durations than others. Educators’ injury-reporting and absenteeism behaviors may be constrained by ethical, social, and administrative attitudes. Educators had higher rates of claims for mental health and assault-related injury, particularly special educators, and education aides, which suggests a need for targeted prevention efforts.     

High-Pressure Water Swelling Sealant Injection Injury to the Hand: a Case Report and Review of the Literature

High-pressure injection injuries (HPII) caused by water swelling sealant are rare at present. The patient generally has small-sized skin lesions, and the misleadingly benign presentation may cause delayed treatment at the early stage of management. In addition, radiographic examination may be underestimated. Subsequently, the inadequate surgical intervention may cause tissue necrosis and poor prognosis. Furthermore, the early recognition of water swelling sealant injected into tissue and emergent surgical intervention are the key to successful management for the patient with HPII caused by injecting water swelling sealant to tissue.     

注射用肉毒毒素制剂及其研发进展

肉毒毒素(Botulinum Toxin,BoNT)已成为现代医学最具多用途的治疗药物之一。通过将肉毒毒素注射到特定过度活动的肌肉中,可以阻断神经和肌肉之间的信号传导,引起肌肉的松弛性麻痹,从而达到治疗的功效。从业者应熟悉各类产品的特性,以实现安全有效地使用。除了已经上市的众多肉毒毒素产品外,目前还在开发其他新型制剂,这些产品将会进一步扩大肉毒毒素的适用范围,以及给患者提供更多的选择。     

改良单图像法手工测量髌骨不稳患者胫骨结节-股骨滑车沟间距的可行性分析

目的 探讨改良单图像法手工测量髌骨不稳患者胫骨结节-股骨滑车沟（tibial tuberosity-trochlear groove，TT-TG）间距的可行性。 方法 选取髌骨不稳患者30例。高年资手术医师A、B，使用改良单图像法手工测量髌骨不稳患者TT-TG间距，对比高资年影像学医师C，使用双图法测量髌骨不稳患者TT-TG间距。应用Cronbach′s alpha系数评价结果的可信度。应用组内相关系数（intraclass correlation coefficient，ICC）评价结果的可重复性。使用Bland-Altman分析图评价结果的一致性。 结果 高年资手术医师A、B使用改良单图像法手工测量髌骨不稳患者TT-TG间距分别和高年资影像学医师C使用双图法测量髌骨不稳患者TT-TG间距比较，Cronbach′s alpha系数分别为0.913和0.959，组内相关系数分别为0.913和0.958。Bland-Altman分析图显示，TT-TG间距差值（mm）的均值为-0.276（95%CI：-3.526~2.974）和0.143（95%CI：-3.110~3.397）。A、B医师之间使用改良单图像法手工测量髌骨不稳患者TT-TG间距比较，Cronbach′s alpha系数为0.891，组内相关系数为0.891。Bland-Altman分析图显示TT-TG间距差值（mm）的均值为-0.276（95%CI：-3.526~2.974）。 结论 改良单图像法手工测量髌骨不稳患者TT-TG间距操作简单，可以准确测量出髌骨不稳患者的TT-TG间距，该方法和双图法可以相互替换使用。