Computer-aided diagnosis has become a necessity for accurate and immediate coronavirus disease 2019 (COVID-19) detection to aid treatment and prevent the spread of the virus. Numerous studies have proposed to use Deep Learning techniques for COVID-19 diagnosis. However, they have used very limited chest X-ray (CXR) image repositories for evaluation with a small number, a few hundreds, of COVID-19 samples. Moreover, these methods can neither localize nor grade the severity of COVID-19 infection. For this purpose, recent studies proposed to explore the activation maps of deep networks. However, they remain inaccurate for localizing the actual infestation making them unreliable for clinical use. This study proposes a novel method for the joint localization, severity grading, and detection of COVID-19 from CXR images by generating the so-called infection maps. To accomplish this, we have compiled the largest dataset with 119,316 CXR images including 2951 COVID-19 samples, where the annotation of the ground-truth segmentation masks is performed on CXRs by a novel collaborative human–machine approach. Furthermore, we publicly release the first CXR dataset with the ground-truth segmentation masks of the COVID-19 infected regions. A detailed set of experiments show that state-of-the-art segmentation networks can learn to localize COVID-19 infection with an F1-score of 83.20%, which is significantly superior to the activation maps created by the previous methods. Finally, the proposed approach achieved a COVID-19 detection performance with 94.96% sensitivity and 99.88% specificity.

IntroductionShort- and long-acting granulocyte-colony stimulating factors (G-CSFs) are approved for the reduction of febrile neutropenia. A systematic literature review was performed to identify randomized controlled trials (RCTs) and non-RCTs reporting the use of G-CSFs following chemotherapy treatment.MethodsMedline®/Medline in-process, Embase®, and the Cochrane Library were searched for studies published between January 2003 and June 2016. A hand-search of relevant conference proceedings was conducted for meetings held between 2012 and 2016. Eligible studies were restricted to those reporting a direct, head-to-head comparison of short- versus long-acting G-CSFs for reduction of chemotherapy-induced febrile neutropenia. Risk-of-bias assessments were performed for full publications only.ResultsThe search strategy yielded 4044 articles for electronic screening. Thirty-six publications were evaluated for the meta-analysis: 11 of 12 RCTs and 2 of 24 non-RCTs administered doses of the short-acting G-CSF filgrastim for ≥ 7 days. In RCT studies, there was no statistically significant difference in outcomes of interest between short- and long-acting G-CSFs. In non-RCTs, the overall risk was lower with long-acting G-CSF than with short-acting G-CSF for incidence of febrile neutropenia [overall relative risk (RR) = 0.67, P  = 0.023], hospitalizations (overall RR = 0.68, P  < 0.05), and chemotherapy dose delays (overall RR = 0.68, P  = 0.020).ConclusionsOverall, the weight of evidence from RCTs indicates little difference in efficacy between the short- and long-acting G-CSFs if dosed according to recommended guidelines. There is some evidence for greater efficacy for long-acting G-CSFs in non-RCTs, which may be a result of under-dosing of short-acting G-CSFs in general practice in real-world usage.FundingHospira Inc, which was acquired by Pfizer Inc in September 2015, and Pfizer Inc.Electronic supplementary materialThe online version of this article (10.1007/s12325-018-0798-6) contains supplementary material, which is available to authorized users.

Coronavirus disease 2019 (COVID-19) has rapidly become a global health concern after its first known detection in December 2019. As a result, accurate and reliable advance warning system for the early diagnosis of COVID-19 has now become a priority. The detection of COVID-19 in early stages is not a straightforward task from chest X-ray images according to expert medical doctors because the traces of the infection are visible only when the disease has progressed to a moderate or severe stage. In this study, our first aim is to evaluate the ability of recent state-of-the-art Machine Learning techniques for the early detection of COVID-19 from chest X-ray images. Both compact classifiers and deep learning approaches are considered in this study. Furthermore, we propose a recent compact classifier, Convolutional Support Estimator Network (CSEN) approach for this purpose since it is well-suited for a scarce-data classification task. Finally, this study introduces a new benchmark dataset called Early-QaTa-COV19 a , which consists of 1065 early-stage COVID-19 pneumonia samples (very limited or no infection signs) labelled by the medical doctors and 12 544 samples for control (normal) class. A detailed set of experiments shows that the CSEN achieves the top (over 97%) sensitivity with over 95.5% specificity b . Moreover, DenseNet-121 network produces the leading performance among other deep networks with 95% sensitivity and 99.74% specificity.

RECQL5 is a member of the RecQ family of DNA helicases and has key roles in homologous recombination, base excision repair, replication and transcription. The clinicopathological significance of RECQL5 expression in breast cancer is unknown. In this study, we have evaluated RECQL5 mRNA expression in 1977 breast cancers, and RECQL5 protein level in 1902 breast cancers [Nottingham Tenovus series (n = 1650) and ER- cohort (n = 252)]. Expression levels were correlated to aggressive phenotypes and survival outcomes. High RECQL5 mRNA expression was significantly associated with high histological grade (P = 0.007), HER2 overexpression (P = 0.032), ER+/HER2-/high proliferation genefu subtype (P < 0.0001), integrative molecular clusters (intClust 1and 9) (P < 0.0001) and poor survival (P < 0.0001). In subgroup analysis, high RECQL5 mRNA level remains significantly associated with poor BCSS in ER+ cohort (P < 0.0001) but not in ER- cohort (P = 0.116). At the protein level, in tumours with low RAD51, high RECQL5 level was significantly associated with high histological grade (P < 0.0001), higher mitotic index (P = 0.008), dedifferentiation (P = 0.025), pleomorphism (P = 0.027) and poor survival (P = 0.003). In subgroup analysis, high RECQL5/low RAD51 remains significantly associated with poor BCSS in ER+ cohort (P = 0.010), but not in ER- cohort (P = 0.628). In multivariate analysis, high RECQL5 mRNA and high RECQL5/low RAD51 nuclear protein coexpression independently influenced survival (P = 0.022) in whole cohort and in the ER+ subgroup. Preclinically, we show that exogenous expression of RECQL5 in MCF10A cells can drive proliferation supporting an oncogenic function for RECQL5 in breast cancer. We conclude that RECQL5 is a promising biomarker in breast cancer.