A Stacked Generalization of 3D Orthogonal Deep Learning Convolutional Neural Networks for Improved Detection of White Matter Hyperintensities in 3D FLAIR Images

BACKGROUND AND PURPOSE:Accurate and reliable detection of white matter hyperintensities and their volume quantification can provide valuable clinical information to assess neurologic disease progression. In this work, a stacked generalization ensemble of orthogonal 3D convolutional neural networks, StackGen-Net, is explored for improving automated detection of white matter hyperintensities in 3D T2-FLAIR images.MATERIALS AND METHODS:Individual convolutional neural networks in StackGen-Net were trained on 2.5D patches from orthogonal reformatting of 3D-FLAIR (n = 21) to yield white matter hyperintensity posteriors. A meta convolutional neural network was trained to learn the functional mapping from orthogonal white matter hyperintensity posteriors to the final white matter hyperintensity prediction. The impact of training data and architecture choices on white matter hyperintensity segmentation performance was systematically evaluated on a test cohort (n = 9). The segmentation performance of StackGen-Net was compared with state-of-the-art convolutional neural network techniques on an independent test cohort from the Alzheimer’s Disease Neuroimaging Initiative-3 (n = 20).RESULTS:StackGen-Net outperformed individual convolutional neural networks in the ensemble and their combination using averaging or majority voting. In a comparison with state-of-the-art white matter hyperintensity segmentation techniques, StackGen-Net achieved a significantly higher Dice score (0.76 [SD, 0.08], F1-lesion (0.74 [SD, 0.13]), and area under precision-recall curve (0.84 [SD, 0.09]), and the lowest absolute volume difference (13.3% [SD, 9.1%]). StackGen-Net performance in Dice scores (median = 0.74) did not significantly differ (P = .22) from interobserver (median = 0.73) variability between 2 experienced neuroradiologists. We found no significant difference (P = .15) in white matter hyperintensity lesion volumes from StackGen-Net predictions and ground truth annotations.CONCLUSIONS:A stacked generalization of convolutional neural networks, utilizing multiplanar lesion information using 2.5D spatial context, greatly improved the segmentation performance of StackGen-Net compared with traditional ensemble techniques and some state-of-the-art deep learning models for 3D-FLAIR.

White matter hyperintensities (WMHs) correspond to pathologic features of axonal degeneration, demyelination, and gliosis observed within cerebral white matter.¹ Clinically, the extent of WMHs in the brain has been associated with cognitive impairment, Alzheimer’s disease and vascular dementia, and increased risk of stroke.^2,3 The detection and quantification of WMH volumes to monitor lesion burden evolution and its correlation with clinical outcomes have been of interest in clinical research.^4,5 Although the extent of WMHs can be visually scored,⁶ the categoric nature of such scoring systems makes quantitative evaluation of disease progression difficult. Manually segmenting WMHs is tedious, prone to inter- and intraobserver variability, and is, in most cases, impractical. Thus, there is an increased interest in developing fast, accurate, and reliable computer-aided automated techniques for WMH segmentation.Convolutional neural network (CNN)-based approaches have been successful in several semantic segmentation tasks in medical imaging.⁷ Recent works have proposed using deep learning–based methods for segmenting WMHs using 2D-FLAIR images.^8-11 More recently, a WMH segmentation challenge¹² was also organized (http://wmh.isi.uu.nl/) to facilitate comparison of automated segmentation of WMHs of presumed vascular origin in 2D multislice T2-FLAIR images. Architectures that used an ensemble of separately trained CNNs showed promising results in this challenge, with 3 of the top 5 winners using ensemble-based techniques.¹²Conventional 2D-FLAIR images are typically acquired with thick slices (3–4 mm) and possible slice gaps. Partial volume effects from a thick slice are likely to affect the detection of smaller lesions, both in-plane and out-of-plane. 3D-FLAIR images, with isotropic resolution, have been shown to achieve higher resolution and contrast-to-noise ratio¹³ and have shown promising results in MS lesion detection using 3D CNNs.¹⁴ Additionally, the isotropic resolution enables viewing and evaluation of the images in multiple planes. This multiplanar reformatting of 3D-FLAIR without the use of interpolating kernels is only possible due to the isotropic nature of the acquisition. Network architectures that use information from the 3 orthogonal views have been explored in recent works for CNN-based segmentation of 3D MR imaging data.¹⁵ The use of data from multiple planes allows more spatial context during training without the computational burden associated with full 3D training.¹⁶ The use of 3 orthogonal views simultaneously mirrors how humans approach this segmentation task.Ensembles of CNNs have been shown to average away the variances in the solution and the choice of model- and configuration-specific behaviors of CNNs.¹⁷ Traditionally, the solutions from these separately trained CNNs are combined by averaging or using a majority consensus. In this work, we propose the use of a stacked generalization framework (StackGen-Net) for combining multiplanar lesion information from 3D CNN ensembles to improve the detection of WMH lesions in 3D-FLAIR. A stacked generalization¹⁸ framework learns to combine solutions from individual CNNs in the ensemble. We systematically evaluated the performance of this framework and compared it with traditional ensemble techniques, such as averaging or majority voting, and state-of-the-art deep learning techniques.     

Importance of serum phosphate in elderly patients with diabetes mellitus

BACKGROUND Metabolic disturbances including changes in serum calcium,magnesium or phosphate(P) influence the prevalence of type 2 diabetes mellitus(DM).We assessed the importance of serum P in elderly patients with type 2 DM vs nondiabetes mellitus(non-DM) in relation to renal function.AIM To determine the association between serum P and serum glucose or insulin resistance in diabetic and non-diabetic patients.METHODS One hundred-ten subjects with a mean age of 69.02±14.3 years were enrolled.Twenty-nine of the participants had type 2 DM(26.4%).The incidence of hypertension,smoking and receiving vitamin D(vitD) derivates were recorded.The participants were classified by both estimated glomerular filtration rate(eGFR) and albuminuria categories according to the Kidney Disease Improving Global Outcomes 2012 criteria.RESULTS We divided the patients in two groups according to the P cut-off point related to DM value.A comparison between high and low P showed that body mass index30.2±6.3 vs 28.1±4.6(P=0.04),mean glucose 63.6 vs 50.2(P=0.03),uric acid 6.7±1.6 vs 6.09±1.7(P=0.05),mean intact-parathyroid hormone 68.06 vs 47.4(P=0.001),systolic blood pressure 147.4±16.7 vs 140..2±16.1(P=0.02),mean albuminuria 63.2 vs 50.6(P=0.04) and eGFR 45.6±22.1 vs 55.4±21.5(P=0.02)were significantly different.χ~2 tests showed a significant association between high P and DM,hypertension,receiving vitD,smoking and eGFR stage(χ~2=6.3,P=0.01,χ~2=3.9,P=0.03,χ~2=6.9,P=0.009,χ~2=7.04,P=0.01 and χ~2=7.36,P=0.04,respectively).The adjusted model showed that older age,female gender and increased body mass index were significant predictors of type 2 DM when entering the covariates.CONCLUSION High serum P contributes to vascular and metabolic disturbances in elderly patients with type 2 DM and renal impairment.     

Chest wall pain following lung stereotactic body radiation therapy using 48 Gy in three fractions: A search for predictors

Purpose

Chest wall pain is an uncommon but bothersome late complication following lung stereotactic body radiation therapy. Despite numerous studies investigating predictors of chest wall pain, no clear consensus has been established for a chest wall constraint. The aim of our study was to investigate factors related to chest wall pain in a homogeneous group of patients treated at our institution.

经9次核酸检测终确诊的新型冠状病毒肺炎患者1例分析

目前新型冠状病毒肺炎(COVID-19)疫情在全球蔓延,形势严峻,并对全球公共卫生事业构成巨大挑战,快速准确的诊断COVID-19对疫情的防控有重要意义。本文报道1例COVID-19患者的调查和确诊过程,以对COVID-19确诊和疫情防控提供有价值的参考。患者为赴渝务工于2020年1月23日返乡人员,在渝期间,其同工地的一同事确诊为COVID-19,之后该工地接连有另外8位同事被确诊。患者返乡后2月2日被当地疫情防控单位采取医学隔离。患者于隔离后不久出现咳嗽,阵发性,干咳为主,偶可咳出黄色痰液等COVID-19相关临床症状,遂被当地新型冠状病毒肺炎定点医疗单位收治,后经市级新型冠状病毒肺炎诊治专家组远程视频会诊转入四川大学华西医院资阳医院。患者先后经历9次核酸检测,在前8次核酸检测均为阴性的情况下,于第9次核酸检测结果为阳性,2月21日最终确诊为新型冠状病毒肺炎。     

Porocarcinoma coexisting at a site of Bowen disease in a 63‐year‐old woman

Porocarcinoma is an unusual, locally aggressive and potentially fatal neoplasm. Several cutaneous malignancies have been described in association with porocarcinoma, including squamous cell carcinoma, basal cell carcinoma and tricholemmal carcinoma. Previous reports have indicated that the occurrence of malignant tumours in combination with porocarcinoma is extremely rare, in particular with regard to Bowen disease (BD). We report an uncommon case of porocarcinoma occurring synchronously in a single BD lesion in a 63‐year‐old woman with multiple BD lesions. The clinical and histological findings confirmed this diagnosis.