No abstract

While Computerised Tomography (CT) may have been the first imaging tool to study human brain, it has not yet been implemented into clinical decision making process for diagnosis of Alzheimers disease (AD). On the other hand, with the nature of being prevalent, inexpensive and non-invasive, CT does present diagnostic features of AD to a great extent. This study explores the significance and impact on the application of the burgeoning deep learning techniques to the task of classification of CT brain images, in particular utilising convolutional neural network (CNN), aiming at providing supplementary information for the early diagnosis of Alzheimers disease. Towards this end, three categories of CT images (N=285) are clustered into three groups, which are AD, Lesion (e.g. tumour) and Normal ageing. In addition, considering the characteristics of this collection with larger thickness along the direction of depth (z) (∼3-5mm), an advanced CNN architecture is established integrating both 2D and 3D CNN networks. The fusion of the two CNN networks is subsequently coordinated based on the average of Softmax scores obtained from both networks consolidating 2D images along spatial axial directions and 3D segmented blocks respectively. As a result, the classification accuracy rates rendered by this elaborated CNN architecture are 85.2%, 80% and 95.3% for classes of AD, Lesion and Normal respectively with an average of 87.6%. Additionally, this improved CNN network appears to outperform the others when in comparison with 2D version only of CNN network as well as a number of state of the art hand-crafted approaches. As a result, these approaches deliver accuracy rates in percentage of 86.3, 85.6±1.10, 86.3±1.04, 85.2±1.60, 83.1±0.35 for 2D CNN, 2D SIFT, 2D 1 KAZE, 3D SIFT and 3D KAZE respectively. The two major contributions of the paper constitute a new 3-D approach while applying deep learning technique to extract signature information rooted in both 2D slices and 3D blocks of CT images and an elaborated hand-crated approach of 3D KAZE.

BACKGROUND: Neuroendocrine carcinoma (NEC) of the breast, a pathologic entity newly defined in the 2003 World Health Organization classification of tumors, is a rare type of tumor that is not well recognized or studied. The purpose of this first case-controlled study is to reveal the clinicopathologic features, therapeutic response, and outcomes of patients with NEC of the breast. METHODS: Seventy-four patients with NEC of the breast who were treated at The University of Texas M. D. Anderson Cancer Center were analyzed; 68 of them had complete clinical follow-up. Two cohorts of invasive mammary carcinoma cases were selected to pair with NEC to reveal demographic, pathologic, and clinical features at presentation, along with therapeutic response to treatment and patient outcomes. RESULTS: NEC was more likely to be estrogen receptor/progesterone receptor positive and human epidermal growth factor receptor 2 negative. Despite similar age and disease stages at presentation, NEC showed a more aggressive course than invasive ductal carcinoma, with a higher propensity for local and distant recurrence and poorer overall survival. High nuclear grade, large tumor size, and regional lymph node metastasis were significant negative prognostic factors for distant recurrence-free survival; high nuclear grade and regional lymph node metastasis were also significant negative prognostic factors for overall survival. Although endocrine therapy and radiation therapy showed a trend toward improved survival, the small number of cases in this study limited the statistical power to reveal therapeutic benefits in NEC of the breast. CONCLUSIONS: NEC is a distinct type of aggressive mammary carcinoma. Novel therapeutic approaches should be explored for this uniquely different clinical entity.

No abstract