Globally, the incidence rate for breast cancer ranks first. Treatment for early-stage breast cancer is highly cost effective. Five-year survival rate for stage 0–2 breast cancer exceeds 90%. Screening mammography has been acknowledged as the most reliable way to diagnose breast cancer at an early stage. Taiwan government has been urging women without any symptoms, aged between 45 and 69, to have a screening mammogram bi-yearly. This brings about a large workload for radiologists. In light of this, this paper presents a deep neural network (DNN)-based model as an efficient and reliable tool to assist radiologists with mammographic interpretation. For the first time in the literature, mammograms are completely classified into BI-RADS categories 0, 1, 2, 3, 4A, 4B, 4C and 5. The proposed model was trained using block-based images segmented from a mammogram dataset of our own. A block-based image was applied to the model as an input, and a BI-RADS category was predicted as an output. At the end of this paper, the outperformance of this work is demonstrated by an overall accuracy of 94.22%, an average sensitivity of 95.31%, an average specificity of 99.15% and an area under curve (AUC) of 0.9723. When applied to breast cancer screening for Asian women who are more likely to have dense breasts, this model is expected to give a higher accuracy than others in the literature, since it was trained using mammograms taken from Taiwanese women.

Introduction: A better understanding of the regulatory role of microorganisms on soil phosphorous (P) mobilization is critical for developing sustainable fertilization practices and reducing P resource scarcity. The phoD genes regulate soil organic P (Po) mobilization.Methods: Based on the long-term P application experiments in acid purple soil of maize system in Southwest China (started in 2010), the experiment included five P levels: 0, 16, 33, 49, and 65.5 kg P hm^–2 (P0, P16, P33, P49, and P65.5, respectively). The molecular speciation of organic P in soil was determined by 31P-nuclear magnetic resonance (NMR), high-throughput sequencing technology, and real-time qPCR were used to analyze the bacterial community and abundance of phoD-harboring bacterial genes, exploring the bacterial community and abundance characteristics of phoD gene and its relationship with the forms of Po and alkaline phosphatase (ALP) activity in the soil.Results: The results showed that the orthophosphate monoesters (OM) were the main Po speciation and varied by P fertilization in acid purple soil. ALP activity decreased as P fertilization increased. Co-occurrence network analysis identified the overall network under five P fertilizations. The keystone taxon base on the network showed that Collimonas, Roseateles, Mesorhizobium, and Cellulomonas positively correlated with both OM and Po. The random forest showed that Cellulomonas, Roseateles, and Rhodoplanes were the key predictors for ALP activity. The keystone taxon was a more important predictor than the dominant taxon for ALP, OM, and Po. The structural equation model (SEM) showed that soil organic matter (SOM), available P (AP), and OM were the main factors influencing the ALP by reshaping phoD-harboring bacteria alpha diversity, community composition, and phoD abundance.Discussion: The phoD-harboring bacterial community composition especially the keystone taxon rather than alpha diversity and abundance dominated the ALP activity, which could promote P utilization over an intensive agroecosystem. These findings improve the understanding of how long-term gradient fertilization influences the community composition and function of P-solubilizing microorganisms in acid purple soil.

Pilocytic astrocytomas are found predominantly in the pediatric population; reports of these tumors are extremely rare in adults. We report 2 cases of adult pilocytic astrocytoma with intracranial hemorrhage. A 32-year-old male presented with neck stiffness and severe headache, and a 34-year-old male was referred for headache and double vision. Computed tomography (CT) and magnetic resonance imaging (MRI) revealed a well-enhanced and circumscribed cystic hemorrhagic tumor with mural nodule over the cerebral hemisphere region. Perfusion-weighted MRI (PWI) was also performed in both patients. The measured relative cerebral blood volume ratios of the mural nodules in these 2 cases were, respectively, 1.34 and 2.81 when compared with normal white matter. After surgical resection, microscopic examination of the lesions showed pilocytic astrocytomas. Since pilocytic astrocytoma and other cystic tumors with mural nodule (such as hemangioblastoma) have similar findings on conventional CT and MRI, PWI is helpful in the differential diagnosis. The literature on hemorrhagic pilocytic astrocytoma is also reviewed.