Search

Encyonema chebalingense W.Zhang & S.Blanco sp. nov. Figs 1���21 Description:���LM: Valves distinctly asymmetrical and dorsiventral, semielliptical or semielliptical-lanceolate, dorsal margin clearly arched, ventral margin nearly straight or slightly concave. Both ends gradually narrowed, apices not or only slightly protracted, broadly to obtusely rounded (Figs 1���9). Length of the observed specimens 17.8���26.0 ��m, width 5.2���6.7 ��m, length/width ratio 3.4���3.9 (n=17). Raphe slightly inclined to the ventral margin, nearly straight and linear. The proximal raphe end is slightly curved to the dorsal margin, the end slit of the distal end is close to the valve edge and conspicuously curved to the ventral margin. Axial area narrow, conspicuously inclined to the ventral side, and one stria (sometimes two) on the middle ventral side is shorter. Striae radiate with areolae indistinguishable under LM. Terminal striae density 10���11 in 10 ��m, becoming 8���10 in 10 ��m toward the central area. SEM: Externally, the valve of E. chebalingense is flat and the transition from the valve face to the mantle is gradual (Figs 10, 11). No stigmoids are present in the central area (Figs 12, 13). The proximal ends of the raphe are clearly enlarged and inclined to the dorsal side, while terminal fissures are hooked to the ventral side of the valve at an angle of almost 90��. The axial area is narrow and linear (Figs 10, 11, 14, 15). Most of the striae are composed by single areolae of different sizes and shapes, mostly short lineolae or slit-like. The middle part of the ventral side has significantly shortened striae (Figs 10���13). Internally, the proximal raphe endings are hidden by an overgrowth of silica (Fig.18), distal raphe ends terminate in small helictoglossae (Figs 16, 17, 19���21). The uniseriate areolae of each stria are arranged between the interstria, and short tectullae project within the striae (Figs 16���20). Areolae 40���45 in 10 ��m within ventral and dorsal striae. Type:��� CHINA. Guangdong Province: Shixing County, Shaoguan City, upper reaches of Mojiang River, 24��43���21��� N, 114��15���24��� E. 357 m asl, Date: X.L. Lin August 23 2020. Etymology:���The specific epithet ��� chebalingense ��� refers to the place from which this new species was collected., Published as part of Huang, Ruohan, Ma, Jin, Wang, Xianyun, Blanco, Sa��l, Kociolek, John Patrick & Zhang, Wei, 2021, Encyonema chebalingense sp. nov., a new freshwater diatom species (Cymbellales, Bacillariophyceae) from Guangdong Province, China, pp. 77-84 in Phytotaxa 508 (1) on pages 78-79, DOI: 10.11646/phytotaxa.508.1.7, http://zenodo.org/record/5425793

During a survey of freshwater diatoms from Mojiang River, Chebaling Nature Preserve in Shaoguan City, Shixing County, Guangdong Province, China, a new Encyonema species, Encyonema chebalingense sp. nov., was discovered. Based on observations with light and scanning electron microscopy, a detailed morphological description of E. chebalingense is here presented. The main features of E. chebalingense include: conspicuously asymmetrical and dorsiventral, semielliptical to semielliptical–lanceolate valves, with a filiform raphe; dorsal margin clearly arched and ventral margin nearly straight or slightly concave; central area on the ventral side formed by 1–2 shorter central striae; and short tectullae projecting within the striae. The new species was compared with some similar species, all of which show similarities to E. chebalingense but differ in features such as dimensions, internal valve structure, stria density and valve shape. This genus is common and abundant in relatively clean waters, and other new species most likely will be recorded in the future from China.

Accurate tumor segmentation is an essential and crucial step for computer-aided brain tumor diagnosis and surgical planning. Subjective segmentations are widely adopted in clinical diagnosis and treating, but they are neither accurate nor reliable. An automatical and objective system for brain tumor segmentation is strongly expected. But they are still facing some challenges such as lower segmentation accuracy, demanding a priori knowledge or requiring the human intervention. In this paper, a novel and new coarse-to-fine method is proposed to segment the brain tumor. This hierarchical framework consists of preprocessing, deep learning network based classification and post-processing. The preprocessing is used to extract image patches for each MR image and obtains the gray level sequences of image patches as the input of the deep learning network. The deep learning network based classification is implemented by a stacked auto-encoder network to extract the high level abstract feature from the input, and utilizes the extracted feature to classify image patches. After mapping the classification result to a binary image, the post-processing is implemented by a morphological filter to get the final segmentation result. In order to evaluate the proposed method, the experiment was applied to segment the brain tumor for the real patient dataset. The final performance shows that the proposed brain tumor segmentation method is more accurate and efficient.