Ureibacillus aquaedulcis sp. nov., isolated from freshwater well and reclassification of Lysinibacillus yapensis and Lysinibacillus antri as Ureibacillus yapensis comb. nov. and Ureibacillus antri comb. Nov.

A Gram-stain-positive aerobic, rod-shaped, spore-producing bacterium forming colonies with convex elevation and a smooth, intact margin was isolated from a freshwater sample collected from a well situated in an agricultural field. The 16S rRNA gene sequence of the isolated strain BA0131T showed the highest sequence similarity to Lysinibacillus yapensis ylb-03T (99.25%) followed by Ureibacillus chungkukjangi 2RL3-2T (98.91%) and U. sinduriensis BLB-1T (98.65%). The strain BA0131T was oxidase and catalase positive and urease negative. It also tested positive for esculin hydrolysis and reduction of potassium nitrate, unlike its phylogenetically closest relatives. The predominant fatty acids in strain BA0131T included were anteiso-C15:0, iso-C16:0, iso-C15:0, iso-C14:0 and the major polar lipids comprised were phosphatidylglycerol, diphosphatidylglycerol and phosphatidylethanolamine. The respiratory quinones identified in strain BA0131T were MK8 (H2) (major) and MK8 (minor). The strain BA0131T shared the lowest dDDH values with L. yapensis ylb-03T (21%) followed by U. chungkukjangi 2RL3-2T (24.2%) and U. sinduriensis BLB-1T (26.4%) suggesting a closer genetic relationship U. sinduriensis BLB-1T. The ANI percentage supported the close relatedness with U. sinduriensis BLB-1T (83.61%) followed by U. chungkukjangi 2RL3-2T (82.03%) and U. yapensis ylb-03T (79.57%). The core genome-based phylogeny constructed using over 13,704 amino acid positions and 92 core genes revealed the distinct phylogenetic position of strain BA0131T among the genus Ureibacillus. The distinct physiological, biochemical characteristics and genotypic relatedness data indicate the strain BA0131T represents a novel species of the genus Ureibacillus for which the name Ureibacillus aquaedulcis sp. nov. (Type strain, BA0131T = MCC 5284 = JCM 36475) is proposed. Additionally, based on extensive genomic and phylogenetic analyses, we propose reclassification of two species, L. yapensis and L. antri, as U. yapensis comb. nov. (Type strain, ylb-03T = JCM 32871T = MCCC 1A12698T) and U. antri (Type strain, SYSU K30002T = CGMCC 1.13504T = KCTC 33955T).

Hybrid Topological Data Analysis and Deep Learning for Basal Cell Carcinoma Diagnosis.

A critical clinical indicator for basal cell carcinoma (BCC) is the presence of telangiectasia (narrow, arborizing blood vessels) within the skin lesions. Many skin cancer imaging processes today exploit deep learning (DL) models for diagnosis, segmentation of features, and feature analysis. To extend automated diagnosis, recent computational intelligence research has also explored the field of Topological Data Analysis (TDA), a branch of mathematics that uses topology to extract meaningful information from highly complex data. This study combines TDA and DL with ensemble learning to create a hybrid TDA-DL BCC diagnostic model. Persistence homology (a TDA technique) is implemented to extract topological features from automatically segmented telangiectasia as well as skin lesions, and DL features are generated by fine-tuning a pre-trained EfficientNet-B5 model. The final hybrid TDA-DL model achieves state-of-the-art accuracy of 97.4% and an AUC of 0.995 on a holdout test of 395 skin lesions for BCC diagnosis. This study demonstrates that telangiectasia features improve BCC diagnosis, and TDA techniques hold the potential to improve DL performance.

LAMA: Lesion-Aware Mixup Augmentation for Skin Lesion Segmentation.

Deep learning can exceed dermatologists' diagnostic accuracy in experimental image environments. However, inaccurate segmentation of images with multiple skin lesions can be seen with current methods. Thus, information present in multiple-lesion images, available to specialists, is not retrievable by machine learning. While skin lesion images generally capture a single lesion, there may be cases in which a patient's skin variation may be identified as skin lesions, leading to multiple false positive segmentations in a single image. Conversely, image segmentation methods may find only one region and may not capture multiple lesions in an image. To remedy these problems, we propose a novel and effective data augmentation technique for skin lesion segmentation in dermoscopic images with multiple lesions. The lesion-aware mixup augmentation (LAMA) method generates a synthetic multi-lesion image by mixing two or more lesion images from the training set. We used the publicly available International Skin Imaging Collaboration (ISIC) 2017 Challenge skin lesion segmentation dataset to train the deep neural network with the proposed LAMA method. As none of the previous skin lesion datasets (including ISIC 2017) has considered multiple lesions per image, we created a new multi-lesion (MuLe) segmentation dataset utilizing publicly available ISIC 2020 skin lesion images with multiple lesions per image. MuLe was used as a test set to evaluate the effectiveness of the proposed method. Our test results show that the proposed method improved the Jaccard score 8.3% from 0.687 to 0.744 and the Dice score 5% from 0.7923 to 0.8321 over a baseline model on MuLe test images. On the single-lesion ISIC 2017 test images, LAMA improved the baseline model's segmentation performance by 0.08%, raising the Jaccard score from 0.7947 to 0.8013 and the Dice score 0.6% from 0.8714 to 0.8766. The experimental results showed that LAMA improved the segmentation accuracy on both single-lesion and multi-lesion dermoscopic images. The proposed LAMA technique warrants further study.

Basal Cell Carcinoma Diagnosis with Fusion of Deep Learning and Telangiectasia Features.

In recent years, deep learning (DL) has been used extensively and successfully to diagnose different cancers in dermoscopic images. However, most approaches lack clinical inputs supported by dermatologists that could aid in higher accuracy and explainability. To dermatologists, the presence of telangiectasia, or narrow blood vessels that typically appear serpiginous or arborizing, is a critical indicator of basal cell carcinoma (BCC). Exploiting the feature information present in telangiectasia through a combination of DL-based techniques could create a pathway for both, improving DL results as well as aiding dermatologists in BCC diagnosis. This study demonstrates a novel "fusion" technique for BCC vs non-BCC classification using ensemble learning on a combination of (a) handcrafted features from semantically segmented telangiectasia (U-Net-based) and (b) deep learning features generated from whole lesion images (EfficientNet-B5-based). This fusion method achieves a binary classification accuracy of 97.2%, with a 1.3% improvement over the corresponding DL-only model, on a holdout test set of 395 images. An increase of 3.7% in sensitivity, 1.5% in specificity, and 1.5% in precision along with an AUC of 0.99 was also achieved. Metric improvements were demonstrated in three stages: (1) the addition of handcrafted telangiectasia features to deep learning features, (2) including areas near telangiectasia (surround areas), (3) discarding the noisy lower-importance features through feature importance. Another novel approach to feature finding with weak annotations through the examination of the surrounding areas of telangiectasia is offered in this study. The experimental results show state-of-the-art accuracy and precision in the diagnosis of BCC, compared to three benchmark techniques. Further exploration of deep learning techniques for individual dermoscopy feature detection is warranted.

Fictibacillus fluitans sp. nov., isolated from freshwater pond.

A Gram-positive, aerobic, rod-shaped, spore-forming bacterium, designated NE201T, was isolated from a freshwater pond in Village Nerur, India. Growth was observed in the range of 15-45 °C temperature with optimum at 30 °C, pH range of 5-9 (optimum at 7.0), and at concentrations of NaCl ranging between 0 and 14% (optimum 0%, w/v). The 16S rRNA gene sequence showed the highest similarity with Fictibacillus enclensis NIO-1003T (JF893461) at 99.01% followed by F. rigui WPCB074T (EU939689) at 98.9% and F. solisalsi CGMCC 1.6854T (EU046268) at 98.66%. The digital DNA-DNA hybridization (dDDH) and orthoANI values for strain NE201T against F. enclensis NIO-1003T (GCA_900094955.1) were 33.7% and 87.68%, respectively. The phylogenetic analysis based on the 16S rRNA gene, 92 core genes derived from the genome, and 20 proteins involving over 20,236 amino acid positions revealed the distinct phylogenetic position of strain NE201T and the formation of a clearly defined monophyletic clade with F. enclensis. The strain NE201T showed a unique carbon utilization and assimilation pattern that differentiated it from F. enclensis NIO-1003T. The major fatty acids were anteiso -C15:0 (51.42%) and iso-C15:0 (18.88%). The major polar lipids were phosphatidylglycerol (PG), phosphatidylethanolamine (PE, and diphosphatidylglycerol (DPG). The antiSMASH analyzed genome of NE201T highlighted its diverse biosynthetic potential, unveiling regions associated with terpene, non-ribosomal peptide synthetases (NRPS), lassopeptides, NI-siderophores, lanthipeptides (LAP), and Type 3 Polyketide Synthases (T3PKS). The overall phenotypic, genotypic, and chemotaxonomic characters strongly suggested that the strain NE201T represents a novel species of genus Fictibacillus for which the name Fictibacillus fluitans sp. nov. is proposed. The type strain is NE201T (= MCC 5285 = JCM 36474).

Improving Automatic Melanoma Diagnosis Using Deep Learning-Based Segmentation of Irregular Networks.

Deep learning has achieved significant success in malignant melanoma diagnosis. These diagnostic models are undergoing a transition into clinical use. However, with melanoma diagnostic accuracy in the range of ninety percent, a significant minority of melanomas are missed by deep learning. Many of the melanomas missed have irregular pigment networks visible using dermoscopy. This research presents an annotated irregular network database and develops a classification pipeline that fuses deep learning image-level results with conventional hand-crafted features from irregular pigment networks. We identified and annotated 487 unique dermoscopic melanoma lesions from images in the ISIC 2019 dermoscopic dataset to create a ground-truth irregular pigment network dataset. We trained multiple transfer learned segmentation models to detect irregular networks in this training set. A separate, mutually exclusive subset of the International Skin Imaging Collaboration (ISIC) 2019 dataset with 500 melanomas and 500 benign lesions was used for training and testing deep learning models for the binary classification of melanoma versus benign. The best segmentation model, U-Net++, generated irregular network masks on the 1000-image dataset. Other classical color, texture, and shape features were calculated for the irregular network areas. We achieved an increase in the recall of melanoma versus benign of 11% and in accuracy of 2% over DL-only models using conventional classifiers in a sequential pipeline based on the cascade generalization framework, with the highest increase in recall accompanying the use of the random forest algorithm. The proposed approach facilitates leveraging the strengths of both deep learning and conventional image processing techniques to improve the accuracy of melanoma diagnosis. Further research combining deep learning with conventional image processing on automatically detected dermoscopic features is warranted.

Enhanced Upconversion and Downshifting emissions from Tb3+, Yb3+ co-doped CaZrO3 phosphor in presence of Li+ ions.

This paper reports the enhanced green photoluminescence from Tb3+, Yb3+ co-doped CaZrO3 phosphor in the presence of Li+ ion synthesized through solid state reaction technique. The structural studies show an increase in the particle size and a shrink in crystal lattice due to Li+ co-doping in the phosphor. The phosphor sample emits intense green upconversion emission (UC) due to Tb3+ ions on excitation with 980 nm radiation which is further enhanced ~ 28 times on Li+ co-doping. The lifetime of 5D4 level of Tb3+ ion decreases in the presence of Li+ ions due to increase in asymmetry in crystal field. The downshifting (DS) emission intensity monitored on 378 and 487nm excitations is also enhanced in the presence of Li+ ions. Thus, the Tb3+, Yb3+, Li+ co-doped CaZrO3 phosphor can be a suitable candidate for UC solid state lighting.