Comparison of animal welfare assessment tools and methodologies: need for an effective approach for captive elephants in Asia.

Welfare is a fundamental aspect of animal management and conservation. In light of growing public awareness and welfare concerns about captive elephants, there is an urgent need for comprehensive, globally coordinated efforts for Asian elephants (Elephas maximus) that participate in religious, logging, or tourist activities in range countries where the majority reside, and where welfare issues have been identified but not addressed. This review provides a comparative analysis of available animal assessment tools. Each offers distinct features for assessment that allow institutions to select criteria for specific needs and available resources. Most are applied to general animal welfare assessments, although some are tailored to particular species, including elephants. The tools span diverse formats, from digital to primarily paper-based assessments. Assessments operate at individual and institutional levels and across multiple welfare domains. Methodologies rely on keeper ratings or expert evaluations, incorporate numerical scoring and Likert scales for welfare grading, and encompass inputs including behaviors, health, and physiological indicators. For tourist camp elephants, one challenge is that the tools were developed in zoos, which may or may not have application to non-zoological settings. Digital tools and assessment methodologies such as keeper ratings face logistical challenges when applied across tourist venues. As with any tool, reliability, validity, and repeatability are essential and must address the unique welfare challenges of diverse captive settings. We propose that a holistic, context-specific, evidence-based, and practical tool be developed to ensure high elephant welfare standards in non-zoological facilities throughout Asia.

MMNet: A Mixing Module Network for Polyp Segmentation.

Traditional encoder-decoder networks like U-Net have been extensively used for polyp segmentation. However, such networks have demonstrated limitations in explicitly modeling long-range dependencies. In such networks, local patterns are emphasized over the global context, as each convolutional kernel focuses on only a local subset of pixels in the entire image. Several recent transformer-based networks have been shown to overcome such limitations. Such networks encode long-range dependencies using self-attention methods and thus learn highly expressive representations. However, due to the computational complexity of modeling the whole image, self-attention is expensive to compute, as there is a quadratic increment in cost with the increase in pixels in the image. Thus, patch embedding has been utilized, which groups small regions of the image into single input features. Nevertheless, these transformers still lack inductive bias, even with the image as a 1D sequence of visual tokens. This results in the inability to generalize to local contexts due to limited low-level features. We introduce a hybrid transformer combined with a convolutional mixing network to overcome computational and long-range dependency issues. A pretrained transformer network is introduced as a feature-extracting encoder, and a mixing module network (MMNet) is introduced to capture the long-range dependencies with a reduced computational cost. Precisely, in the mixing module network, we use depth-wise and 1 × 1 convolution to model long-range dependencies to establish spatial and cross-channel correlation, respectively. The proposed approach is evaluated qualitatively and quantitatively on five challenging polyp datasets across six metrics. Our MMNet outperforms the previous best polyp segmentation methods.

Radiologic finding of intraosseous gas: A rare case of emphysematous osteomyelitis of the foot.

Emphysematous osteomyelitis is a rare but potentially life-threatening infection which is characterized by presence of intraosseous gas. It is a very rare form of osteomyelitis which is complicated by infection with gas forming organisms. In majority of the cases, it has been found to be associated with comorbidities like immunosuppressive therapies, diabetes mellitus, alcohol use, and several others. Early identification on radiologic imaging is necessary to enable implementation of prompt treatment plan.

Polyp segmentation with consistency training and continuous update of pseudo-label.

Polyp segmentation has accomplished massive triumph over the years in the field of supervised learning. However, obtaining a vast number of labeled datasets is commonly challenging in the medical domain. To solve this problem, we employ semi-supervised methods and suitably take advantage of unlabeled data to improve the performance of polyp image segmentation. First, we propose an encoder-decoder-based method well suited for the polyp with varying shape, size, and scales. Second, we utilize the teacher-student concept of training the model, where the teacher model is the student model's exponential average. Third, to leverage the unlabeled dataset, we enforce a consistency technique and force the teacher model to generate a similar output on the different perturbed versions of the given input. Finally, we propose a method that upgrades the traditional pseudo-label method by learning the model with continuous update of pseudo-label. We show the efficacy of our proposed method on different polyp datasets, and hence attaining better results in semi-supervised settings. Extensive experiments demonstrate that our proposed method can propagate the unlabeled dataset's essential information to improve performance.