28 January 2023 in Medical & Biological Engineering & Computing
The ongoing COVID-19 pandemic caused by the SARS-CoV-2 virus has already resulted in 6.6 million deaths with more than 637 million people infected after only 30 months since the first occurrences of the disease in December 2019. Hence, rapid and accurate detection and diagnosis of the disease is the first priority all over the world. Researchers have been working on various methods for COVID-19 detection and as the disease infects lungs, lung image analysis has become a popular research area for detecting the presence of the disease. Medical images from chest X-rays (CXR), computed tomography (CT) images, and lung ultrasound images have been used by automated image analysis systems in artificial intelligence (AI)- and machine learning (ML)-based approaches. Various existing and novel ML, deep learning (DL), transfer learning (TL), and hybrid models have been applied for detecting and classifying COVID-19, segmentation of infected regions, assessing the severity, and tracking patient progress from medical images of COVID-19 patients. In this paper, a comprehensive review of some recent approaches on COVID-19-based image analyses is provided surveying the contributions of existing research efforts, the available image datasets, and the performance metrics used in recent works. The challenges and future research scopes to address the progress of the fight against COVID-19 from the AI perspective are also discussed. The main objective of this paper is therefore to provide a summary of the research works done in COVID detection and analysis from medical image datasets using ML, DL, and TL models by analyzing their novelty and efficiency while mentioning other COVID-19-based review/survey researches to deliver a brief overview on the maximum amount of information on COVID-19-based existing researches.
1 January 2026 in IEEE Access
9 March 2026 in IEEE Access
SPSibi Chakravarthy Parivendan
Sibi Chakravarthy Parivendan
Pose estimation enables quantitative animal phenotyping, but progress is limited by sparse annotated datasets and domain variability in real-world farm environments. This study evaluates cross-species transfer learning by adapting a zebra pose model (ZebraPose) for 27-keypoint dairy cattle pose estimation. We systematically evaluated three training configurations: zebra-only pre-training, cattle-specific fine-tuning, and combined dataset training. While the combined training achieved strong benchmark performance (average precision [AP] = 0.86, average recall [AR] = 0.87, percentage correct keypoints [PCK] at 0.5 IoU = 0.869), generalization to unseen farm environments deteriorated significantly. Analysis reveals that synthetic pretraining data and anatomical similarity alone are insufficient for robust cross-farm deployment, despite comparable model architectures and training protocols. The persistent domain gap—characterized by environmental heterogeneity, lighting variation, and pose diversity—demonstrates that successful livestock phenotyping requires environment-aware model development and multi-site dataset diversity rather than single-species transfer learning approaches. These findings establish practical constraints on cross-species adaptation for animal pose estimation and inform future directions toward farm-adaptive phenotyping systems.