Cell segmentation is the task of identifying cell nuclei instances in fluorescence microscopy images. The goal of this paper is to benchmark the performance of representative deep learning techniques for cell nuclei segmentation using standard datasets and common evaluation criteria. This research establishes an important baseline for cell nuclei segmentation, enabling researchers to continually refine and deploy neural models for real-world clinical applications.
Using facial recognition as a use-case scenario, we attempt to identify sources of bias in a model developed using transfer learning. To achieve this task, we developed a model based on a pre-trained facial recognition model, and scrutinized the accuracy of the model’s image classification against factors such as age, gender, and race to observe whether or not the model performed better on some demographic groups than others. By identifying the bias and finding potential sources of bias, his work contributes a unique technical perspective from the view of a small scale developer to emerging discussions of accountability and transparency in AI.
In the battle against Alzheimer's disease, early detection is critical to mitigating symptoms in patients. Here, the authors use a collection of MRI scans, layering with deep learning computer modeling, to investigate early stages of AD which can be hard to catch by human eye. Their model is successful, able to outperform previous models, and detected regions of interest in the brain for further consideration.
The application of machine learning techniques has facilitated the automatic annotation of behavior in video sequences, offering a promising approach for ethological studies by reducing the manual effort required for annotating each video frame. Nevertheless, before solely relying on machine-generated annotations, it is essential to evaluate the accuracy of these annotations to ensure their reliability and applicability. While it is conventionally accepted that there cannot be a perfect annotation, the degree of error associated with machine-generated annotations should be commensurate with the error between different human annotators. We hypothesized that machine learning supervised with adequate human annotations would be able to accurately predict body parts from video sequences. Here, we conducted a comparative analysis of the quality of annotations generated by humans and machines for the body parts of sheep during treadmill walking. For human annotation, two annotators manually labeled six body parts of sheep in 300 frames. To generate machine annotations, we employed the state-of-the-art pose-estimating library, DeepLabCut, which was trained using the frames annotated by human annotators. As expected, the human annotations demonstrated high consistency between annotators. Notably, the machine learning algorithm also generated accurate predictions, with errors comparable to those between humans. We also observed that abnormal annotations with a high error could be revised by introducing Kalman Filtering, which interpolates the trajectory of body parts over the time series, enhancing robustness. Our results suggest that conventional transfer learning methods can generate behavior annotations as accurate as those made by humans, presenting great potential for further research.
With the advance of technology, artificial intelligence (AI) is now applied widely in society. In the study of AI, machine learning (ML) is a subfield in which a machine learns to be better at performing certain tasks through experience. This work focuses on the convolutional neural network (CNN), a framework of ML, applied to an image classification task. Specifically, we analyzed the performance of the CNN as the type of neural activation function changes.
Modern artificial neural networks have been remarkably successful in various applications, from speech recognition to computer vision. However, it remains less clear whether they can implement abstract concepts, which are essential to generalization and understanding. To address this problem, the authors investigated the above vs. below task, a simple concept-based task that honeybees can solve, using a conventional neural network. They found that networks achieved 100% test accuracy when a visual target was presented below a black bar, however only 50% test accuracy when a visual target was presented below a reference shape.
Plastic pollution in the ocean is a major global concern. Remotely Operated Vehicles (ROVs) have promise for removing debris from the ocean, but more research is needed to achieve full effectiveness of the ROV technology. Wahlig and Gonzales tackle this issue by developing a deep learning model to distinguish trash from the environment in ROV images.
Greenspaces (urban and wetland areas that contain vegetation) are beneficial to reducing pollution, while airplanes are a highly-polluting method of transportation. The authors examine the intersection of these two environmental factors by processing satellite images to reveal what percentage of flight paths go over greenspaces at major US airports.