Artificial intelligence (AI) is increasingly transforming the healthcare sector by enabling advanced automated decision-making. However, implementing Machine Learning (ML) systems in medical imaging applications presents significant challenges, such as ensuring consistent results across different environments, maintaining comprehensive records of experimental processes, and establishing reliable methods for model comparison and evaluation. These issues become more evident as medical AI shifts towards a hybrid Cloud-Edge Continuum (CEC), adding complexity to workload orchestration and performance monitoring across diverse infrastructures. To address these challenges, this work introduces a modular Edge Micro Data Centre (EMDC) architecture that supports a scalable experiment tracking framework designed for AI model deployments in healthcare. The approach extends MLflow with a domain-specific module for medical image segmentation, incorporating several clinically relevant performance metrics. The EMDC architecture enables distributed processing and performance monitoring within a hybrid CEC environment. By aligning MLOps principles with CEC infrastructure, the proposed system facilitates reliable and scalable AI integration into the healthcare sector.

Pedestrian detection is used in many vision based applications ranging from video surveillance to autonomous driving. Despite achieving high performance, it is still largely unknown how well existing detectors generalize to unseen data. This is important because a practical detector should be ready to use in various scenarios in applications. To this end, we conduct a comprehensive study in this paper, using a general principle of direct cross-dataset evaluation. Through this study, we find that existing state-of-the-art pedestrian detectors, though perform quite well when trained and tested on the same dataset, generalize poorly in cross dataset evaluation. We demonstrate that there are two reasons for this trend. Firstly, their designs (e.g. anchor settings) may be biased towards popular benchmarks in the traditional single-dataset training and test pipeline, but as a result largely limit their generalization capability. Secondly, the training source is generally not dense in pedestrians and diverse in scenarios. Under direct cross-dataset evaluation, surprisingly, we find that a general purpose object detector, without pedestrian-tailored adaptation in design, generalizes much better compared to existing state-of-the-art pedestrian detectors. Furthermore, we illustrate that diverse and dense datasets, collected by crawling the web, serve to be an efficient source of pre-training for pedestrian detection. Accordingly, we propose a progressive training pipeline and find that it works well for autonomous-driving oriented pedestrian detection. Consequently, the study conducted in this paper suggests that more emphasis should be put on cross-dataset evaluation for the future design of generalizable pedestrian detectors. Code and models can be accessed at https://github.com/hasanirtiza/Pedestron.

Robust cell detection plays a key role in the development of reliable methods for automated analysis of microscopy images. It is a challenging problem due to low contrast, variable fluorescence, weak boundaries, conjoined and overlapping cells, causing most cell detection methods to fail in difficult situations. One approach for overcoming these challenges is to use cell proposals, which enable the use of more advanced features from ambiguous regions and/or information from adjacent frames to make better decisions. However, most current methods rely on simple proposal generation and scoring methods, which limits the performance they can reach. In this paper, we propose a convolutional neural network based method which generates cell proposals to facilitate cell detection, segmentation and tracking. We compare our method against commonly used proposal generation and scoring methods and show that our method generates significantly better proposals, and achieves higher final recall and average precision.