Development of a cloud framework for training and deployment of deep learning models in Radiology: automatic segmentation of the human spine from CT-scans as a case-study

Abstract

AbstractAdvancements in artificial intelligence (AI) and the digitalization of healthcare are revolutionizing clinical practices, with the deployment of AI models playing a crucial role in enhancing diagnostic accuracy and treatment outcomes. Our current study aims at bridging image data collected in a clinical setting, with deployment of deep learning algorithms for the segmentation of the human spine. The developed pipeline takes a decentralized approach, where selected clinical images are sent to a trusted research environment, part of private tenant in a cloud service provider. As a use-case scenario, we used the TotalSegmentator CT-scan dataset, along with its annotated ground-truth spine data, to train a ResSegNet model native to the MONAI-Label framework. Training and validation were conducted using high performance GPUs available on demand in the Trusted Research Environment. Segmentation model performance benchmarking involved metrics such as dice score, intersection over union, accuracy, precision, sensitivity, specificity, bounding F1 score, Cohen’s kappa, area under the curve, and Hausdorff distance. To further assess model robustness, we also trained a state-of-the-art nnU-Net model using the same dataset and compared both models with a pre-trained spine segmentation model available within MONAI-Label. The ResSegNet model, deployable via MONAI-Label, demonstrated performance comparable to the state-of-the-art nnU-Net framework, with both models showing strong results across multiple segmentation metrics. This study successfully trained, evaluated and deployed a decentralized deep learning model for CT-scan spine segmentation in a cloud environment. This new model was validated against state-of-the-art alternatives. This comprehensive comparison highlights the value of the MONAI-Label as an effective tool for label generation, model training, and deployment, further highlighting its user-friendly nature and ease of deployment in clinical and research settings. Further we also demonstrate that such tools can be deployed in private and safe decentralized cloud environments for clinical use.Author SummaryIn the rapidly evolving field of medical imaging, the integration of artificial intelligence (AI) and cloud computing is becoming increasingly critical for advancing diagnostic and treatment capabilities. To address the growing demand for flexible digital frameworks in the clinical environment supporting the deployment of data-driven applications, we have developed and deployed a cloud-based Trusted Research Environment designed specifically for training, validation, and deployment of deep learning models focused on semantic segmentation in musculoskeletal radiology. This environment facilitates the efficient handling of large datasets and the accessibility of algorithmic output for the physicians, optimizing the interface between development and clinical translation. The established framework enables significant improvements in the deployment of deep learning tools for image analysis in the clinical setting. In our current use-case, we have utilized this environment to train and evaluate two advanced deep learning models for the segmentation of the human spine from CT scans. By leveraging the computational power and flexibility of the cloud-based infrastructure, we were able to perform rigorous training and comparison of these models, aiming to enhance the accuracy and reliability of spine segmentation in clinical practice. This approach not only streamlines the process of model development but also provides valuable insights into the performance and potential clinical applications of these AI-driven segmentation tools.