Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

IODeep: an IOD for the introduction of deep learning in the DICOM standard

Salvatore Contino, Luca Cruciata, Orazio Gambino, Roberto Pirrone

TL;DR

IODeep ensures full integration of a trained AI model in a DICOM infrastructure, and it enables a scenario where a trained model can be either fine-tuned with hospital data or trained in a federated learning scheme shared by different hospitals.

Abstract

Background and Objective: In recent years, Artificial Intelligence (AI) and in particular Deep Neural Networks (DNN) became a relevant research topic in biomedical image segmentation due to the availability of more and more data sets along with the establishment of well known competitions. Despite the popularity of DNN based segmentation on the research side, these techniques are almost unused in the daily clinical practice even if they could support effectively the physician during the diagnostic process. Apart from the issues related to the explainability of the predictions of a neural model, such systems are not integrated in the diagnostic workflow, and a standardization of their use is needed to achieve this goal. Methods: This paper presents IODeep a new DICOM Information Object Definition (IOD) aimed at storing both the weights and the architecture of a DNN already trained on a particular image dataset that is labeled as regards the acquisition modality, the anatomical region, and the disease under investigation. Results: The IOD architecture is presented along with a DNN selection algorithm from the PACS server based on the labels outlined above, and a simple PACS viewer purposely designed for demonstrating the effectiveness of the DICOM integration, while no modifications are required on the PACS server side. Also a service based architecture in support of the entire workflow has been implemented. Conclusion: IODeep ensures full integration of a trained AI model in a DICOM infrastructure, and it is also enables a scenario where a trained model can be either fine-tuned with hospital data or trained in a federated learning scheme shared by different hospitals. In this way AI models can be tailored to the real data produced by a Radiology ward thus improving the physician decision making process. Source code is freely available at https://github.com/CHILab1/IODeep.git

IODeep: an IOD for the introduction of deep learning in the DICOM standard

TL;DR

IODeep ensures full integration of a trained AI model in a DICOM infrastructure, and it enables a scenario where a trained model can be either fine-tuned with hospital data or trained in a federated learning scheme shared by different hospitals.

Abstract

Background and Objective: In recent years, Artificial Intelligence (AI) and in particular Deep Neural Networks (DNN) became a relevant research topic in biomedical image segmentation due to the availability of more and more data sets along with the establishment of well known competitions. Despite the popularity of DNN based segmentation on the research side, these techniques are almost unused in the daily clinical practice even if they could support effectively the physician during the diagnostic process. Apart from the issues related to the explainability of the predictions of a neural model, such systems are not integrated in the diagnostic workflow, and a standardization of their use is needed to achieve this goal. Methods: This paper presents IODeep a new DICOM Information Object Definition (IOD) aimed at storing both the weights and the architecture of a DNN already trained on a particular image dataset that is labeled as regards the acquisition modality, the anatomical region, and the disease under investigation. Results: The IOD architecture is presented along with a DNN selection algorithm from the PACS server based on the labels outlined above, and a simple PACS viewer purposely designed for demonstrating the effectiveness of the DICOM integration, while no modifications are required on the PACS server side. Also a service based architecture in support of the entire workflow has been implemented. Conclusion: IODeep ensures full integration of a trained AI model in a DICOM infrastructure, and it is also enables a scenario where a trained model can be either fine-tuned with hospital data or trained in a federated learning scheme shared by different hospitals. In this way AI models can be tailored to the real data produced by a Radiology ward thus improving the physician decision making process. Source code is freely available at https://github.com/CHILab1/IODeep.git
Paper Structure (7 sections, 5 figures, 1 table, 2 algorithms)

This paper contains 7 sections, 5 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. Theoretical Background
  3. Motivation of the work
  4. IODeep architecture
  5. The ROI prediction workflow
  6. Comparison with the DICOM WG-23 proposal
  7. Conclusion

Figures (5)

  • Figure 1: E-R diagram representing the connection between IODeep and the Dicom Model of the Real World
  • Figure 2: Representation of the U-net neural network used in our example, and its JSON description.
  • Figure 3: Sequence diagram of the ROI prediction scenario
  • Figure 4: The viewer interface for ROI validation. (a) Predicted ROIs are displayed and outlined in red. (b) Validated ROIs are outlined in green.
  • Figure 5: Component diagram representing the service implementation of the proposed framework.