Migrating to the Modern PACS: Challenges and Opportunities

A responsible framework for applying artificial intelligence on medical images and signals at the point-of-care: the PACS-AI platform

The potential of artificial intelligence (AI) in medicine lies in its ability to enhance clinicians' capacity to analyze medical images, thereby improving diagnostic precision and accuracy, thus enhancing current tests. However, the integration of AI within healthcare is fraught with difficulties. Heterogeneity among healthcare system applications, reliance on proprietary closed-source software, and rising cyber-security threats pose significant challenges. Moreover, prior to their deployment in clinical settings, AI models must demonstrate their effectiveness across a wide range of scenarios and must be validated by prospective studies, but doing so requires testing in an environment mirroring the clinical workflow which is difficult to achieve without dedicated software. Finally, the use of AI techniques in healthcare raises significant legal and ethical issues, such as the protection of patient privacy, the prevention of bias, and the monitoring of the device's safety and effectiveness for regulatory compliance. This review describes challenges to AI integration in healthcare and provides guidelines on how to move forward. We describe an open-source solution that we developed which integrates AI models into the Picture Archives Communication System (PACS), called PACS-AI. This approach aims to increase the evaluation of AI models by facilitating their integration and validation with existing medical imaging databases. PACS-AI may overcome many current barriers to AI deployment and offers a pathway towards responsible, fair, and effective deployment of AI models in healthcare. Additionally, we propose a list of criteria and guidelines that AI researchers should adopt when publishing a medical AI model, to enhance standardization and reproducibility.

NAM National Plan for Health Workforce Well-being: Applications for Radiology

The National Academy of Medicine Plan for Health Workforce Well-Being identifies seven priority areas, including creating positive work environments, addressing burnout and stress, promoting transparency and equity in compensation, providing education and training to promote resilience, enhancing community and social support systems, addressing the stigma associated with seeking help for mental health and substance use disorders and fostering leadership commitment and accountability for workforce well-being. This paper will explore the National Plan for Health Workforce Well-Being, providing an overview of the seven priority areas and offering strategies for implementation in radiology.

Clinician and computer: a study on doctors' perceptions of artificial intelligence in skeletal radiography

BACKGROUND

Traumatic musculoskeletal injuries are a common presentation to emergency care, the first-line investigation often being plain radiography. The interpretation of this imaging frequently falls to less experienced clinicians despite well-established challenges in reporting. This study presents novel data of clinicians' confidence in interpreting trauma radiographs, their perception of AI in healthcare, and their support for the development of systems applied to skeletal radiography.

METHODS

A novel questionnaire was distributed through a network of collaborators to clinicians across the Southeast of England. Over a three-month period, responses were compiled into a database before undergoing statistical review.

RESULTS

The responses of 297 participants were included. The mean self-assessed knowledge of AI in healthcare was 3.68 out of ten, with significantly higher knowledge reported by the most senior doctors (Specialty Trainee/Specialty Registrar or above = 4.88). 13.8% of participants reported an awareness of AI in their clinical practice. Overall, participants indicated substantial favourability towards AI in healthcare (7.87) and in AI applied to skeletal radiography (7.75). There was a preference for a hypothetical system indicating positive findings rather than ruling as negative (7.26 vs 6.20).

CONCLUSIONS

This study identifies clear support, amongst a cross section of student and qualified doctors, for both the general use of AI technology in healthcare and in its application to skeletal radiography for trauma. The development of systems to address this demand appear well founded and popular. The engagement of a small but reticent minority should be sought, along with improving the wider education of doctors on AI.

Design and Implementation of a Cloud PACS Architecture

The limitations of the classic PACS (picture archiving and communication system), such as the backward-compatible DICOM network architecture and poor security and maintenance, are well-known. They are challenged by various existing solutions employing cloud-related patterns and services. However, a full-scale cloud-native PACS has not yet been demonstrated. The paper introduces a vendor-neutral cloud PACS architecture. It is divided into two main components: a cloud platform and an access device. The cloud platform is responsible for nearline (long-term) image archive, data flow, and backend management. It operates in multi-tenant mode. The access device is responsible for the local DICOM (Digital Imaging and Communications in Medicine) interface and serves as a gateway to cloud services. The cloud PACS was first implemented in an Amazon Web Services environment. It employs a number of general-purpose services designed or adapted for a cloud environment, including Kafka, OpenSearch, and Memcached. Custom services, such as a central PACS node, queue manager, or flow worker, also developed as cloud microservices, bring DICOM support, external integration, and a management layer. The PACS was verified using image traffic from, among others, computed tomography (CT), magnetic resonance (MR), and computed radiography (CR) modalities. During the test, the system was reliably storing and accessing image data. In following tests, scaling behavior differences between the monolithic Dcm4chee server and the proposed solution are shown. The growing number of parallel connections did not influence the monolithic server's overall throughput, whereas the performance of cloud PACS noticeably increased. In the final test, different retrieval patterns were evaluated to assess performance under different scenarios. The current production environment stores over 450 TB of image data and handles over 4000 DICOM nodes.

Comparison of the Utility of High-Resolution CT-DWI and T2WI-DWI Fusion Images for the Localization of Cholesteatoma

BACKGROUND AND PURPOSE

Cholesteatoma is an aggressive disease that may lead to hearing impairment. This study aimed to compare the utility of high-resolution CT and TSE-DWI fusion images with that of T2WI and TSE-DWI fusion images in the localization of middle ear cholesteatoma.

MATERIALS AND METHODS

Seventy-one patients with middle ear cholesteatoma were retrospectively recruited. High-resolution CT, T2WI with fat suppression, and TSE-DWI scans were obtained, and image fusion was performed using a 3D reconstruction postprocessing workstation to form CT-DWI and T2WI-DWI fusion images. The quality of the 2 fused images was subjectively evaluated using a 5-point Likert scale with the horizontal semicircular canal transverse position as the reference. Receiver operating characteristic analysis was performed, and the diagnostic efficacies of CT-DWI and T2WI-DWI fusion images in localizing middle ear cholesteatoma were calculated.

RESULTS

The overall quality of T2WI-DWI fusion images was slightly higher than that of CT-DWI fusion images (P < .001), and the semicircular canal was slightly less clear on T2WI-DWI than on CT-DWI (P < .001). No statistical difference was found in the diagnostic confidence between them. In the localization of middle ear cholesteatoma, the accuracy, sensitivity, and specificity of T2WI-DWI fusion images and CT-DWI fusion images were equivalent for involvement of the attic, tympanic cavity, mastoid antrum, and mastoid process, with no statistically significant differences.

CONCLUSIONS

T2WI-DWI fusion images could replace CT-DWI in the preoperative selection of surgical options for middle ear cholesteatoma.

Determining the Effect of the Picture Archiving and Communication System (PACS) on Different Dimensions of Users' Work

The impact of the picture archiving and communication system (PACS) on healthcare costs, information access, image quality, and user workflow has been well studied. However, there is insufficient evidence on the effect of this system on different dimensions of the users' work. The objective of this study was to evaluate the impact of the PACS on different dimensions of users' work (external communication, service quality, user intention to use the PACS, daily routine, and complaints on users) and to compare the opinions of different groups of users about the PACS. This study was performed on the PACS users (n = 72) at Kerman University of Medical Sciences, including radiologists, radiology staff, ward heads, and physicians. Data were collected using a questionnaire consisting of two parts: demographic information of the participants and 5-point Likert scale questions concerning the five dimensions of users' work. Data were analyzed using descriptive statistics, ANOVA, and Pearson's correlation coefficient statistical tests. The mean of scores given by the PACS users was 4.31 ± 0.86 for external communication, 4.18 ± 0.96 for user intention to use the PACS, 3.91 ± 0.7 for service quality, 3.16 ± 0.56 for daily routine, and 3.08 ± 1.05 for complaints on users. Radiologists and radiology staff had a more positive opinion about the PACS than other clinicians such as physicians (P < 0.01, CI = 95%). Factors such as user age (P < 0.01, CI = 95%), job (P < 0.001, CI = 95%), work experience (P < 0.001, CI = 95%), and PACS training method (P=0.037, CI = 95%) were related to the impact of the PACS on different dimensions of users' work. This study showed that the PACS has a positive effect on different dimensions of users' work, especially on external communication, user intention to use the system, and service quality. It is recommended to implement PACSs in medical centers to support users' work and to maintain and strengthen the capabilities and functions of radiology departments.

Obstacles and Solutions Driving the Development of a National Teleradiology Network

Background: Teleradiology has the potential to link medical experts and specialties despite geographical separation. In a project report about hospital-based teleradiology, the significance of technical and human factors during the implementation and growth of a teleradiology network are explored. Evaluation: The article identifies major obstacles during the implementation and growth of the teleradiology network of the Berlin Trauma Hospital (BG Unfallkrankenhaus Berlin) between 2004 and 2020 in semi-structured interviews with senior staff members. Quantitative analysis of examination numbers, patient numbers, and profits relates the efforts of the staff members to the monetary benefits and success of the network. Identification of qualitative and quantitative factors for success: Soft and hard facilitators and solutions driving the development of the national teleradiology network are identified. Obstacles were often solved by technical innovations, but the time span between required personal efforts, endurance, and flexibility of local and external team members. The article describes innovations driven by teleradiology and hints at the impact of teleradiology on modern medical care by relating the expansion of the teleradiology network to patient transfers and profits. Conclusion: In addition to technical improvements, interpersonal collaborations were key to the success of the teleradiology network of the Berlin Trauma Hospital and remained a unique feature and selling point of this teleradiology network.

Clinicians' Perceptions of Picture Archiving and Communication System (PACS) Use in Patient Care in Eastern Province Hospitals in Saudi Arabia

Purpose

The picture archiving and communication system (PACS) is one of the most important tools used in patient care in many hospitals worldwide. It allows clinicians to remotely communicate and consult with other clinicians on patient cases and view diagnostic images from different angles, thus facilitating patient diagnosis and treatment. Several studies have been conducted in Saudi Arabia to evaluate different aspects of PACS use; however, no comprehensive study has been conducted in its Eastern Province. This study aimed to investigate clinicians’ perceptions of the advantages and disadvantages of the use of PACS in Eastern Province hospitals in Saudi Arabia and identify the factors that affect their perceptions and its use. In addition, it aimed to gather recommendations of clinicians for improving the system and its implementation.

Methods

A qualitative approach with grounded theory method was employed. A sample of 18 residents, radiologists, and consultants from three Eastern Province hospitals in Saudi Arabia participated in the study. Data were collected using semi-structured interviews over a period of 7 months.

Results

The perceived advantages of PACS included providing quality images and the ability to manipulate their resolution, whereas the perceived barriers included low-speed internet connections and technical problems. Participants recommended providing clinicians remote access to the system and implementing a mobile PACS application. The theory that emerged from the analysis revealed that demographic, system-related, and hospital-related factors affected participants’ perspectives of PACS and its use.

Conclusion

The results of this study and its theoretical model can help identify areas of improvement and inform policy and strategic planning for the effective implementation of PACS in patient care in Saudi Arabia.

Disaster Planning During SARS-CoV-2/COVID: One Radiology Informatics Team's Story

Disasters cause a major disruption to normal operations. Hospital information systems are often well-prepared for events such as fires or natural disasters. This type of disaster planning focuses on redundancy and manual workarounds. The SARS-CoV-2/COVID pandemic represented a new type of disaster for our radiology informatics team. In this pandemic, the information systems continued to work but the employees, and the computers that they worked with, had to be distanced. The purpose of this manuscript is to discuss the four phases of the disaster planning process: mitigation, planning, response, and recovery. We will illustrate the process with the example of how our radiology informatics team responded to the SARS-CoV-2/COVID pandemic.

An Open-Source, Vender Agnostic Hardware and Software Pipeline for Integration of Artificial Intelligence in Radiology Workflow

Although machine learning (ML) has made significant improvements in radiology, few algorithms have been integrated into clinical radiology workflow. Complex radiology IT environments and Picture Archiving and Communication System (PACS) pose unique challenges in creating a practical ML schema. However, clinical integration and testing are critical to ensuring the safety and accuracy of ML algorithms. This study aims to propose, develop, and demonstrate a simple, efficient, and understandable hardware and software system for integrating ML models into the standard radiology workflow and PACS that can serve as a framework for testing ML algorithms. A Digital Imaging and Communications in Medicine/Graphics Processing Unit (DICOM/GPU) server and software pipeline was established at a metropolitan county hospital intranet to demonstrate clinical integration of ML algorithms in radiology. A clinical ML integration schema, agnostic to the hospital IT system and specific ML models/frameworks, was implemented and tested with a breast density classification algorithm and prospectively evaluated for time delays using 100 digital 2D mammograms. An open-source clinical ML integration schema was successfully implemented and demonstrated. This schema allows for simple uploading of custom ML models. With the proposed setup, the ML pipeline took an average of 26.52 s per second to process a batch of 100 studies. The most significant processing time delays were noted in model load and study stability times. The code is made available at " http://bit.ly/2Z121hX ". We demonstrated the feasibility to deploy and utilize ML models in radiology without disrupting existing radiology workflow.

The Case for User-Centered Artificial Intelligence in Radiology

Past technology transition successes and failures have demonstrated the importance of user-centered design and the science of human factors; these approaches will be critical to the success of artificial intelligence in radiology.

Challenges of Implementing Picture Archiving and Communication System in Multiple Hospitals: Perspectives of Involved Staff and Users

Today, despite the advantages of the PACS system, its implementation in some healthcare organizations faces many challenges. One of the important factors in the successful implementation of a PACS system is identifying and prioritizing the challenges from the perspectives of involved staff and user of this system. Therefore, the aim of this study was to determine and compare the challenges of implementing PACS from perspectives these users in educational hospitals. This study was conducted on all IT and medical equipment staff, and radiology residents (n = 140) in Kerman University of Medical Sciences (KUMS) and Shiraz University of Medical Sciences (SUMS) in 2016. The data were collected through two researcher-made questionnaires. Their validity was approved by radiologists, IT staff, and medical informatics specialists and their reliability through calculation of Cronbach's Alpha (0.969 and 0.795). We used Multivariate Analysis of Variance (MANOVA) to compare the scores given by three groups of participants in the challenges and Univariate Analysis of Variance (ANOVA) to compare the scores in two universities. The participants believed that technical challenges were more important than other challenges (x̄=3.74, SD = 0.7). IT experts (x̄=3.87, SD = 1) and radiology residents (x̄=3.95, SD = 0.9) gave the higher scores to the "shortage of high quality monitors" factor and medical equipment experts (x̄=4.26, SD = 0.87) to the "low speed of communication networks" factor among all technical challenges. The mean scores given to technical (x̄=76.1, SD = 13.5) and managerial (x̄=16, SD = 5.9) challenges in SUMS were more than the scores of the same challenges in KUMS (x̄=69.9, SD = 15.7) and (x̄=11.9, SD = 6.4) (p < 0.05). The technical challenges are the most common challenges to PACS implementation, and different universities experience different levels of technical challenges. Eliminating implementation challenges can reduce the risk of failure in the utilization process. Based on the results of this study, providing necessary infrastructures such as appropriate monitors and upgraded IT equipment can prevent many of the PACS implementation challenges.