Artificial Intelligence for the Future Radiology Diagnostic Service

Abstract

Radiology historically has been a leader of digital transformation in healthcare. The introduction of digital imaging systems, picture archiving and communication systems (PACS), and teleradiology transformed radiology services over the past 30 years. Radiology is again at the crossroad for the next generation of transformation, possibly evolving as a one-stop integrated diagnostic service. Artificial intelligence and machine learning promise to offer radiology new powerful new digital tools to facilitate the next transformation. The radiology community has been developing computer-aided diagnosis (CAD) tools based on machine learning (ML) over the past 20 years. Among various AI techniques, deep-learning convolutional neural networks (CNN) and its variants have been widely used in medical image pattern recognition. Since the 1990s, many CAD tools and products have been developed. However, clinical adoption has been slow due to a lack of substantial clinical advantages, difficulties integrating into existing workflow, and uncertain business models. This paper proposes three pathways for AI's role in radiology beyond current CNN based capabilities 1) improve the performance of CAD, 2) improve the productivity of radiology service by AI-assisted workflow, and 3) develop radiomics that integrate the data from radiology, pathology, and genomics to facilitate the emergence of a new integrated diagnostic service.

Explainable machine learning methods and respiratory oscillometry for the diagnosis of respiratory abnormalities in sarcoidosis

“…Previous research has established that diagnostic easiness is a fundamental attribute for occupied non-specialist clinicians [ 53 ]. Studies in radiology [ 54 ], ophthalmology [ 55 ], and cardiology [ 56 ] have shown that ML methods may contribute to improving the medical service by AI-assisted workflow. The present study confirms and extends these findings to respiratory physiology showing that machine learning algorithms help diagnose respiratory abnormalities in sarcoidosis.…”

Neurosurgery and artificial intelligence

“…Some challenges in neurosurgical care can be circumvented by computer-assisted diagnosis (CAD) and AI. By using a vast amount of anatomical, morphological and connectivity information, AI and CAD can significantly help neuroradiologists and neurosurgeons to make effective and efficient diagnoses, accelerating the triage and hence the workflow to initiate the treatment, reducing the human labour as well as the costs [45] . Multiple studies have demonstrated that door-to-needle times play a crucial role in reducing mortality and improving the prognosis, and obtaining and interpreting radiological images, and the lack of access to neurologists are the major reasons causing delays in delivering emergency treatments for conditions such as stroke [46] – [48] .…”

State of the Art and New Concepts in Giant Cell Tumor of Bone: Imaging Features and Tumor Characteristics

“…In the era of computer-aided diagnosis tools based on machine learning, deep-learning convolutional neural networks (CNN) and their variants have been increasingly used in medical image pattern recognition as integrative instruments to aid radiologists in the correct diagnosis [ 90 ]. In this regard, the same group of He et al [ 91 ] aimed to predict GCTB local recurrence after intralesional curettage using a deep CNN, evaluating pre-surgery MR images, whose results were compared with the same analysis performed by four musculoskeletal radiologists of at least 12 years’ experience.…”