Within six months of the discovery of X-ray in 1895, the technology was used to scan the interior of the human body, paving the way for many innovations in the field of medicine, including an ultrasound device in 1950, a CT scanner in 1972, and MRI in 1980. More recent decades have witnessed developments such as digital imaging using a picture archiving and communication system, computer-aided detection/diagnosis, organ-specific workstations, and molecular, functional, and quantitative imaging. One of the latest technical breakthrough in the field of radiology has been imaging genomics and robotic interventions for biopsy and theragnosis. This review provides an engineering perspective on these developments and several other megatrends in radiology.
Biological Markers/analysis ; Biomedical Engineering ; Diagnosis, Computer-Assisted/*trends ; Diagnostic Imaging/*trends ; Equipment Design ; Genomics ; Humans ; Image Processing, Computer-Assisted/*trends ; Radiology Information Systems/*trends ; Robotics ; Systems Integration ; User-Computer Interface

Artificial intelligence (AI) will likely affect various fields of medicine. This article aims to explain the fundamental principles of clinical validation, device approval, and insurance coverage decisions of AI algorithms for medical diagnosis and prediction. Discrimination accuracy of AI algorithms is often evaluated with the Dice similarity coefficient, sensitivity, specificity, and traditional or free-response receiver operating characteristic curves. Calibration accuracy should also be assessed, especially for algorithms that provide probabilities to users. As current AI algorithms have limited generalizability to real-world practice, clinical validation of AI should put it to proper external testing and assisting roles. External testing could adopt diagnostic case-control or diagnostic cohort designs. A diagnostic case-control study evaluates the technical validity/accuracy of AI while the latter tests the clinical validity/accuracy of AI in samples representing target patients in real-world clinical scenarios. Ultimate clinical validation of AI requires evaluations of its impact on patient outcomes, referred to as clinical utility, and for which randomized clinical trials are ideal. Device approval of AI is typically granted with proof of technical validity/accuracy and thus does not intend to directly indicate if AI is beneficial for patient care or if it improves patient outcomes. Neither can it categorically address the issue of limited generalizability of AI. After achieving device approval, it is up to medical professionals to determine if the approved AI algorithms are beneficial for real-world patient care. Insurance coverage decisions generally require a demonstration of clinical utility that the use of AI has improved patient outcomes.

Artificial intelligence (AI) will likely affect various fields of medicine. This article aims to explain the fundamental principles of clinical validation, device approval, and insurance coverage decisions of AI algorithms for medical diagnosis and prediction.Discrimination accuracy of AI algorithms is often evaluated with the Dice similarity coefficient, sensitivity, specificity, and traditional or free-response receiver operating characteristic curves. Calibration accuracy should also be assessed, especially for algorithms that provide probabilities to users. As current AI algorithms have limited generalizability to realworld practice, clinical validation of AI should put it to proper external testing and assisting roles. External testing could adopt diagnostic case-control or diagnostic cohort designs. A diagnostic case-control study evaluates the technical validity/ accuracy of AI while the latter tests the clinical validity/accuracy of AI in samples representing target patients in realworld clinical scenarios. Ultimate clinical validation of AI requires evaluations of its impact on patient outcomes, referred to as clinical utility, and for which randomized clinical trials are ideal. Device approval of AI is typically granted with proof of technical validity/accuracy and thus does not intend to directly indicate if AI is beneficial for patient care or if it improves patient outcomes. Neither can it categorically address the issue of limited generalizability of AI. After achieving device approval, it is up to medical professionals to determine if the approved AI algorithms are beneficial for real-world patient care. Insurance coverage decisions generally require a demonstration of clinical utility that the use of AI has improved patient outcomes.

PURPOSE: Charcot-Marie-Tooth disease (CMT) is a peripheral neuropathy mainly divided into CMT type 1 (CMT1) and CMT2 according to the phenotype and genotype. Although molecular pathologies for each genetic causative have not been revealed in CMT2, the correlation between cell death and accumulation of misfolded proteins in the endoplasmic reticulum (ER) of Schwann cells is well documented in CMT1. Establishment of in vitro models of ER stress-mediated Schwann cell death might be useful in developing drug-screening systems for the treatment of CMT1. MATERIALS AND METHODS: To develop high-throughput screening (HTS) systems for CMT1, we generated cell models using transient expression of mutant proteins and chemical induction. RESULTS: Overexpression of wild type and mutant peripheral myelin protein 22 (PMP22) induced ER stress. Similar results were obtained from mutant myelin protein zero (MPZ) proteins. Protein localization revealed that expressed mutant PMP22 and MPZ proteins accumulated in the ER of Schwann cells. Overexpression of wild type and L16P mutant PMP22 also reduced cell viability, implying protein accumulation-mediated ER stress causes cell death. To develop more stable screening systems, we mimicked the ER stress-mediated cell death in Schwann cells using ER stress inducing chemicals. Thapsigargin treatment caused cell death via ER stress in a dose dependent manner, which was measured by expression of ER stress markers. CONCLUSION: We have developed genetically and chemically induced ER stress models using Schwann cells. Application of these models to HTS systems might facilitate the elucidation of molecular pathology and development of therapeutic options for CMT1.
Cell Death ; Cell Survival ; Charcot-Marie-Tooth Disease* ; Endoplasmic Reticulum ; Endoplasmic Reticulum Stress ; Genotype ; Mass Screening* ; Mutant Proteins ; Myelin P0 Protein ; Myelin Sheath ; Pathology, Molecular ; Peripheral Nervous System Diseases ; Phenotype ; Schwann Cells ; Thapsigargin

No abstract available.