The British journal of radiology
-
Computer-aided diagnosis (CAD) has been a popular area of research and development in the past few decades. In CAD, machine learning methods and multidisciplinary knowledge and techniques are used to analyze the patient information and the results can be used to assist clinicians in their decision making process. CAD may analyze imaging information alone or in combination with other clinical data. ⋯ The new state-of-the-art machine learning technique, known as deep learning (DL), has revolutionized speech and text recognition as well as computer vision. The potential of major breakthrough by DL in medical image analysis and other CAD applications for patient care has brought about unprecedented excitement of applying CAD, or artificial intelligence (AI), to medicine in general and to radiology in particular. In this paper, we will provide an overview of the recent developments of CAD using DL in breast imaging and discuss some challenges and practical issues that may impact the advancement of artificial intelligence and its integration into clinical workflow.
-
Review
Artificial Intelligence: reshaping the practice of radiological sciences in the 21st century.
Advances in computing hardware and software platforms have led to the recent resurgence in artificial intelligence (AI) touching almost every aspect of our daily lives by its capability for automating complex tasks or providing superior predictive analytics. AI applications are currently spanning many diverse fields from economics to entertainment, to manufacturing, as well as medicine. ⋯ We further summarize the current status of AI in radiological sciences, highlighting, with examples, its impressive achievements and effect on re-shaping the practice of medical imaging and radiotherapy in the areas of computer-aided detection, diagnosis, prognosis, and decision support. Moving beyond the commercial hype of AI into reality, we discuss the current challenges to overcome, for AI to achieve its promised hope of providing better precision healthcare for each patient while reducing cost burden on their families and the society at large.
-
A cohort of high dose-rate (HDR) monotherapy patients was analyzed to (i) establish the frequency of non-malignant urethral stricture; (ii) explore the relation between stricture formation with the dose distribution along the length of the urethra, and MRI radiomics features of the prostate gland. ⋯ Urethral stricture has been reported as a specific late effect with prostate HDR brachytherapy. Our study reported a relatively low stricture rate of 3% and no association between post-treatment stricture and urethral dosimetry was identified. MRI radiomics features can potentially identify patients who are more prone to develop strictures.
-
To evaluate role of multiparametric MRI (mp-MRI) in differentiation between invasive and non-invasive bladder cancer and accuracy of vesical imaging reporting and data system (VI-RADS) score. ⋯ The VI-RADS system was recently suggested for the uniform evaluation of muscle invasion in cancer bladder by mp-MRI. In this paper, we applied this system to 50 cases to evaluate its ease and compared the results with the histopathological findings for evaluation of its accuracy.
-
To evaluate the therapeutic response, progression free survival (PFS), overall survival (OS) and clinical toxicity of 177Lu-PSMA-617 PSMA targeted radioligand therapy (PRLT) in the setting of heavily pre-treated metastatic castrate-resistant prostate cancer (mCPRC) patients and also examine the association of prognostic variables with therapeutic outcome in such patient cohort. ⋯ The present work explored in a large teriary cancer care setting, the efficacy of 177Lu-PSMA-617 PRLT, in an aggressive and unselected subset of mCRPC. The response and outcome was correlated with a number of prognostic variables, including molecular imaging findings (FDG uptake in the metastatic lesions), PSA DT and Gleason score.