Fahmid U. Chowdhury

Artificial intelligence (AI) can revolutionize clinical workflows in radiology but requires organizational change. An institutional strategy to develop and evaluate AI tools is outlined. A multidisciplinary AI board with a patient and public involvement and engagement group was created. A comprehensive framework was formed, comprising workstreams covering information governance; technical rigor, performance, and safety; economic considerations; and ethical and medical-legal aspects. In addition to recurring meetings, a workshop with clinicians, information technology specialists, and patient representatives helped to identify priority use cases. Technical infrastructure was enhanced to support the development, performance assessment, and deployment of AI tools. Primary areas for AI applications included training staff, vetting of image requests, quality assurance, image interpretation, and communicating imaging findings to patients. Potential barriers, gaps in evidence, and subsequent actions for AI implementation were outlined. Avenues for collaboration with industry and market-available solutions were outlined. A virtual Picture Archiving and Communication System server was developed and then connected to a deployment platform for performance evaluation of AI products. Establishing an institutional AI board and imaging AI sandbox has guided safe, effective AI implementation while creating an ideal setting for innovation and industry partnership. Our approach to the integration of imaging AI provides a pragmatic guide for other institutions.

Objectives To evaluate the utility of a standardized qualitative scoring system for treatment response assessment at 18F-FDG PET-CT in patients undergoing chemoradiotherapy for locally advanced cervical carcinoma and correlate this with subsequent patient outcome. Methods Ninety-six consecutive patients with locally advanced cervical carcinoma treated with radical chemoradiotherapy (CRT) in a single centre between 2011 and 2014 underwent 18F-FDG PET-CT approximately 3 months post-treatment. Tumour metabolic response was assessed qualitatively using a 5-point scale ranging from background level activity only through to progressive metabolic disease. Clinical and radiological (MRI pelvis) follow-up was performed in all patients. Progression-free (PFS) and overall survival (OS) was calculated using the Kaplan-Meier method (Mantel-Cox log-rank) and correlated with qualitative score using Chi-squared test. Results Forty patients (41.7 %) demonstrated complete metabolic response (CMR) on post-treatment PET-CT (Score 1/2) with 38 patients (95.0 %) remaining disease free after a minimum follow-up period of 18 months. Twenty-four patients (25.0 %) had indeterminate residual uptake (ID, Score 3) at primary or nodal sites after treatment, of these eight patients (33.3 %) relapsed on follow-up, including all patients with residual nodal uptake (n = 4Eleven11 of 17 patients (64.7 %) with significant residual uptake (partial metabolic response, PMR, Score 4) subsequently relapsed. In 15 patients (15.6 %) PET-CT demonstrated progressive disease (PD, Score 5) following treatment. Kaplan-Meier analysis showed a highly statistically significant difference in PFS and OS between patients with CMR, indeterminate uptake, PMR and PD (Log-rank, P < 0.0001). Chi-squared test demonstrated a highly statistically significant association between increasing qualitative score and risk of recurrence or death (P < 0.001). Conclusion Use of a 5-point qualitative scoring system to assess metabolic response to CRT in locally advanced cervical carcinoma predicts survival outcome and this prognostic information may help guide further patient management.

Commenting on “Teaching NeuroImages: Hypometabolism of the primary motor cortex in primary lateral sclerosis: The stripe sign,” Dr. Turner proposes that when primary lateral sclerosis (PLS) symptoms start in the upper extremity, the disease invariably progresses to amyotrophic lateral sclerosis

To the Editor: In the large, randomized, clinical trial conducted by Carrier et al. (Aug. 20 issue),¹ the use of computed tomography (CT) of the abdomen and pelvis did not confer any additional advantage over the use of limited cancer screening for the detection of underlying cancer among patients with unprovoked venous thromboembolism. The mean age of the patients was 53 years. Here we report the results of a similar Italian trial conducted in 195 cancer-free patients who were randomly assigned to receive either limited cancer screening or an extensive CT investigation involving the thorax, abdomen, and pelvis.² The mean . . .