Comparative effectiveness of standard vs. AI-assisted PET/CT reading workflow for pre-treatment lymphoma staging: a multi-institutional reader study evaluation.

Background: Fluorine-18 fluorodeoxyglucose (FDG)-positron emission tomography/computed tomography (PET/CT) is widely used for staging high-grade lymphoma, with the time to evaluate such studies varying depending on the complexity of the case. Integrating artificial intelligence (AI) within the reporting workflow has the potential to improve quality and efficiency. The aims of the present study were to evaluate the influence of an integrated research prototype segmentation tool implemented within diagnostic PET/CT reading software on the speed and quality of reporting with variable levels of experience, and to assess the effect of the AI-assisted workflow on reader confidence and whether this tool influenced reporting behaviour. Methods: Nine blinded reporters (three trainees, three junior consultants and three senior consultants) from three UK centres participated in a two-part reader study. A total of 15 lymphoma staging PET/CT scans were evaluated twice: first, using a standard PET/CT reporting workflow; then, after a 6-week gap, with AI assistance incorporating pre-segmentation of disease sites within the reading software. An even split of PET/CT segmentations with gold standard (GS), false-positive (FP) over-contour or false-negative (FN) under-contour were provided. The read duration was calculated using file logs, while the report quality was independently assessed by two radiologists with >15 years of experience. Confidence in AI assistance and identification of disease was assessed via online questionnaires for each case. Results: There was a significant decrease in time between non-AI and AI-assisted reads (median 15.0 vs. 13.3 min, p < 0.001). Sub-analysis confirmed this was true for both junior (14.5 vs. 12.7 min, p = 0.03) and senior consultants (15.1 vs. 12.2 min, p = 0.03) but not for trainees (18.1 vs. 18.0 min, p = 0.2). There was no significant difference between report quality between reads. AI assistance provided a significant increase in confidence of disease identification (p < 0.001). This held true when splitting the data into FN, GS and FP. In 19/88 cases, participants did not identify either FP (31.8%) or FN (11.4%) segmentations. This was significantly greater for trainees (13/30, 43.3%) than for junior (3/28, 10.7%, p = 0.05) and senior consultants (3/30, 10.0%, p = 0.05). Conclusions: The study findings indicate that an AI-assisted workflow achieves comparable performance to humans, demonstrating a marginal enhancement in reporting speed. Less experienced readers were more influenced by segmentation errors. An AI-assisted PET/CT reading workflow has the potential to increase reporting efficiency without adversely affecting quality, which could reduce costs and report turnaround times. These preliminary findings need to be confirmed in larger studies.

The COVID-19 pandemic: impact on NHS England PET-CT services and lessons learnt.

PURPOSE: The purpose of the study was to examine the impact of the first wave of COVID-19 on National Health Service (NHS) 18F-fluorodeoxyglucose positron emission tomography computed tomography (FDG PET-CT) scanning activity across England. METHODS: Monthly FDG PET-CT scanning activity was collected from 41/48 NHS England provider sites. Data from 31/41 sites were stratified by nononcology/oncology, cancer type, with lung cancer and lymphoma split into specific indications, turn-around times and delays due to radiotracer. RESULTS: In April and May 2020, a 32 and 31% decrease in activity was observed, a larger decrease for noncancer compared with cancer FDG PET-CT. In June 2020, activity started to recover with 6% fewer scans recorded compared with June 2019. Of the six most common indications, lung and oesophageal cancer had the largest decrease in activity and slowest recovery. Lymphoma and melanoma showed the smallest decrease and fastest recovery. Lung cancer scans for initial diagnosis/staging saw the largest fall and slowest recovery compared with scans for known lung cancer. There was no percentage increase in overall turn-around time compared with the same months in 2019, and no increase in turn-around time of more than 7 working days due to FDG supply during April and May 2020 compared with the 3 previous months. CONCLUSIONS: There is no correlation between FDG PET-CT activity (fall and recovery) in England and the ability to provide the service by NHS England. It most likely reflects a combination of changes in health-seeking behaviour, NHS health policy and a decrease in the use of investigations that carry a high risk of COVID-19 transmission.

Interaction of interferon alpha therapy with thyroid function tests in the management of hepatitis C: a case report.

BACKGROUND: Interferon alpha is a widely used therapeutic agent in the treatment of hepatitis C virus infection. Clinical thyroid disease is seen in nearly 15 % of patients receiving interferon alpha for hepatitis C virus infection. The mechanism of thyroid dysfunction with interferon alpha is either autoimmune or inflammatory. We report a case of young woman who developed biphasic thyroid dysfunction posing a diagnostic challenge, while receiving interferon alpha treatment for hepatitis C virus infection. CASE PRESENTATION: A 29-year-old, Caucasian woman with type 1 diabetes and hepatitis C virus infection was referred with hyperthyroidism, while she was at 17 weeks of a planned 24-week course of interferon alpha therapy. A laboratory investigation revealed a thyroid stimulation hormone level of 0.005 mU/L (0.350-4.94), free thyroxine of 45.6 pmol/L (9.0-19.0) and free tri-iodothyronine of 12.6 pmol/L (2.6-5.7). She had a mild neutropenia and alanine aminotransferase at double the reference value. Her thyroid peroxidase antibody level was 497 ku/L (<5.6) and thyroid inhibitory factor 7 IU/L (>1.8 iu/l is positive). Thyroid scintigraphy with technetium99 scan confirmed a normal-sized thyroid gland with diffuse but normal overall uptake. A diagnosis of interferon alpha-triggered autoimmune hyperthyroidism as opposed to an inflammatory thyroiditis was made. She was offered radioactive iodine therapy, as thionamides were considered inappropriate in view of her liver disease and mild neutropenia. Due to our patient's personal circumstances, radioactive iodine therapy was delayed by 8 weeks and her thyrotoxic symptoms were controlled with beta-blockers alone. A repeat thyroid function test, 4 weeks post treatment with interferon alpha, indicated spontaneous conversion to hypothyroidism with a thyroid stimulation hormone level of 100 mU/L, free thyroxine of 5.2 pmol/L and free tri-iodothyronine of 1.7 pmol/L. She subsequently received levothyroxine for 4 months only and had remained euthyroid for the last 3 months without any treatment. CONCLUSIONS: Initial investigations favored the autoimmune nature of hyperthyroidism but follow-up of the case, interestingly, was more consistent with inflammatory thyroiditis. We propose that this can be explained either on the basis of autoimmune subacute thyroiditis or a change in the nature of thyroid stimulation hormone receptor antibody production from stimulating-type to blocking-type antibodies, with disappearance of the latter on discontinuation of interferon alpha.