Peptide Receptor Radionuclide Therapy Is Effective for Clinical Control of Symptomatic Metastatic Insulinoma: A Long-Term Retrospective Analysis.

Metastatic insulinoma is a rare malignant neuroendocrine tumor characterized by inappropriate insulin secretion, resulting in life-threatening hypoglycemia, which is often difficult to treat. There is currently very limited information about the efficacy of peptide receptor radionuclide therapy (PRRT) for clinical control of hypoglycemia. The aim of this long-term retrospective study was to evaluate the therapeutic efficacy of PRRT for improving hypoglycemia, to evaluate the change of medication after PRRT, and to calculate progression-free survival (PFS) and overall survival (OS). Methods: Inclusion criteria were histologically proven somatostatin receptor-positive metastatic malignant insulinoma and at least 2 cycles of [90Y]Y-DOTATOC or [177Lu]Lu-DOTATOC therapy from early 2000 to early 2022. A semiquantitative scoring system was used to quantify the severity and frequency of hypoglycemic episodes under background antihypoglycemic therapy (somatostatin analog, diazoxide, everolimus, corticosteroids): score 0, no hypoglycemic episodes; score 1, hypoglycemic events requiring additional conservative treatment with optimization of nutrition; score 2, severe hypoglycemia necessitating hospitalization and combined medication or history of hypoglycemic coma. Hypoglycemic score before and after PRRT was analyzed. Time of benefit was defined as a time range of fewer hypoglycemic episodes in the observation period than at baseline. Information on antihypoglycemic medication before and after therapy, PFS, and OS was recorded. Results: Twenty-six of 32 patients with a total of 106 [90Y]Y-DOTATOC/[177Lu]Lu-DOTATOC cycles were included. The average observation period was 21.5 mo (range, 2.3-107.4 mo). Before therapy, 81% (n = 21) of the patients had a hypoglycemia score of 2 and 19% (n = 5) had a score of 1. After PRRT, 81% of patients (n = 21) had a decreased score, and the remaining 5 patients showed a stable situation. There was temporary worsening of hypoglycemia just after injection of [90Y]Y-DOTATOC/[177Lu]Lu-DOTATOC in 19% of patients. The average time of benefit in the observation period was 17.2 mo (range, 0-70.2 mo). Antihypoglycemic medication reduction was achieved in 58% (n = 15) of patients. The median OS and PFS after the start of PRRT were 19.7 mo (95% CI, 6.5-32.9 mo) and 11.7 mo (95% CI, 4.9-18.5 mo), respectively. Conclusion: To our knowledge, our study included the largest cohort of patients with malignant insulinoma to be evaluated. Long-lasting symptom control and reduction of antihypoglycemic medications were shown in most patients after late-line PRRT.

Reduction in Radiologist Interpretation Time of Serial CT and MR Imaging Findings with Deep Learning Identification of Relevant Priors, Series and Finding Locations.

RATIONALE AND OBJECTIVES: Finding comparison to relevant prior studies is a requisite component of the radiology workflow. The purpose of this study was to evaluate the impact of a deep learning tool simplifying this time-consuming task by automatically identifying and displaying the finding in relevant prior studies. MATERIALS AND METHODS: The algorithm pipeline used in this retrospective study, TimeLens (TL), is based on natural language processing and descriptor-based image-matching algorithms. The dataset used for testing comprised 3872 series of 246 radiology examinations from 75 patients (189 CTs, 95 MRIs). To ensure a comprehensive testing, five finding types frequently encountered in radiology practice were included: aortic aneurysm, intracranial aneurysm, kidney lesion, meningioma, and pulmonary nodule. After a standardized training session, nine radiologists from three university hospitals performed two reading sessions on a cloud-based evaluation platform resembling a standard RIS/PACS. The task was to measure the diameter of the finding-of-interest on two or more exams (a most recent and at least one prior exam): first without use of TL, and a second session at an interval of at least 21 days with the use of TL. All user actions were logged for each round, including time needed to measure the finding at all timepoints, number of mouse clicks, and mouse distance traveled. The effect of TL was evaluated in total, per finding type, per reader, per experience (resident vs. board-certified radiologist), and per modality. Mouse movement patterns were analyzed with heatmaps. To assess the effect of habituation to the cases, a third round of readings was performed without TL. RESULTS: Across scenarios, TL reduced the average time needed to assess a finding at all timepoints by 40.1% (107 vs. 65 seconds; p < 0.001). Largest accelerations were demonstrated for assessment of pulmonary nodules (-47.0%; p < 0.001). Less mouse clicks (-17.2%) were needed for finding evaluation with TL, and mouse distance traveled was reduced by 38.0%. Time needed to assess the findings increased from round 2 to round 3 (+27.6%; p < 0.001). Readers were able to measure a given finding in 94.4% of cases on the series initially proposed by TL as most relevant series for comparison. The heatmaps showed consistently simplified mouse movement patterns with TL. CONCLUSION: A deep learning tool significantly reduced both the amount of user interactions with the radiology image viewer and the time needed to assess findings of interest on cross-sectional imaging with relevant prior exams.