Building and Querying RDF/OWL Database of Semantically Annotated Nuclear Medicine Images.

As the use of positron emission tomography-computed tomography (PET-CT) has increased rapidly, there is a need to retrieve relevant medical images that can assist image interpretation. However, the images themselves lack the explicit information needed for query. We constructed a semantically structured database of nuclear medicine images using the Annotation and Image Markup (AIM) format and evaluated the ability the AIM annotations to improve image search. We created AIM annotation templates specific to the nuclear medicine domain and used them to annotate 100 nuclear medicine PET-CT studies in AIM format using controlled vocabulary. We evaluated image retrieval from 20 specific clinical queries. As the gold standard, two nuclear medicine physicians manually retrieved the relevant images from the image database using free text search of radiology reports for the same queries. We compared query results with the manually retrieved results obtained by the physicians. The query performance indicated a 98 % recall for simple queries and a 89 % recall for complex queries. In total, the queries provided 95 % (75 of 79 images) recall, 100 % precision, and an F1 score of 0.97 for the 20 clinical queries. Three of the four images missed by the queries required reasoning for successful retrieval. Nuclear medicine images augmented using semantic annotations in AIM enabled high recall and precision for simple queries, helping physicians to retrieve the relevant images. Further study using a larger data set and the implementation of an inference engine may improve query results for more complex queries.

Correlation of Uptake Patterns on Single-Photon Emission Computed Tomography/Computed Tomography (SPECT/CT) and Treatment Response in Patients with Knee Pain.

PURPOSE: To determine whether treatment response in patients with knee pain could be predicted using uptake patterns on single-photon emission computed tomography/computed tomography (SPECT/CT) images. METHODS: Ninety-five patients with knee pain who had undergone SPECT/CT were included in this retrospective study. Subjects were divided into three groups: increased focal uptake (FTU), increased irregular tracer uptake (ITU), and no tracer uptake (NTU). A numeric rating scale (NRS-11) assessed pain intensity. We analyzed the association between uptake patterns and treatment response using Pearson's chi-square test and Fisher's exact test. Uptake was quantified from SPECT/CT with region of interest (ROI) counting, and an intraclass correlation coefficient (ICC) calculated agreement. We used Student's t-test to calculate statistically significant differences of counts between groups and the Pearson correlation to measure the relationship between counts and initial NRS-1k1. Multivariate logistic regression analysis determined which variables were significantly associated with uptake. RESULTS: The FTU group included 32 patients; ITU, 39; and NTU, 24. With conservative management, 64 % of patients with increased tracer uptake (TU, both focal and irregular) and 36 % with NTU showed positive response. Conservative treatment response of FTU was better than NTU, but did not differ from that of ITU. Conservative treatment response of TU was significantly different from that of NTU (OR 3.1; p = 0.036). Moderate positive correlation was observed between ITU and initial NRS-11. Age and initial NRS-11 significantly predicted uptake. CONCLUSIONS: Patients with uptake in their knee(s) on SPECT/CT showed positive treatment response under conservative treatment.

Can Initial (18)F-FDG PET-CT Imaging Give Information on Metastasis in Patients with Primary Renal Cell Carcinoma?

PURPOSE: The aim of this study was to investigate the relationship between the maximum standardized uptake values (SUVmax) of primary renal cancers with and without metastatic lesions, if any. We also studied the relationship between the size of primary renal cancers and their SUVmax, and tried to find a clinical value of (18)F-FDG PET-CT for the initial evaluation of renal cell carcinoma (RCC). METHODS: The cases of 23 patients, 16 men and 7 women, who underwent PET-CT examination before operation were retrospectively reviewed. We measured the SUVmax of the primary renal cancers and those of any existing metastatic lesions, and the size of the primary renal cancers. We compared the SUVmax of primary RCCs with metastases and those without metastases, SUVmax of primary RCC and those of metastases, and studied the correlation between the size and SUVmax of primary RCCs. RESULTS: The SUVmax of primary RCC of the 16 patients without metastasis ranged from 1.1 to 5.6 with a median value of 2.6. Those of the patients with metastasis ranged from 2.9 to 7.6 with a median of 5.0. The size of the all 23 primary renal cancers ranged from 1.7 cm to 13.5 cm, with a median of 4.5 cm, and their SUVmax ranged from 1.1 to 7.6, with a median of 2.9. There was a statistically significant difference between the SUVmax of the primary RCC with metastasis (5.3 ± 1.7) and those without metastasis (2.9 ± 1.0). There was a moderate positive correlation between the sizes and SUVmax of all 23 primary RCCs. However, there was no statistically significant correlation between the sizes and SUVmax of primary RCCs with metastatic lesions and the same for RCCs without metastasis. The cutoff value of SUVmax for predicting extra-renal lesion was 4.4 and that for size was 5.8 cm according to the receiver operating characteristic curves. CONCLUSIONS: Those who have primary RCC with high SUVmax are suggested to have a likelihood of metastasis. Also, there was a moderate trend of increasing value of SUVmax of primary RCC as their size increases. Physicians should beware of missing extra-renal lesions elsewhere.