Bone scintigraphy (BS) is one of the most frequently utilized diagnostic techniques in detecting cancer bone metastasis, and it occupies an enormous workload for nuclear medicine physicians. So, we aimed to architecture an automatic image interpreting system to assist physicians for diagnosis. We developed an artificial intelligence (AI) model based on a deep neural network with 12,222 cases of 99mTc-MDP bone scintigraphy and evaluated its diagnostic performance of bone metastasis. This AI model demonstrated considerable diagnostic performance, the areas under the curve (AUC) of receiver operating characteristic (ROC) was 0.988 for breast cancer, 0.955 for prostate cancer, 0.957 for lung cancer, and 0.971 for other cancers. Applying this AI model to a new dataset of 400 BS cases, it represented comparable performance to that of human physicians individually classifying bone metastasis. Further AI-consulted interpretation also improved human diagnostic sensitivity and accuracy. In total, this AI model performed a valuable benefit for nuclear medicine physicians in timely and accurate evaluation of cancer bone metastasis.
Copper is an element required for cell proliferation and angiogenesis. Human prostate cancer xenografts with increased 64Cu radioactivity were visualized previously by PET using 64CuCl2 as a radiotracer (64CuCl2 PET). This study aimed to determine whether the increased tumor 64Cu radioactivity was due to increased cellular uptake of 64Cu mediated by human copper transporter 1 (hCtr1) or simply due to nonspecific binding of ionic 64CuCl2 to tumor tissue. In addition, the functional role of hCtr1 in proliferation of prostate cancer cells and tumor growth was also assessed. Methods: A lentiviral vector encoding short-hairpin RNA specific for hCtr1 (Lenti-hCtr1-shRNA) was constructed for RNA interference–mediated knockdown of hCtr1 expression in prostate cancer cells. The degree of hCtr1 knockdown was determined by Western blot, and the effect of hCtr1 knockdown on copper uptake and proliferation were examined in vitro by cellular 64Cu uptake and cell proliferation assays. The effects of hCtr1 knockdown on tumor uptake of 64Cu were determined by PET quantification and tissue radioactivity assay. The effects of hCtr1 knockdown on tumor growth were assessed by PET/CT and tumor size measurement with a caliper. Results: RNA interference–mediated knockdown of hCtr1 was associated with the reduced cellular uptake of 64Cu and the suppression of prostate cancer cell proliferation in vitro. At 24 h after intravenous injection of the tracer 64CuCl2, the 64Cu uptake by the tumors with knockdown of hCtr1 (4.02 ± 0.31 percentage injected dose per gram [%ID/g] in Lenti-hCtr1-shRNA-PC-3 and 2.30 ± 0.59 %ID/g in Lenti-hCtr1-shRNA-DU-145) was significantly lower than the 64Cu uptake by the control tumors without knockdown of hCtr1 (7.21 ± 1.48 %ID/g in Lenti-SCR-shRNA-PC-3 and 5.57 ± 1.20 %ID/g in Lenti-SCR-shRNA-DU-145, P < 0.001) by PET quantification. Moreover, the volumes of prostate cancer xenograft tumors with knockdown of hCtr1 (179 ± 111 mm3 for Lenti-hCtr1-shRNA-PC-3 or 39 ± 22 mm3 for Lenti-hCtr1-shRNA-DU-145) were significantly smaller than those without knockdown of hCtr1 (536 ± 191 mm3 for Lenti- SCR-shRNA-PC-3 or 208 ± 104 mm3 for Lenti-SCR-shRNA-DU-145, P < 0.01). Conclusion: Overall, data indicated that hCtr1 is a promising theranostic target, which can be further developed for metabolic imaging of prostate cancer using 64CuCl2 PET/CT and personalized cancer therapy targeting copper metabolism.