Search

Pheochromocytomas and paragangliomas (PPGLs) are rare tumors arising from the neural crest cells that form the sympathetic and parasympathetic nervous systems. Radiotherapy with [We retrospectively analyzed the cases of 25 patients with unresectable PPGLs treated with [The median follow-up time was 42 months (range 2-136 months). The median overall survival was 63 months. The overall survival (OS) was significantly shorter in the high-MTV group (log-rank test, p = 0.049) and the high-TLG group (p = 0.049), with no significant difference between the high- and low-SUVmax groups (p = 0.19). Likewise, there was no significant difference in prognosis according to pheochromocytoma or paraganglioma, metastasis location, age, or prior chemotherapy. A history of external radiation before [High MTV and high TLG were significantly associated with a poor prognosis after [

A 49-year-old Japanese man had a chief complaint of left hypochondrium pain, and a CT scan revealed a mass in the left retroperitoneal space. CT and MRI scans revealed a hemorrhagic component and surrounding fibrous tissues. FDG PET/CT images showed increased uptake in the peripheral rim of the mass, indicating a malignant tumor. The SUV max was 7.6. We surgically resected the mass. The pathological examination confirmed the diagnosis of chronic expanding hematoma. It is difficult to differentiate CEH from malignant tumors on imaging; this should be recognized as a diagnostic pitfall.

Radioactive iodine (RAI) therapy is a useful treatment for Graves' disease (GD). Most RAI sessions administer ≤ 500 MBq of iodine (I)-131. Sometimes patients require repeated RAI, often for longer periods of remission. We investigated the characteristics of patients for whom high dose (mostly 1110 MBq of I-131) RAI was effective as RAI therapy for GD.We retrospectively analyzed the cases of 79 patients who underwent RAI for GD in a multicenter setting. We divided the patients into two groups based on the I-131 dose administered: the low dose (LD) group who received ≤ 500 MBq (n = 44) and the high dose (HD) group who received 500 MBq (n = 35). The therapeutic effect was defined as achieving remission and reaching the point of participating in thyroid hormone replacement therapy within 1 year after RAI. We compared the LD and HD groups' remission rates and conducted a multivariate logistic regression analysis of predictive factors for remission. In a simulation, using the formula for predicting the probability of remission obtained from the analysis results, we estimated how much the remission rate would change if the I-131 dose is increased from 500 to 1110 MBq.The mean ± standard deviation I-131 dose administered in the LD group was 480 ± 6 MBq, and that of the HD group was 1054 ± 265 MBq. Thirty-five patients (80%) in the LD group and 26 patients (74%) in the HD group achieved remission; this difference in the remission rate was not significant. The multivariate analysis results demonstrated that the absorbed dose and thyroid-stimulating antibody (TSAb) were independent predictors of remission. Seven patients (8.9%) showed an increased probability of remission from 50% to 50% when the higher RAI dose was applied (1110 MBq instead of 500 MBq). The thyroid volume and TSAb values in these patients were relatively large at 54.7 ± 34.2 mL and 1378.4 ± 586.3%, respectively.Although the overall remission rate was not significantly different between the patients who received high- or low-dose I-131, treatment with high-dose RAI may improve the probability of remission in patients with a massive thyroid volume and/or high-TSAb Graves' disease.

Background To improve the diagnostic accuracy of axillary lymph node (LN) metastasis in breast cancer patients using 2-[18F]FDG-PET/CT, we constructed an artificial intelligence (AI)-assisted diagnosis system that uses deep-learning technologies. Materials and methods Two clinicians and the new AI system retrospectively analyzed and diagnosed 414 axillae of 407 patients with biopsy-proven breast cancer who had undergone 2-[18F]FDG-PET/CT before a mastectomy or breast-conserving surgery with a sentinel lymph node (LN) biopsy and/or axillary LN dissection. We designed and trained a deep 3D convolutional neural network (CNN) as the AI model. The diagnoses from the clinicians were blended with the diagnoses from the AI model to improve the diagnostic accuracy. Results Although the AI model did not outperform the clinicians, the diagnostic accuracies of the clinicians were considerably improved by collaborating with the AI model: the two clinicians' sensitivities of 59.8% and 57.4% increased to 68.6% and 64.2%, respectively, whereas the clinicians' specificities of 99.0% and 99.5% remained unchanged. Conclusions It is expected that AI using deep-learning technologies will be useful in diagnosing axillary LN metastasis using 2-[18F]FDG-PET/CT. Even if the diagnostic performance of AI is not better than that of clinicians, taking AI diagnoses into consideration may positively impact the overall diagnostic accuracy.

Additional file 1

Background: To improve the diagnostic accuracy of axillary lymph node (LN) metastasis in breast cancer patients using FDG-PET/CT, we constructed an artificial intelligence (AI)-assisted diagnosis system that uses deep-learning technologies.Materials and Methods: Two clinicians and the new AI system retrospectively analyzed and diagnosed 414 axillae of 407 patients with biopsy-proven breast cancer who had undergone FDG-PET/CT before a mastectomy or breast-conserving surgery with a sentinel lymph node (LN) biopsy and/or axillary LN dissection. We designed and trained a deep 3D convolutional neural network (CNN) as the AI model. The diagnoses from the clinicians were blended with the diagnoses from the AI model to improve the diagnostic accuracy.Results: Although the AI model did not outperform the clinicians, the diagnostic accuracies of the clinicians were considerably improved by collaborating with the AI model: the two clinicians' sensitivities of 59.8% and 57.4% increased to 68.6% and 64.2%, respectively, whereas the clinicians' specificities of 99.0% and 99.5% remained unchanged.Conclusions: It is expected that AI using deep-learning technologies will be useful in diagnosing axillary LN metastasis using FDG-PET/CT. Even if the diagnostic performance of AI is not better than that of clinicians, taking AI diagnoses into consideration may positively impact the overall diagnostic accuracy.