Qian Zhao

Aims: To investigate the value of quantitative ^99m Tc-labelled methylene diphosphonate ( ^99m Tc-MDP) single-photon emission CT (SPECT)/CT fusion imaging in the differential diagnosis of spinal infections. Methods: A total of 90 patients with confirmed spinal infections, prior to any clinical treatment, underwent ^99m Tc-MDP SPECT/CT fusion imaging. The maximum, mean, and minimum standardized uptake values (SUVmax, SUVmean, SUVmin), bone metabolic volume (MBV), total bone uptake (TBU), and CT Hounsfield unit (HU) values were measured in both affected and normal vertebrae. Multidimensional comparisons of SPECT/CT parameters were performed, including within-subject analyses comparing affected and adjacent normal vertebrae in the same infection type, as well as inter-group comparisons across different types of spinal infections. Diagnostic performance was assessed using receiver operating characteristic (ROC) curve analysis to determine the area under the curve (AUC) and optimal cut-off values, while the linear associations between quantitative SPECT/CT parameters of affected vertebrae and laboratory biomarkers were evaluated. Results: The median SUVmax of affected vertebrae in pyogenic spondylitis (PS) was 21.17 (IQR 17.19 to 22.01), significantly higher than that observed in spinal tuberculosis (STB) (17.57 (IQR 15.02 to 18.98)) and brucellar spondylitis (BS) (15.63 (IQR 14.28 to 16.90)). SUVmax demonstrated strong diagnostic performance in differentiating PS from BS, with an AUC of 0.852, yielding 95.0% sensitivity and 71.7% specificity at an optimal cut-off value of 18.51. Similarly, CT HU values showed moderate discriminative ability for distinguishing BS from STB, achieving an AUC of 0.741, with 80.0% sensitivity and 65.0% specificity at a cut-off of 706 HU. Furthermore, a strong positive correlation was observed between SUVmax and CT HU values across all three infection groups. In addition, SUVmax exhibited a significant positive correlation with serum inflammatory markers in patients with PS. Conclusion: Quantitative ^99m Tc-MDP SPECT/CT fusion imaging enables objective assessment of spinal infection severity, thereby facilitating the differential diagnosis of distinct aetiological types of spondylitis. Cite this article: Bone Joint Res 2026;15(11):1292–1306.

A 49-year-old woman with cT3N1M0 stage IIIA HER2-positive invasive breast cancer is described in this retrospective case report. After six cycles of TCHP neoadjuvant chemotherapy, breast MRI confirmed that the primary lesion and axillary lymph nodes achieved radiological complete response. However, newly enlarged lymph nodes in levels II and III of the left neck were detected by neck ultrasound and contrast-enhanced CT. Subsequent 18F-FAPI-04 PET/CT revealed significantly elevated tracer uptake in these cervical lymph nodes, with a maximum standardized uptake value (SUVmax) of 18.2, which was highly suspicious for metastasis. Ultrasound-guided core needle biopsy and postoperative histopathological examination finally confirmed that these cervical lymph nodes were benign reactive lymphoid hyperplasia with focal necrosis and inflammatory cell infiltration, and the patient achieved pathological complete response in both breast and axillary regions without any lymph node metastasis. This case reveals that despite the high sensitivity of FAPI PET/CT in detecting malignant tumor lesions, benign post-treatment inflammatory processes can induce significant FAP upregulation, leading to typical false-positive results. Clinical interpretation of FAPI PET/CT findings must be closely integrated with the patient’s treatment history and multimodality examinations, and histopathology should remain the gold standard for definitive lesion characterization to avoid unnecessary misdiagnosis and overtreatment.

Objective: To develop and internally validate a multimodal machine-learning model integrating clinical characteristics, laboratory markers, conventional imaging findings, and quantitative SPECT/CT parameters for differentiating spinal tuberculosis (STB) from pyogenic spondylitis (PS), and to evaluate the incremental diagnostic value of quantitative SPECT/CT parameters. Methods: This retrospective study included 96 patients with STB and 69 with PS confirmed by microbiological, molecular, or histopathological examinations between September 2024 and May 2026. Demographic characteristics, laboratory markers, conventional imaging findings, and quantitative SPECT/CT parameters were collected. Two prespecified integrated quantitative SPECT/CT parameters, LBI _SUVmax and LBI _SUVmean , were used to construct a baseline model, a quantitative SPECT/CT-only model, and a fusion model. Elastic Net logistic regression was used for the primary analysis, and radial basis function support vector machine (RBF-SVM) was used for robustness analysis. Internal validation was performed using repeated stratified nested cross-validation. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), Brier score, and calibration measures. Incremental diagnostic value was assessed using 2, 000 patient-level paired bootstrap replicates. Two prespecified sensitivity analyses were also performed. Results: All seven integrated quantitative SPECT/CT parameters were significantly higher in the PS group than in the STB group (all P < 0.01). In the Elastic Net analysis, the baseline, quantitative SPECT/CT-only, and fusion models achieved AUCs of 0.788, 0.871, and 0.899, respectively. Compared with the baseline model, the fusion model increased the AUC by 0.110 (95% CI, 0.054–0.172) and reduced the Brier score by 0.048 (95% CI, 0.024–0.070). The RBF-SVM fusion model achieved an AUC of 0.957; however, its incremental AUC over the corresponding baseline model was only 0.021 (95% CI, −0.003 to 0.050). Both sensitivity analyses yielded findings consistent in direction with the primary analysis, and inclusion of all seven quantitative parameters did not further improve model performance. Conclusion: LBI _SUVmax and LBI _SUVmean improved the discrimination between STB and PS when added to conventional clinical, laboratory, and imaging information and demonstrated consistent incremental value in the Elastic Net primary analysis and prespecified sensitivity analyses. Integrated quantitative SPECT/CT parameters may therefore provide useful complementary diagnostic information; however, their clinical applicability requires confirmation through multicenter external validation and prospective studies.

Objective: To evaluate the predictive value of tabular deep learning models trained on handcrafted ¹⁸ F-FDG PET/CT PyRadiomics features and clinical data for cancer-related cognitive impairment (CRCI) among patients with diffuse large B-cell lymphoma without central nervous system involvement (non-CNS DLBCL). Material and methods: We retrospectively analyzed 112 non-CNS DLBCL patients who underwent brain ¹⁸ F-fluorodeoxyglucose ( ¹⁸ F-FDG)PET/CT. Based on Montreal Cognitive Assessment (MoCA) and Functional Assessment of Cancer Therapy-Cognitive Function (FACT-Cog) scores, patients were classified into the CRCI group (n = 73) and the non-CRCI group (n = 39) and randomly partitioned into training (n=89) and test (n=23) sets at an 8:2 ratio. Five-fold cross-validation was performed within the training set for model development, and bootstrap resampling was used to estimate 95% confidence intervals for AUC. Radiomic features were extracted with PyRadiomics from automatically segmented brain regions using MOOSE120 software. These handcrafted PET/CT radiomic features and clinical variables were organized as structured tabular datasets; raw PET/CT images were not used as direct model inputs. Feature selection was performed using correlation coefficients. The performance of seven tabular deep learning models was evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA), and different input modalities (clinical, PET, CT, and combined) were compared. Shapley additive explanations (SHAP) were applied to interpret feature contributions. Results: The AutoInt and Neural Oblivious Decision Ensembles (NODE) models showed the best predictive performance, achieving training areas under the curve (AUCs) of 0.905 and 0.904, and test AUCs of 0.858 and 0.808, respectively. DCA suggested potential clinical utility. In the modality-specific analysis, the AutoInt model integrating CT, PET, and clinical features achieved a training AUC of 0.905 and a test AUC of 0.858, representing the most favorable test-set performance among the evaluated AutoInt input modalities. A CT texture feature from the left occipital lobe emerged as the highest-ranked model contributor in SHAP analysis, with a mean absolute attribution score of approximately 0.0078. Conclusions: Tabular deep learning models based on handcrafted PET/CT PyRadiomics features showed preliminary potential for predicting CRCI in patients with non-CNS DLBCL. Among the evaluated models, AutoInt achieved the most favorable performance in the exploratory internal test set. Multimodal integration of PET, CT, and clinical tabular features may provide complementary information for CRCI prediction. SHAP analysis identified a left occipital CT texture feature as the top-ranked model contributor; however, this finding should be regarded as exploratory rather than a validated biomarker.

The primary objective of this investigation was to evaluate the predictive utility of diffusely increased 18F-FDG uptake in the spleen or bone marrow in ly

Background: Prostate cancer is one of the most prevalent malignant tumors of the male genitourinary system. The occurrence of metastasis significantly influences treatment strategies and prognosis. However, current risk assessments for metastatic disease primarily rely on single imaging or pathological indicators, which are often limited by suboptimal accuracy and considerable individual variability.Objective: This study aimed to develop a high-performance predictive model for prostate cancer metastasis by integrating semiquantitative parameters from [¹⁸F]PSMA-1007 PET/CTwith key clinicopathological features.Methods: We retrospectively analyzed data from prostate cancer patients, includingPSMA PET/CT-derived features (SUVmax, SUVmean, PSMA-TVp, TL-PSMAp) and clinical-pathological variables (age, tPSA, Gleason score). Five machine learningalgorithms—Logistic Regression, Support Vector Machine, Random Forest, Naive Bayes, and XGBoost—were evaluated for metastasis prediction performance. Model performance was assessed using accuracy, sensitivity, precision, and area under the ROC curve (AUC). Shapley additive explanations (SHAP) were applied to interpret the most effective model.Results: Among the five algorithms, the XGBoost model achieved an accuracy of 90.32%, sensitivity of 90.0%, specificity of 94.74%, and an AUC of 0.8977. SHAP analysis identified PSMA-TVp, TL-PSMAp as the most important predictors, followed by SUVmax, tPSA, and Gleason score. These findings highlight the key role of PSMA-derived tumor burden in metastasis prediction. Force plots further revealed the individual-level contributions of features, supporting the model’s clinical interpretability.Conclusion: The XGBoost-based multimodal model integrating PET/CT semiquantitative parameters with clinicopathological data demonstrated excellent accuracy and interpretability in predicting prostate cancer metastasis. This approach has strong potential for clinical application and may provide a valuable tool for personalized treatment decision-making.

Introduction: This study aimed to assess the diagnostic efficacy of the PRIMARY score, based on the ¹⁸F-labeled prostate-specific membrane antigen (PSMA-1007) positron emission tomography (PET)/computed tomography (CT) with multiparametric magnetic resonance imaging (mpMRI) PI-RADS, in detecting clinically significant prostate cancer (csPCa).Materials and Methods: In this retrospective cohort study, 137 patients with suspected prostate cancer (PCa) underwent [¹⁸F]PSMA-1007 PET/CT and mpMRI before transrectal ultrasound (TRUS)-guided needle biopsy was performed. Patients were categorized into csPCa and non-csPCa groups based on histopathological findings. The diagnostic performance of total prostate-specific antigen (TPSA), maximum standardized uptake value (SUVmax), the standardized Prostate Imaging Reporting and Data System (PI-RADS v2. 1) of mpMRI, and the PRIMARY score was evaluated using receiver operating characteristic (ROC) curves. The area under the curve (AUC), sensitivity, and specificity were calculated. Factors with a P-value 18F]PSMA-1007 PET/CT in conjunction with the PI-RADSv2.1 score, offers enhanced discrimination of csPCa.

Relapsing polychondritis (RP) is a rare immune‐mediated systemic inflammatory disease with diverse clinical manifestations. Independent involvement of the respiratory system in RP is uncommon. In the event of respiratory involvement as the initial airway‐only manifestation, the diagnosis of RP is challenging and might be delayed, and patients with respiratory involvement exhibit a poor prognosis. However, no specific diagnostic method is currently available for RP with respiratory system involvement as the main clinical manifestation. We present a 49‐year‐old female with the complaint of chronic dry cough accompanied by shortness of breath after exercise that has persisted for over a year. The patient was treated using corticosteroids. The patient's symptoms improved rapidly with the administration of 5 days of methylprednisolone sodium succinate at a dose of 40 mg/day. The treatment was then switched to methylprednisolone tablets at a dose of 40 mg/day, and the dosage was reduced by 4 mg every week until the cessation of therapy. Meanwhile, oral cyclophosphamide tablets were administered once every day at a dose of 100 mg each time. After 1 month of treatment, the symptoms of cough disappeared, the modified british medical research council (mMRC) grade dropped from 4 to 2, and the COPD assessment test (CAT) score dropped from 30 to 17. Repeated CT of the chest revealed that the tracheal wall thickening had alleviated. No recurrence was revealed in the follow‐up visit 12 months after drug withdrawal. The patient underwent ¹⁸F‐FDG PET/CT examination before hormone and immunosuppressive therapy, and ¹⁸F‐FAPI PET/CT examination was performed 5 days later. The ¹⁸F‐FDG PET/CT method revealed slight thickening of the local wall of the trachea and the left and right main bronchus, with no increase in the FDG metabolism, and no abnormalities in the rest of the cartilage. ¹⁸F‐FAPI PET‐CT imaging showed increased FAPI uptake in various parts of the body, including trachea and bronchus. The present study reports that compared to ¹⁸F‐FDG PET/CT, the ¹⁸F‐FAPI PET/CT revealed more lesions and provided a better image contrast, suggesting the latter as a suitable diagnostic method for RP, which could assist in improving the clinical management of RP patients.

Affiliations of all authors as they appear in the published original version of the article1 Department of Nuclear Medicine, General Hospital of Ningxia Medical University, Yinchuan, Ningxia Hui Autonomous Region, China2 School of Clinical Medicine, Ningxia Medical University, Yinchuan, Ningxia Hui Autonomous Region, China3 Department of Nuclear Medicine, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong Province, China* Correspondence: cecilia_hh@126.comKeywords: cancer-associated fibroblasts1, FAPI2, molecular probe3, 131I4, identification5Corrigendum on: Department of Nuclear Medicine, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong Province, ChinaIncorrect AffiliationIn the published article, there was an error in affiliation [3]. Instead of “[Department of Nuclear Medicine, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong Province, China]”, it should be “[Department of Nuclear Medicine, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong Province, China]”. The authors apologize for this error and state that this does not change the scientific conclusions of the article in any way. The original article has been updated