Prediction of EGFR mutation status in lung adenocarcinoma based on 18F-FDG PET/CT radiomic features.

The earlier identification of EGFR mutation status in lung adenocarcinoma patients is crucial for treatment decision-making. Radiomics, which involves high-throughput extraction of imaging features from medical images for quantitative analysis, can quantify tumor heterogeneity and assess tumor biology non-invasively. This field has gained attention from researchers in recent years. The aim of this study is to establish a model based on 18F-FDG PET/CT radiomic features to predict the epidermal growth factor receptor (EGFR) mutation status of lung adenocarcinoma and evaluate its performance. 155 patients with lung adenocarcinoma who underwent 18F-FDG PET/CT scans and EGFR gene detection before treatment were retrospectively analyzed. The LIFEx packages was used to perform 3D volume of interest (VOI) segmentation manually on DICOM images and extract 128 radiomic features. The Wilcoxon rank sum test and least absolute shrinkage and selection operator (LASSO) regression algorithm were applied to filter the radiomic features and establish models. The performance of the models was evaluated by the receiver operating characteristic (ROC) curve and the area under the curve (AUC). Among the models we have built, the radiomic model based on 18F-FDG PET/CT has the best prediction performance for EGFR gene mutation status, with an AUC of 0.90 (95% CI 0.84~0.96) in the training set and 0.79 (95% CI 0.64~0.94) in the test set. In conclusion, we have established a radiomics model based on 18F-FDG PET/CT, which has good predictive performance in identifying EGFR gene mutation status in lung adenocarcinoma patients.

Diagnosis performance of 99mTc-MIBI and multimodality imaging for hyperparathyroidism.

This study aimed to examine the diagnosis performance of 99mTc-methoxyisobutylisonitrisonitrile (99mTc-MIBI) and multimodality imaging [ultrasound, single-photon emission computed tomography/computed tomography (SPECT/CT)] for hyperparathyroidism (HPT). From Nov. 2009 to Dec. 2015, clinical data of a total of 43 HPT patients (16 males and 27 females; 26-70 years old, average age: 51.60±10.66 years old) were retrospectively analyzed. Among them, 19 patients with primary hyperparathyroidism (PHPT) underwent 99mTc-MIBI planar imaging, 24 [15 with PHPT and 9 with secondary hyperparathyroidism (SHPT)] underwent SPECT/CT hybrid imaging, and 41 (33 with PHPT and 8 with SHPT) had neck ultrasound imaging. Final diagnosis was determined by pathological examination after surgery. The positive rate was compared between different imaging modalities, and the correlation analysis was conducted between imaging results and lesion size or serum parathyroid hormone (PTH) level. The results showed that the total positive rates of 99mTc-MIBI imaging, ultrasound, and the two combined imaging in the 43 HPT cases were 90.70% (39/43), 58.54% (24/41), and 100% (41/41), respectively. According to lesion numbers, the positive rates were 79.10% (53/67), 53.23% (33/62), and 88.71% (55/62), respectively. SPECT/CT hybrid images were positive in all the 24 patients who underwent this examination. The mean maximum diameters of the lesions in 99mTc-MIBI positive and negative patients were 1.96±0.95 cm and 1.36±0.67 cm respectively, with statistically significant difference noted (P=0.03). The T/NT of 99mTc-MIBI imaging at the early phase was correlated positively with serum PTH level (r=0.40, P=0.01). The T/NT of 99mTc-MIBI imaging at both the early phase and the delay phase was correlated positively with lesion size (r=0.51, and r=0.45, respectively; P<0.01 for both). It was concluded that 99mTc-MIBI imaging presents significant value for location diagnosis of HPT, especially when combined with SPECT/CT hybrid imaging or ultrasound. The 99mTc-MIBI uptake correlates positively with serum PTH level and lesion size.

Diagnosis Performance of 99mTc-MIBI and Multimodality Imaging for Hyperparathyroidism / 华中科技大学学报（医学）（英德文版）

This study aimed to examine the diagnosis performance of 99mTc-methoxyisobutylisonitrisonitrile (99mTc-MIBI) and multimodality imaging [ultrasound,single-photon emission computed tomography/computed tomography (SPECT/CT)] for hyperparathyroidism (HPT).From Nov.2009 to Dec.2015,clinical data of a total of 43 HPT patients (16 males and 27 females;26-70 years old,average age:51.60±10.66 years old) were retrospectively analyzed.Among them,19 patients with primary hyperparathyroidism (PHPT) underwent 99mTc-MIBI planar imaging,24 [15 with PHPT and 9 with secondary hyperparathyroidism (SHPT)] underwent SPECT/CT hybrid imaging,and 41 (33 with PHPT and 8 with SHPT) had neck ultrasound imaging.Final diagnosis was determined by pathological examination after surgery.The positive rate was compared between different imaging modalities,and the correlation analysis was conducted between imaging results and lesion size or serum parathyroid hormone (PTH) level.The results showed that the total positive rates of 99mTc-MIBI imaging,ultrasound,and the two combined imaging in the 43 HPT cases were 90.70％ (39/43),58.54％ (24/41),and 100％ (41/41),respectively.According to lesion numbers,the positive rates were 79.10％ (53/67),53.23％ (33/62),and 88.71％ (55/62),respectively.SPECT/CT hybrid images were positive in all the 24 patients who underwent this examination.The mean maximum diameters of the lesions in 99mTc-MIBI positive and negative patients were 1.96±0.95 cm and 1.36±0.67 cm respectively,with statistically significant difference noted (P=0.03).The T/NT of 99mTc-MIBI imaging at the early phase was correlated positively with serum PTH level (r=0.40,P=0.01).The T/NT of 99mTc-MIBI imaging at both the early phase and the delay phase was correlated positively with lesion size (r=0.51,and r=0.45,respectively;P＜0.01 for both).It was concluded that 99mTc-MIBI imaging presents significant value for location diagnosis of HPT,especially when combined with SPECT/CT hybrid imaging or ultrasound.The 99mTc-MIBI uptake correlates positively with serum PTH level and lesion size.