RESUMO
BACKGROUND: To investigate whether radiomic features from (18F)-fluorodeoxyglucose positron emission tomography/computed tomography [(18F)-FDG PET/CT] can predict epidermal growth factor receptor (EGFR) mutation status and prognosis in patients with lung adenocarcinoma. METHODS: One hundred and seventy-four consecutive patients with lung adenocarcinoma underwent (18F)-FDG PET/CT and EGFR gene testing were retrospectively analyzed. Radiomic features combined with clinicopathological factors to construct a random forest (RF) model to identify EGFR mutation status. The mutant/wild-type model was trained on a training group (n=139) and validated in an independent validation group (n=35). The second RF classifier predicting the 19/21 mutation site was also built and evaluated in an EGFR mutation subset (training group, n=80; validation group, n=25). Radiomic score and 5 clinicopathological factors were integrated into a multivariate Cox proportional hazard (CPH) model for predicting overall survival (OS). AUC (the area under the receiver characteristic curve) and C-index were calculated to evaluate the model's performance. RESULTS: Of 174 patients, 109 (62.6%) harbored EGFR mutations, 21L858R was the most common mutation type [55.9% (61/109)]. The mutant/wild-type model was identified in the training (AUC, 0.77) and validation (AUC, 0.71) groups. The 19/21 mutation site model had an AUC of 0.82 and 0.73 in the training and validation groups, respectively. The C-index of the CPH model was 0.757. The survival time between targeted therapy and chemotherapy for patients with EGFR mutations was significantly different (P=0.03). CONCLUSIONS: Radiomic features based on (18F)-FDG PET/CT combined with clinicopathological factors could reflect genetic differences and predict EGFR mutation type and prognosis.
RESUMO
BACKGROUND: Dual-energy CT (DECT) has been used to detect myocardial infarct. However, few comparable studies with histopathological findings as gold standard have been published. PURPOSE: To investigate the accuracy of DECT iodine maps for detecting acute myocardial infarction compared with single photon emission computed tomography (SPECT) in a canine model using histopathological findings as the reference standard. MATERIAL AND METHODS: A model of myocardial ischemia was created by ligating the left anterior descending (LAD) coronary artery after thoracotomy in six dogs, while another three dogs undergoing thoracotomy without LAD ligature served as a control group. Contrast-enhanced DECT scans of the heart were performed, followed by resting 99mTc-MIBI SPECT myocardial perfusion imaging in all nine dogs before and 3 h after the procedure. Triphenyltetrazolium chloride (TTC) staining was performed and analyzed. In the short axis of the left ventricle, the wall surface was divided into 17 segments, which were assessed for infarcted myocardium on conventional CT from average-weighted data, DECT myocardial iodine maps, conventional CT plus DECT, SPECT, and histopathology. Inter-observer and inter-modality agreement for conventional CT, DECT myocardial iodine maps, and SPECT were calculated. CT value of infracted and non-infracted areas was measured. RESULTS: With the histopathological results as the reference standard, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were 75.0% (30/40), 92.0% (104/113), 76.9% (30/39), 91.2% (104/114), 87.6% (134/153) for conventional CT, 85.0% (34/40), 84.1% (95/113), 65.4% (34/52), 94.1% (95/101), 84.3% (129/153) for DECT myocardial iodine maps; 87.5% (35/40), 92.9% (105/113), 81.4% (35/43), 95.5% (105/110), 91.5% (140/153) for conventional CT plus DECT; 82.5% (33/40), 90.3% (102/113), 75.0% (33/44), and 93.6% (102/109), 88.2% (135/153) for SPECT, respectively. Excellent inter-observer agreement (Kappa value >0.8) and good inter-modality agreement (Kappa value >0.6) for each modality were found. CT values of infarcted myocardium (26 ± 22 HU, 36 ± 33 HU, 34 ± 16 HU) were lower than those of non-infarcted myocardium (115 ± 16 HU, 121 ± 28 HU, 123 ± 11 HU) on images of 140 kVp, 80 kVp, and average-weighted 120 kVp images (all P < 0.05). CONCLUSION: With histopathology as the reference standard, DECT myocardial iodine maps can detect acute myocardial infarction with diagnostic accuracy comparable to resting SPECT myocardial perfusion imaging in a canine model. DECT plus conventional CT had a potential to improve the detection of acute myocardial infarction.
