Establishment and validation of an AI-aid method in the diagnosis of myocardial perfusion imaging.

BACKGROUND: This study aimed to develop and validate an AI (artificial intelligence)-aid method in myocardial perfusion imaging (MPI) to differentiate ischemia in coronary artery disease. METHODS: We retrospectively selected 599 patients who had received gated-MPI protocol. Images were acquired using hybrid SPECT-CT systems. A training set was used to train and develop the neural network and a validation set was used to test the predictive ability of the neural network. We used a learning technique named "YOLO" to carry out the training process. We compared the predictive accuracy of AI with that of physician interpreters (beginner, inexperienced, and experienced interpreters). RESULTS: Training performance showed that the accuracy ranged from 66.20% to 94.64%, the recall rate ranged from 76.96% to 98.76%, and the average precision ranged from 80.17% to 98.15%. In the ROC analysis of the validation set, the sensitivity range was 88.9 ~ 93.8%, the specificity range was 93.0 ~ 97.6%, and the AUC range was 94.1 ~ 96.1%. In the comparison between AI and different interpreters, AI outperformed the other interpreters (most P-value < 0.05). CONCLUSION: The AI system of our study showed excellent predictive accuracy in the diagnosis of MPI protocols, and therefore might be potentially helpful to aid radiologists in clinical practice and develop more sophisticated models.

Prediction of EGFR-TP53 genes co-mutations in patients with lung adenocarcinoma (LUAD) by 18F-FDG PET/CT radiomics.

PURPOSE: This retrospective study was undertaken to assess the predictive efficacy of 18F-FDG PET/CT -derived radiomic features concerning the co-mutation status of epidermal growth factor receptor (EGFR) and TP53 in LUAD. METHODS: A cohort of 150 LUAD patients underwent pretreatment 18F-FDG PET/CT scans with known mutation status of EGFR and TP53 were collected. The feature extraction based on their PET/CT images utilized the Pyradiomics package based on the 3D Slicer. The optimal radiomic features were selected through correlation analysis and the Gradient Boosting Decision Tree (GBDT) algorithm, followed by the construction of the radiomic model. The clinical model incorporated meaningful clinical variables, whereas the complex model integrated both the radiomic and clinical models. The area under the receiver operating characteristic curve (AUC) facilitated the comparison of prediction performance across the three models. The DCA gauged the clinical utility of these models. RESULTS: The patient cohort was randomly allocated into a training set (n = 105) and a validation set (n = 45) in a 7:3 ratio. Eleven PET and eleven CT optimal radiomic features were selected to construct the radiomic model. The model showed a good ability to discriminate the co-occurrence of EGFR and TP53, with AUC equal to 0.850 in the training set, and 0.748 in the validation set, compared with 0.750 and 0.626 for the clinical model. The complex model exhibited the highest AUC values, with 0.880 and 0.794 in both sets, but there were no significant differences compared to the radiomic model. The DCA revealed favorable clinical value.

Peri- and intra-nodular radiomic features based on 18F-FDG PET/CT to distinguish lung adenocarcinomas from pulmonary granulomas.

Objective: To compare the effectiveness of radiomic features based on 18F-FDG PET/CT images within (intranodular) and around (perinodular) lung nodules/masses in distinguishing between lung adenocarcinoma and pulmonary granulomas. Methods: For this retrospective study, 18F-FDG PET/CT images were collected for 228 patients. Patients diagnosed with lung adenocarcinoma (n = 156) or granulomas (n = 72) were randomly assigned to a training (n = 159) and validation (n = 69) groups. The volume of interest (VOI) of intranodular, perinodular (1-5 voxels, termed Lesion_margin1 to Lesion_margin5) and total area (intra- plus perinodular region, termed Lesion_total1 to Lesion_total5) on PET/CT images were delineated using PETtumor and Marge tool of segmentation editor. A total of 1,037 radiomic features were extracted separately from PET and CT images, and the optimal features were selected to develop radiomic models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). Results: Good and acceptable performance was, respectively, observed in the training (AUC = 0.868, p < 0.001) and validation (AUC = 0.715, p = 0.004) sets for the intranodular radiomic model. Among the perinodular models, the Lesion_margin2 model demonstrated the highest AUC in both sets (0.883 and 0.616, p < 0.001 and p = 0.122). Similarly, in terms of total models, Lesion_total2 model was found to outperform others in the training (AUC = 0.879, p < 0.001) and validation (AUC = 0.742, p = 0.001) sets, slightly surpassing the intranodular model. Conclusion: When intra- and perinodular radiomic features extracted from the immediate vicinity of the nodule/mass up to 2 voxels distance on 18F-FDG PET/CT imaging are combined, improved differential diagnostic performance in distinguishing between lung adenocarcinomas and granulomas is achieved compared to the intra- and perinodular radiomic features alone.

Confirmation of intestinal and bladder perforations in a peritoneal dialysis patient using SPECT/CT: a case report and review of literature.

Background: Peritoneal dialysis (PD) is a common treatment method for patients with renal failure. While peritonitis and tube floating migration are commonly observed complications, visceral perforation caused by PD is relatively rare. We present a case report of a patient undergoing PD due to renal failure, who encountered two instances of visceral perforation. In both occurrences, Single-Photon Emission Computed Tomography/Computed Tomography (SPECT/CT) played a pivotal role in providing accurate diagnoses and precise localization of the perforation sites. This report underscores the paramount significance of SPECT/CT in diagnosing visceral perforations in the context of PD. Case presentation: A 73-year-old elderly male has been undergoing PD for 1 year due to renal failure. Recently, there has been impaired drainage of the PD catheter. The clinical team suspected the occurrence of peritonitis. The patient underwent a 99mTc Sodium Pertechnetate (99mTc-NaTcO4) SPECT/CT examination, which identified intestinal perforation. After 20 days of conservative treatment, a SPECT/CT follow-up examination revealed the resolution of the intestinal perforation, but a new bladder perforation emerged. The dialysis catheter was methodically and gradually withdrawn in stages while simultaneously performing bladder decompression. Following these interventions, the patient remained free from peritonitis and cystitis. Conclusion: The utilization of SPECT/CT proved to be highly valuable in the accurate diagnosis of visceral perforation, a relatively rare complication observed in PD patients.

Disseminated cryptococcosis mimicking malignant lymphoma on 18F-FDG PET/CT: A case report.

RATIONALE: Disseminated cryptococcosis is extremely rare and is easily misdiagnosed as a malignant lymphoma. 18F-Fluorodeoxyglucose Positron Emission Tomography (PET)/ computed tomography (CT) may be useful to assess the involvement of disseminated cryptococcosis and to evaluate residual disease after treatment. PATIENT CONCERNS: A 21-years-old man presented with fever and cough for a month, with multiple red nodules scattered on the skin. 18F- Fluorodeoxyglucose PET/CT revealed multiple hypermetabolic lymph nodes in the upper and lower parts of the diaphragmatic region and hypermetabolic nodules in the skin. According to the PET/CT results, malignant lymphoma was considered a possibility, especially T-cell lymphoma involving the skin. DIAGNOSIS: Cryptococcosis was diagnosed using inguinal lymph node biopsy and blood culture. INTERVENTIONS: The patient received two months of amphotericin B, fluconazole, and half a month of meropenem. OUTCOMES: The patient's body temperature returned to normal and the red nodules on the skin disappeared. Most of the hypermetabolic enlarged lymph nodes disappeared, which was confirmed by reexamination with PET/CT. LESSONS: Disseminated cryptococcosis is easily misdiagnosed as malignant lymphoma, especially when the lymph nodes are more involved. When multiple hypermetabolic enlarged lymph nodes appear on PET/CT, except for lymphoma, specific infections should also be considered.

18F-FDG PET/CT Findings in a Patient With Primary Mucinous Cystadenocarcinoma of the Breast.

A 50-year-old woman presented with a mass in the upper outer quadrant of her left breast, which proved to be a mucinous cystadenocarcinoma by biopsy. An F-FDG PET/CT was performed for staging, which showed that the breast tumor was the only lesion with abnormal F-FDG avidity. Breast-conserving surgery was performed following a negative sentinel lymph node biopsy of the left axilla, and primary mucinous cystadenocarcinoma of the breast was finally diagnosed.

Standardized Uptake Value Using Thyroid Quantitative SPECT/CT for the Diagnosis and Evaluation of Graves' Disease: A Prospective Multicenter Study.

The clinical applications of the quantitative single photon emission computed tomography (SPECT)/computed tomography (CT) are being expanded to a variety of fields of nuclear medicine. However, clinical application of quantitative SPECT/CT for the evaluation of Graves' disease (GD) still needs further investigation. Our aim was to investigate the feasibility of standard uptake value (SUV) of the thyroid for the clinical diagnosis and evaluation of GD. In this prospective multicenter study, 116 patients diagnosed with GD (Graves group) and 74 healthy volunteers (control group) were enrolled from 8 different hospitals. All patients underwent technetium pertechnetate (99mTcO4 -) SPECT/CT imaging with Q.Metrix quantitative software and 24-hour thyroid radioactive iodine uptake (24h-RAIU) test. The SUVmax and SUVmean in Graves group were significantly higher than those of control group (P<0.01). Cut-off values of SUVmax and SUVmean to predict GD were 231.425 and 116.66 by ROC curves, respectively. The SUVmax and SUVmean in Graves patients were significantly related to serum thyroxine level with correlation coefficient of 0.493 and 0.512 for FT3 and 0.449 and 0.464 for FT4, respectively (all P<0.01). Additionally, the SUVmax and SUVmean in GD positively correlated with 24h-RAIU with a coefficient of 0.832 and 0.830, respectively (P<0.01). The volumes determined by Q.Metrix (35.65 ± 20.56ml) of 72 subjects also positively correlated with that from ultrasound (36.67 ± 21.00ml) with a coefficient of 0.927 (P<0.01). SUV measurements derived from thyroid SPECT/CT may be useful for the clinical diagnosis and evaluation of GD.

Three Primary Carcinomas on 18F-FDG PET/CT: Intrahepatic Cholangiocarcinoma, Papillary Renal Cell Carcinoma, and Clear Cell Renal Cell Carcinoma.

A CT scan was performed on a 67-year-old man newly diagnosed with acute pancreatitis. The scan revealed a low-density lesion in the liver, a left renal nodule, and a right renal cystic mass. Intense F-FDG uptake was observed in the liver lesion and left renal nodule. No abnormal uptake was observed in the right renal mass. In addition, another focal intense uptake was observed in segment VII of the liver. Biopsies revealed intrahepatic cholangiocarcinomas in the 2 liver lesions, papillary renal cell carcinoma in the left renal lesion and clear cell renal cell carcinoma in the right renal lesion.

Diagnosis of Multiple Primary Intestinal-Type Adenocarcinoma in the Lung by 18F-FDG PET/CT.

A 74-year-old man with multiple soft tissue lesions in the lung, which were suspected to be metastatic neoplasms, underwent F-FDG PET/CT scan to detect primary malignancy. The images demonstrated that the lung and 2 retroperitoneal lymph nodes were the only affected organ or tissues with suspected primary lung neoplasms. Multiple intestinal-type adenocarcinoma was eventually diagnosed by CT-guided transthoracic needle aspiration biopsy.

Enhanced Stim1 expression is associated with acquired chemo-resistance of cisplatin in osteosarcoma cells.

Osteosarcoma is the most common primary malignant bone tumor. Although cisplatin is the primary chemotherapy used in osteosarcoma treatment, the cisplatin resistance remains a big challenge for improving overall survival. The store-operated calcium (Ca2+) entry (SOCE) and its major mediator Stim1 have been shown to be implicated in a number of pathological processes typical for cancer. In this study, we showed that Stim1 expression was significantly increased in chemo-resistant osteosarcoma tissues compared with chemo-sensitivity tissues. Patients with Sitm1 expression exhibited poorer overall survival than Stim1-negative patients. Moreover, un-regulation of Stim1 expression and SOCE were also observed in cisplatin-resistant MG63/CDDP cells compared with their parental cells. Cisplatin treatment obviously reduced Stim1 expression and SOCE in cisplatin-sensitivity MG63 cells, but had no effects on MG63/CDDP cells. In addition, cisplatin resulted in a more pronounced increase of endoplasmic reticulum (ER) stress in MG63 cells than in their resistant variants, which was evidenced by the activation of molecular markers of ER stress, GRP78, CHOP and ATF4. Knockdown of Stim1 using siRNA remarkably enhanced cisplatin-induced apoptosis and ER stress in MG63/CDDP cells, thereby sensitizing cancer cells to cisplatin. On the other hand, overexpression of Stim1 markedly reversed apoptosis and ER stress following cisplatin treatment. Taken together, these results demonstrate that Stim1 as well as Ca2+ entry contributes cisplatin resistance via inhibition of ER stress-mediated apoptosis, and provide important clues to the mechanisms involved in cisplatin resistance for osteosarcoma treatment. Stim1 represents as a target of cisplatin and blockade of Stim1-mediated Ca2+ entry may be a useful strategy to improve the efficacy of cisplatin to treat osteosarcoma.