Positron Emission Tomography-computed Tomography Imaging Research Articles

Identification of Mild cognitive impairment based on quadruple GCN model constructed with multiple features from higher-order brain connectivity

Mild cognitive impairment (MCI) is the early stage of Alzheimer's disease, which is associated with abnormal brain proteins, the recognition of MCI being a challenging task. Recent studies have shown that the performance of MCI identification can be improved by combining protein features captured in Positron Emission Computed Tomography(PET). Nevertheless, there are still great challenges in extracting effective features from the vast amount of information. Most brain networks only considered the unilateral features of nodes or edges, ignored the interactions between them. In response to this problem, our study proposed to combine the quadruple Siamese network and GCN with self-attention pooling(QS-SAGCN) for MCI identification. In detail, we constructed the multiple protein features network(MPN) and higher-order MPN(MPHN) by PET images to promote the MCI identification. Furthermore, a pooling operation with self-attention mechanism was incorporated into GCN(SAGCN), which considered the node characteristics and topology in the graph network to facilitate the acquisition of robust biomarkers, simultaneously. Additionally we combined quadruple Siamese network with SAGCN as classification framework to improve the identification accuracy. Our proposed MCI identification method was evaluated on 230 subjects (including 117 MCI subjects, 113 normal control subjects) with both 18F-AV-1451 PET and 18F-AV-45 PET data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Experimental results showed that 1) QS-SAGCN enhanced the ability of feature identification, laying the foundation for obtaining more effective biomarkers for MCI patients; 2) The MCI identification accuracy (93.5%) was obtained by combining QS-SAGCN and higher-order network, indicating that the framework had advantages in mental disorders recognition. Finally, through comparison, the accuracy of our proposed MCI recognition method was superior to some of the existing state-of-the-art methods. Overall, the MCI identification method in this study was effective and promising to assist in the diagnosis of MCI in future clinical practice.

Evaluating the efficacy of breast cancer treatments using PET-CT Imaging

Positron emission tomography-computed tomography (PET-CT) scans are used to detect and stage cancer and can be used to evaluate the effectiveness of treatments used for patients with different types of cancer. The current study aims to evaluate the effectiveness of treatments provided to breast cancer patients and the effect of treatment on the right and left breasts separately. A sample of (84) female left and right breast cancer patients were treated with radiation therapy and/or chemotherapy. The efficacy of the treatments was evaluated on 18 follow-up patients among the original sample who already underwent a PET-CT scan before starting their treatment. Treatment efficacy was evaluated by measuring the standard uptake value (SUV) of cancer lesions in patients before and after treatment. Results showed that 32.1% of the diagnosed lesions did not change their SUV values, 39.3% were treated, 27.4% were new lesions do not present in the original PET-CT scan, and 1.2% for lesions that increased the value of the SUV. Moreover, the results also showed that left breast cancer was more responsive to treatment than right breast cancer, while chemotherapy was more effective than radiation therapy. In summary, the efficacy of chemotherapy and/or radiotherapy for both right and left breast cancer patients was evaluated using PET-CT technology. Only one-third of the cancerous lesions were treated using the treatment methods described in this study. The research is unique in that it is the first in Palestine to investigate the feasibility and efficacy of the treatment delivered to breast cancer patients.

The role of single positron emission computed tomography imaging in the diagnosis of brain death whenever Trans-cranial Doppler fails to support it: A retrospective cohort study.

Although there is widespread acceptance of the concept of brain death/death by neurologic criteria (BD/DNC), there is marked variability in the use of ancillary tests worldwide. Transcranial Doppler (TCD) is a useful ancillary test for brain death confirmation because it is safe, noninvasive, and done at the bedside. However, it is considered less sensitive than Single Photon Emission Computed Tomography (SPECT) Tc-HMPAO (99m). This study aims to test the yield of brain perfusion SPECT testing after a TCD has demonstrated some level of intracranial blood flow among patients fulfilling clinical criteria for BD/DNC. This was a single-center retrospective cohort study of all the patients fulfilling clinical criteria for BD/DNC who underwent brain perfusion SPECT after an intracerebral circulatory arrest was not confirmed by TCD between July 2016 and January 2022. TCD was an initial ancillary test performed in 252 patients (99.6%) fulfilling clinical criteria for BD/DNC. A complete circulatory arrest was demonstrated in 228 (90.5%) patients. Brain perfusion SPECT was performed in the remaining 24 patients. The absence of cerebral perfusion consistent with BD/DNC was found in 21 cases (87.5%). BD/DN could not be confirmed in three patients (12.5%). SPECT testing has a high diagnostic yield when TCD fails to confirm a suspected diagnosis of BD/DNC. Combining these two modalities may be an optimal strategy for BD/DNC diagnosis when this is required by local regulations or when confounding factors interfere with the performance of a complete clinical assessment.

Isolated Axillary Lymph Node Recurrence from Serous Ovarian Carcinoma: A Case Report

Ovarian cancer is the most mortal gynecological malignancy among women worldwide. The appropriate treatment protocol is cytoreductive surgery and the main aim is to remove all primary carcinoma focus and all metastatic lesions. A 37 years old woman (gravida 5, para 3) presented with complaints of abdominal distension. During the gynecological examination, bilateral adnexal masses in the solid structure were observed. Staging surgery was performed and 8 cycles of adjuvant chemotherapy regimen were given. A pathological axillary lymph node was detected in the positron emission tomography-computed tomography (PET/CT) imaging at the follow-up 6 months after the end of the chemotherapy regimen. The biopsy result from the axillary lymph node was reported as serous carcinoma metastasis. Metastasis of ovarian carcinoma to the axillary lymph node is uncommon and has a poor prognosis. High-grade ovarian serous carcinoma with axillary lymph node metastasis was presented in this case report.

Positron Emission Tomography-Computed Tomography and Magnetic Resonance Imaging Assessments in a Mouse Model of Implant-Related Bone and Joint Staphylococcus aureus Infection.

Osteomyelitis is an infection of the bone, associated with an inflammatory process. Imaging plays an important role in establishing the diagnosis and the most appropriate patient management. However, data are lacking regarding the use of preclinical molecular imaging techniques to assess osteomyelitis progression in experimental models. This study aimed to compare structural and molecular imaging to assess disease progression in a mouse model of implant-related bone and joint infections caused by Staphylococcus aureus. In SWISS mice, the right femur was implanted with a resorbable filament impregnated with S. aureus (infected group, n = 10) or sterile culture medium (uninfected group, n = 6). Eight animals (5 infected, 3 uninfected) were analyzed with magnetic resonance imaging (MRI) at 1, 2, and 3 weeks postintervention, and 8 mice were analyzed with [18F]fluorodeoxyglucose (FDG)-positron emission tomography (PET)-computed tomography (CT) at 48 h and at 1, 2, and 3 weeks postintervention. In infected animals, CT showed bone lesion progression, mainly in the distal epiphysis, although some uninfected animals presented evident bone sequestra at 3 weeks. MRI showed a lesion in the articular area that persisted for 3 weeks in infected animals. This lesion was smaller and less evident in the uninfected group. At 48 h postintervention, FDG-PET showed higher joint uptake in the infected group than in the uninfected group (P = 0.025). Over time, the difference between groups increased. These results indicate that FDG-PET imaging was much more sensitive than MRI and CT for differentiating between infection and inflammation at early stages. FDG-PET clearly distinguished between infection and postsurgical bone healing (in uninfected animals) from 48 h to 3 weeks after implantation. IMPORTANCE Our results encourage future investigations on the utility of the model for testing different therapeutic procedures for osteomyelitis.

Diagnostic value of dynamic 18F-FDG PET/CT imaging in non-small cell lung cancer and FDG hypermetabolic lymph nodes.

We aimed to investigate the diagnostic value of dynamic 2-deoxy-2-[18F]-fluoro-D-glucose positron emission tomography-computed tomography in non-small cell lung cancer and fluoro-D-glucose hypermetabolic lymph nodes. Patients who made an active appointment for positron emission tomography-computed tomography were randomly enrolled by referring to previous imaging data and clinical information. Finally, 34 histopathologically confirmed non-small cell lung cancers (18 adenocarcinoma and 16 squamous cell carcinoma cases) were prospectively studied using dynamic and static 2-deoxy-2-[18F]-fluoro-D-glucose positron emission tomography-computed tomography imaging (the diagnostic study has not yet been registered on a clinical trial platform). In dynamic positron emission tomography images, a volume of interest, defined by the thoracic aorta, was selected for estimating the arterial input function. Patlak and irreversible two-tissue compartment model analyses were performed based on the pixel points to obtain first-order characteristic kinetic parameters for each lesion and hypermetabolic lymph node. The first-order characteristic kinetic parameters were obtained based on the basic data of dynamic positron emission tomography images in the corresponding model and the lesion delineation of region-of-interest based on computed tomography images, such as V_Median (the median gray intensity of V), k3_Entropy, VB_Entropy, K1_Uniformity, and ki_Uniformity. The first-order characteristic kinetic parameters were also modeled by logistic regression for the differential diagnosis of non-small cell lung cancer and hypermetabolic lymph nodes. Maximum and mean standard uptake values (SUVmax and SUVmean, respectively) were obtained from static positron emission tomography images. The diagnostic efficacy of the parameters was evaluated using the receiver operating characteristic curve and the DeLong test. There was a significant difference in the V_Median values of adenocarcinoma and squamous cell carcinoma. The regression models for K1, k3, and V provided good predictions of adenocarcinoma and squamous cell carcinoma typology. Significant differences were observed in k3_Entropy, VB_Entropy, K1_Uniformity, and ki_Uniformity between benign and malignant lymph nodes. The regression model of Ki, VB, and k3 could make a good prediction for identifying benign and malignant lymph nodes. Dynamic 2-deoxy-2-[18F]-fluoro-D-glucose positron emission tomography-computed tomography imaging showed high diagnostic value in the staging of non-small cell lung cancer and fluoro-D-glucose hypermetabolic lymph nodes, and can be of great use in non-small cell lung cancer lymph node staging and surgical decision-making.

MSRA-Net: Tumor segmentation network based on Multi-scale Residual Attention

Automatic Medical segmentation of medical images is an important part in the field of computer medical diagnosis, among which tumor segmentation is an important branch of medical image segmentation. Accurate automatic segmentation method is very important in medical diagnosis and treatment. Positron emission computed tomography (PET) and X-ray computed tomography (CT) images are widely used in medical image segmentation to help doctors accurately locate information such as tumor location and shape, providing metabolic and anatomical information, respectively. At present, PET/CT images have not been effectively combined in the research of medical image segmentation, and the complementary semantic information between the superficial and deep layers of neural network has not been ensured. To solve the above problems, this paper proposed a Multi-scale Residual Attention network (MSRA-Net) for tumor segmentation of PET/CT. We first use an attention-fusion based approach to automatically learn the tumor-related areas of PET images and weaken the irrelevant area. Then, the segmentation results of PET branch are processed to optimize the segmentation results of CT branch by using attention mechanism. The proposed neural network (MSRA-Net) can effectively fuse PET image and CT image, which can improve the precision of tumor segmentation by using complementary information of the multi-modal image, and reduce the uncertainty of single modal image segmentation. Proposed model uses multi-scale attention mechanism and residual module, which fuse multi-scale features to form complementary features of different scales. We compare with state-of-the-art medical image segmentation methods. The experiment showed that the Dice coefficient of the proposed network in soft tissue sarcoma and lymphoma datasets increased by 8.5% and 6.1% respectively compared with UNet, showing a significant improvement.

Imaging Recommendations for Theranostic PET-CT in Oncology

AbstractWe in this article have presented a review of the guideline recommendations on theranostic positron emission tomography-computed tomography (PET-CT) imaging which will be helpful to assist practitioners in providing appropriate patient care. Multiple guidelines by different societies and medical associations provide standards for diagnosis, imaging, and treatment of cancer patients. They have generated a number of recommendations related to 68Ga-DOTATATE and 68Ga-PSMA-11 PET-CT, which are the classical examples of theranostic PET-CT imaging in current practice.

Isolated meningeal myeloid sarcoma with recurrent MLL-AF6 translocation: a case report

This study aimed to help improve the diagnosis and treatment of isolated myeloid sarcoma. We report the case of a female adolescent patient with isolated meningeal myeloid sarcoma. She was admitted to our department because of vomiting, headache and hearing loss. Positron emission tomography-computed tomography and brain magnetic resonance imaging showed multiple intracranial space-occupying lesions. A complete examination, including morphology, cytology, immunophenotyping, cytogenetics and molecular biology tests of cerebrospinal fluid and bone marrow, was conducted. The diagnosis of primary myeloid sarcoma of the central nervous system with mixed lineage leukemia gene rearrangement with AF6 was established. The patient underwent systemic chemotherapy and intrathecal treatment followed by whole-brain radiotherapy. She achieved complete remission for 84 months and has not developed bone marrow involvement during follow-up. The combination of morphology, cytology, flow cytometry, cytogenetics and molecular analysis can improve the definite diagnosis of isolated myeloid sarcoma.

Computational Analysis of Tumor Treating Fields for Non-Small Cell Lung Cancer in Full Thoracic Models

Tumor Treating Fields (TTFields) are alternating electric fields at 150 to 200 kHz that exert their anticancer effect by destroying tumor cells when they undergo mitosis. TTFields are currently being tested in patients with non-small cell lung cancer with advanced disease (NCT02973789) and those with brain metastasis (NCT02831959). However, the distribution of these fields within the thoracic compartment remains poorly understood. Using positron emission tomography-computed tomography image data sets obtained from a series of 4 patients with poorly differentiated adenocarcinoma, the positron emission tomography-positive gross tumor volume (GTV), clinical target volume (CTV), and structures from the chest surface to the intrathoracic compartment were manually segmented, followed by 3-dimensional physics simulation and computational modeling using finite element analysis. Electric field-volume histograms, specific absorption rate-volume histograms, and current density-volume histograms were generated to produce plan quality metrics (95%, 50%, and 5% volumes) for quantitative comparisons between models. Unlike other organs in the body, the lungs have a large volume of air, which has a very low electric conductivity value. Our comprehensive and individualized models demonstrated heterogeneity in electric field penetration to the GTVs with differences upwards of 200% and yielded a diverse range of TTFields distributions. Target contact with the conductive pleura intensified TTFields at the GTV and CTV. Furthermore, in a sensitivity analysis, varying electric conductivity and mass density of the CTV altered TTFields coverage to both the CTV and GTV. Personalized modeling is important to accurately estimate target coverage at the tumor volumes and surrounding normal tissue structures in the thorax.

An Automated Method for Artifical Intelligence Assisted Diagnosis of Active Aortitis Using Radiomic Analysis of FDG PET-CT Images.

The aim of this study was to develop and validate an automated pipeline that could assist the diagnosis of active aortitis using radiomic imaging biomarkers derived from [18F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET-CT) images. The aorta was automatically segmented by convolutional neural network (CNN) on FDG PET-CT of aortitis and control patients. The FDG PET-CT dataset was split into training (43 aortitis:21 control), test (12 aortitis:5 control) and validation (24 aortitis:14 control) cohorts. Radiomic features (RF), including SUV metrics, were extracted from the segmented data and harmonized. Three radiomic fingerprints were constructed: A-RFs with high diagnostic utility removing highly correlated RFs; B used principal component analysis (PCA); C-Random Forest intrinsic feature selection. The diagnostic utility was evaluated with accuracy and area under the receiver operating characteristic curve (AUC). Several RFs and Fingerprints had high AUC values (AUC > 0.8), confirmed by balanced accuracy, across training, test and external validation datasets. Good diagnostic performance achieved across several multi-centre datasets suggests that a radiomic pipeline can be generalizable. These findings could be used to build an automated clinical decision tool to facilitate objective and standardized assessment regardless of observer experience.

The impact of variance in carnitine palmitoyltransferase-1 expression on breast cancer prognosis is stratified by clinical and anthropometric factors.

CPT1A is a rate-limiting enzyme in fatty acid oxidation and is upregulated in high-risk breast cancer. Obesity and menopausal status' relationship with breast cancer prognosis is well established, but its connection with fatty acid metabolism is not. We utilized RNA sequencing data in the Xena Functional Genomics Explorer, to explore CPT1A's effect on breast cancer patients' survival probability. Using [18F]-fluorothymidine positron emission tomography-computed tomography images from The Cancer Imaging Archive, we segmented these analyses by obesity and menopausal status. In 1214 patients, higher CPT1A expression is associated with lower breast cancer survivability. We confirmed a previously observed protective relationship between obesity and breast cancer in pre-menopausal patients and supported this data using two-sided Pearson correlations. Taken together, these analyses using open-access databases bolster the potential role of CPT1A-dependent fatty acid metabolism as a pathogenic factor in breast cancer.

Colonoscopy following the positron emission tomography/computed tomography scan in patients with incidental colorectal uptake: what is the most effective management?

Colorectal cancer is one of the most common malignancies. Survival rates are directly related to the stage of cancer at the time of diagnosis, emphasizing the value of early diagnosis. Positron emission tomography with 18F-fluorodeoxyglucose is the gold standard imaging technique in staging, monitoring after treatment, and follow-up. We aimed to assess the importance of incidental 18F-fluorodeoxyglucose uptake by colon and rectum in positron emission tomography-computed tomography imaging to determine a significant cutoff value for further investigation using colonoscopy and histopathological assessment. We performed a retrospective analysis of patients with both 18F-fluorodeoxyglucose-positron emission tomography/computed tomography scan and colonoscopy during 1 year and included the cases who had undergone a colonoscopy within 3 months following the positron emission tomography/computed tomography scan due to an incidental positive finding. Patients with a diagnosed colorectal malignancy or with a history of previous colorectal operations were excluded. A total of 81 patients were included in this study. Among 81 colonoscopic evaluations, histopathology revealed malignancy in 8 patients, and the prevalence of incidental colorectal cancer 18F-fluorodeoxyglucose uptake was found to be 9.87%. SUVmax was found to be significantly related to malignancy and other colonoscopic findings (p<0.001). SUVmax cutoff value to suggest colorectal cancer was found to be median [7.9 (4.1-12.7)] (p<0.001). Regarding the studies determining a significant cutoff value, incidental colonic 18F-fluorodeoxyglucose uptake on positron emission tomography/computed tomography should lead the clinician to further investigation with colonoscopic biopsy, although the cutoff values for SUVmax are not certain and different in almost every published study, and negative positron emission tomography.computed tomography findings should not completely rule out malignancy, especially in high-risk patients.

Positron Emission Tomography-Computed Tomography Imaging of Selective Lobar Delivery of Stem Cells in Ex Vivo Lung Model of Mechanical Ventilation.

Introduction: The delivery of cell therapies may be an important frontier to treat different respiratory diseases in the near future. However, the cell size, delivery conditions, cell viability, and effect in the pulmonary function are critical factors. We performed a proof-of-concept experiment using ex vivo lungs and novel subglottic airway device that allows for selective lobar isolation and administration of drugs and biologics in liquid solution deep into the lung tissues, while simultaneously ventilating the rest of the lung lobes. Methods: We used radiolabeled cells and positron emission tomography-computed tomography (PET-CT) imaging to demonstrate the feasibility of high-yield cell delivery to a specifically targeted lobe. This study proposes an alternative delivery method of live cells labeled with radioactive isotope into the lung parenchyma and tracks the cell delivery using PET-CT imaging. The technique combines selective lobar isolation and lobar infusion to carry large particles distal to the trachea, subtending bronchial segments and reaching alveoli in targeted regions. Results: The solution with cells and carrier achieved a complete and homogeneous lobar distribution. An increase in tissue density was shown on the computed tomography (CT) scan, and the PET-CT imaging demonstrated retention of the activity at central, peripheral lung parenchyma, and pleural surface. The increase in CT density and metabolic activity of the isotope was restricted to the desired lobe only without leak to other lobes. Conclusion: The selective lobe delivery is targeted and imaging-guided by bronchoscopy and CT to a specific diseased lobe during mechanical ventilation. The feasibility of high-yield cell delivery demonstrated in this study will lead to the development of potential novel therapies that contribute to lung health.

Hotspot on 18F-FET PET/CT to Predict Aggressive Tumor Areas for Radiotherapy Dose Escalation Guiding in High-Grade Glioma.

The standard therapy strategy for high-grade glioma (HGG) is based on the maximal surgery followed by radio-chemotherapy (RT-CT) with insufficient control of the disease. Recurrences are mainly localized in the radiation field, suggesting an interest in radiotherapy dose escalation to better control the disease locally. We aimed to identify a similarity between the areas of high uptake on O-(2-[18F]-fluoroethyl)-L-tyrosine (FET) positron emission tomography/computed tomography (PET) before RT-CT, the residual tumor on post-therapy NADIR magnetic resonance imaging (MRI) and the area of recurrence on MRI. This is an ancillary study from the IMAGG prospective trial assessing the interest of FET PET imaging in RT target volume definition of HGG. We included patients with diagnoses of HGG obtained by biopsy or tumor resection. These patients underwent FET PET and brain MRIs, both after diagnosis and before RT-CT. The follow-up consisted of sequential brain MRIs performed every 3 months until recurrence. Tumor delineation on the initial MRI 1 (GTV 1), post-RT-CT NADIR MRI 2 (GTV 2), and progression MRI 3 (GTV 3) were performed semi-automatically and manually adjusted by a neuroradiologist specialist in neuro-oncology. GTV 2 and GTV 3 were then co-registered on FET PET data. Tumor volumes on FET PET (MTV) were delineated using a tumor to background ratio (TBR) ≥ 1.6 and different % SUVmax PET thresholds. Spatial similarity between different volumes was performed using the dice (DICE), Jaccard (JSC), and overlap fraction (OV) indices and compared together in the biopsy or partial surgery group (G1) and the total or subtotal surgery group (G2). Another overlap index (OV') was calculated to determine the threshold with the highest probability of being included in the residual volume after RT-CT on MRI 2 and in MRI 3 (called "hotspot"). A total of 23 patients were included, of whom 22% (n = 5) did not have a NADIR MRI 2 due to a disease progression diagnosed on the first post-RT-CT MRI evaluation. Among the 18 patients who underwent a NADIR MRI 2, the average residual tumor was approximately 71.6% of the GTV 1. A total of 22% of patients (5/23) showed an increase in GTV 2 without diagnosis of true progression by the multidisciplinary team (MDT). Spatial similarity between MTV and GTV 2 and between MTV and GTV 3 were higher using a TBR ≥ 1.6 threshold. These indices were significantly better in the G1 group than the G2 group. In the FET hotspot analysis, the best similarity (good agreement) with GTV 2 was found in the G1 group using a 90% SUVmax delineation method and showed a trend of statistical difference with those (poor agreement) in the G2 group (OV' = 0.67 vs. 0.38, respectively, p = 0.068); whereas the best similarity (good agreement) with GTV 3 was found in the G1 group using a 80% SUVmax delineation method and was significantly higher than those (poor agreement) in the G2 group (OV'= 0.72 vs. 0.35, respectively, p = 0.014). These results showed modest spatial similarity indices between MTV, GTV 2, and GTV 3 of HGG. Nevertheless, the results were significantly improved in patients who underwent only biopsy or partial surgery. TBR ≥ 1.6 and 80-90% SUVmax FET delineation methods showing a good agreement in the hotspot concept for targeting standard dose and radiation boost. These findings need to be tested in a larger randomized prospective study.

Clinical predictors and implications of cardiac inflammation detected on positron emission tomography (PET) in patients referred for premature ventricular complex (PVC) ablation.

Positron emission tomography computed tomography (PET-CT) is not routinely used for premature ventricular complexes (PVCs). Whether specific clinical factors are associated with abnormal PET-CT results is not clear. The treatment courses and baseline characteristics of consecutive patients in a single center between 2012 and 2021, age > 18years old, and who received 18F-fluorodeoxyglucose (FDG) PET-CT imaging for evaluation of PVCs were retrospectively analyzed. A total of 102 patients was included. Of these, 27 patients (26.4%) had abnormal PET-CT and 61 (59.8%) had normal imaging. Abnormal PET-CT findings were associated with non-sustained ventricular tachycardia (NSVT) (95.2% vs. 52.6%, p = 0.001), higher number of PVC morphologies (2.29 ± 0.7 vs. 1.31 ± 0.6, p < 0.001), greater PVC coupling interval dispersion (72.47 ± 66.4ms vs. 13.42 ± 17.9ms, p < 0.001), and greater likelihood of fast heart rate dependent PVCs (78.5% vs. 38.2%, p = 0.017). Fourteen (51.8%) patients had an abnormal PET-CT and abnormal late gadolinium enhancement (LGE). Patients with abnormal PET-CT were more frequently treated with immunosuppression (81.4% vs. 3.2%, p < .0001) than with catheter ablation (11.1% vs. 45.9%, p = 0.002) compared to the normal PET-CT group. Over a median follow-up of 862days (IQR 134, 1407), PVC burden decreased in both groups [from 23 ± 16% to 9 ± 10% (p < 0.001) in abnormal PET-CT group and from 21 ± 15% to 7 ± 10% (p < 0.001) in normal PET-CT group]. Abnormal PET-CT findings were more commonly associated with NSVT, multiform PVCs, greater PVC coupling interval dispersion, and fast heart rate dependent PVCs. LGE was not sensitive for detecting inflammation. Immunosuppression was effective in managing PVCs with abnormal PET-CT.

Cross modality fusion for modality-specific lung tumor segmentation in PET-CT images

Although positron emission tomography-computed tomography (PET-CT) images have been widely used, it is still challenging to accurately segment the lung tumor. The respiration, movement and imaging modality lead to large modality discrepancy of the lung tumors between PET images and CT images. To overcome these difficulties, a novel network is designed to simultaneously obtain the corresponding lung tumors of PET images and CT images. The proposed network can fuse the complementary information and preserve modality-specific features of PET images and CT images. Due to the complementarity between PET images and CT images, the two modality images should be fused for automatic lung tumor segmentation. Therefore, cross modality decoding blocks are designed to extract modality-specific features of PET images and CT images with the constraints of the other modality. The edge consistency loss is also designed to solve the problem of blurred boundaries of PET images and CT images. The proposed method is tested on 126 PET-CT images with non-small cell lung cancer, and Dice similarity coefficient scores of lung tumor segmentation reach 75.66 ± 19.42 in CT images and 79.85 ± 16.76 in PET images, respectively. Extensive comparisons with state-of-the-art lung tumor segmentation methods have also been performed to demonstrate the superiority of the proposed network.

An image registration method for voxel-wise analysis of whole-body oncological PET-CT

Whole-body positron emission tomography-computed tomography (PET-CT) imaging in oncology provides comprehensive information of each patient’s disease status. However, image interpretation of volumetric data is a complex and time-consuming task. In this work, an image registration method targeted towards computer-aided voxel-wise analysis of whole-body PET-CT data was developed. The method used both CT images and tissue segmentation masks in parallel to spatially align images step-by-step. To evaluate its performance, a set of baseline PET-CT images of 131 classical Hodgkin lymphoma (cHL) patients and longitudinal image series of 135 head and neck cancer (HNC) patients were registered between and within subjects according to the proposed method. Results showed that major organs and anatomical structures generally were registered correctly. Whole-body inverse consistency vector and intensity magnitude errors were on average less than 5 mm and 45 Hounsfield units respectively in both registration tasks. Image registration was feasible in time and the nearly automatic pipeline enabled efficient image processing. Metabolic tumor volumes of the cHL patients and registration-derived therapy-related tissue volume change of the HNC patients mapped to template spaces confirmed proof-of-concept. In conclusion, the method established a robust point-correspondence and enabled quantitative visualization of group-wise image features on voxel level.

Consolidative mediastinal radiotherapy for advanced-stage classical Hodgkin lymphoma with bulky disease in patients who achieve complete response after chemotherapy in PET-CT era.

The role of consolidation mediastinal radiotherapy (RT) for mediastinal bulky disease in advanced-stage classical Hodgkin lymphoma (cHL) is controversial in the positron emission tomography/computed tomography (PET-CT) era. We reviewed the medical charts of patients with advanced-stage (clinical stage IIX-IVX) cHL and mediastinal bulky that achieved a complete response after first line chemotherapy treatment between August 2010 and December 2020 and compared the results of those who received with those who did not receive consolidation mediastinal RT. Inclusion criteria required PET-CT imaging for staging and response assessment. We included 115 patients; 91 received mediastinal RT and 24 did not. Patient's characteristics were balanced between the two groups. The median age in patients that received and did not receive mediastinal RT was 28 years and 24.5 years, respectively. Median International Prognostic Score among patients that received and did not receive mediastinal RT was 2 and 2.5, respectively. Disease free survival (DFS) was statistically better in patients that received mediastinal RT (p = 0.013). Two-year DFS for patients that received and did not receive mediastinal RT was 95.2% [95% confidence interval (95% CI): 87.6-98.2%] and 76.4% (95% CI: 52.2-89.4%), respectively. Overall survival (OS) was not different between the two groups (p = 0.617). In multivariate analysis, not receiving mediastinal radiotherapy and only achieving partial response (vs. complete response) after 2 cycles of chemotherapy were factors predictive of lower DFS. DFS, but not OS, was superior in patients that received mediastinal RT.

Prediction Model of Residual Neural Network for Pathological Confirmed Lymph Node Metastasis of Ovarian Cancer.

Purpose We want to develop a model for predicting lymph node status based on positron emission computed tomography (PET) images of untreated ovarian cancer patients. We use the feature map formed by wavelet transform and the parameters obtained by image segmentation to build the model. The model is expected to help clinicians and provide additional information about what to do with first-visit patients. Materials and Methods Our study included 224 patients with ovarian cancer. We have chosen two main methods to extract information from images. On the one hand, we segmented the image to extract the parameters to evaluate the clustering effect. On the other hand, we used wavelet transform to extract the image's texture information to form the image's feature map. Based on the above two kinds of information, we used residual neural network and support vector machine for modeling. Results We established a model to predict lymph node metastasis in patients with primary ovarian cancer using PET images. On the training set, our accuracy was 0.8854, AUC: 0.9472, CI: 0.9098-0.9752, sensitivity was 0.9865, and specificity was 0.7952. On the test set, our accuracy was 0.9104, AUC: 0.9259, CI: 0.8417-0.9889, sensitivity was 0.8125, and specificity was 1.0000. Conclusions We used wavelet transform to process the preoperative medical images of ovarian cancer patients, and the residual neural network can effectively predict the lymph node metastasis of ovarian cancer patients, which is undoubted of great significance for patients' staging and treatment options.