Combined Positron Emission Tomography Research Articles

St. John's wort extract with a high hyperforin content does not induce P-glycoprotein activity at the human blood-brain barrier.

St. John's wort (SJW) extract, a herbal medicine with antidepressant effects, is a potent inducer of intestinal and/or hepatic cytochrome P450 (CYP) enzymes and P-glycoprotein (P-gp), which can cause clinically relevant drug interactions. It is currently not known whether SJW can also induce P-gp activity at the human blood-brain barrier (BBB), which may potentially lead to decreased brain exposure and efficacy of certain central nervous system (CNS)-targeted P-gp substrate drugs. In this study, we used a combination of positron emission tomography (PET) imaging and cocktail phenotyping to gain a comprehensive picture on the effect of SJW on central and peripheral P-gp and CYP activities. Before and after treatment of healthy volunteers (n = 10) with SJW extract with a high hyperforin content (3-6%) for 12-19 days (1800 mg/day), the activity of P-gp at the BBB was assessed by means of PET imaging with the P-gp substrate [11C]metoclopramide and the activity of peripheral P-gp and CYPs was assessed by administering a low-dose phenotyping cocktail (caffeine, omeprazole, dextromethorphan, and midazolam or fexofenadine). SJW significantly increased peripheral P-gp, CYP3A, and CYP2C19 activity. Conversely, no significant changes in the peripheral metabolism, brain distribution, and P-gp-mediated efflux of [11C]metoclopramide across the BBB were observed following the treatment with SJW extract. Our data suggest that SJW does not lead to significant P-gp induction at the human BBB despite its ability to induce peripheral P-gp and CYPs. Simultaneous intake of SJW with CNS-targeted P-gp substrate drugs is not expected to lead to P-gp-mediated drug interactions at the BBB.

Breast cancer lesion segmentation based on co-learning feature fusion and Transformer

The PET/CT imaging technology combining positron emission tomography (PET) and computed tomography (CT) is the most advanced imaging examination method currently, and is mainly used for tumor screening, differential diagnosis of benign and malignant tumors, staging and grading. This paper proposes a method for breast cancer lesion segmentation based on PET/CT bimodal images, and designs a dual-path U-Net framework, which mainly includes three modules: encoder module, feature fusion module and decoder module. Among them, the encoder module uses traditional convolution for feature extraction of single mode image; The feature fusion module adopts collaborative learning feature fusion technology and uses Transformer to extract the global features of the fusion image; The decoder module mainly uses multi-layer perceptron to achieve lesion segmentation. This experiment uses actual clinical PET/CT data to evaluate the effectiveness of the algorithm. The experimental results show that the accuracy, recall and accuracy of breast cancer lesion segmentation are 95.67%, 97.58% and 96.16%, respectively, which are better than the baseline algorithm. Therefore, it proves the rationality of the single and bimodal feature extraction method combining convolution and Transformer in the experimental design of this article, and provides reference for feature extraction methods for tasks such as multimodal medical image segmentation or classification.

Tumor-Targeted Perfluorinated Micelles as Efficient Theranostic Agents Combining Positron Emission Tomography and Radiosensitization.

We report the synthesis of biocompatible perfluorinated micelles designed to improve radiotherapeutic efficacy in a radioresistant tumor environment. In vitro and in vivo behaviors of perfluorinated micelles were assessed at both cellular and tissular levels. The micellar platform offers key advantages as theranostic tool: (i) small size, allowing deep tissue penetration; (ii) oxygen transport to hypoxic tissues; (iii) negligible toxicity in the absence of ionizing radiation; (iv) internalization into cancer cells; (v) potent radiosensitizing effect; and (vi) excellent tumor-targeting properties, as monitored by positron emission tomography. We have demonstrated strong in vitro radiosensitizing effects of the micelle and in vivo tumor targeting, making this nanometric carrier a promising tool for the potentiation of focused radiotherapy.

Are central and systemic inflammation associated with fatigue in cerebral small vessel disease?

Fatigue is a common symptom in cerebral small vessel disease (SVD), but its pathogenesis is poorly understood. It has been suggested that inflammation may play a role. We determined whether central (neuro) inflammation and peripheral inflammation were associated with fatigue in SVD. Notably, 36 patients with moderate-to-severe SVD underwent neuropsychometric testing, combined positron emission tomography and magnetic resonance imaging (PET-MRI) scan, and blood draw for the analysis of inflammatory blood biomarkers. Microglial signal was taken as a proxy for neuroinflammation, assessed with radioligand 11C-PK11195. Of these, 30 subjects had full PET datasets for analysis. We assessed global 11C-PK11195 binding and hotspots of 11C-PK11195 binding in the normal-appearing white matter, lesioned tissue, and combined total white matter. Peripheral inflammation was assessed with serum C-reactive protein (CRP) and using the Olink cardiovascular III proteomic panel comprising 92 biomarkers of cardiovascular inflammation and endothelial activation. Fatigue was assessed using the fatigue severity scale (FSS), the visual analog fatigue scale, and a subscale of the Geriatric Depression Scale. Mean (SD) age was 68.7 (11.2) years, and 63.9% were male. Of these, 55.6% showed fatigue on the FSS. Fatigued participants had higher disability scores (p = 0.02), higher total GDS scores (p = 0.02), and more commonly reported a history of depression (p = 0.04). 11C-PK11195 ligand binding in the white matter was not associated with any measure of fatigue. Serum CRP was significantly associated with average fatigue score on FSS (ρ = 0.48, p = 0.004); this association persisted when controlling for age, sex, disability score, and depression (β = 0.49, 95% CI (0.17, 2.26), p = 0.03). Blood biomarkers from the Olink panel showed no association with fatigue. In symptomatic SVD patients, neuroinflammation, assessed with microglial marker 11C-PK11195, was not associated with fatigue. We found some evidence for a role of systematic inflammation, evidenced by an association between fatigue severity and raised CRP, but further studies are required to understand this relationship and inform whether it could be therapeutically modified to reduce fatigue severity. Data for this study are available from the corresponding author upon reasonable request.

Thoracic aortic microcalcification activity in combined positron emission tomography and magnetic resonance imaging.

Non-invasive detection of pathological changes in thoracic aortic disease remains an unmet clinical need particularly for patients with congenital heart disease. Positron emission tomography combined with magnetic resonance imaging (PET-MRI) could provide a valuable low-radiation method of aortic surveillance in high-risk groups. Quantification of aortic microcalcification activity using sodium [18F]fluoride holds promise in the assessment of thoracic aortopathies. We sought to evaluate aortic sodium [18F]fluoride uptake in PET-MRI using three methods of attenuation correction compared to positron emission tomography computed tomography (PET-CT) in patients with bicuspid aortic valve, METHODS: Thirty asymptomatic patients under surveillance for bicuspid aortic valve disease underwent sodium [18F]fluoride PET-CT and PET-MRI of the ascending thoracic aorta during a single visit. PET-MRI data were reconstructed using three iterations of attenuation correction (Dixon, radial gradient recalled echo with two [RadialVIBE-2] or four [RadialVIBE-4] tissue segmentation). Images were qualitatively and quantitatively analysed for aortic sodium [18F]fluoride uptake on PET-CT and PET-MRI. Aortic sodium [18F]fluoride uptake on PET-MRI was visually comparable with PET-CT using each reconstruction and total aortic standardised uptake values on PET-CT strongly correlated with each PET-MRI attenuation correction method (Dixon R = 0.70; RadialVIBE-2 R = 0.63; RadialVIBE-4 R = 0.64; p < 0.001 for all). Breathing related artefact between soft tissue and lung were detected using Dixon and RadialVIBE-4 but not RadialVIBE-2 reconstructions, with the presence of this artefact adjacent to the atria leading to variations in blood pool activity estimates. Consequently, quantitative agreements between radiotracer activity on PET-CT and PET-MRI were most consistent with RadialVIBE-2. Ascending aortic microcalcification analysis in PET-MRI is feasible with comparable findings to PET-CT. RadialVIBE-2 tissue attenuation correction correlates best with the reference standard of PET-CT and is less susceptible to artefact. There remain challenges in segmenting tissue types in PET-MRI reconstructions, and improved attenuation correction methods are required.

PET/SPECT/spectral-CT/CBCT imaging in a small-animal radiation therapy platform: A Monte Carlo study-Part I: Quad-modal imaging.

In spite of the tremendous potential of game-changing biological image- and/or biologically guided radiation therapy (RT) and adaptive radiation therapy for cancer treatment, existing limited strategies for integrating molecular imaging and/or biological information with RT have impeded the translation of preclinical research findings to clinical applications. Additionally, there is an urgent need for a highly integrated small-animal radiation therapy (SART) platform that can seamlessly combine therapeutic and diagnostic capabilities to comprehensively enhance RT for cancer treatment. We investigated a highly integrated quad-modal on-board imaging configuration combining positron emission tomography (PET), single-photon emission computed tomography (SPECT), photon-counting spectral CT, and cone-beam computed tomography (CBCT) in a SART platform using a Monte Carlo model as a proof-of-concept. The quad-modal on-board imaging configuration of the SART platform was designed and evaluated by using the GATE Monte Carlo code. A partial-ring on-board PET imaging subsystem, utilizing advanced semiconductor thallium bromide detector technology, was designed to achieve high sensitivity and spatial resolution. On-board SPECT, photon-counting spectral-CT, and CBCT imaging were performed using a single cadmium zinc telluride flat detector panel. The absolute peak sensitivity and scatter fraction of the PET subsystem were estimated by using simulated phantoms described in the NEMA NU-4 standard. The spatial resolution of the PET image of the platform was evaluated by imaging a simulated micro-Derenzo hot-rod phantom. To evaluate the quantitative imaging capability of the system's spectral CT, the Bayesian eigentissue decomposition (ETD) method was utilized to quantitatively decompose the virtual noncontrast (VNC) electron densities and iodine contrast agent fractions in the Kidney1 inserts mixed with the iodine contrast agent within the simulated phantoms. The performance of the proposed quad-model imaging in the platform was validated by imaging a simulated phantom with multiple imaging probes, including an iodine contrast agent and radioisotopes of 18F and 99mTc. The PET subsystem demonstrated an absolute peak sensitivity of 18.5% at the scanner center, with an energy window of 175-560KeV, and a scatter fraction of only 3.5% for the mouse phantom, with a default energy window of 480-540KeV. The spatial resolution of PET on-board imaging exceeded 1.2mm. All imaging probes were identified clearly within the phantom. The PET and SPECT images agreed well with the actual spatial distributions of the tracers within the phantom. Average relative errors on electron density and iodine contrast agent fraction in the Kidney1 inserts were less than 3%. High-quality PET images, SPECT images, spectral-CT images (including iodine contrast agent fraction images and VNC electron density images), and CBCT images of the simulated phantom demonstrated the comprehensive multimodal imaging capability of the system. The results demonstrated the feasibility of the proposed quad-modal imaging configuration in a SART platform. The design incorporates anatomical, molecular, and functional information about tumors, thereby facilitating successful translation of preclinical studies into clinical practices.

Treatment Response to Neoadjuvant Therapy in Squamous Esophageal Cancer-Correlation Between Metabolic Response and Histopathology.

Esophageal cancer is among the leading causes of cancer-related mortality worldwide. Patients presenting with localized and loco-regionally advanced cancer without distant metastases have reasonable survival with multimodality management. Adequate and comprehensive staging is the backbone for proper selection of patients fit for curative treatment. Positron emission tomography (PET) in combination with contrast-enhanced computed tomography (CECT) is utilized as the standard staging modality. Multimodality treatment has been able to achieve evaluable tumor responses including pathological complete response (pCR). It is, therefore, necessary to understand whether the impact of neoadjuvant therapy can be evaluated on imaging, i.e., standardized uptake value (SUV) on PET scan done for response assessment and if this can be correlated with histopathological response and later, with survival. Squamous cell carcinoma (SCC) is more common globally and in the Indian subcontinent; hence, we chose this subgroup to evaluate our hypothesis. This is a single institution, retrospective study. Out of the 1967 patients who were treated between 2009 and 2019, 1369 (78.54%) patients had SCC. Out of these, 44 received NACTRT, whereas 1325 received NACT followed by curative surgery. The standardized uptake value (SUV) of 18-fluorodeoxyglucose was recorded during pre- and post-neoadjuvant treatment (NAT) using positron emission tomography (PET). The histopathology of the final resection specimen was evaluated using the Mandard tumor regression grade (TRG) criteria with response being graded from 0 to 5 as no residual tumor (NRT), scanty residual tumor (SRT), and residual tumor We attempted to find a cut-off value of the post neoadjuvant SUV of the primary tumor site which correlated with achievement of better histopathological response. Out of 1325 patients of SCC esophagus who underwent surgery, 943 patients had available data of TRG, and it was categorized into the 0-2 category which had 325 patients (34.5%) and 3-5 category, 618 patients (65.5%). The SUV was taken only from the PET scans done at our institution, so as to achieve a more homogenous cohort, and this was available for 186 patients, 151 from the NACT group and 35 from the NACTRT group. The ROC method was used to find the cut-off for SUV (5.05) in the NACT cohort, which depicted significant difference in the outcome. Out of these, 93 patients who underwent NACT had SUV > 5.05 and 58 had SUV < 5.05. It was found that the subjective and objective histopathological scores correlated at a p value of < 0.0001. Specifically, the majority of cases with SRT tended to be in the 3-5 category of TRG, whereas cases with NRT are predominantly in the 0-2 category. In the ≥ 5.05 category of SUV, there were 76 cases with SRT. In the NACT cohort, the < 5.05 category of SUV, there are 26 cases with SRT and 32 cases with NRT. Among cases with SRT, 74.5% had SUV ≥ 5.05, while 25.5% had SUV < 5.05. Among cases with NRT, 34.7% had SUV ≥ 5.05, while 65.3% had SUV < 5.05 (p value 0.007). No significant association was found in the radio-pathological correlation in the NACTRT group. Our study confirms the correlation of post neoadjuvant chemotherapy PET SUV with histopathological response, the cut-off of SUV being 5.05 in our cohort. This confirms the predictive value of FDG PET as demonstrated in other studies. Furthermore, its prognostic value with respect to survival has been verified in multiple other studies. With larger scale randomized studies, we may be able to identify the group of patients who have borderline operability anatomically as well as physiologically, where alternative treatment regimens may be indicated to improve outcomes.

Recent advances in combined Positron Emission Tomography and Magnetic Resonance Imaging

Abstract Hybrid imaging modalities combine two or more medical imaging techniques offering exciting new possibilities to image the structure, function and biochemistry of the human body in far greater detail than has previously been possible to improve patient diagnosis. In this context, simultaneous Positron Emission Tomography and Magnetic Resonance (PET/MR) imaging offers great complementary information, but it also poses challenges from the point of view of hardware and software compatibility. The PET signal may interfere with the MR magnetic field and vice-versa, posing several challenges and constrains in the PET instrumentation for PET/MR systems. Additionally, anatomical maps are needed to properly apply attenuation and scatter corrections to the resulting reconstructed PET images, as well motion estimates to minimize the effects of movement throughout the acquisition. In this review, we summarize the instrumentation implemented in modern PET scanners to overcome these limitations, describing the historical development of hybrid PET/MR scanners. We pay special attention to the methods used in PET to achieve attenuation, scatter and motion correction when it is combined with MR, and how both imaging modalities may be combined in PET image reconstruction algorithms.

New imaging strategy for large vessel vasculitis (based on the EULAR-2023 recommendations)

Large vessel vasculitis (LVV), including Takayasu's arteritis (AT, or non-specific aortoarteritis) and giant cell arteritis (GCA), is caused by granulomatous inflammation affecting mainly the aorta and its main branches. Damage to the vascular wall leads to ischemia of the corresponding organs and can be complicated by loss of vision, cerebral insufficiency and other life-threatening phenomena. The early diagnosis of these diseases in clinical practice is a difficult task that can only be solved by comparing the clinical symptoms, the results of the physical, laboratory and instrumental examination and the vascular biopsy.A comparative analysis of the 2018 and 2023 EULAR recommendations for imaging in LVV is presented. Duplex ultrasound (USDS) of not only temporal but also axillary arteries is recommended for GCA and magnetic resonance imaging (MRI) for AT. Alternative methods for GCA are MRI or positron emission tomography (PET) in combination with computed tomography (CT) and intravenous administration of fluorodeoxyglucose labelled with the short-lived fluoride isotope 18 (FDG-PET/CT), and for AT – FDG-PET/CT, CT or ultrasound examination. MRI, CT or ultrasound can be used for long-term monitoring of structural damage, especially to assess pre-existing vascular inflammation.

Evaluating the cost-effectiveness of [18F]FDG-PET/CT for investigation of persistent or recurrent neutropenic fever in high-risk haematology patients

BackgroundA recent randomised trial demonstrated [18F]fluorodeoxyglucose positron-emission tomography in combination with low-dose CT (FDG-PET/CT), compared to standard of care computed tomography (CT) imaging, positively impacted antimicrobial management and outcomes of acute leukaemia and haematopoietic stem cell transplant recipients with persistent and recurrent neutropenic fever. We conducted an economic evaluation from a healthcare perspective alongside the clinical trial.MethodsUnit costs in Australian dollars were applied to all resources used (antimicrobials, diagnostic tests, ICU and hospital bed days). Effectiveness was measured as number of patients with antimicrobial rationalisation, 6-month mortality and quality-adjusted life years (QALYs) derived from patient-reported trial-based health-related quality-of-life. Generalised linear models were used to analyse costs and outcomes. Incremental cost-effectiveness ratios (ICERs) for all outcomes and net monetary benefit (NMB) for QALYs were calculated. We performed bootstrapping with 1000 replications using the recycled predictions method.ResultsThe adjusted healthcare costs were lower for FDG-PET/CT (mean $49,563; 95%CI 36,867, 65,133) compared to CT (mean $57,574; 95% CI 44,837, 73,347). The difference in QALYs between the two groups was small (0.001; 95% CI -0.001, 0.004). When simulated 1000 times, FDG-PET/CT was the dominant strategy as it was cheaper with better outcomes than the standard CT group in 74% of simulations. The estimated NMBs at willingness-to-pay thresholds of $50,000 and $100,000 per QALY were positive, thus FDG-PET/CT remained cost-effective at these thresholds.ConclusionsFDG-PET/CT is cost effective when compared to CT for investigation of persistent/recurrent neutropenic fever in high-risk patients, providing further support for incorporation of FDG-PET/CT into clinical guidelines and funding.Trial registrationThis trial is registered with ClinicalTrials.gov, NCT03429387.

O-26 - Combining Positron Emission Tomography and Hyperpolarized Magnetic Resonance to Interrogate Prostate Cancer Metabolism

O-26 - Combining Positron Emission Tomography and Hyperpolarized Magnetic Resonance to Interrogate Prostate Cancer Metabolism

Impact of positron-emission tomography on the surgical treatment of locoregionally recurrent colorectal cancer

The effect of positron emission tomography (PET) on the surgical treatment of locoregionally recurrent colorectal cancer (LRRCRC) remains unclear and warrants further investigation. A total of 193 patients with LRRCRC were identified from a prospectively maintained institutional database, of whom 134 LRRCRCs were deemed resectable and underwent resection with curative intent, whereas the remaining 59 LRRCRCs were unresectable. Patients with resectable LRRCRC were further classified according to whether recurrence was detected solely by PET (n=35, PET-only group) or by a combination of computed tomography (CT)/magnetic resonance imaging (MRI) and PET (n=99, CT/MRI/PET group). Clinicopathologic features, operative morbidity/mortality, and overall survival were compared between the patient groups based on long-term follow-up for at least 5 years. Patients in the PET-only group tended to have less extensive organ resection (p=0.0074), less blood loss (p<0.0001), and shorter operation time and hospitalization (p<0.0001), but surgical complication and readmission rates were not significantly different (p>0.05) compared with the CT/MRI/PET group. Although the PET-only group had significantly higher R0 resection rate (80% vs. 54.55%, p=0.0079), they also had a higher risk (17.14% vs. 2.02%, p=0.0011) of sham operation. The estimated 5-year and 10-year survival rates significantly decreased in order (p<0.0001) from PET-only (85.71% and 57.98%) and CT/MRI/PET (41.41% and 15.93%) to unresectable group of patients (16.95% and 1.88%). Subset analysis of the CT/MRI/PET group indicated that PET improved surgical decision-making because 24 (24.2%) LRRCRCs that manifested on CT/MRI as equivocal lesions were later confirmed by PET as resectable recurrences, while 18 (19.4%) LRRCRCs that manifested on CT/MRI as resectable lesions were later diagnosed by PET as more disseminated unresectable recurrences and precluded futile surgery. PET alone can identify a subset (20.9%) of LRRCRCs with less tumor burden for timely surgery; PET in combination with CT/MRI can better define the resectability of LRRCRCs. The positive impacts of PET can translate into better surgical outcomes, with enhanced safety and patient survival.

Combined positron emission tomography and contrast enhanced CT (PET/CeCT) is a feasible single investigation in the staging of oesophagogastric cancers: single-centre pilot study experience during the COVID-19 pandemic.

Staging of oesophagogastric (OG) cancers usually involves endoscopy (OGD), and separate visits for contrast enhanced computed tomography (CeCT) and positron emission tomography (PET/CT). At the height of the COVID-19 pandemic, some of our patients underwent single-visit combined staging with PET/CeCT. We compare this novel pathway with standard separate imaging in time to completion of staging, to start of treatment, and cost. We identified all patients discussed at our OG multidisciplinary team (MDT) meeting in 2020. Clinical records revealed dates of investigations and treatments. Data were tabulated in Excel, with statistical analysis in SPSS. All patients followed the same MDT process and image reviewing criteria. Costs were compared using prices supplied by finance departments. A total of 211 new patients were discussed at our MDT in 2020. Of these, 48 patients had combined PET/CeCT staging, and 68 had separate scans. Median time (interquartile range) in days from OGD to final imaging was 9 (6-23) for the combined group versus 21 (16-28) for the separate group (p≤0.001). Median time (days) from OGD to treatment start was 37 (29-52) for combined versus 55 (40-71) for separate (p≤0.001). No combined scans were of insufficient diagnostic quality for the MDT. PET/CeCT had a potential cost saving of £113 per patient. PET/CeCT allows accurate radiological staging of OG cancers with a single scan. Patients completed staging and started treatment faster, with a potential saving of £10,509 in one year. PET/CeCT has become standard staging at our trust, and we aim to incorporate radiotherapy planning images too.

Value of PET imaging in head and neck cancer

The combination of positron-emission tomography (PET) with cross-sectional imaging in particular is becoming increasingly important in the diagnosis of head and neck tumors because, in addition to pure anatomy, the metabolic activity of tissue can be visualized and assessed. The combination of PET and computed tomography (CT) is already an established procedure in head and neck tumor patients in some indications, e.g., for primary tumor detection in cancer of unknown primary (CUP) syndrome or also after completed primary radio(chemo)therapy for evaluation of response, especially also with regard to nodal status. In some cases, salvage neck dissection can thus be avoided in the case of PET-negative findings. In the context of primary diagnosis, PET/CT imaging can be used primarily to evaluate distant metastasis. According to current guidelines, PET-based imaging is not (yet) of value in determining the local extent at initial diagnosis. Achallenge is the still limited reimbursement by health insurance companies, which currently allow only certain indications, and the still lack of nationwide coverage.

Improved Neural Network-Based System for Early and Accurate Diagnosis of Alzheimer Disease

Alzheimer's disorder is a neurological condition that develops over time and mainly impacts cognitive processes like memory, thought, and behavior. It is one of the most typical reasons for dementia, a syndrome marked by a loss of cognitive ability that interferes with individual daily activities. Recent techniques for diagnosing Alzheimer's illness frequently combine positron emission tomography (PET) scans with magnetic resonance imaging (MRI), which can identify mutations in the brain caused by the illness, such as the buildup of beta-amyloid plaques and tau tangles. Furthermore, analysis of blood samples and cerebrospinal fluid is also a widely used method for the diagnosis of Alzheimer’s disease. Machine learning and deep learning-based techniques play a vital role in examining complex structures in brain images and other data, contributing to the timely and precise identification of Alzheimer's disease. Artificial intelligence-based techniques can help prompt detection and treatment, leading to more efficient care for Alzheimer's disease. This study uses convolutional neural networks (CNN) with MRI-based datasets for early and accurate diagnosis of Alzheimer’s disease. The proposed approach has shown excellent results in AD diagnosis.

PET/CT scan improves detection of metastatic disease compared with CT scan alone in women with high-grade neuroendocrine cervical cancer: a NeCTuR study

ObjectiveTo determine the optimal imaging modality for women with high-grade neuroendocrine carcinoma of the cervix.MethodsWomen with high-grade neuroendocrine carcinoma of the cervix who had undergone a computed tomography (CT) scan...

Multitask Learning with Convolutional Neural Networks and Vision Transformers Can Improve Outcome Prediction for Head and Neck Cancer Patients.

Neural-network-based outcome predictions may enable further treatment personalization of patients with head and neck cancer. The development of neural networks can prove challenging when a limited number of cases is available. Therefore, we investigated whether multitask learning strategies, implemented through the simultaneous optimization of two distinct outcome objectives (multi-outcome) and combined with a tumor segmentation task, can lead to improved performance of convolutional neural networks (CNNs) and vision transformers (ViTs). Model training was conducted on two distinct multicenter datasets for the endpoints loco-regional control (LRC) and progression-free survival (PFS), respectively. The first dataset consisted of pre-treatment computed tomography (CT) imaging for 290 patients and the second dataset contained combined positron emission tomography (PET)/CT data of 224 patients. Discriminative performance was assessed by the concordance index (C-index). Risk stratification was evaluated using log-rank tests. Across both datasets, CNN and ViT model ensembles achieved similar results. Multitask approaches showed favorable performance in most investigations. Multi-outcome CNN models trained with segmentation loss were identified as the optimal strategy across cohorts. On the PET/CT dataset, an ensemble of multi-outcome CNNs trained with segmentation loss achieved the best discrimination (C-index: 0.29, 95% confidence interval (CI): 0.22-0.36) and successfully stratified patients into groups with low and high risk of disease progression (p=0.003). On the CT dataset, ensembles of multi-outcome CNNs and of single-outcome ViTs trained with segmentation loss performed best (C-index: 0.26 and 0.26, CI: 0.18-0.34 and 0.18-0.35, respectively), both with significant risk stratification for LRC in independent validation (p=0.002 and p=0.011). Further validation of the developed multitask-learning models is planned based on a prospective validation study, which has recently completed recruitment.

Value of PET imaging in head and neck cancer

The combination of positron-emission tomography (PET) with cross-sectional imaging in particular is becoming increasingly important in the diagnosis of head and neck tumors because, in addition to pure anatomy, the metabolic activity of tissue can be visualized and assessed. The combination of PET and computed tomography (CT) is already an established procedure in head and neck tumor patients in some indications, e.g., for primary tumor detection in cancer of unknown primary (CUP) syndrome or also after completed primary radio(chemo)therapy for evaluation of response, especially also with regard to nodal status. In some cases, salvage neck dissection can thus be avoided in the case of PET-negative findings. In the context of primary diagnosis, PET/CT imaging can be used primarily to evaluate distant metastasis. According to current guidelines, PET-based imaging is not (yet) of value in determining the local extent at initial diagnosis. Achallenge is the still limited reimbursement by health insurance companies, which currently allow only certain indications, and the still lack of nationwide coverage.

Fusion-based tensor radiomics using reproducible features: Application to survival prediction in head and neck cancer

BackgroundNumerous features are commonly generated in radiomics applications as applied to medical imaging, and identification of robust radiomics features (RFs) can be an important step to derivation of reliable, reproducible solutions. In this work, we utilize a tensor radiomics (TR) framework, where numerous fusions are explored, to generate different flavours of RFs, and we aimed to identify RFs that are robust to fusion techniques in head and neck cancer. Overall, we aimed to predict progression-free survival (PFS) using Hybrid Machine Learning Systems (HMLS) and reproducible RFs. MethodsThe study was performed on 408 patients with head and neck cancer from The Cancer Imaging Archive. After image preprocessing, 15 fusion techniques were employed to combine Positron Emission Tomography (PET) and Computed Tomography (CT) images. Subsequently, 215 RFs were extracted through a standardized radiomics software, with 17 ‘flavours’ generated using PET-only, CT-only, and 15 fused PET&CT images. The variability of RFs across flavours was studied using the Intraclass Correlation Coefficient (ICC). Furthermore, the features were categorized into seven reliability groups, 106 reproducible RFs with ICC>0.75 were selected, highly correlated flavours were removed, Principal Component Analysis was used to convert 17 flavours to 1 attribute, the polynomial function was utilized to increase RFs, and Analysis of variance (ANOVA) was used to select the relevant attributes. Finally, 3 classifiers including Random Forest (RFC), Logistic regression (LR), and Multi-layer perceptron were applied to the preselected relevant attributes to predict binary PFS. In 5-fold cross-validation, 80% of 4 divisions were utilized to train the model, and the remaining 20% was utilized to evaluate the model. Further, the remaining fold was used for external nested testing. ResultsReliability analysis indicated that most morphological features belong to the high-reliability category. By contrast, local intensity and statistical features extracted from images belong to the low-reliability category. In the tensor framework, the highest 5-fold cross-validation accuracy of 76.7%±3.3% with an external nested testing of 70.6%±6.7% resulted from the reproducible TR+polynomial function+ANOVA+LR algorithm while the accuracy of 70.0%±4.2% with the external nested testing of 67.7%±4.9% was achieved through the PCA fusion+RFC (non-tensor paradigm). ConclusionsThis study demonstrated that using reproducible RFs as utilized within a tensor fusion radiomics framework, linked with ANOVA and LR, added value to prediction of progression-free survival outcome in head and neck cancer patients.

Role of 18F-choline and 18F-fluorodeoxyglucose positron emission tomography in combination with magnetic resonance imaging in brachytherapy planning for locally advanced cervical cancer: A pilot study.

This pilot study aims to describe the advantages of combining metabolic and anatomic imaging modalities in brachytherapy (BT) planning for locally advanced cervical cancer (LACC) and to evaluate the supplementary value of Fluoro(F)-Choline positron emission tomography/computed tomography (PET/CT) in comparison to 18F-fluorodeoxyglucose (FDG) in this setting. A prospective cohort of six patients with LACC was included in this study. Each patient underwent BT planning CT scan, magnetic resonance imaging (MRI), and both FDG and F-Choline PET/CT scans on the same day, with BT applicators in place. Patients were treated according to the standard of care. Metabolic target volumes (TV) were generated retrospectively and compared with the anatomic volumes using Dice coefficients and absolute volume comparison. The threshold at which the metabolic and anatomic volumes were the most concordant was found to be 35% maximum standardized uptake value (SUV max) for both PET/CT scans. Amongst the six patients in this cohort, three in the FDG cohort and four in the F-Choline cohort were found to have more than ten percent ratio of excess (increase) in their MRI gross tumor volumes (GTV) when incorporating the metabolic information from the PET/CT scans. However, no significant changes were needed in the high risk-clinical target volumes (CTVHR) for both PET tracers. FDG and F-Choline PET/CT scans can substantially modify the BT GTV on MRI, without affecting the CTVHR. F-Choline is potentially more informative than FDG in assessing residual TV, particularly in cases with significant post-radiation inflammatory changes.