EJNMMI Physics最新文献

{"title":"Reduction of [⁶⁸Ga]Ga-DOTA-TATE injected activity for digital PET/MR in comparison with analogue PET/CT.","authors":"Christina P W Cox, Tessa Brabander, Erik Vegt, Quido G de Lussanet de la Sablonière, Laura H Graven, Frederik A Verburg, Marcel Segbers","doi":"10.1186/s40658-024-00629-z","DOIUrl":"10.1186/s40658-024-00629-z","url":null,"abstract":"<p><strong>Background: </strong>New digital detectors and block-sequential regularized expectation maximization (BSREM) reconstruction algorithm improve positron emission tomography (PET)/magnetic resonance (MR) image quality. The impact on image quality may differ from analogue PET/computed tomography (CT) protocol. The aim of this study is to determine the potential reduction of injected [⁶⁸Ga]Ga-DOTA-TATE activity for digital PET/MR with BSREM reconstruction while maintaining at least equal image quality compared to the current analogue PET/CT protocol.</p><p><strong>Methods: </strong>NEMA IQ phantom data and 25 patients scheduled for a diagnostic PET/MR were included. According to our current protocol, 1.5 MBq [⁶⁸Ga]Ga-DOTA-TATE per kilogram (kg) was injected. After 60 min, scans were acquired with 3 (≤ 70 kg) or 4 (> 70 kg) minutes per bedposition. PET/MR scans were reconstructed using BSREM and factors β 150, 300, 450 and 600. List mode data with reduced counts were reconstructed to simulate scans with 17%, 33%, 50% and 67% activity reduction. Image quality was measured quantitatively for PET/CT and PET/MR phantom and patient data. Experienced nuclear medicine physicians performed visual image quality scoring and lesion counting in the PET/MR patient data.</p><p><strong>Results: </strong>Phantom analysis resulted in a possible injected activity reduction of 50% with factor β = 600. Quantitative analysis of patient images revealed a possible injected activity reduction of 67% with factor β = 600. Both with equal or improved image quality as compared to PET/CT. However, based on visual scoring a maximum activity reduction of 33% with factor β = 450 was acceptable, which was further limited by lesion detectability analysis to an injected activity reduction of 17% with factor β = 450.</p><p><strong>Conclusion: </strong>A digital [⁶⁸Ga]Ga-DOTA-TATE PET/MR together with BSREM using factor β = 450 result in 17% injected activity reduction with quantitative values at least similar to analogue PET/CT, without compromising on PET/MR visual image quality and lesion detectability.</p>","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"11 1","pages":"27"},"PeriodicalIF":3.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11266332/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140136543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"¹⁵⁵Tb production by cyclotrons: what level of ¹⁵⁵Gd enrichment allows clinical applications?","authors":"Francesca Barbaro, Luciano Canton, Nikolay Uzunov, Laura De Nardo, Laura Melendez-Alafort","doi":"10.1186/s40658-024-00630-6","DOIUrl":"10.1186/s40658-024-00630-6","url":null,"abstract":"<p><strong>Background: </strong>¹⁵⁵Tb represents a potentially useful radionuclide for diagnostic medical applications, but its production remains a challenging problem, in spite of the fact that many production routes have been already investigated and tested. A recent experimental campaign, conducted with low-energy proton beams impinging on a ¹⁵⁵Gd target with 91.9% enrichment, demonstrated a significant co-production of ^156gTb, a contaminant of great concern since its half-life is comparable to that of ¹⁵⁵Tb and its high-energy γ emissions severely impact on the dose released and on the quality of the SPECT images. In the present investigation, the isotopic purity of the enriched ¹⁵⁵Gd target necessary to minimize the co-production of contaminant radioisotopes, in particular ^156gTb, was explored using various computational simulations.</p><p><strong>Results: </strong>Starting from the recent experimental data obtained with a 91.9% ¹⁵⁵Gd-enriched target, the co-production of other Tb radioisotopes besides ¹⁵⁵Tb has been theoretically evaluated using the Talys code. It was found that ¹⁵⁶Gd, with an isotopic content of 5.87%, was the principal contributor to the co-production of ^156gTb. The analysis also demonstrated that the maximum amount of ¹⁵⁶Gd admissible for ¹⁵⁵Tb production with a radionuclidic purity higher than 99% was 1%. A less stringent condition was obtained through computational dosimetry analysis, suggesting that a 2% content of ¹⁵⁶Gd in the target can be tolerated to limit the dose increase to the patient below the 10% limit. Moreover, it has been demonstrated that the imaging properties of the produced ¹⁵⁵Tb are not severely affected by this level of impurity in the target.</p><p><strong>Conclusions: </strong>¹⁵⁵Tb can be produced with a quality suitable for medical applications using low-energy proton beams and ¹⁵⁵Gd-enriched targets, if the ¹⁵⁶Gd impurity content does not exceed 2%. Under these conditions, the dose increase due to the presence of contaminant radioisotopes remains below the 10% limit and good quality images, comparable to those of ¹¹¹In, are guaranteed.</p>","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"11 1","pages":"26"},"PeriodicalIF":3.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11286608/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140131025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sequential deep learning image enhancement models improve diagnostic confidence, lesion detectability, and image reconstruction time in PET.","authors":"Meghi Dedja, Abolfazl Mehranian, Kevin M Bradley, Matthew D Walker, Patrick A Fielding, Scott D Wollenweber, Robert Johnsen, Daniel R McGowan","doi":"10.1186/s40658-024-00632-4","DOIUrl":"10.1186/s40658-024-00632-4","url":null,"abstract":"<p><strong>Background: </strong>Investigate the potential benefits of sequential deployment of two deep learning (DL) algorithms namely DL-Enhancement (DLE) and DL-based time-of-flight (ToF) (DLT). DLE aims to enhance the rapidly reconstructed ordered-subset-expectation-maximisation algorithm (OSEM) images towards block-sequential-regularised-expectation-maximisation (BSREM) images, whereas DLT aims to improve the quality of BSREM images reconstructed without ToF. As the algorithms differ in their purpose, sequential application may allow benefits from each to be combined. 20 FDG PET-CT scans were performed on a Discovery 710 (D710) and 20 on Discovery MI (DMI; both GE HealthCare). PET data was reconstructed using five combinations of algorithms:1. ToF-BSREM, 2. ToF-OSEM + DLE, 3. OSEM + DLE + DLT, 4. ToF-OSEM + DLE + DLT, 5. ToF-BSREM + DLT. To assess image noise, 30 mm-diameter spherical VOIs were drawn in both lung and liver to measure standard deviation of voxels within the volume. In a blind clinical reading, two experienced readers rated the images on a five-point Likert scale based on lesion detectability, diagnostic confidence, and image quality.</p><p><strong>Results: </strong>Applying DLE + DLT reduced noise whilst improving lesion detectability, diagnostic confidence, and image reconstruction time. ToF-OSEM + DLE + DLT reconstructions demonstrated an increase in lesion SUV_max of 28 ± 14% (average ± standard deviation) and 11 ± 5% for data acquired on the D710 and DMI, respectively. The same reconstruction scored highest in clinical readings for both lesion detectability and diagnostic confidence for D710.</p><p><strong>Conclusions: </strong>The combination of DLE and DLT increased diagnostic confidence and lesion detectability compared to ToF-BSREM images. As DLE + DLT used input OSEM images, and because DL inferencing was fast, there was a significant decrease in overall reconstruction time. This could have applications to total body PET.</p>","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"11 1","pages":"28"},"PeriodicalIF":4.0,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10942956/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140136544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Validation of image-derived input function using a long axial field of view PET/CT scanner for two different tracers.","authors":"Xavier Palard-Novello, Denise Visser, Nelleke Tolboom, Charlotte L C Smith, Gerben Zwezerijnen, Elsmarieke van de Giessen, Marijke E den Hollander, Frederik Barkhof, Albert D Windhorst, Bart Nm van Berckel, Ronald Boellaard, Maqsood Yaqub","doi":"10.1186/s40658-024-00628-0","DOIUrl":"10.1186/s40658-024-00628-0","url":null,"abstract":"<p><strong>Background: </strong>Accurate image-derived input function (IDIF) from highly sensitive large axial field of view (LAFOV) PET/CT scanners could avoid the need of invasive blood sampling for kinetic modelling. The aim is to validate the use of IDIF for two kinds of tracers, 3 different IDIF locations and 9 different reconstruction settings.</p><p><strong>Methods: </strong>Eight [¹⁸F]FDG and 10 [¹⁸F]DPA-714 scans were acquired respectively during 70 and 60 min on the Vision Quadra PET/CT system. PET images were reconstructed using various reconstruction settings. IDIFs were taken from ascending aorta (AA), descending aorta (DA), and left ventricular cavity (LV). The calibration factor (CF) extracted from the comparison between the IDIFs and the manual blood samples as reference was used for IDIFs accuracy and precision assessment. To illustrate the effect of various calibrated-IDIFs on Patlak linearization for [¹⁸F]FDG and Logan linearization for [¹⁸F]DPA-714, the same target time-activity curves were applied for each calibrated-IDIF.</p><p><strong>Results: </strong>For [¹⁸F]FDG, the accuracy and precision of the IDIFs were high (mean CF ≥ 0.82, SD ≤ 0.06). Compared to the striatum influx (K_i) extracted using calibrated AA IDIF with the updated European Association of Nuclear Medicine Research Ltd. standard reconstruction (EARL2), K_i mean differences were < 2% using the other calibrated IDIFs. For [¹⁸F]DPA714, high accuracy of the IDIFs was observed (mean CF ≥ 0.86) except using absolute scatter correction, DA and LV (respectively mean CF = 0.68, 0.47 and 0.44). However, the precision of the AA IDIFs was low (SD ≥ 0.10). Compared to the distribution volume (V_T) in a frontal region obtained using calibrated continuous arterial sampler input function as reference, V_T mean differences were small using calibrated AA IDIFs (for example V_T mean difference = -5.3% using EARL2), but higher using calibrated DA and LV IDIFs (respectively + 12.5% and + 19.1%).</p><p><strong>Conclusions: </strong>For [¹⁸F]FDG, IDIF do not need calibration against manual blood samples. For [¹⁸F]DPA-714, AA IDIF can replace continuous arterial sampling for simplified kinetic quantification but only with calibration against arterial blood samples. The accuracy and precision of IDIF from LAFOV PET/CT system depend on tracer, reconstruction settings and IDIF VOI locations, warranting careful optimization.</p>","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"11 1","pages":"25"},"PeriodicalIF":4.0,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10933214/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140109594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical feasibility study of early 30-minute dynamic FDG-PET scanning protocol for patients with lung lesions.","authors":"Fen Du, Xieraili Wumener, Yarong Zhang, Maoqun Zhang, Jiuhui Zhao, Jinpeng Zhou, Yiluo Li, Bin Huang, Rongliang Wu, Zeheng Xia, Zhiheng Yao, Tao Sun, Ying Liang","doi":"10.1186/s40658-024-00625-3","DOIUrl":"10.1186/s40658-024-00625-3","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;This study aimed to evaluate the clinical feasibility of early 30-minute dynamic 2-deoxy-2-[&lt;sup&gt;18&lt;/sup&gt;F]fluoro-D-glucose (&lt;sup&gt;18&lt;/sup&gt;F-FDG) positron emission tomography (PET) scanning protocol for patients with lung lesions in comparison to the standard 65-minute dynamic FDG-PET scanning as a reference.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Dynamic &lt;sup&gt;18&lt;/sup&gt;F-FDG PET images of 146 patients with 181 lung lesions (including 146 lesions confirmed by histology) were analyzed in this prospective study. Dynamic images were reconstructed into 28 frames with a specific temporal division protocol for the scan data acquired 65 min post-injection. Ki images and quantitative parameters Ki based on two different acquisition durations [the first 30 min (Ki-30 min) and 65 min (Ki-65 min)] were obtained by applying the irreversible two-tissue compartment model using in-house Matlab software. The two acquisition durations were compared for Ki image quality (including visual score analysis and number of lesions detected) and Ki value (including accuracy of Ki, the value of differential diagnosis of lung lesions and prediction of PD-L1 status) by Wilcoxon's rank sum test, Spearman's rank correlation analysis, receiver operating characteristic (ROC) curve, and the DeLong test. The significant testing level (alpha) was set to 0.05.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The quality of the Ki-30 min images was not significantly different from the Ki-65 min images based on visual score analysis (P &gt; 0.05). In terms of Ki value, among 181 lesions, Ki-65 min was statistically higher than Ki-30 min (0.027 ± 0.017 ml/g/min vs. 0.026 ± 0.018 ml/g/min, P &lt; 0.05), while a very high correlation was obtained between Ki-65 min and Ki-30 min (r = 0.977, P &lt; 0.05). In the differential diagnosis of lung lesions, ROC analysis was performed on 146 histologically confirmed lesions, the area under the curve (AUC) of Ki-65 min, Ki-30 min, and SUVmax was 0.816, 0.816, and 0.709, respectively. According to the Delong test, no significant differences in the diagnostic accuracies were found between Ki-65 min and Ki-30 min (P &gt; 0.05), while the diagnostic accuracies of Ki-65 min and Ki-30 min were both significantly higher than that of SUVmax (P &lt; 0.05). In 73 (NSCLC) lesions with definite PD-L1 expression results, the Ki-65 min, Ki-30 min, and SUVmax in PD-L1 positivity were significantly higher than that in PD-L1 negativity (P &lt; 0.05). And no significant differences in predicting PD-L1 positivity were found among Ki-65 min, Ki-30 min, and SUVmax (AUC = 0.704, 0.695, and 0.737, respectively, P &gt; 0.05), according to the results of ROC analysis and Delong test.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study indicates that an early 30-minute dynamic FDG-PET acquisition appears to be sufficient to provide quantitative images with good-quality and accurate Ki values for the assessment of lung lesions and prediction of PD-L1 expression. Protocols with a shortened early 30","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"11 1","pages":"23"},"PeriodicalIF":4.0,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10914647/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140027665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of a prognostic nomogram model in locally advanced NSCLC based on metabolic features of PET/CT and hematological inflammatory indicators.","authors":"Congjie Wang, Jian Fang, Tingshu Jiang, Shanliang Hu, Ping Wang, Xiuli Liu, Shenchun Zou, Jun Yang","doi":"10.1186/s40658-024-00626-2","DOIUrl":"10.1186/s40658-024-00626-2","url":null,"abstract":"<p><strong>Background: </strong>We combined the metabolic features of ¹⁸F-FDG-PET/CT and hematological inflammatory indicators to establish a predictive model of the outcomes of patients with locally advanced non-small cell lung cancer (LA-NSCLC) receiving concurrent chemoradiotherapy.</p><p><strong>Results: </strong>A predictive nomogram was developed based on sex, CEA, systemic immune-inflammation index (SII), mean SUV (SUVmean), and total lesion glycolysis (TLG). The nomogram presents nice discrimination that yielded an AUC of 0.76 (95% confidence interval: 0.66-0.86) to predict 1-year PFS, with a sensitivity of 63.6%, a specificity of 83.3%, a positive predictive value of 83.7%, and a negative predictive value of 62.9% in the training set. The calibration curves and DCA suggested that the nomogram had good calibration and fit, as well as promising clinical effectiveness in the training set. In addition, survival analysis indicated that patients in the low-risk group had a significantly longer mPFS than those in the high-risk group (16.8 months versus 8.4 months, P < 0.001). Those results were supported by the results in the internal and external test sets.</p><p><strong>Conclusions: </strong>The newly constructed predictive nomogram model presented promising discrimination, calibration, and clinical applicability and can be used as an individualized prognostic tool to facilitate precision treatment in clinical practice.</p>","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"11 1","pages":"24"},"PeriodicalIF":4.0,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10914655/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140027666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Feasibility study of a SiPM-fiber detector for non-invasive measurement of arterial input function for preclinical and clinical positron emission tomography.","authors":"Sara de Scals, Luis Mario Fraile, José Manuel Udías, Laura Martínez Cortés, Marta Oteo, Miguel Ángel Morcillo, José Luis Carreras-Delgado, María Nieves Cabrera-Martín, Samuel España","doi":"10.1186/s40658-024-00624-4","DOIUrl":"10.1186/s40658-024-00624-4","url":null,"abstract":"","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"11 1","pages":"22"},"PeriodicalIF":4.0,"publicationDate":"2024-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10912379/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140021220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of kilovoltage and quality reference mAs on CT-based attenuation correction in 177Lu SPECT/CT imaging: a phantom study","authors":"Maikol Salas-Ramirez, Julian Leube, Michael Lassmann, Johannes Tran-Gia","doi":"10.1186/s40658-024-00622-6","DOIUrl":"https://doi.org/10.1186/s40658-024-00622-6","url":null,"abstract":"CT-based attenuation correction (CT-AC) plays a major role in accurate activity quantification by SPECT/CT imaging. However, the effect of kilovoltage peak (kVp) and quality-reference mAs (QRM) on the attenuation coefficient image (μ-map) and volume CT dose index (CTDIvol) have not yet been systematically evaluated. Therefore, the aim of this study was to fill this gap and investigate the influence of kVp and QRM on CT-AC in 177Lu SPECT/CT imaging. Seventy low-dose CT acquisitions of an Electron Density Phantom (seventeen inserts of nine tissue-equivalent materials) were acquired using various kVp and QRM combinations on a Siemens Symbia Intevo Bold SPECT/CT system. Using manufacturer reconstruction software, 177Lu μ-maps were generated for each CT image, and three low-dose CT related aspects were examined. First, the μ-map-based attenuation values (μmeasured) were compared with theoretical values (μtheoretical). Second, changes in 177Lu activity expected due to changes in the μ-map were calculated using a modified Chang method. Third, the noise in the μ-map was assessed by measuring the coefficient of variation in a volume of interest in the homogeneous section of the Electron Density Phantom. Lastly, two phantoms were designed to simulate attenuation in four tissue-equivalent materials for two different source geometries (1-mL and 10-mL syringes). 177Lu SPECT/CT imaging was performed using three different reconstruction algorithms (xSPECT Quant, Flash3D, STIR), and the SPECT-based activities were compared against the nominal activities in the sources. The largest relative errors between μmeasured and μtheoretical were observed in the lung inhale insert (range: 18%-36%), while it remained below 6% for all other inserts. The resulting changes in 177Lu activity quantification were -3.5% in the lung inhale insert and less than -2.3% in all other inserts. Coefficient of variation and CTDIvol ranged from 0.3% and 3.6 mGy (130 kVp, 35 mAs) to 0.4% and 0.9 mGy (80 kVp, 20 mAs), respectively. The SPECT-based activity quantification using xSPECT Quant reconstructions outperformed all other reconstruction algorithms. This study shows that kVp and QRM values in low-dose CT imaging have a minimum effect on quantitative 177Lu SPECT/CT imaging, while the selection of low values of kVp and QRM reduce the CTDIvol.","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"2015 1","pages":""},"PeriodicalIF":4.0,"publicationDate":"2024-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139969679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fit of biokinetic data in molecular radiotherapy: a machine learning approach","authors":"Davide Ciucci, Bartolomeo Cassano, Salvatore Donatiello, Federica Martire, Antonio Napolitano, Claudia Polito, Elena Solfaroli Camillocci, Gianluca Cervino, Ludovica Pungitore, Claudio Altini, Maria Felicia Villani, Milena Pizzoferro, Maria Carmen Garganese, Vittorio Cannatà","doi":"10.1186/s40658-024-00623-5","DOIUrl":"https://doi.org/10.1186/s40658-024-00623-5","url":null,"abstract":"In literature are reported different analytical methods (AM) to choose the proper fit model and to fit data of the time-activity curve (TAC). On the other hand, Machine Learning algorithms (ML) are increasingly used for both classification and regression tasks. The aim of this work was to investigate the possibility of employing ML both to classify the most appropriate fit model and to predict the area under the curve (τ). Two different ML systems have been developed for classifying the fit model and to predict the biokinetic parameters. The two systems were trained and tested with synthetic TACs simulating a whole-body Fraction Injected Activity for patients affected by metastatic Differentiated Thyroid Carcinoma, administered with [131I]I-NaI. Test performances, defined as classification accuracy (CA) and percentage difference between the actual and the estimated area under the curve (Δτ), were compared with those obtained using AM varying the number of points (N) of the TACs. A comparison between AM and ML were performed using data of 20 real patients. As N varies, CA remains constant for ML (about 98%), while it improves for F-test (from 62 to 92%) and AICc (from 50 to 92%), as N increases. With AM, $$Delta tau$$ can reach down to − 67%, while using ML $$Delta tau$$ ranges within ± 25%. Using real TACs, there is a good agreement between τ obtained with ML system and AM. The employing of ML systems may be feasible, having both a better classification and a better estimation of biokinetic parameters.","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"18 1","pages":""},"PeriodicalIF":4.0,"publicationDate":"2024-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139920909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Kinetic 18F-FDG PET/CT imaging of hepatocellular carcinoma: a dual input four-compartment model","authors":"Tao Wang, Yinglei Deng, Sidan Wang, Jianfeng He, Shaobo Wang","doi":"10.1186/s40658-024-00619-1","DOIUrl":"https://doi.org/10.1186/s40658-024-00619-1","url":null,"abstract":"The endoplasmic reticulum plays an important role in glucose metabolism and has not been explored in the kinetic estimation of hepatocellular carcinoma (HCC) via 18F-fluoro-2-deoxy-d-glucose PET/CT. A dual-input four-compartment (4C) model, regarding endoplasmic reticulum was preliminarily used for kinetic estimation to differentiate 28 tumours from background liver tissue from 24 patients with HCC. Moreover, parameter images of the 4C model were generated from one patient with negative findings on conventional metabolic PET/CT. Compared to the dual-input three-compartment (3C) model, the 4C model has better fitting quality, a close transport rate constant (K1) and a dephosphorylation rate constant (k6/k4), and a different removal rate constant (k2) and phosphorylation rate constant (k3) in HCC and background liver tissue. The K1, k2, k3, and hepatic arterial perfusion index (HPI) from the 4C model and k3, HPI, and volume fraction of blood (Vb) from the 3C model were significantly different between HCC and background liver tissues (all P < 0.05). Meanwhile, the 4C model yielded additional kinetic parameters for differentiating HCC. The diagnostic performance of the top ten genes from the most to least common was HPI(4C), Vb(3C), HPI(3C), SUVmax, k5(4C), k3(3C), k2(4C), v(4C), K1(4C) and Vb(4C). Moreover, a patient who showed negative findings on conventional metabolic PET/CT had positive parameter images in the 4C model. The 4C model with the endoplasmic reticulum performed better than the 3C model and produced additional useful parameters in kinetic estimation for differentiating HCC from background liver tissue.","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"6 1","pages":""},"PeriodicalIF":4.0,"publicationDate":"2024-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139920918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}