Keeping Up With ChatGPT: Evaluating Its Recognition and Interpretation of Nuclear Medicine Images.

PURPOSE: The latest iteration of GPT4 (generative pretrained transformer) is a large multimodal model that can integrate both text and image input, but its performance with medical images has not been systematically evaluated. We studied whether ChatGPT with GPT-4V(ision) can recognize images from common nuclear medicine examinations and interpret them. PATIENTS AND METHODS: Fifteen representative images (scintigraphy, 11; PET, 4) were submitted to ChatGPT with GPT-4V(ision), both in its Default and "Advanced Data Analysis (beta)" version. ChatGPT was asked to name the type of examination and tracer, explain the findings and whether there are abnormalities. ChatGPT should also mark anatomical structures or pathological findings. The appropriateness of the responses was rated by 3 nuclear medicine physicians. RESULTS: The Default version identified the examination and the tracer correctly in the majority of the 15 cases (60% or 53%) and gave an "appropriate" description of the findings or abnormalities in 47% or 33% of cases, respectively. The Default version cannot manipulate images. "Advanced Data Analysis (beta)" failed in all tasks in >90% of cases. A "major" or "incompatible" inconsistency between 3 trials of the same prompt was observed in 73% (Default version) or 87% of cases ("Advanced Data Analysis (beta)" version). CONCLUSIONS: Although GPT-4V(ision) demonstrates preliminary capabilities in analyzing nuclear medicine images, it exhibits significant limitations, particularly in its reliability (ie, correctness, predictability, and consistency).

Assessing regional hepatic function changes after hypertrophy induction by radioembolisation: comparison of gadoxetic acid-enhanced MRI and 99mTc-mebrofenin hepatobiliary scintigraphy.

BACKGROUND: To compare Gd-ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) and 99mTc-labelled mebrofenin hepatobiliary scintigraphy (HBS) as imaging-based liver function tests after unilateral radioembolisation (RE) in patients with primary or secondary liver malignancies. METHODS: Twenty-three patients with primary or secondary liver malignancies who underwent Gd-EOB-DTPA-enhanced MRI within a prospective study (REVoluTion) were evaluated. REVoluTion was a prospective open-label, non-randomised, therapy-optimising study of patients undergoing right-sided or sequential RE for contralateral liver hypertrophy at a single centre in Germany. MRI and hepatobiliary scintigraphy were performed before RE (baseline) and 6 weeks after (follow-up). This exploratory subanalysis compared liver enhancement on hepatobiliary phase MRI normalised to the spleen (liver-to-spleen ratio (LSR)) and the muscle (liver-to-muscle ratio (LMR)) with mebrofenin uptake on HBS for the total liver (TL) and separately for the right (RLL) and left liver lobe (LLL). RESULTS: Mebrofenin uptake at baseline and follow-up each correlated significantly with LSR and LMR on MRI for TL (≤ 0.013) and RLL (≤ 0.049). Regarding the LLL, mebrofenin uptake correlated significantly with LMR (baseline, p = 0.013; follow-up, p = 0.004), whereas with LSR, a borderline significant correlation was only seen at follow-up (p = 0.051; p = 0.046). CONCLUSION: LSRs and LMR correlate with mebrofenin uptake in HBS. This study indicates that Gd-EOB-DTPA-enhanced MRI and 99mTc-labelled mebrofenin HBS may equally be used to assess an increase in contralateral liver lobe function after right-sided RE. RELEVANCE STATEMENT: MRI may be a convenient and reliable method for assessing the future liver remnant facilitating treatment planning and monitoring of patients after RE-induced hypertrophy induction. KEY POINTS: • Both MRI and HBS can assess liver function after RE. • Liver enhancement on MRI correlates with mebrofenin uptake on HBS. • MRI might be a convenient alternative for estimating future liver remnants after hypertrophy induction.

Plasma Markers for Therapy Response Monitoring in Patients with Neuroendocrine Tumors Undergoing Peptide Receptor Radionuclide Therapy.

BACKGROUND: Pretherapeutic chromogranin A, alkaline phosphatase (ALP), or De Ritis ratio (aspartate aminotransferase/alanine aminotransferase) are prognostic factors in patients with metastatic neuroendocrine tumors (NET) undergoing peptide receptor radionuclide therapy (PRRT). However, their value for intratherapeutic monitoring remains unclear. We evaluated if changes in plasma markers during PRRT can help identify patients with unfavorable outcomes. METHODS: A monocentric retrospective analysis of 141 patients with NET undergoing PRRT with [177Lu]Lu-DOTATOC was conducted. Changes in laboratory parameters were calculated by dividing the values determined immediately before each cycle of PRRT by the pretherapeutic value. Patients with low vs. high PFS were compared with the Wilcoxon rank-sum test. RESULTS: Progression, relapse, or death after PRRT was observed in 103/141 patients. Patients with low PFS showed a significant relative ALP increase before the third (p = 0.014) and fourth (p = 0.039) cycles of PRRT. Kaplan-Meier analysis revealed a median PFS of 24.3 months (95% CI, 20.7-27.8 months) in patients with decreasing ALP values (Δ > 10%) during treatment, 12.5 months (95% CI, 9.2-15.8 months) in patients with increasing ALP values (Δ > 10%), and 17.7 months (95% CI, 13.6-21.8 months) with stable ALP values (Δ ± 10%). CONCLUSIONS: Based on these exploratory data, a rise in plasma ALP might indicate disease progression and should be interpreted cautiously during therapy.

Metallacages with 2,6-dipicolinoylbis(N,N-dialkylthioureas) as novel platforms in nuclear medicine for 68Ga, 177Lu and 198Au.

BACKGROUND: Heterometallic gold metallacages are of great interest for the incorporation of several cations. Especially in nuclear medicine, those metallacages can serve as a platform for radionuclides relevant for imaging or therapy (e.g. 68Ga or 177Lu). Moreover, the radionuclide 198Au is an attractive beta emitter, for potential application in nuclear medicine. Here, we aim to synthesize a new set of gold metallacages and to study their ability to coordinate to 68Ga, 177Lu and 198Au. RESULTS: New heterometallic gold metallacages of composition [M{Au(Lmorph-κS)}3] (M = La3+, Tb3+, Lu3+ or Y3+) and [Ga{Au(Lmorph-κS)}2]NO3 have been synthesized from 2,6-dipicolinoylbis(N,N-morpholinylthiourea) (H2Lmorph) with [AuCl(THT)] and the target M3+ metal ions in yields ranging from 33 (Lu) to 62% (Tb). The characterization of the compounds bases on ESI-MS, 1H NMR, IR, EA and single-crystal X-ray diffraction techniques (all except the Ga derivative). Selected gold cages derived from H2Lmorph were compared to previously reported gold cages that were derived from 2,6-dipicolinoylbis(N,N-diethylthiourea) (H2Ldiethyl). The tested metallacages show similar IC50 values close to that of auranofin in four different cancer cell lines (MCF-7, PC-3, U383, U343), e.g. 4.5 ± 0.7 µM for [Ga{Au(Ldiethyl)}2]NO3 on PC-3. The radiolabeling experiments thereof show high radiochemical purities with 68Ga and 198Au and low radiochemical purity with 177Lu. CONCLUSIONS: The results indicate that these gold metallacages could serve as a novel platform for inclusion of different (radio)nuclides with potential theranostic applications in nuclear medicine.

Combination of tumor asphericity and an extracellular matrix-related prognostic gene signature in non-small cell lung cancer patients.

One important aim of precision oncology is a personalized treatment of patients. This can be achieved by various biomarkers, especially imaging parameters and gene expression signatures are commonly used. So far, combination approaches are sparse. The aim of the study was to independently validate the prognostic value of the novel positron emission tomography (PET) parameter tumor asphericity (ASP) in non small cell lung cancer (NSCLC) patients and to investigate associations between published gene expression profiles and ASP. This was a retrospective evaluation of PET imaging and gene expression data from three public databases and two institutional datasets. The whole cohort comprised 253 NSCLC patients, all treated with curative intent surgery. Clinical parameters, standard PET parameters and ASP were evaluated in all patients. Additional gene expression data were available for 120 patients. Univariate Cox regression and Kaplan-Meier analysis was performed for the primary endpoint progression-free survival (PFS) and additional endpoints. Furthermore, multivariate cox regression testing was performed including clinically significant parameters, ASP, and the extracellular matrix-related prognostic gene signature (EPPI). In the whole cohort, a significant association with PFS was observed for ASP (p < 0.001) and EPPI (p = 0.012). Upon multivariate testing, EPPI remained significantly associated with PFS (p = 0.018) in the subgroup of patients with additional gene expression data, while ASP was significantly associated with PFS in the whole cohort (p = 0.012). In stage II patients, ASP was significantly associated with PFS (p = 0.009), and a previously published cutoff value for ASP (19.5%) was successfully validated (p = 0.008). In patients with additional gene expression data, EPPI showed a significant association with PFS, too (p = 0.033). The exploratory combination of ASP and EPPI showed that the combinatory approach has potential to further improve patient stratification compared to the use of only one parameter. We report the first successful validation of EPPI and ASP in stage II NSCLC patients. The combination of both parameters seems to be a very promising approach for improvement of risk stratification in a group of patients with urgent need for a more personalized treatment approach.

Evaluation of the 177mLu-concentration in in-house produced 177Lu-radiopharmaceuticals and commercially available Lutathera®.

BACKGROUND: 177Lu-radiopharmaceuticals can contain the metastable impurity [177mLu]lutetium with a physical half-life of 160.4 days, in varying concentrations depending on the route of production of the radionuclidic precursor [177Lu]lutetium. Due to the long half-life of [177mLu]lutetium, difficulties with waste disposal or sterility testing could arise. Here, we analyzed several 177Lu-samples of different origins and suppliers regarding their 177mLu-concentration. RESULTS: All samples tested showed a 177mLu-concentration in the range that was stated on the certificate of analysis from the supplier which is in accordance with the European Pharmacopoeia. CONCLUSIONS: Although all 177mLu-concentrations were in accordance with the European Pharmacopoeia, we need to take into account the respective national legislation regarding radioactivity release limits. With regard to the German legislation, several probes for sterility testing in external laboratories could not be released for transport due to the concentration of [177mLu]lutetium. Moreover, waste water tanks should specifically be monitored for 177mLu-concentration, when e.g. Lutathera® is administered in the clinic.

Prognostic Value of the De Ritis Ratio for Overall Survival in Patients with Metastatic Castration-Resistant Prostate Cancer Undergoing [177Lu]Lu-PSMA-617 Radioligand Therapy.

The De Ritis ratio (=aspartate transaminase/alanine transaminase) has shown prognostic value in different cancer types. This is the first such analysis in prostate cancer patients undergoing radioligand therapy (RLT) with [177Lu]Lu-PSMA-617. This retrospective monocentric analysis included 91 patients with a median of 3 RLT cycles (range 1-6) and median cumulative activity of 17.3 GBq. Univariable Cox regression regarding overall survival (OS) included age, different types of previous treatment, metastatic patterns and different laboratory parameters before RLT. Based on multivariable Cox regression, a prognostic score was derived. Seventy-two patients (79%) died (median follow-up in survivors: 19.8 months). A higher number of previous chemotherapy lines, the presence of liver metastases, brain metastases, a higher tumor load on PSMA-PET, a higher prostate-specific antigen (PSA) level, lower red blood cell count, lower hemoglobin, higher neutrophil-lymphocyte ratio and higher De Ritis ratio were associated with shorter OS (each p < 0.05). In multivariable Cox, a higher number of chemotherapy lines (range, 0-2; p = 0.036), brain metastases (p < 0.001), higher PSA (p = 0.004) and higher De Ritis ratio before RLT (hazard ratio, 1.27 per unit increase; p = 0.023) remained significant. This prognostic score separated five groups with a significantly different median OS ranging from 4.9 to 28.1 months (log-rank test, p < 0.001). If validated independently, the De Ritis ratio could enhance multifactorial models for OS after RLT.

ChatGPT: Can You Prepare My Patients for [18F]FDG PET/CT and Explain My Reports?

We evaluated whether the artificial intelligence chatbot ChatGPT can adequately answer patient questions related to [18F]FDG PET/CT in common clinical indications before and after scanning. Methods: Thirteen questions regarding [18F]FDG PET/CT were submitted to ChatGPT. ChatGPT was also asked to explain 6 PET/CT reports (lung cancer, Hodgkin lymphoma) and answer 6 follow-up questions (e.g., on tumor stage or recommended treatment). To be rated "useful" or "appropriate," a response had to be adequate by the standards of the nuclear medicine staff. Inconsistency was assessed by regenerating responses. Results: Responses were rated "appropriate" for 92% of 25 tasks and "useful" for 96%. Considerable inconsistencies were found between regenerated responses for 16% of tasks. Responses to 83% of sensitive questions (e.g., staging/treatment options) were rated "empathetic." Conclusion: ChatGPT might adequately substitute for advice given to patients by nuclear medicine staff in the investigated settings. Improving the consistency of ChatGPT would further increase reliability.

Prognostic role of radiomics-based body composition analysis for the 1-year survival for hepatocellular carcinoma patients.

BACKGROUND: Parameters of body composition have prognostic potential in patients with oncologic diseases. The aim of the present study was to analyse the prognostic potential of radiomics-based parameters of the skeletal musculature and adipose tissues in patients with advanced hepatocellular carcinoma (HCC). METHODS: Radiomics features were extracted from a cohort of 297 HCC patients as post hoc sub-study of the SORAMIC randomized controlled trial. Patients were treated with selective internal radiation therapy (SIRT) in combination with sorafenib or with sorafenib alone yielding two groups: (1) sorafenib monotherapy (n = 147) and (2) sorafenib and SIRT (n = 150). The main outcome was 1-year survival. Segmentation of muscle tissue and adipose tissue was used to retrieve 881 features. Correlation analysis and feature cleansing yielded 292 features for each patient group and each tissue type. We combined 9 feature selection methods with 10 feature set compositions to build 90 feature sets. We used 11 classifiers to build 990 models. We subdivided the patient groups into a train and validation cohort and a test cohort, that is, one third of the patient groups. RESULTS: We used the train and validation set to identify the best feature selection and classification model and applied it to the test set for each patient group. Classification yields for patients who underwent sorafenib monotherapy an accuracy of 75.51% and area under the curve (AUC) of 0.7576 (95% confidence interval [CI]: 0.6376-0.8776). For patients who underwent treatment with SIRT and sorafenib, results are accuracy = 78.00% and AUC = 0.8032 (95% CI: 0.6930-0.9134). CONCLUSIONS: Parameters of radiomics-based analysis of the skeletal musculature and adipose tissue predict 1-year survival in patients with advanced HCC. The prognostic value of radiomics-based parameters was higher in patients who were treated with SIRT and sorafenib.

Cholecystitis induced by Yttrium-90 radioembolization of advanced liver tumors: prospective evaluation of a management algorithm in 197 consecutive patients.

BACKGROUND: Cholecystitis is a rare but dolorous complication after Y90-radioembolization of liver malignancies. PURPOSE: To decide the occlusion of the cystic artery (CA) to prevent cholecystitis after Y90 radioembolization using an algorithm. MATERIAL AND METHODS: In 130 patients, the gallbladder was at risk of embolization as the right liver lobe was targeted. Precautionary measures (e.g. coil occlusion of the cystic artery) were decided by enhancement of the gallbladder in pre-treatment Tc99m-MAA SPECT/CT and performed directly before Y90 radioembolization. In non-enhancing cases, the CA was left open. The outcome was determined by clinical symptoms of acute or chronic cholecystitis as well as imaging and laboratory parameters. Findings were additionally classified according to the Tokyo Guidelines of acute cholecystitis. RESULTS: Only 16 patients demonstrated enhancement of the gallbladder in Tc99m-MAA SPECT/CT. Including additional indications from angiographic findings, prophylactic measures were scheduled in 22 patients (standard of care). Thus, 121 patients were at risk of non-target embolization to the gallbladder during Y90 microsphere administration (investigative arm). Four cases (3.0%) of cholecystitis occurred by clinical presentation: two patients with onset of acute symptoms within 48 h after Y90 radioembolization ("embolic cholecystitis") and two patients with late onset of symptoms ("radiogenic cholecystitis"). The incidence of cholecystitis was not significantly more frequent without indication of precautionary measures (investigative cohort 2.9% vs. standard of care 4.7%; P = 0.53). CONCLUSION: The overall incidence of cholecystitis after Y90 radioembolization is low. Determination of cystic artery intervention using Tc99m-MAA SPECT/CT successfully balances the incidence of symptomatic cholecystitis with unnecessary vessel occlusion.

Sentinel lymph node biopsy in recurrent or secondary oral squamous cell carcinoma after previous neck dissection.

OBJECTIVES: The aim of this retrospective study was to evaluate the potential of sentinel lymph node biopsy (SLNB) in patients with recurrent or a secondary oral squamous cell carcinoma (OSCC) without clinical signs of lymph node metastases (cN0), who were previously treated with a surgical approach. PATIENTS AND METHODS: Retrospective analysis of all patients with cN0 recurrent or secondary OSCC, who were treated using SLNB after previous neck dissection. Endpoints were sentinel lymph node (SLN) detection rate, negative predictive value (NPV) and sensitivity. RESULTS: A total of 17 patients with a mean age of 68.6 years were included. SLN were detected in 15 of 17 cases (detection rate: 88.2%). In seven patients (41.2%), a bilateral or contralateral lymph drainage of a unilateral carcinoma was found. Two patients (11.8%) demonstrated a positive SLN upon pathohistological analysis, which led to an upstaging. In one case, a non-SLN was positive, which is considered a false-negative result. The mean follow-up for all patients with histologically negative SLN including the patients without a detected SLN was 11.8 months (range: 0-31 months). Of these, one patient developed (isolated) neck recurrence after 12 months resulting in an overall NPV of 86.7% and a sensitivity of 50.0% for the SLNB as a neck staging procedure. CONCLUSION: SLNB can improve the staging of patients with recurrent or secondary OSCC, who present with a history of a previous neck dissection. Further studies are required to demonstrate the oncological benefit of SLNB in this patient cohort.

Optimization of 177Lu-labelling of DOTA-TOC, PSMA-I&T and FAPI-46 for clinical application.

BACKGROUND: 177Lu-radiopharmaceuticals are routinely used for the treatment of various tumor entities. The productions of radiopharmaceuticals follow strict good-manufacturing practice guidelines and synthesis optimizations thereof have a strong impact on e.g. the quality of the product, radiation safety and costs. The purpose of this study is to optimize the precursor load of three radiopharmaceuticals. For that, different precursor loads were evaluated and compared to previously reported findings. RESULTS: All three radiopharmaceuticals were successfully synthesized in high radiochemical purities and yields on the ML Eazy. The precursor load was optimized for [177Lu]Lu-FAPI-46 from 27.0 to 9.7 µg/GBq, for [177Lu]Lu-DOTATOC from 11 to 10 µg/GBq and for [177Lu]Lu-PSMA-I&T from 16.3 to 11.6 µg/GBq. CONCLUSIONS: We successfully reduced the precursor load for all three radiopharmaceuticals while maintaining their quality.

Impact of body composition in advanced hepatocellular carcinoma: A subanalysis of the SORAMIC trial.

BACKGROUND: Body composition parameters have been reported to be prognostic factors in patients with oncologic diseases. However, the available data on patients with HCC are conflicting. The aim of this study was to assess the impact of body composition on survival in patients with HCC treated with sorafenib or selective internal radioembolization (SIRT) and sorafenib. METHODS: This is an exploratory subanalysis of the prospective, randomized controlled SORAMIC trial. Within the palliative arm of the study, patients were selected if a baseline abdominal CT was available. A broad set of skeletal muscle and adipose tissue parameters were measured at the L3 level. Low skeletal muscle mass (LSMM) and density parameters were defined using published cutoffs. The parameters were correlated with overall survival. RESULTS: Of 424 patients in the palliative study arm, 369 patients were included in the analysis. There were 192 patients in the combined sorafenib/SIRT and 177 patients in the sorafenib group. Median overall survival was 9.9 months for the entire cohort and 10.8 and 9.2 months for the SIRT/sorafenib and sorafenib groups, respectively. There was no relevant association of either body composition parameter with overall survival in either the overall cohort or in the SIRT/sorafenib or sorafenib subgroups. CONCLUSIONS: This subanalysis of the prospective SORAMIC trial does not suggest a relevant influence of body composition parameters of survival in patients with advanced HCC. Body composition parameters therefore do not serve in patient allocation in this palliative treatment cohort.

[177Lu]Lu-PSMA Therapy as an Individual Treatment Approach for Patients with High-Grade Glioma: Dosimetry Results and Critical Statement.

The theranostic use of prostate-specific membrane antigen (PSMA) appears to be promising in patients with high-grade glioma. This study investigated [177Lu]Lu-PSMA therapy as an individual treatment approach with a focus on intratherapeutic dosimetry. Methods: Three patients were treated with a median of 6.03 GBq (interquartile range [IQR], 5.74-6.10) of [177Lu]Lu-PSMA. Intratherapeutic dosimetry was performed using a hybrid scenario with planar whole-body scintigraphy at 2, 24, and 48 h after treatment injection and SPECT/CT at 48 h after injection. Additive whole-body scintigraphy at 8 d after injection was performed on 1 patient. Results: The median doses were 0.56 Gy (IQR, 0.36-1.25 Gy) to tumor, 0.27 Gy (IQR, 0.16-0.57 Gy) to risk organs, 2.13 Gy (IQR, 1.55-2.89 Gy) to kidneys, and 0.76 Gy (IQR, 0.70-1.20 Gy) to salivary glands. Whole-body exposure was 0.11 Gy (IQR, 0.06-0.18 Gy). Conclusion: Because the intratherapeutic tumor dose is lower than that used in external radiation oncology, the effectiveness of treatment is questionable.

Altered limbic functional connectivity in individuals with subjective cognitive decline: Converging and diverging findings across Chinese and German cohorts.

INTRODUCTION: It remains unclear whether functional brain networks are consistently altered in individuals with subjective cognitive decline (SCD) of diverse ethnic and cultural backgrounds and whether the network alterations are associated with an amyloid burden. METHODS: Cross-sectional resting-state functional magnetic resonance imaging connectivity (FC) and amyloid-positron emission tomography (PET) data from the Chinese Sino Longitudinal Study on Cognitive Decline and German DZNE Longitudinal Cognitive Impairment and Dementia cohorts were analyzed. RESULTS: Limbic FC, particularly hippocampal connectivity with right insula, was consistently higher in SCD than in controls, and correlated with SCD-plus features. Smaller SCD subcohorts with PET showed inconsistent amyloid positivity rates and FC-amyloid associations across cohorts. DISCUSSION: Our results suggest an early adaptation of the limbic network in SCD, which may reflect increased awareness of cognitive decline, irrespective of amyloid pathology. Different amyloid positivity rates may indicate a heterogeneous underlying etiology in Eastern and Western SCD cohorts when applying current research criteria. Future studies should identify culture-specific features to enrich preclinical Alzheimer's disease in non-Western populations. HIGHLIGHTS: Common limbic hyperconnectivity across Chinese and German subjective cognitive decline (SCD) cohorts was observed. Limbic hyperconnectivity may reflect awareness of cognition, irrespective of amyloid load. Further cross-cultural harmonization of SCD regarding Alzheimer's disease pathology is required.

Same same but different: dopamine transporter SPECT on scanners with CZT vs. NaI detectors.

BACKGROUND: The aims of this study were to establish a normal database (NDB) for semiquantification of dopamine transporter (DAT) single-photon emission computed tomography (SPECT) with [123I]FP-CIT on a cadmium zinc telluride (CZT) camera, test the preexisting NaI-derived NDB for use in CZT scans, and compare the diagnostic findings in subjects imaged with a CZT scanner with either the preexisting NaI-based NDB or our newly defined CZT NDB. METHODS: The sample comprised 73 subjects with clinically uncertain parkinsonian syndrome (PS) who prospectively underwent [123I]FP-CIT SPECT on a CZT camera according to standard guidelines with identical acquisition and reconstruction protocols (DaTQUANT). Two experienced readers visually assessed the images and binarized the subjects into "non-neurodegenerative PS" and "neurodegenerative PS". Twenty-five subjects from the "non-neurodegenerative PS" subgroup were randomly selected to establish a CZT NDB. The remaining 48 subjects were defined as "test group". DaTQUANT was used to determine the specific binding ratio (SBR). For the test group, SBR values were transformed to z-scores for the putamen utilizing both the CZT NDB and the manufacturer-provided NaI-based NDB (GE NDB). A predefined fixed cut-off of -2 was used for dichotomization of z-scores to classify neurodegenerative and non-neurodegenerative PS. Performance of semiquantification using the two NDB to identify subjects with neurodegenerative PS was assessed in comparison with the visual rating. Furthermore, a randomized head-to-head comparison of both detector systems was performed semiquantitatively in a subset of 32 out of all 73 subjects. RESULTS: Compared to the visual rating as reference, semiquantification based on the dedicated CZT NDB led to fewer discordant ratings than the GE NDB in CZT scans (3 vs. 8 out of 48 subjects). This can be attributed to the putaminal z-scores being consistently higher with the GE NDB on a CZT camera (median absolute difference of 1.68), suggesting an optimal cut-off of -0.5 for the GE NDB instead of -2.0. Average binding ratios and z-scores were significantly lower in CZT compared to NaI data. CONCLUSIONS: Use of a dedicated, CZT-derived NDB is recommended in [123I]FP-CIT SPECT with a CZT camera since it improves agreement between semiquantification and visual assessment.

A machine learning tool to improve prediction of mediastinal lymph node metastases in non-small cell lung cancer using routinely obtainable [18F]FDG-PET/CT parameters.

BACKGROUND: In patients with non-small cell lung cancer (NSCLC), accuracy of [18F]FDG-PET/CT for pretherapeutic lymph node (LN) staging is limited by false positive findings. Our aim was to evaluate machine learning with routinely obtainable variables to improve accuracy over standard visual image assessment. METHODS: Monocentric retrospective analysis of pretherapeutic [18F]FDG-PET/CT in 491 consecutive patients with NSCLC using an analog PET/CT scanner (training + test cohort, n = 385) or digital scanner (validation, n = 106). Forty clinical variables, tumor characteristics, and image variables (e.g., primary tumor and LN SUVmax and size) were collected. Different combinations of machine learning methods for feature selection and classification of N0/1 vs. N2/3 disease were compared. Ten-fold nested cross-validation was used to derive the mean area under the ROC curve of the ten test folds ("test AUC") and AUC in the validation cohort. Reference standard was the final N stage from interdisciplinary consensus (histological results for N2/3 LNs in 96%). RESULTS: N2/3 disease was present in 190 patients (39%; training + test, 37%; validation, 46%; p = 0.09). A gradient boosting classifier (GBM) with 10 features was selected as the final model based on test AUC of 0.91 (95% confidence interval, 0.87-0.94). Validation AUC was 0.94 (0.89-0.98). At a target sensitivity of approx. 90%, test/validation accuracy of the GBM was 0.78/0.87. This was significantly higher than the accuracy based on "mediastinal LN uptake > mediastinum" (0.7/0.75; each p < 0.05) or combined PET/CT criteria (PET positive and/or LN short axis diameter > 10 mm; 0.68/0.75; each p < 0.001). Harmonization of PET images between the two scanners affected SUVmax and visual assessment of the LNs but did not diminish the AUC of the GBM. CONCLUSIONS: A machine learning model based on routinely available variables from [18F]FDG-PET/CT improved accuracy in mediastinal LN staging compared to established visual assessment criteria. A web application implementing this model was made available.

Performance of Deauville Criteria in [18F]FDG-PET/CT Diagnostics of Giant Cell Arteritis.

In this retrospective study, PET/CT data from 59 patients with suspected giant cell arteritis (GCA) were reviewed using the Deauville criteria to determine an optimal cut-off between PET positivity and negativity. Seventeen standardised vascular regions were analysed per patient by three investigators blinded to clinical information. Statistical analysis included ROC curves with areas under the curve (AUC), Cohen's and Fleiss' kappa (κ) to calculate sensitivity, specificity, accuracy, and agreement. According to final clinician's diagnosis and the revised 2017 ACR criteria GCA was confirmed in 29 of 59 (49.2 %) patients. With a diagnostic cut-off ≥ 4 (highest tracer uptake of a vessel wall exceeds liver uptake) for PET positivity, all investigators achieved high accuracy (range, 89.8-93.2%) and AUC (range, 0.94-0.97). Sensitivity and specificity ranged from 89.7-96.6% and 83.3-96.7%, respectively. Agreement between the three investigators suggested 'almost perfect agreement' (Fleiss' κ = 0.84) A Deauville score of ≥4 as threshold for PET positivity yielded excellent results with high accuracy and almost perfect inter-rater agreement, suggesting a standardized, reproducible, and reliable score in diagnosing GCA. However, the small sample size and reference standard could lead to biases. Therefore, verification in a multicentre study with a larger patient cohort and prospective setting is needed.

MR Imaging Volumetric Response after Yttrium-90 Radioembolization for Colorectal Liver Metastases: Predictability at Baseline and Correlation with Survival.

PURPOSE: To prove the utility of magnetic resonance (MR) imaging response as a surrogate end point of treatment efficacy and survival after yttrium-90 transarterial radioembolization (TARE) for colorectal liver metastases (CRLMs), and to investigate whether outcomes can be predicted at baseline using MR imaging or clinical variables. MATERIALS AND METHODS: A total of 50 (135) patients with TARE for CRLMs between August 2008 and January 2020 and peri-interventional MR imaging within defined timeframes were included for tumor segmentation. Pretreatment and posttreatment target tumor volumes were measured according to the volumetric Response Evaluation Criteria In Solid Tumors (vRECIST) and the quantitative European Association for the Study of the Liver (qEASL) criteria. Cox regression models were used to analyze the impact of MR morphologic response, vascularity at baseline, and clinical variables on patient survival. Logistic regression analyses were used to evaluate the predictors of MR morphologic response at baseline. RESULTS: The median survival was 337 days (95% confidence interval [CI], 243-431). As opposed to the vRECIST, the application of the qEASL criteria 3 months after the treatment allowed for a significant (P < .05) separation of the survival curves for partial response, stable disease, and progressive disease with a median survival of 412 days (95% CI, 57-767) in responders. High tumor burden and technetium-99m lung shunt significantly decreased the probability of survival. MR morphologic response was not predictable at baseline using imaging or clinical data. CONCLUSIONS: MR response according to the qEASL criteria outperformed the vRECIST in measuring the biologic impact of TARE and predicting patient survival. Baseline contrast enhancement did not predict MR response to treatment, which may reflect elevated dose requirements in tumors with a high proportion of viable tumor volume.

Transarterial Yttrium-90 Radioembolization in Intrahepatic Cholangiocarcinoma Patients: Outcome Assessment Applying a Prognostic Score.

Radioembolization (RE) is a viable therapy option in patients with intrahepatic cholangiocarcinoma (ICC). This study delineates a prognostic score regarding overall survival (OS) after RE using routine pre-therapeutic parameters. A retrospective analysis of 39 patients (median age, 61 [range, 32−82] years; 26 females, 13 males) with ICC and 42 RE procedures was conducted. Cox regression for OS included age, ECOG, hepatic and extrahepatic tumor burden, thrombosis of the portal vein, ascites, laboratory parameters and dose reduction due to hepatopulmonary shunt. Median OS after RE was 8.0 months. Using univariable Cox, ECOG ≥ 1 (hazard ratio [HR], 3.8), AST/ALT quotient (HR, 1.86), high GGT (HR, 1.002), high CA19-9 (HR, 1.00) and dose reduction of 40% (HR, 3.8) predicted shorter OS (each p < 0.05). High albumin predicted longer OS (HR, 0.927; p = 0.045). Multivariable Cox confirmed GGT ≥ 750 [U/L] (HR, 7.84; p < 0.001), ECOG > 1 (HR, 3.76; p = 0.021), albumin ≤ 41.1 [g/L] (HR, 3.02; p = 0.006) as a three-point pre-therapeutic prognostic score. More specifically, median OS decreased from 15.3 months (0 risk factors) to 7.6 months (1 factor) or 1.8 months (≥2 factors; p < 0.001). The proposed score may aid in improved pre-therapeutic patient identification with (un-)favorable OS after RE and facilitate the balance between potential life prolongation and overaggressive patient selection.