Prediction of therapy response of breast cancer patients with machine learning based on clinical data and imaging data derived from breast [18F]FDG-PET/MRI.

PURPOSE: To evaluate if a machine learning prediction model based on clinical and easily assessable imaging features derived from baseline breast [18F]FDG-PET/MRI staging can predict pathologic complete response (pCR) in patients with newly diagnosed breast cancer prior to neoadjuvant system therapy (NAST). METHODS: Altogether 143 women with newly diagnosed breast cancer (54 ± 12 years) were retrospectively enrolled. All women underwent a breast [18F]FDG-PET/MRI, a histopathological workup of their breast cancer lesions and evaluation of clinical data. Fifty-six features derived from positron emission tomography (PET), magnetic resonance imaging (MRI), sociodemographic / anthropometric, histopathologic as well as clinical data were generated and used as input for an extreme Gradient Boosting model (XGBoost) to predict pCR. The model was evaluated in a five-fold nested-cross-validation incorporating independent hyper-parameter tuning within the inner loops to reduce the risk of overoptimistic estimations. Diagnostic model-performance was assessed by determining the area under the curve of the receiver operating characteristics curve (ROC-AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. Furthermore, feature importances of the XGBoost model were evaluated to assess which features contributed most to distinguish between pCR and non-pCR. RESULTS: Nested-cross-validation yielded a mean ROC-AUC of 80.4 ± 6.0% for prediction of pCR. Mean sensitivity, specificity, PPV, and NPV of 54.5 ± 21.3%, 83.6 ± 4.2%, 63.6 ± 8.5%, and 77.6 ± 8.1% could be achieved. Histopathological data were the most important features for classification of the XGBoost model followed by PET, MRI, and sociodemographic/anthropometric features. CONCLUSION: The evaluated multi-source XGBoost model shows promising results for reliably predicting pathological complete response in breast cancer patients prior to NAST. However, yielded performance is yet insufficient to be implemented in the clinical decision-making process.

Deep learning-based scan range optimization can reduce radiation exposure in coronary CT angiography.

OBJECTIVES: Cardiac computed tomography (CT) is essential in diagnosing coronary heart disease. However, a disadvantage is the associated radiation exposure to the patient which depends in part on the scan range. This study aimed to develop a deep neural network to optimize the delimitation of scan ranges in CT localizers to reduce the radiation dose. METHODS: On a retrospective training cohort of 1507 CT localizers randomly selected from calcium scoring and angiography scans and acquired between 2010 and 2017, optimized scan ranges were delimited by two radiologists in consensus. A neural network was trained to reproduce the scan ranges and was tested on two randomly selected and independent validation cohorts: an internal cohort of 233 CT localizers (January 2018-June 2020) and an external cohort from a nearby hospital of 298 CT localizers (July 2020-December 2020). Localizers where a bypass surgery was visible were excluded. The effective radiation dose to the patient was simulated using a Monte Carlo simulation. Scan ranges of radiographers, radiologists, and the network were compared using an equivalence test; likewise, the reduction in effective dose was tested using a superior test. RESULTS: The network replicated the radiologists' scan ranges with a Dice score of 96.5 ± 0.02 (p < 0.001, indicating equivalence). The generated scan ranges resulted in an effective dose reduction of 10.0% (p = 0.002) in the internal cohort and 12.6% (p < 0.001) in the external cohort compared to the scan ranges delimited by radiographers in clinical routine. CONCLUSIONS: Automatic delimitation of the scan range can result in a radiation dose reduction to the patient. CLINICAL RELEVANCE STATEMENT: Fully automated delimitation of the scan range using a deep neural network enables a significant reduction in radiation exposure during CT coronary angiography compared to manual examination planning. It can also reduce the workload of the radiographers. KEY POINTS: • Scan range delimitation for coronary computed tomography angiography could be performed with high accuracy by a deep neural network. • Automated scan ranges showed a high agreement of 96.5% with the scan ranges of radiologists. • Using a Monte Carlo simulation, automated scan ranges reduced the effective dose to the patient by up to 12.6% (0.9 mSv) compared to the scan ranges of radiographers in clinical routine.

Designing clinical trials based on modern imaging and metastasis-directed treatments in patients with oligometastatic breast cancer: a consensus recommendation from the EORTC Imaging and Breast Cancer Groups.

Breast cancer remains the most common cause of cancer death among women. Despite its considerable histological and molecular heterogeneity, those characteristics are not distinguished in most definitions of oligometastatic disease and clinical trials of oligometastatic breast cancer. After an exhaustive review of the literature covering all aspects of oligometastatic breast cancer, 35 experts from the European Organisation for Research and Treatment of Cancer Imaging and Breast Cancer Groups elaborated a Delphi questionnaire aimed at offering consensus recommendations, including oligometastatic breast cancer definition, optimal diagnostic pathways, and clinical trials required to evaluate the effect of diagnostic imaging strategies and metastasis-directed therapies. The main recommendations are the introduction of modern imaging methods in metastatic screening for an earlier diagnosis of oligometastatic breast cancer and the development of prospective trials also considering the histological and molecular complexity of breast cancer. Strategies for the randomisation of imaging methods and therapeutic approaches in different subsets of patients are also addressed.

International EANM-SNMMI-ISMRM consensus recommendation for PET/MRI in oncology.

PREAMBLE: The Society of Nuclear Medicine and Molecular Imaging (SNMMI) is an international scientific and professional organization founded in 1954 to promote the science, technology, and practical application of nuclear medicine. The European Association of Nuclear Medicine (EANM) is a professional non-profit medical association that facilitates communication worldwide between individuals pursuing clinical and research excellence in nuclear medicine. The EANM was founded in 1985. The merged International Society for Magnetic Resonance in Medicine (ISMRM) is an international, nonprofit, scientific association whose purpose is to promote communication, research, development, and applications in the field of magnetic resonance in medicine and biology and other related topics and to develop and provide channels and facilities for continuing education in the field.The ISMRM was founded in 1994 through the merger of the Society of Magnetic Resonance in Medicine and the Society of Magnetic Resonance Imaging. SNMMI, ISMRM, and EANM members are physicians, technologists, and scientists specializing in the research and practice of nuclear medicine and/or magnetic resonance imaging. The SNMMI, ISMRM, and EANM will periodically define new guidelines for nuclear medicine practice to help advance the science of nuclear medicine and/or magnetic resonance imaging and to improve the quality of service to patients throughout the world. Existing practice guidelines will be reviewed for revision or renewal, as appropriate, on their fifth anniversary or sooner, if indicated. Each practice guideline, representing a policy statement by the SNMMI/EANM/ISMRM, has undergone a thorough consensus process in which it has been subjected to extensive review. The SNMMI, ISMRM, and EANM recognize that the safe and effective use of diagnostic nuclear medicine imaging and magnetic resonance imaging requires specific training, skills, and techniques, as described in each document. Reproduction or modification of the published practice guideline by those entities not providing these services is not authorized. These guidelines are an educational tool designed to assist practitioners in providing appropriate care for patients. They are not inflexible rules or requirements of practice and are not intended, nor should they be used, to establish a legal standard of care. For these reasons and those set forth below, the SNMMI, the ISMRM, and the EANM caution against the use of these guidelines in litigation in which the clinical decisions of a practitioner are called into question. The ultimate judgment regarding the propriety of any specific procedure or course of action must be made by the physician or medical physicist in light of all the circumstances presented. Thus, there is no implication that an approach differing from the guidelines, standing alone, is below the standard of care. To the contrary, a conscientious practitioner may responsibly adopt a course of action different from that set forth in the guidelines when, in the reasonable judgment of the practitioner, such course of action is indicated by the condition of the patient, limitations of available resources, or advances in knowledge or technology subsequent to publication of the guidelines. The practice of medicine includes both the art and the science of the prevention, diagnosis, alleviation, and treatment of disease. The variety and complexity of human conditions make it impossible to always reach the most appropriate diagnosis or to predict with certainty a particular response to treatment. Therefore, it should be recognized that adherence to these guidelines will not ensure an accurate diagnosis or a successful outcome. All that should be expected is that the practitioner will follow a reasonable course of action based on current knowledge, available resources, and the needs of the patient to deliver effective and safe medical care. The sole purpose of these guidelines is to assist practitioners in achieving this objective.

[18F]FDG PET/MRI in children suffering from lymphoma: does MRI contrast media make a difference?

OBJECTIVES: Evaluate the influence of an MRI contrast agent application on primary and follow-up staging in pediatric patients with newly diagnosed lymphoma using [18F]FDG PET/MRI to avoid adverse effects and save time and costs during examination. METHODS: A total of 105 [18F]FDG PET/MRI datasets were included for data evaluation. Two different reading protocols were analyzed by two experienced readers in consensus, including for PET/MRI-1 reading protocol unenhanced T2w and/or T1w imaging, diffusion-weighted imaging (DWI), and [18F]FDG PET imaging and for PET/MRI-2 reading protocol an additional T1w post contrast imaging. Patient-based and region-based evaluation according to the revised International Pediatric Non-Hodgkin's Lymphoma (NHL) Staging System (IPNHLSS) was performed, and a modified standard of reference was applied comprising histopathology and previous and follow-up cross-sectional imaging. Differences in staging accuracy were assessed using the Wilcoxon and McNemar tests. RESULTS: In patient-based analysis, PET/MRI-1 and PET/MRI-2 both determined a correct IPNHLSS tumor stage in 90/105 (86%) exams. Region-based analysis correctly identified 119/127 (94%) lymphoma-affected regions. Sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy for PET/MRI-1 and PET/MRI-2 were 94%, 97%, 90%, 99%, 97%, respectively. There were no significant differences between PET/MRI-1 and PET/MRI-2. CONCLUSIONS: The use of MRI contrast agents in [18F]FDG PET/MRI examinations has no beneficial effect in primary and follow-up staging of pediatric lymphoma patients. Therefore, switching to a contrast agent-free [18F]FDG PET/MRI protocol should be considered in all pediatric lymphoma patients. CLINICAL RELEVANCE STATEMENT: This study gives a scientific baseline switching to a contrast agent-free [18F]FDG PET/MRI staging in pediatric lymphoma patients. This could avoid side effects of contrast agents and saves time and costs by a faster staging protocol for pediatric patients. KEY POINTS: • No additional diagnostic benefit of MRI contrast agents at [18F]FDG PET/MRI examinations of pediatric lymphoma primary and follow-up staging • Highly accurate primary and follow-up staging of pediatric lymphoma patients at MRI contrast-free [18F]FDG PET/MRI.

Towards a fast PET/MRI protocol for breast cancer imaging: maintaining diagnostic confidence while reducing PET and MRI acquisition times.

OBJECTIVES: To investigate the diagnostic feasibility of a shortened breast PET/MRI protocol in breast cancer patients. METHODS: Altogether 90 women with newly diagnosed T1tumor-staged (T1ts) and T2tumor-staged (T2ts) breast cancer were included in this retrospective study. All underwent a dedicated comprehensive breast [18F]FDG-PET/MRI. List-mode PET data were retrospectively reconstructed with 20, 15, 10, and 5 min for each patient to simulate the effect of reduced PET acquisition times. The SUVmax/mean of all malign breast lesions was measured. Furthermore, breast PET data reconstructions were analyzed regarding image quality, lesion detectability, signal-to-noise ratio (SNR), and image noise (IN). The simultaneously acquired comprehensive MRI protocol was then shortened by retrospectively removing sequences from the protocol. Differences in malignant breast lesion detectability between the original and the fast breast MRI protocol were evaluated lesion-based. The 20-min PET reconstructions and the original MRI protocol served as reference. RESULTS: In all PET reconstructions, 127 congruent breast lesions could be detected. Group comparison and T1ts vs. T2ts subgroup comparison revealed no significant difference of subjective image quality between 20, 15, 10, and 5 min acquisition times. SNR of qualitative image evaluation revealed no significant difference between different PET acquisition times. A slight but significant increase of IN with decreasing PET acquisition times could be detected. Lesion SUVmax group comparison between all PET acquisition times revealed no significant differences. Lesion-based evaluation revealed no significant difference in breast lesion detectability between original and fast breast MRI protocols. CONCLUSIONS: Breast [18F]FDG-PET/MRI protocols can be shortened from 20 to below 10 min without losing essential diagnostic information. KEY POINTS: • A highly accurate breast cancer evaluation is possible by the shortened breast [18F]FDG-PET/MRI examination protocol. • Significant time saving at breast [18F]FDG-PET/MRI protocol could increase patient satisfaction and patient throughput for breast cancer patients at PET/MRI.

Recurrent prostate cancer: combined role for MRI and PSMA-PET in 68Ga-PSMA-11 PET/MRI.

OBJECTIVES: To investigate the specific strengths of MRI and PET components in 68Ga-PSMA-11 PET/MRI for staging of patients with biochemically recurrent prostate cancer (PCa). METHODS: Patients with biochemical recurrence of PCa and contrast-enhanced whole-body 68Ga-PSMA-11 PET/MRI including a dedicated pelvic multiparametric MRI were included in this retrospective study. Imaging datasets of MRI and PET were evaluated separately regarding local PCa recurrence (Tr), pelvic lymph node metastases (N1), distant lymph node metastases (M1a), bone metastases (M1b), and soft tissue metastases (M1c) according to PROMISE version 1. Data evaluation was performed patient- and region-/lesion-based. Cox regression revealed a PSA of 1.69 ng/mL as a cut-off for subgroup analysis. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were evaluated for each image component. Differences in staging accuracy were assessed using the Wilcoxon and McNemar test. RESULTS: Altogether 102 patients (mean aged 68 ± 8 years, median PSA 1.33 ng/mL) were included. PCa was found in 70/102 (68%) patients. Accuracy of MRI in the detection of Tr, N1, M + , M1a, and M1b was 100%, 79%, 90%, 97%, and 95% for PSA < 1.69 ng/mL and 100%, 87%, 87%, 91%, and 96% for PSA > 1.69 ng/mL. Accuracy of 68Ga-PSMA-11 PET was 93%, 97%, 93%, 98%, and 100% for PSA < 1.69 ng/mL and 87%, 91%, 96%, 100%, and 96% for PSA > 1.69 ng/mL. CONCLUSIONS: Combined assessment of 68Ga-PSMA-11 PET/MRI improves tumor localization in men with biochemical recurrence. The MRI detected local recurrence of PCa more often whereas 68 Ga-PSMA-11 PET detected lymph node metastases more often, especially for PSA < 1.69 ng/mL. CLINICAL RELEVANCE STATEMENT: This study gives a scientific baseline to improve the understanding and reading of 68Ga-PSMA-11 PET/MRI imaging in patients with biochemically recurrent PCa by showing the specific strength of each imaging component. KEY POINTS: • Combining the individual modality strengths of 68Ga-PSMA-11 PET/MRI improves tumor localization in men with biochemical recurrence of prostate cancer. • MRI component of 68 Ga-PSMA-11 PET/MRI shows its strength in detecting local recurrence of prostate cancer, especially at PSA < 1.69 ng/mL. • 68 Ga-PSMA-11 PET component shows its strength in detecting local and distant lymph node metastases, especially at PSA < 1.69 ng/mL.

Simultaneous multislice diffusion-weighted imaging versus standard diffusion-weighted imaging in whole-body PET/MRI.

OBJECTIVE: To compare standard (STD-DWI) single-shot echo-planar imaging DWI and simultaneous multislice (SMS) DWI during whole-body positron emission tomography (PET)/MRI regarding acquisition time, image quality, and lesion detection. METHODS: Eighty-three adults (47 females, 57%), median age of 64 years (IQR 52-71), were prospectively enrolled from August 2018 to March 2020. Inclusion criteria were (a) abdominal or pelvic tumors and (b) PET/MRI referral from a clinician. Patients were excluded if whole-body acquisition of STD-DWI and SMS-DWI sequences was not completed. The evaluated sequences were axial STD-DWI at b-values 50-400-800 s/mm2 and the apparent diffusion coefficient (ADC), and axial SMS-DWI at b-values 50-300-800 s/mm2 and ADC, acquired with a 3-T PET/MRI scanner. Three radiologists rated each sequence's quality on a five-point scale. Lesion detection was quantified using the anatomic MRI sequences and PET as the reference standard. Regression models were constructed to quantify the association between all imaging outcomes/scores and sequence type. RESULTS: The median whole-body STD-DWI acquisition time was 14.8 min (IQR 14.1-16.0) versus 7.0 min (IQR 6.7-7.2) for whole-body SMS-DWI, p < 0.001. SMS-DWI image quality scores were higher than STD-DWI in the abdomen (OR 5.31, 95% CI 2.76-10.22, p < 0.001), but lower in the cervicothoracic junction (OR 0.21, 95% CI 0.10-0.43, p < 0.001). There was no significant difference in the chest, mediastinum, pelvis, and rectum. STD-DWI detected 276/352 (78%) lesions while SMS-DWI located 296/352 (84%, OR 1.46, 95% CI 1.02-2.07, p = 0.038). CONCLUSIONS: In cancer staging and restaging, SMS-DWI abbreviates acquisition while maintaining or improving the diagnostic yield in most anatomic regions. KEY POINTS: • Simultaneous multislice diffusion-weighted imaging enables faster whole-body image acquisition. • Simultaneous multislice diffusion-weighted imaging maintains or improves image quality when compared to single-shot echo-planar diffusion-weighted imaging in most anatomical regions. • Simultaneous multislice diffusion-weighted imaging leads to superior lesion detection.

Targeting early stages of cardiotoxicity from anti-PD1 immune checkpoint inhibitor therapy.

AIMS: Cardiac immune-related adverse events (irAEs) from immune checkpoint inhibition (ICI) targeting programmed death 1 (PD1) are of growing concern. Once cardiac irAEs become clinically manifest, fatality rates are high. Cardio-oncology aims to prevent detrimental effects before manifestation of severe complications by targeting early pathological changes. We therefore aimed to investigate early consequences of PD1 inhibition for cardiac integrity to prevent the development of overt cardiac disease. METHODS AND RESULTS: We investigated cardiac-specific consequences from anti-PD1 therapy in a combined biochemical and in vivo phenotyping approach. Mouse hearts showed broad expression of the ligand PDL1 on cardiac endothelial cells as a main mediator of immune-crosstalk. Using a novel melanoma mouse model, we assessed that anti-PD1 therapy promoted myocardial infiltration with CD4+ and CD8+ T cells, the latter being markedly activated. Left ventricular (LV) function was impaired during pharmacological stress, as shown by pressure-volume catheterization. This was associated with a dysregulated myocardial metabolism, including the proteome and the lipidome. Analogous to the experimental approach, in patients with metastatic melanoma (n = 7) receiving anti-PD1 therapy, LV function in response to stress was impaired under therapy. Finally, we identified that blockade of tumour necrosis factor alpha (TNFα) preserved LV function without attenuating the anti-cancer efficacy of anti-PD1 therapy. CONCLUSIONS: Anti-PD1 therapy induces a disruption of cardiac immune homeostasis leading to early impairment of myocardial functional integrity, with potential prognostic effects on the growing number of treated patients. Blockade of TNFα may serve as an approach to prevent the manifestation of ICI-related cardiotoxicity.

First experiences with dynamic renal [68Ga]Ga-DOTA PET/CT: a comparison to renal scintigraphy and compartmental modelling to non-invasively estimate the glomerular filtration rate.

PURPOSE: The determination of the glomerular filtration rate (GFR) is decisive for a variety of clinical issues, for example, to monitor the renal function in radionuclide therapy patients. Renal scintigraphy using glomerularly filtered tracers allows combined acquisition of renograms and GFR estimation but requires repeated blood sampling for several hours. In contrast, dynamic PET imaging using the glomerularly filtered tracer [68Ga]Ga-DOTA bears the potential to non-invasively estimate the GFR by compartmental kinetic modelling. Here, we report the, to our knowledge, first comparison of human renal dynamic [68Ga]Ga-DOTA PET imaging in comparison to renal scintigraphy and compare PET-derived to serum creatinine-derived GFR measurements. METHODS: Dynamic [68Ga]Ga-DOTA PET data were acquired for 30 min immediately after tracer injection in 12 patients. PET and renal scintigraphy images were visually interpreted in a consensus read by three nuclear medicine physicians. The functional renal cortex was segmented to obtain time-activity curves. The arterial input function was estimated from the PET signal in the abdominal aorta. Single-compartmental tracer kinetic modelling was performed to calculate the GFR using complete 30-min (GFRPET-30) and reduced 15-min PET data sets (GFRPET-15) to evaluate whether a shorter acquisition time is sufficient for an accurate GFR estimation. A modified approach excluding minutes 2 to 10 was applied to reduce urinary spill-over effects. Serum creatinine-derived GFRCKD (CKD-EPI-formula) was used as reference standard. RESULTS: PET image interpretation revealed the same findings as conventional scintigraphy (2/12 patients with both- and 1/12 patients with right-sided urinary obstruction). Model fit functions were substantially improved for the modified approach to exclude spill-over. Depending on the modelling approach, GFRCKD and both GFRPET-30 and GFRPET-15 were well correlated with interclass correlation coefficients (ICCs) from 0.74 to 0.80 and Pearson's correlation coefficients (PCCs) from 0.74 to 0.81. For a subgroup of patients with undisturbed urinary efflux (n = 9), correlations were good to excellent (ICCs from 0.82 to 0.95 and PCCs from 0.83 to 0.95). Overall, GFRPET-30 and GFRPET-15 were excellently correlated (ICCs from 0.96 to 0.99 and PCCs from 0.96 to 0.99). CONCLUSION: Renal [68Ga]Ga-DOTA PET can be a suitable alternative to conventional scintigraphy. Visual assessment of PET images and conventional renograms revealed comparable results. GFR values derived by non-invasive single-compartmental-modelling of PET data show a good correlation to serum creatinine-derived GFR values. In patients with undisturbed urinary efflux, the correlation was excellent. Dynamic PET data acquisition for 15 min is sufficient for visual evaluation and GFR derivation.

Artificial intelligence guided enhancement of digital PET: scans as fast as CT?

PURPOSE: Both digital positron emission tomography (PET) detector technologies and artificial intelligence based image post-reconstruction methods allow to reduce the PET acquisition time while maintaining diagnostic quality. The aim of this study was to acquire ultra-low-count fluorodeoxyglucose (FDG) ExtremePET images on a digital PET/computed tomography (CT) scanner at an acquisition time comparable to a CT scan and to generate synthetic full-dose PET images using an artificial neural network. METHODS: This is a prospective, single-arm, single-center phase I/II imaging study. A total of 587 patients were included. For each patient, a standard and an ultra-low-count FDG PET/CT scan (whole-body acquisition time about 30 s) were acquired. A modified pix2pixHD deep-learning network was trained employing 387 data sets as training and 200 as test cohort. Three models (PET-only and PET/CT with or without group convolution) were compared. Detectability and quantification were evaluated. RESULTS: The PET/CT input model with group convolution performed best regarding lesion signal recovery and was selected for detailed evaluation. Synthetic PET images were of high visual image quality; mean absolute lesion SUVmax (maximum standardized uptake value) difference was 1.5. Patient-based sensitivity and specificity for lesion detection were 79% and 100%, respectively. Not-detected lesions were of lower tracer uptake and lesion volume. In a matched-pair comparison, patient-based (lesion-based) detection rate was 89% (78%) for PERCIST (PET response criteria in solid tumors)-measurable and 36% (22%) for non PERCIST-measurable lesions. CONCLUSION: Lesion detectability and lesion quantification were promising in the context of extremely fast acquisition times. Possible application scenarios might include re-staging of late-stage cancer patients, in whom assessment of total tumor burden can be of higher relevance than detailed evaluation of small and low-uptake lesions.

Comparison of nodal staging between CT, MRI, and [18F]-FDG PET/MRI in patients with newly diagnosed breast cancer.

PURPOSE: To compare CT, MRI, and [18F]-fluorodeoxyglucose positron emission tomography ([18F]-FDG PET/MRI) for nodal status, regarding quantity and location of metastatic locoregional lymph nodes in patients with newly diagnosed breast cancer. MATERIALS AND METHODS: One hundred eighty-two patients (mean age 52.7 ± 11.9 years) were included in this prospective double-center study. Patients underwent dedicated contrast-enhanced chest/abdomen/pelvis computed tomography (CT) and whole-body ([18F]-FDG PET/) magnet resonance imaging (MRI). Thoracal datasets were evaluated separately regarding quantity, lymph node station (axillary levels I-III, supraclavicular, internal mammary chain), and lesion character (benign vs. malign). Histopathology served as reference standard for patient-based analysis. Patient-based and lesion-based analyses were compared by a McNemar test. Sensitivity, specificity, positive and negative predictive values, and accuracy were assessed for all three imaging modalities. RESULTS: On a patient-based analysis, PET/MRI correctly detected significantly more nodal positive patients than MRI (p < 0.0001) and CT (p < 0.0001). No statistically significant difference was seen between CT and MRI. PET/MRI detected 193 lesions in 75 patients (41.2%), while MRI detected 123 lesions in 56 patients (30.8%) and CT detected 104 lesions in 50 patients, respectively. Differences were statistically significant on a lesion-based analysis (PET/MRI vs. MRI, p < 0.0001; PET/MRI vs. CT, p < 0.0001; MRI vs. CT, p = 0.015). Subgroup analysis for different lymph node stations showed that PET/MRI detected significantly more lymph node metastases than MRI and CT in each location (axillary levels I-III, supraclavicular, mammary internal chain). MRI was superior to CT only in axillary level I (p = 0.0291). CONCLUSION: [18F]-FDG PET/MRI outperforms CT or MRI in detecting nodal involvement on a patient-based analysis and on a lesion-based analysis. Furthermore, PET/MRI was superior to CT or MRI in detecting lymph node metastases in all lymph node stations. Of all the tested imaging modalities, PET/MRI showed the highest sensitivity, whereas CT showed the lowest sensitivity, but was most specific.

Phantom-based acquisition time and image reconstruction parameter optimisation for oncologic FDG PET/CT examinations using a digital system.

BACKGROUND: New-generation silicon-photomultiplier (SiPM)-based PET/CT systems exhibit an improved lesion detectability and image quality due to a higher detector sensitivity. Consequently, the acquisition time can be reduced while maintaining diagnostic quality. The aim of this study was to determine the lowest 18F-FDG PET acquisition time without loss of diagnostic information and to optimise image reconstruction parameters (image reconstruction algorithm, number of iterations, voxel size, Gaussian filter) by phantom imaging. Moreover, patient data are evaluated to confirm the phantom results. METHODS: Three phantoms were used: a soft-tissue tumour phantom, a bone-lung tumour phantom, and a resolution phantom. Phantom conditions (lesion sizes from 6.5 mm to 28.8 mm in diameter, lesion activity concentration of 15 kBq/mL, and signal-to-background ratio of 5:1) were derived from patient data. PET data were acquired on an SiPM-based Biograph Vision PET/CT system for 10 min in list-mode format and resampled into time frames from 30 to 300 s in 30-s increments to simulate different acquisition times. Different image reconstructions with varying iterations, voxel sizes, and Gaussian filters were probed. Contrast-to-noise-ratio (CNR), maximum, and peak signal were evaluated using the 10-min acquisition time image as reference. A threshold CNR value ≥ 5 and a maximum (peak) deviation of ± 20% were considered acceptable. 20 patient data sets were evaluated regarding lesion quantification as well as agreement and correlation between reduced and full acquisition time standard uptake values (assessed by Pearson correlation coefficient, intraclass correlation coefficient, Bland-Altman analyses, and Krippendorff's alpha). RESULTS: An acquisition time of 60 s per bed position yielded acceptable detectability and quantification results for clinically relevant phantom lesions ≥ 9.7 mm in diameter using OSEM-TOF or OSEM-TOF+PSF image reconstruction, a 4-mm Gaussian filter, and a 1.65 × 1.65 x 2.00-mm3 or 3.30 × 3.30 x 3.00-mm3 voxel size. Correlation and agreement of patient lesion quantification between full and reduced acquisition times were excellent. CONCLUSION: A threefold reduction in acquisition time is possible. Patients might benefit from more comfortable examinations or reduced radiation exposure, if instead of the acquisition time the applied activity is reduced.

Pediatric age estimation from radiographs of the knee using deep learning.

OBJECTIVES: Age estimation, especially in pediatric patients, is regularly used in different contexts ranging from forensic over medicolegal to clinical applications. A deep neural network has been developed to automatically estimate chronological age from knee radiographs in pediatric patients. METHODS: In this retrospective study, 3816 radiographs of the knee from pediatric patients from a German population (acquired between January 2008 and December 2018) were collected to train a neural network. The network was trained to predict chronological age from the knee radiographs and was evaluated on an independent validation cohort of 423 radiographs (acquired between January 2019 and December 2020) and on an external validation cohort of 197 radiographs. RESULTS: The model showed a mean absolute error of 0.86 ± 0.72 years and 0.9 ± 0.71 years on the internal and external validation cohorts, respectively. Separating age classes (< 14 years from ≥ 14 years and < 18 years from ≥ 18 years) showed AUCs between 0.94 and 0.98. CONCLUSIONS: The chronological age of pediatric patients can be estimated with good accuracy from radiographs of the knee using a deep neural network. KEY POINTS: • Radiographs of the knee can be used for age estimations in pediatric patients using a standard deep neural network. • The network showed a mean absolute error of 0.86 ± 0.72 years in an internal validation cohort and of 0.9 ± 0.71 years in an external validation cohort. • The network can be used to separate the age classes < 14 years from ≥ 14 years with an AUC of 0.97 and < 18 years from ≥ 18 years with an AUC of 0.94.

Deep Learning-driven classification of external DICOM studies for PACS archiving.

OBJECTIVES: Over the course of their treatment, patients often switch hospitals, requiring staff at the new hospital to import external imaging studies to their local database. In this study, the authors present MOdality Mapping and Orchestration (MOMO), a Deep Learning-based approach to automate this mapping process by combining metadata analysis and a neural network ensemble. METHODS: A set of 11,934 imaging series with existing anatomical labels was retrieved from the PACS database of the local hospital to train an ensemble of neural networks (DenseNet-161 and ResNet-152), which process radiological images and predict the type of study they belong to. We developed an algorithm that automatically extracts relevant metadata from imaging studies, regardless of their structure, and combines it with the neural network ensemble, forming a powerful classifier. A set of 843 anonymized external studies from 321 hospitals was hand-labeled to assess performance. We tested several variations of this algorithm. RESULTS: MOMO achieves 92.71% accuracy and 2.63% minor errors (at 99.29% predictive power) on the external study classification task, outperforming both a commercial product (82.86% accuracy, 1.36% minor errors, 96.20% predictive power) and a pure neural network ensemble (72.69% accuracy, 10.3% minor errors, 99.05% predictive power) performing the same task. We find that the highest performance is achieved by an algorithm that combines all information into one vote-based classifier. CONCLUSION: Deep Learning combined with metadata matching is a promising and flexible approach for the automated classification of external DICOM studies for PACS archiving. KEY POINTS: • The algorithm can successfully identify 76 medical study types across seven modalities (CT, X-ray angiography, radiographs, MRI, PET (+CT/MRI), ultrasound, and mammograms). • The algorithm outperforms a commercial product performing the same task by a significant margin (> 9% accuracy gain). • The performance of the algorithm increases through the application of Deep Learning techniques.

18F-flutemetamol positron emission tomography in cardiac amyloidosis.

PURPOSE: Bone-tracer scintigraphy has an established role in diagnosis of cardiac amyloidosis (CA) as it detects transthyretin amyloidosis (ATTR). Positron emission tomography (PET) with amyloid tracers has shown high sensitivity for detection of both ATTR and light-chain (AL) CA. We aimed to investigate the accuracy of 18F-flutemetamol in CA. METHODS: We enrolled patients with CA or non-amyloid heart failure (NA-HF), who underwent cardiac 18F-flutemetamol PET/MRI or PET/CT. Myocardial and blood pool standardized tracer uptake values (SUV) were estimated. Late gadolinium enhancement (LGE) and T1 mapping/ extracellular volume (ECV) estimation were performed. RESULTS: We included 17 patients (12 with CA, 5 with NA-HF). PET/MRI was conducted in 13 patients, while PET/CT was conducted in 4. LGE was detected in 8 of 9 CA patients. Global relaxation time and ECV were higher in CA (1448 vs. 1326, P = 0.02 and 58.9 vs. 33.7%, P = 0.006, respectively). Positive PET studies were demonstrated in 2 of 12 patients with CA (AL and ATTR). Maximal and mean SUV did not differ between groups (2.21 vs. 1.69, P = 0.18 and 1.73 vs. 1.30, P = 0.13). CONCLUSION: Although protein-independent binding is supported by our results, the diagnostic yield of PET was low. We demonstrate here for the first time the low sensitivity of PET for CA.

Functional imaging using radiomic features in assessment of lymphoma.

Lymphomas are typically large, well-defined, and relatively homogeneous tumors, and therefore represent ideal targets for the use of radiomics. Of the available functional imaging tests, [18F]FDG-PET for body lymphoma and diffusion-weighted MRI (DWI) for central nervous system (CNS) lymphoma are of particular interest. The current literature suggests that two main applications for radiomics in lymphoma show promise: differentiation of lymphomas from other tumors, and lymphoma treatment response and outcome prognostication. In particular, encouraging results reported in the limited number of presently available studies that utilize functional imaging suggest that (1) MRI-based radiomics enables differentiation of CNS lymphoma from glioblastoma, and (2) baseline [18F]FDG-PET radiomics could be useful for survival prognostication, adding to or even replacing commonly used metrics such as standardized uptake values and metabolic tumor volume. However, due to differences in biological and clinical characteristics of different lymphoma subtypes and an increasing number of treatment options, more data are required to support these findings. Furthermore, a consensus on several critical steps in the radiomics workflow -most importantly, image reconstruction and post processing, lesion segmentation, and choice of classification algorithm- is desirable to ensure comparability of results between research institutions.

Magnetic resonance imaging and ultrasound for prediction of residual tumor size in early breast cancer within the ADAPT subtrials.

BACKGROUND: Prediction of histological tumor size by post-neoadjuvant therapy (NAT) ultrasound and magnetic resonance imaging (MRI) was evaluated in different breast cancer subtypes. METHODS: Imaging was performed after 12-week NAT in patients enrolled into three neoadjuvant WSG ADAPT subtrials. Imaging performance was analyzed for prediction of residual tumor measuring ≤10 mm and summarized using positive (PPV) and negative (NPV) predictive values. RESULTS: A total of 248 and 588 patients had MRI and ultrasound, respectively. Tumor size was over- or underestimated by < 10 mm in 4.4% and 21.8% of patients by MRI and in 10.2% and 15.8% by ultrasound. Overall, NPV (proportion of correctly predicted tumor size ≤10 mm) of MRI and ultrasound was 0.92 and 0.83; PPV (correctly predicted tumor size > 10 mm) was 0.52 and 0.61. MRI demonstrated a higher NPV and lower PPV than ultrasound in hormone receptor (HR)-positive/human epidermal growth factor receptor 2 (HER2)-positive and in HR-/HER2+ tumors. Both methods had a comparable NPV and PPV in HR-/HER2- tumors. CONCLUSIONS: In HR+/HER2+ and HR-/HER2+ breast cancer, MRI is less likely than ultrasound to underestimate while ultrasound is associated with a lower risk to overestimate tumor size. These findings may help to select the most optimal imaging approach for planning surgery after NAT. TRIAL REGISTRATION: Clinicaltrials.gov , NCT01815242 (registered on March 21, 2013), NCT01817452 (registered on March 25, 2013), and NCT01779206 (registered on January 30, 2013).

Clinical impact of PET/MRI in oligometastatic colorectal cancer.

BACKGROUND: Oligometastatic colorectal cancer (CRC) is potentially curable and demands individualised strategies. METHODS: This single-centre retrospective study investigated if positron emission tomography (PET)/magnetic resonance imaging (MR) had a clinical impact on oligometastatic CRC relative to the standard of care imaging (SCI). Adult patients with oligometastatic CRC on SCI who also underwent PET/MR between 3/2016 and 3/2019 were included. The exclusion criterion was lack of confirmatory standard of reference, either surgical pathology, intraoperative gross confirmation or imaging follow-up. SCI consisted of contrast-enhanced (CE) computed tomography (CT) of the chest/abdomen/pelvis, abdominal/pelvic CE-MR, and/or CE whole-body PET/CT with diagnostic quality (i.e. standard radiation dose) CT. Follow-up was evaluated until 3/2020. RESULTS: Thirty-one patients constituted the cohort, 16 (52%) male, median patient age was 53 years (interquartile range: 49-65 years). PET/MR and SCI results were divergent in 19% (95% CI 9-37%) of the cases, with PET/MR leading to management changes in all of them. The diagnostic accuracy of PET/MR was 90 ± 5%, versus 71 ± 8% for SCI. In a pairwise analysis, PET/MR outperformed SCI when compared to the reference standard (p = 0.0412). CONCLUSIONS: These findings suggest the potential usefulness of PET/MR in the management of oligometastatic CRC.

Just another "Clever Hans"? Neural networks and FDG PET-CT to predict the outcome of patients with breast cancer.

BACKGROUND: Manual quantification of the metabolic tumor volume (MTV) from whole-body 18F-FDG PET/CT is time consuming and therefore usually not applied in clinical routine. It has been shown that neural networks might assist nuclear medicine physicians in such quantification tasks. However, little is known if such neural networks have to be designed for a specific type of cancer or whether they can be applied to various cancers. Therefore, the aim of this study was to evaluate the accuracy of a neural network in a cancer that was not used for its training. METHODS: Fifty consecutive breast cancer patients that underwent 18F-FDG PET/CT were included in this retrospective analysis. The PET-Assisted Reporting System (PARS) prototype that uses a neural network trained on lymphoma and lung cancer 18F-FDG PET/CT data had to detect pathological foci and determine their anatomical location. Consensus reads of two nuclear medicine physicians together with follow-up data served as diagnostic reference standard; 1072 18F-FDG avid foci were manually segmented. The accuracy of the neural network was evaluated with regard to lesion detection, anatomical position determination, and total tumor volume quantification. RESULTS: If PERCIST measurable foci were regarded, the neural network displayed high per patient sensitivity and specificity in detecting suspicious 18F-FDG foci (92%; CI = 79-97% and 98%; CI = 94-99%). If all FDG-avid foci were regarded, the sensitivity degraded (39%; CI = 30-50%). The localization accuracy was high for body part (98%; CI = 95-99%), region (88%; CI = 84-90%), and subregion (79%; CI = 74-84%). There was a high correlation of AI derived and manually segmented MTV (R2 = 0.91; p < 0.001). AI-derived whole-body MTV (HR = 1.275; CI = 1.208-1.713; p < 0.001) was a significant prognosticator for overall survival. AI-derived lymph node MTV (HR = 1.190; CI = 1.022-1.384; p = 0.025) and liver MTV (HR = 1.149; CI = 1.001-1.318; p = 0.048) were predictive for overall survival in a multivariate analysis. CONCLUSION: Although trained on lymphoma and lung cancer, PARS showed good accuracy in the detection of PERCIST measurable lesions. Therefore, the neural network seems not prone to the clever Hans effect. However, the network has poor accuracy if all manually segmented lesions were used as reference standard. Both the whole body and organ-wise MTV were significant prognosticators of overall survival in advanced breast cancer.