Search

Objectives: Evaluation of sarcopenia from computed tomography (CT) is often based on measuring skeletal muscle area on a single transverse slice. Automatic segmentation of muscle volume has a lower variance and may be a better proxy for the total muscle volume than single-slice areas. The aim of the study was to determine which abdominal and thoracic anatomical volumes were best at predicting the total muscle volume. Methods: A cloud-based artificial intelligence tool (recomia.org) was used to segment all skeletal muscle of the torso of 994 patients who had performed whole-torso CT 2008–2020 for various clinical indications. Linear regression models for several anatomical volumes and single-slice areas were compared with regard to predicting the total torso muscle volume. Results: The muscle volume from the tip of the coccyx and 25 cm cranially was the best of the abdominal volumes and was significantly better than the L3 slice muscle area (R2 0.935 vs 0.830, P

Abstract Background Scintigraphy using technetium-99m labelled dimercaptosuccinic acid ([99mTc]Tc-DMSA), taken up in the proximal tubules, is the standard in functional imaging of the renal cortex. Recent guidelines recommend performing [99mTc]Tc-DMSA scintigraphy with single photon emission computed tomography (SPECT). Prostate-specific membrane antigen (PSMA) targeted positron emission tomography (PET) is used for staging and localization of recurrence in prostate cancer. A high renal uptake is often seen on PSMA PET, concordant with known PSMA expression in proximal tubules. This suggests PSMA PET could be used analogous to [99mTc]Tc-DMSA scintigraphy for renal cortical imaging. [18F]PSMA-1007 is a promising radiopharmaceutical for this purpose due to low urinary clearance. In this study, we aimed to compare [18F]PSMA-1007 PET to [99mTc]Tc-DMSA SPECT regarding split renal uptake and presence of renal uptake defects, in patients with prostate cancer. Three readers interpreted PET and SPECT images regarding presence of renal uptake defects, with each kidney split into cranial, mid and caudal segments. Kidneys were segmented in PET and SPECT images, and left renal uptake as a percentage of total renal uptake was measured. Results Twenty patients with prostate cancer were included. 2 participants had single kidneys; thus 38 kidneys were evaluated. A total of 29 defects were found on both [99mTc]Tc-DMSA SPECT and [18F]PSMA-1007 PET. Cohen’s kappa for concordance regarding presence of any defect was 0.76 on a per-segment basis and 0.67 on a per-kidney basis. Spearman’s r for left renal uptake percentage between [99mTc]Tc-DMSA SPECT and [18F]PSMA-1007 PET was 0.95. Conclusions [18F]PSMA-1007 PET is comparable to [99mTc]Tc-DMSA SPECT for detection of uptake defects in this setting. Measurements of split renal function made using [18F]PSMA-1007 PET are valid and strongly correlated to measurements made with [99mTc]Tc-DMSA SPECT.

Purpose: Meticulous manual delineations of the prostate and the surrounding organs at risk are necessary for prostate cancer radiation therapy to avoid side effects to the latter. This process is time consuming and hampered by inter- and intraobserver variability, all of which could be alleviated by artificial intelligence (AI). This study aimed to evaluate the performance of AI compared with manual organ delineations on computed tomography (CT) scans for radiation treatment planning. Methods and Materials: Manual delineations of the prostate, urinary bladder, and rectum of 1530 patients with prostate cancer who received curative radiation therapy from 2006 to 2018 were included. Approximately 50% of those CT scans were used as a training set, 25% as a validation set, and 25% as a test set. Patients with hip prostheses were excluded because of metal artifacts. After training and fine-tuning with the validation set, automated delineations of the prostate and organs at risk were obtained for the test set. Sørensen-Dice similarity coefficient, mean surface distance, and Hausdorff distance were used to evaluate the agreement between the manual and automated delineations. Results: The median Sørensen-Dice similarity coefficient between the manual and AI delineations was 0.82, 0.95, and 0.88 for the prostate, urinary bladder, and rectum, respectively. The median mean surface distance and Hausdorff distance were 1.7 and 9.2 mm for the prostate, 0.7 and 6.7 mm for the urinary bladder, and 1.1 and 13.5 mm for the rectum, respectively. Conclusions: Automated CT-based organ delineation for prostate cancer radiation treatment planning is feasible and shows good agreement with manually performed contouring.

Abstract Background Segmenting the whole-body somatostatin receptor-expressing tumour volume (SRETVwb) on positron emission tomography/computed tomography (PET/CT) images is highly time-consuming but has shown value as an independent prognostic factor for survival. An automatic method to measure SRETVwb could improve disease status assessment and provide a tool for prognostication. This study aimed to develop an artificial intelligence (AI)-based method to detect and quantify SRETVwb and total lesion somatostatin receptor expression (TLSREwb) from [68Ga]Ga-DOTA-TOC/TATE PET/CT images. Methods A UNet3D convolutional neural network (CNN) was used to train an AI model with [68Ga]Ga-DOTA-TOC/TATE PET/CT images, where all tumours were manually segmented with a semi-automatic method. The training set consisted of 148 patients, of which 108 had PET-positive tumours. The test group consisted of 30 patients, of which 25 had PET-positive tumours. Two physicians segmented tumours in the test group for comparison with the AI model. Results There were good correlations between the segmented SRETVwb and TLSREwb by the AI model and the physicians, with Spearman rank correlation coefficients of r = 0.78 and r = 0.73, respectively, for SRETVwb and r = 0.83 and r = 0.81, respectively, for TLSREwb. The sensitivity on a lesion detection level was 80% and 79%, and the positive predictive value was 83% and 84% when comparing the AI model with the two physicians. Conclusion It was possible to develop an AI model to segment SRETVwb and TLSREwb with high performance. A fully automated method makes quantification of tumour burden achievable and has the potential to be more widely used when assessing PET/CT images.

Abstract Background 18F-Fluorodeoxyglucose positron emission combined with computed tomography (FDG-PET/CT) has been proposed to improve preoperative staging in patients with bladder cancer subjected to radical cystectomy (RC). Objective Our aim was to assess the accuracy of FDG-PET/CT for lymph node staging ascertained at the multidisciplinary tumour board compared to lymph node status in the surgical lymphadenectomy specimen obtained at RC, and to explore potential factors associated with false-positive FDG-PET/CT results. Design, setting and participants Consecutive patients with bladder cancer undergoing RC with extended lymph node dissection between 2011 and 2019 without preoperative chemotherapy in a tertial referral cystectomy unit were included in the study. Outcome measurements and statistical analyses Sensitivity, specificity, positive and negative predictive values and likelihood ratios were calculated. Potential factors investigated for association with false-positive FDG-PET/CT were; bacteriuria within four weeks prior to FDG-PET/CT, Bacillus Calmette–Guerin (BCG) treatment within 12 months prior to FDG-PET/CT and transurethral resection of bladder tumour (TURB) within four weeks prior to FDG-PET/CT. Results Among 157 patients included for analysis, 44 (28%) were clinically node positive according to FDG-PET/CT. The sensitivity and specificity for detection of lymph node metastasis were 50% and 84%, respectively, and the corresponding positive predictive and negative predictive values were 61% and 76%. Positive and negative likelihood ratios were 3.0 and 0.6, respectively. No association was found between bacteriuria, previous BCG treatment or TURB within 28 days and false-positive FDG-PET/CT results. Conclusions Preoperative FDG-PET/CT prior to RC had a clinically meaningful high specificity (84%) but lower sensitivity (50%) for detection of lymph node metastases compared to lymph node status in an extended pelvic lymphadenectomy template. We could not identify any factors associated with false-positive FDG-PET/CT outcomes.

Abstract Background [18F]PSMA-1007 is a prostate specific membrane antigen (PSMA) ligand for positron emission tomography (PET) imaging of prostate cancer. Current guidelines recommend imaging 90–120 min after injection but strong data about optimal timing is lacking. Our aim was to study whether imaging after 1 h and 2 h leads to a different number of detected lesions, with a specific focus on lesions that might lead to a change in treatment. Methods 195 patients underwent PET with computed tomography imaging 1 and 2 h after injection of [18F]PSMA-1007. Three readers assessed the status of the prostate or prostate bed and suspected metastases. We analyzed the location and number of found metastases to determine N- and M-stage of patients. We also analyzed standardized uptake values (SUV) in lesions and in normal tissue. Results Significantly more pelvic lymph nodes and bone metastases were found and higher N- and M-stages were seen after 2 h. In twelve patients (6.1%) two or three readers agreed on a higher N- or M-stage after 2 h. Conversely, in two patients (1.0%), two readers agreed on a higher stage at 1 h. SUVs in suspected malignant lesions and in normal tissues were higher at 2 h, but lower in the blood pool and urinary bladder. Conclusions Imaging at 2 h after injection of [18F]PSMA-1007 leads to more suspected metastases found than after 1 h, with higher staging in some patients and possible effect on patient treatment.

Abstract Background [18F]PSMA-1007 is a promising tracer for integrated positron emission tomography and computed tomography (PET/CT). Objective Our aim was to assess the diagnostic accuracy of [18F]PSMA-1007 PET/CT for primary staging of lymph node metastasis before robotic-assisted laparoscopy (RALP) with extended lymph node dissection (ePLND). Design, Setting and Participants The study was a retrospective cohort in a tertiary referral center. Men with prostate cancer that underwent surgical treatment for intermediate- or high-risk prostate cancer between May 2019 and August 2021 were included. Interventions [18F]PSMA-1007 PET/CT for initial staging followed by RALP and ePLND. Outcome measurements and statistical analyses Sensitivity and specificity were calculated both for the entire cohort and for patients with lymph node metastasis ≥ 3 mm. Positive (PPV) and negative (NPV) predictive values were calculated. Results and limitations Among 104 patients included in the analyses, 26 patients had lymph node metastasis based on pathology reporting and metastases were ≥ 3 mm in size in 13 of the cases (50%). In the entire cohort, the sensitivity and specificity of [18F]PSMA-1007 were 26.9% (95% confidence interval (CI); 11.6–47.8) and 96.2% (95% CI; 89.2–99.2), respectively. The sensitivity and specificity of [18F]PSMA-1007 to detect a lymph node metastasis ≥ 3 mm on PET/CT were 53.8% (95% CI; 25.1–80.8) and 96.7% (95% CI; 90.7–99.3), respectively. PPV was 70% and NPV 93.6%. Conclusions In primary staging of intermediate- and high-risk prostate cancer, [18F]PSMA-1007 PET/CT is highly specific for prediction of lymph node metastases, but the sensitivity for detection of metastases smaller than 3 mm is limited. Based on our results, [18F]PSMA-1007 PET/CT cannot completely replace ePLND. Patient summary This study investigated the use of an imaging method based on a prostate antigen-specific radiopharmaceutical tracer to detect lymph node prostate cancer metastasis. We found that it is unreliable to discover small metastasis.

Abstract Background Metabolic positron emission tomography/computed tomography (PET/CT) parameters describing tumour activity contain valuable prognostic information, but to perform the measurements manually leads to both intra- and inter-reader variability and is too time-consuming in clinical practice. The use of modern artificial intelligence-based methods offers new possibilities for automated and objective image analysis of PET/CT data. Purpose We aimed to train a convolutional neural network (CNN) to segment and quantify tumour burden in [18F]-fluorodeoxyglucose (FDG) PET/CT images and to evaluate the association between CNN-based measurements and overall survival (OS) in patients with lung cancer. A secondary aim was to make the method available to other researchers. Methods A total of 320 consecutive patients referred for FDG PET/CT due to suspected lung cancer were retrospectively selected for this study. Two nuclear medicine specialists manually segmented abnormal FDG uptake in all of the PET/CT studies. One-third of the patients were assigned to a test group. Survival data were collected for this group. The CNN was trained to segment lung tumours and thoracic lymph nodes. Total lesion glycolysis (TLG) was calculated from the CNN-based and manual segmentations. Associations between TLG and OS were investigated using a univariate Cox proportional hazards regression model. Results The test group comprised 106 patients (median age, 76 years (IQR 61–79); n = 59 female). Both CNN-based TLG (hazard ratio 1.64, 95% confidence interval 1.21–2.21; p = 0.001) and manual TLG (hazard ratio 1.54, 95% confidence interval 1.14–2.07; p = 0.004) estimations were significantly associated with OS. Conclusion Fully automated CNN-based TLG measurements of PET/CT data showed were significantly associated with OS in patients with lung cancer. This type of measurement may be of value for the management of future patients with lung cancer. The CNN is publicly available for research purposes.

Abstract Background Radical cystectomy for urinary bladder cancer is a procedure associated with a high risk of complications, and poor overall survival (OS) due to both patient and tumour factors. Sarcopenia is one such patient factor. We have developed a fully automated artificial intelligence (AI)-based image analysis tool for segmenting skeletal muscle of the torso and calculating the muscle volume. Methods All patients who have undergone radical cystectomy for urinary bladder cancer 2011–2019 at Sahlgrenska University Hospital, and who had a pre-operative computed tomography of the abdomen within 90 days of surgery were included in the study. All patients CT studies were analysed with the automated AI-based image analysis tool. Clinical data for the patients were retrieved from the Swedish National Register for Urinary Bladder Cancer. Muscle volumes dichotomised by the median for each sex were analysed with Cox regression for OS and logistic regression for 90-day high-grade complications. The study was approved by the Swedish Ethical Review Authority (2020-03985). Results Out of 445 patients who underwent surgery, 299 (67%) had CT studies available for analysis. The automated AI-based tool failed to segment the muscle volume in seven (2%) patients. Cox regression analysis showed an independent significant association with OS (HR 1.62; 95% CI 1.07–2.44; p = 0.022). Logistic regression did not show any association with high-grade complications. Conclusion The fully automated AI-based CT image analysis provides a low-cost and meaningful clinical measure that is an independent biomarker for OS following radical cystectomy.

Abstract Background In Prostate-specific membrane antigen (PSMA) positron emission tomography with computed tomography (PET-CT), there is significant renal uptake. The standard in renal cortical functional imaging is scintigraphy with technetium-99m labeled dimercaptosuccinic acid (DMSA). Using [68Ga]Ga-PSMA-11 PET for renal imaging has been suggested, but using [18F]PSMA-1007 has not been explored. The aims of this study were to establish the optimal time point for renal imaging after [18F]PSMA-1007 injection, to investigate the reproducibility of split renal uptake measurements, and to determine the margin for reduction in administered activity. Methods Twelve adult male patients with prostate cancer underwent [18F]PSMA-1007 PET-CT at 8 time points up to 5.5 h post-injection (p.i.). List-mode data were binned to durations of 10 to 120 s per bed position (bp). Left renal percentage of total renal uptake (LRU%) was measured, and the difference between highest and lowest measurement per patient (“delta max”) was calculated. Images acquired at 1 h, 2 h, and 5.5 h p.i. with durations of 10 to 120 s/bp were rated regarding image quality. Results Imaging at 2 h p.i. with 60 s/bp yielded acceptable quality in all cases. Increasing acquisition time to 15 min for a single bp would allow reducing administered activity to 0.27 MBq/kg, resulting in an effective dose of 0.4 mSv for a 1-year old child weighing 10 kg. The median delta max of LRU% measurements was 2.7% (range 1.8–7.3%). Conclusions Renal [18F]PSMA-1007 PET-CT is feasible, with imaging 2 h p.i., acceptable split renal uptake variability, and effective dose and acquisition time comparable to those of [99mTc]Tc-DMSA scintigraphy.

Abstract Background The aim of the study was to develop and test an artificial intelligence (AI)-based method to improve the quality of [18F]fluorodeoxyglucose (FDG) positron emission tomography (PET) images. Methods A convolutional neural network (CNN) was trained by using pairs of excellent (acquisition time of 6 min/bed position) and standard (acquisition time of 1.5 min/bed position) or sub-standard (acquisition time of 1 min/bed position) images from 72 patients. A test group of 25 patients was used to validate the CNN qualitatively and quantitatively with 5 different image sets per patient: 4 min/bed position, 1.5 min/bed position with and without CNN, and 1 min/bed position with and without CNN. Results Difference in hotspot maximum or peak standardized uptake value between the standard 1.5 min and 1.5 min CNN images fell short of significance. Coefficient of variation, the noise level, was lower in the CNN-enhanced images compared with standard 1 min and 1.5 min images. Physicians ranked the 1.5 min CNN and the 4 min images highest regarding image quality (noise and contrast) and the standard 1 min images lowest. Conclusions AI can enhance [18F]FDG-PET images to reduce noise and increase contrast compared with standard images whilst keeping SUVmax/peak stability. There were significant differences in scoring between the 1.5 min and 1.5 min CNN image sets in all comparisons, the latter had higher scores in noise and contrast. Furthermore, difference in SUVmax and SUVpeak fell short of significance for that pair. The improved image quality can potentially be used either to provide better images to the nuclear medicine physicians or to reduce acquisition time/administered activity.

Abstract To develop an artificial intelligence (AI)-based method for the detection of focal skeleton/bone marrow uptake (BMU) in patients with Hodgkin’s lymphoma (HL) undergoing staging with FDG-PET/CT. The results of the AI in a separate test group were compared to the interpretations of independent physicians. The skeleton and bone marrow were segmented using a convolutional neural network. The training of AI was based on 153 un-treated patients. Bone uptake significantly higher than the mean BMU was marked as abnormal, and an index, based on the total squared abnormal uptake, was computed to identify the focal uptake. Patients with an index above a predefined threshold were interpreted as having focal uptake. As the test group, 48 un-treated patients who had undergone a staging FDG-PET/CT between 2017–2018 with biopsy-proven HL were retrospectively included. Ten physicians classified the 48 cases regarding focal skeleton/BMU. The majority of the physicians agreed with the AI in 39/48 cases (81%) regarding focal skeleton/bone marrow involvement. Inter-observer agreement between the physicians was moderate, Kappa 0.51 (range 0.25–0.80). An AI-based method can be developed to highlight suspicious focal skeleton/BMU in HL patients staged with FDG-PET/CT. Inter-observer agreement regarding focal BMU is moderate among nuclear medicine physicians.

Abstract Background This study investigates the patterns of PET-positive lymph nodes (LNs) in anal cancer. The aim was to provide information that could inform future anal cancer radiotherapy contouring guidelines. Methods The baseline [18F]-FDG PET-CTs of 190 consecutive anal cancer patients were retrospectively assessed. LNs with a Deauville score (DS) of ≥3 were defined as PET-positive. Each PET-positive LN was allocated to a LN region and a LN sub-region; they were then mapped on a standard anatomy reference CT. The association between primary tumor localization and PET-positive LNs in different regions were analyzed. Results PET-positive LNs (n = 412) were identified in 103 of 190 patients (54%). Compared to anal canal tumors with extension into the rectum, anal canal tumors with perianal extension more often had inguinal (P

Abstract Background Body composition is associated with survival outcome in oncological patients, but it is not routinely calculated. Manual segmentation of subcutaneous adipose tissue (SAT) and muscle is time-consuming and therefore limited to a single CT slice. Our goal was to develop an artificial-intelligence (AI)-based method for automated quantification of three-dimensional SAT and muscle volumes from CT images. Methods Ethical approvals from Gothenburg and Lund Universities were obtained. Convolutional neural networks were trained to segment SAT and muscle using manual segmentations on CT images from a training group of 50 patients. The method was applied to a separate test group of 74 cancer patients, who had two CT studies each with a median interval between the studies of 3 days. Manual segmentations in a single CT slice were used for comparison. The accuracy was measured as overlap between the automated and manual segmentations. Results The accuracy of the AI method was 0.96 for SAT and 0.94 for muscle. The average differences in volumes were significantly lower than the corresponding differences in areas in a single CT slice: 1.8% versus 5.0% (p

Abstract Background [18F]-fluorodeoxyglucose (FDG) positron emission tomography with computed tomography (PET-CT) is a well-established modality in the work-up of patients with suspected or confirmed diagnosis of lung cancer. Recent research efforts have focused on extracting theragnostic and textural information from manually indicated lung lesions. Both semi-automatic and fully automatic use of artificial intelligence (AI) to localise and classify FDG-avid foci has been demonstrated. To fully harness AI’s usefulness, we have developed a method which both automatically detects abnormal lung lesions and calculates the total lesion glycolysis (TLG) on FDG PET-CT. Methods One hundred twelve patients (59 females and 53 males) who underwent FDG PET-CT due to suspected or for the management of known lung cancer were studied retrospectively. These patients were divided into a training group (59%; n = 66), a validation group (20.5%; n = 23) and a test group (20.5%; n = 23). A nuclear medicine physician manually segmented abnormal lung lesions with increased FDG-uptake in all PET-CT studies. The AI-based method was trained to segment the lesions based on the manual segmentations. TLG was then calculated from manual and AI-based measurements, respectively and analysed with Bland-Altman plots. Results The AI-tool’s performance in detecting lesions had a sensitivity of 90%. One small lesion was missed in two patients, respectively, where both had a larger lesion which was correctly detected. The positive and negative predictive values were 88% and 100%, respectively. The correlation between manual and AI TLG measurements was strong (R 2 = 0.74). Bias was 42 g and 95% limits of agreement ranged from − 736 to 819 g. Agreement was particularly high in smaller lesions. Conclusions The AI-based method is suitable for the detection of lung lesions and automatic calculation of TLG in small- to medium-sized tumours. In a clinical setting, it will have an added value due to its capability to sort out negative examinations resulting in prioritised and focused care on patients with potentially malignant lesions.

Abstract Background A novel generation of PET scanners based on silicon (Si)-photomultiplier (PM) technology has recently been introduced. Concurrently, there has been development of new reconstruction methods aimed at increasing the detectability of small lesions without increasing image noise. The combination of new detector technologies and new reconstruction algorithms has been found to increase image quality. However, it is unknown to what extent the demonstrated improvement of image quality is due to scanner hardware development or improved reconstruction algorithms. To isolate the contribution of the hardware, this study aimed to compare the ability to detect small hotspots in phantoms using the latest generation SiPM-based PET/CT scanner (GE Discovery MI) relative to conventional PM-based PET/CT scanner (GE Discovery 690), using identical reconstruction protocols. Materials and methods Two different phantoms (NEMA body and Jasczcak) with fillable spheres (31 μl to 26.5 ml) and varying sphere-to-background-ratios (SBR) were scanned in one bed position for 15–600 s on both scanners. The data were reconstructed using identical reconstruction parameters on both scanners. The recovery-coefficient (RC), noise level, contrast (spherepeak/backgroundpeak-value), and detectability of each sphere were calculated and compared between the scanners at each acquisition time. Results The RC-curves for the NEMA phantom were near-identical for both scanners at SBR 10:1. For smaller spheres in the Jaszczak phantom, the contrast was 1.22 higher for the DMI scanner at SBR 15:1. The ratio decreased for lower SBR, with a ratio of 1.03 at SBR 3.85:1. Regarding the detectability of spheres, the sensitivity was 98% and 88% for the DMI and D690, respectively, for SBR 15:1. For SBR 7.5, the sensitivity was 75% and 83% for the DMI and D690, respectively. For SBR 3.85:1, the sensitivity was 43% and 30% for the DMI and D690, respectively. Conclusion Marginally higher contrast in small spheres was seen for the SiPM-based scanner but there was no significant difference in detectability between the scanners. It was difficult to detect differences between the scanners, suggesting that the SiPM-based detectors are not the primary reason for improved image quality.

Background: It is time-consuming for oncologists to delineate volumes for radiotherapy treatment in computer tomography (CT) images. Automatic delineation based on image processing exists, but with varied accuracy and moderate time savings. Using convolutional neural network (CNN), delineations of volumes are faster and more accurate. We have used CTs with the annotated structure sets to train and evaluate a CNN. Material and methods: The CNN is a standard segmentation network modified to minimize memory usage. We used CTs and structure sets from 75 cervical cancers and 191 anorectal cancers receiving radiation therapy at Skåne University Hospital 2014-2018. Five structures were investigated: left/right femoral heads, bladder, bowel bag, and clinical target volume of lymph nodes (CTVNs). Dice score and mean surface distance (MSD) (mm) evaluated accuracy, and one oncologist qualitatively evaluated auto-segmentations. Results: Median Dice/MSD scores for anorectal cancer: 0.91–0.92/1.93–1.86 femoral heads, 0.94/2.07 bladder, and 0.83/6.80 bowel bag. Median Dice scores for cervical cancer were 0.93–0.94/1.42–1.49 femoral heads, 0.84/3.51 bladder, 0.88/5.80 bowel bag, and 0.82/3.89 CTVNs. With qualitative evaluation, performance on femoral heads and bladder auto-segmentations was mostly excellent, but CTVN auto-segmentations were not acceptable to a larger extent. Discussion: It is possible to train a CNN with high overlap using structure sets as ground truth. Manually delineated pelvic volumes from structure sets do not always strictly follow volume boundaries and are sometimes inaccurately defined, which leads to similar inaccuracies in the CNN output. More data that is consistently annotated is needed to achieve higher CNN accuracy and to enable future clinical implementation.

Abstract Background Artificial intelligence (AI) is about to transform medical imaging. The Research Consortium for Medical Image Analysis (RECOMIA), a not-for-profit organisation, has developed an online platform to facilitate collaboration between medical researchers and AI researchers. The aim is to minimise the time and effort researchers need to spend on technical aspects, such as transfer, display, and annotation of images, as well as legal aspects, such as de-identification. The purpose of this article is to present the RECOMIA platform and its AI-based tools for organ segmentation in computed tomography (CT), which can be used for extraction of standardised uptake values from the corresponding positron emission tomography (PET) image. Results The RECOMIA platform includes modules for (1) local de-identification of medical images, (2) secure transfer of images to the cloud-based platform, (3) display functions available using a standard web browser, (4) tools for manual annotation of organs or pathology in the images, (5) deep learning-based tools for organ segmentation or other customised analyses, (6) tools for quantification of segmented volumes, and (7) an export function for the quantitative results. The AI-based tool for organ segmentation in CT currently handles 100 organs (77 bones and 23 soft tissue organs). The segmentation is based on two convolutional neural networks (CNNs): one network to handle organs with multiple similar instances, such as vertebrae and ribs, and one network for all other organs. The CNNs have been trained using CT studies from 339 patients. Experienced radiologists annotated organs in the CT studies. The performance of the segmentation tool, measured as mean Dice index on a manually annotated test set, with 10 representative organs, was 0.93 for all foreground voxels, and the mean Dice index over the organs were 0.86 (0.82 for the soft tissue organs and 0.90 for the bones). Conclusion The paper presents a platform that provides deep learning-based tools that can perform basic organ segmentations in CT, which can then be used to automatically obtain the different measurement in the corresponding PET image. The RECOMIA platform is available on request at www.recomia.org for research purposes.

Abstract Background Prostate-specific membrane antigen (PSMA) radiotracers such as [18F]PSMA-1007 used with positron emission tomography-computed tomography (PET-CT) is promising for initial staging and detection of recurrent disease in prostate cancer patients. The block-sequential regularization expectation maximization algorithm (BSREM) is a new PET reconstruction algorithm, which provides higher image contrast while also reducing noise. The aim of the present study was to evaluate the influence of different acquisition times and different noise-suppressing factors in BSREM (β values) in [18F]PSMA-1007 PET-CT regarding quantitative data as well as a visual image quality assessment. We included 35 patients referred for clinical [18F]PSMA-1007 PET-CT. Four megabecquerels per kilogramme were administered and imaging was performed after 120 min. Eighty-four image series per patient were created with combinations of acquisition times of 1–4 min/bed position and β values of 300–1400. The noise level in normal tissue and the contrast-to-noise ratio (CNR) of pathological uptakes versus the local background were calculated. Image quality was assessed by experienced nuclear medicine physicians. Results The noise level in the liver, spleen, and muscle was higher for low β values and low acquisition times (written as activity time products (ATs = administered activity × acquisition time)) and was minimized at maximum AT (16 MBq/kg min) and maximum β (1400). There was only a small decrease above AT 10. The median CNR increased slowly with AT from approximately 6 to 12 and was substantially lower at AT 4 and higher at AT 14–16. At AT 4–6, many images were regarded as being of unacceptable quality. For AT 8, β values of 700–900 were considered of acceptable quality. Conclusions An AT of 8 (for example as in our study, 4 MB/kg with an acquisition time of 2 min) with a β value of 700 performs well regarding noise level, CNR, and visual image quality assessment.

Here, we aimed to develop and validate a fully automated artificial intelligence (AI)-based method for the detection and quantification of suspected prostate tumour/local recurrence, lymph node metastases, and bone metastases from [18F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) images. Images from 660 patients were included. Segmentations by one expert reader were ground truth. A convolutional neural network (CNN) was developed and trained on a training set, and the performance was tested on a separate test set of 120 patients. The AI method was compared with manual segmentations performed by several nuclear medicine physicians. Assessment of tumour burden (total lesion volume (TLV) and total lesion uptake (TLU)) was performed. The sensitivity of the AI method was, on average, 79% for detecting prostate tumour/recurrence, 79% for lymph node metastases, and 62% for bone metastases. On average, nuclear medicine physicians’ corresponding sensitivities were 78%, 78%, and 59%, respectively. The correlations of TLV and TLU between AI and nuclear medicine physicians were all statistically significant and ranged from R = 0.53 to R = 0.83. In conclusion, the development of an AI-based method for prostate cancer detection with sensitivity on par with nuclear medicine physicians was possible. The developed AI tool is freely available for researchers.

V/P SPECT from 4 consecutive patients with COVID-19 suggests that ventilation and perfusion images may be applied to diagnose or exclude pulmonary embolism, verify nonsegmental diversion of perfusion from the ventilated areas (dead space ventilation) that may represent inflammation of the pulmonary vasculature, detect the reversed mismatch of poor ventilation and better preserved perfusion (shunt perfusion) in bilateral pulmonary inflammation and indicate redistribution of lung perfusion (antigravitational hyperperfusion) due to cardiac congestion. V/P mismatch and reversed mismatch may be extensive enough to diminish dramatically preserved matching ventilation/perfusion and to induce severe hypoxemia in COVID-19.

Abstract Background A new generation of positron emission tomography with computed tomography (PET-CT) was recently introduced using silicon (Si) photomultiplier (PM)-based technology. Our aim was to compare the image quality and diagnostic performance of a SiPM-based PET-CT (Discovery MI; GE Healthcare, Milwaukee, WI, USA) with a time-of-flight PET-CT scanner with a conventional PM detector (Gemini TF; Philips Healthcare, Cleveland, OH, USA), including reconstruction algorithms per vendor’s recommendations. Methods Imaging of the National Electrical Manufacturers Association IEC body phantom and 16 patients was carried out using 1.5 min/bed for the Discovery MI PET-CT and 2 min/bed for the Gemini TF PET-CT. Images were analysed for recovery coefficients for the phantom, signal-to-noise ratio in the liver, standardized uptake values (SUV) in lesions, number of lesions and metabolic TNM classifications in patients. Results In phantom, the correct (> 90%) activity level was measured for spheres ≥17 mm for Discovery MI, whereas the Gemini TF reached a correct measured activity level for the 37-mm sphere. In patient studies, metabolic TNM classification was worse using images obtained from the Discovery MI compared those obtained from the Gemini TF in 4 of 15 patients. A trend toward more malignant, inflammatory and unclear lesions was found using images acquired with the Discovery MI compared with the Gemini TF, but this was not statistically significant. Lesion-to-blood-pool SUV ratios were significantly higher in images from the Discovery MI compared with the Gemini TF for lesions smaller than 1 cm (p

Abstract Background Lung cancer is one of the most common cancers in the world. Early detection and correct staging are fundamental for treatment and prognosis. Positron emission tomography with computed tomography (PET/CT) is recommended clinically. Silicon (Si) photomultiplier (PM)-based PET technology and new reconstruction algorithms are hoped to increase the detection of small lesions and enable earlier detection of pathologies including metastatic spread. The aim of this study was to compare the diagnostic performance of a SiPM-based PET/CT (including a new block-sequential regularization expectation maximization (BSREM) reconstruction algorithm) with a conventional PM-based PET/CT including a conventional ordered subset expectation maximization (OSEM) reconstruction algorithm. The focus was patients admitted for 18F-fluorodeoxyglucose (FDG) PET/CT for initial diagnosis and staging of suspected lung cancer. Patients were scanned on both a SiPM-based PET/CT (Discovery MI; GE Healthcare, Milwaukee, MI, USA) and a PM-based PET/CT (Discovery 690; GE Healthcare, Milwaukee, MI, USA). Standardized uptake values (SUV) and image interpretation were compared between the two systems. Image interpretations were further compared with histopathology when available. Results Seventeen patients referred for suspected lung cancer were included in our single injection, dual imaging study. No statically significant differences in SUVmax of suspected malignant primary tumours were found between the two PET/CT systems. SUVmax in suspected malignant intrathoracic lymph nodes was 10% higher on the SiPM-based system (p = 0.026). Good consistency (14/17 cases) between the PET/CT systems were found when comparing simplified TNM staging. The available histology results did not find any obvious differences between the systems. Conclusion In a clinical setting, the new SiPM-based PET/CT system with a new BSREM reconstruction algorithm provided a higher SUVmax for suspected lymph node metastases compared to the PM-based system. However, no improvement in lung cancer detection was seen.

Abstract Background Block-sequential regularized expectation maximization (BSREM), commercially Q. Clear (GE Healthcare, Milwaukee, WI, USA), is a reconstruction algorithm that allows for a fully convergent iterative reconstruction leading to higher image contrast compared to conventional reconstruction algorithms, while also limiting noise. The noise penalization factor β controls the trade-off between noise level and resolution and can be adjusted by the user. The aim was to evaluate the influence of different β values for different activity time products (ATs = administered activity × acquisition time) in whole-body 18F-fluorodeoxyglucose (FDG) positron emission tomography with computed tomography (PET-CT) regarding quantitative data, interpretation, and quality assessment of the images. Twenty-five patients with known or suspected malignancies, referred for clinical 18F-FDG PET-CT examinations acquired on a silicon photomultiplier PET-CT scanner, were included. The data were reconstructed using BSREM with β values of 100–700 and ATs of 4–16 MBq/kg × min/bed (acquisition times of 1, 1.5, 2, 3, and 4 min/bed). Noise level, lesion SUVmax, and lesion SUVpeak were calculated. Image quality and lesion detectability were assessed by four nuclear medicine physicians for acquisition times of 1.0 and 1.5 min/bed position. Results The noise level decreased with increasing β values and ATs. Lesion SUVmax varied considerably between different β values and ATs, whereas SUVpeak was more stable. For an AT of 6 (in our case 1.5 min/bed), the best image quality was obtained with a β of 600 and the best lesion detectability with a β of 500. AT of 4 generated poor-quality images and false positive uptakes due to noise. Conclusions For oncologic whole-body 18F-FDG examinations on a SiPM-based PET-CT, we propose using an AT of 6 (i.e., 4 MBq/kg and 1.5 min/bed) reconstructed with BSREM using a β value of 500–600 in order to ensure image quality and lesion detection rate as well as a high patient throughput. We do not recommend using AT

Abstract Background The Deauville score (DS) is a clinical tool, based on the comparison between lesion and reference organ uptake of 18F-fluorodeoxyglucose (FDG), used to stratify patients with lymphoma into categories reflecting their disease status. With a plethora of positron emission tomography with computed tomography (PET-CT) hard- and software algorithms, standard uptake value (SUV) in lesions and reference organs may differ which affects DS classification and therefore medical treatment. The EANM Research Ltd. (EARL) harmonization program from the European Association of Nuclear Medicine (EANM) partly mitigates this issue, but local preferences are common in clinical practice. We have investigated the discordance in DS calculated from patients with lymphoma referred for 18F-FDG PET-CT reconstructed with three different algorithms: the newly introduced block-sequential regularization expectation-maximization algorithm commercially sold as Q. Clear (QC, GE Healthcare, Milwaukee, WI, USA), compliant with the newly proposed updated EARL recommendations, and two settings compliant with the current EARL recommendations (EARLlower and EARLupper, representing the lower and upper limit of the EARL recommendations). Methods Fifty-two patients with non-Hodgkin and Hodgkin lymphoma were included (18 females and 34 males). Segmentation of mediastinal blood pool and liver were semi-automatically performed, whereas segmentation of lesions was done manually. From these segmentations, SUVmax and SUVpeak were obtained and DS calculated. Results There was a significant difference in DS between the QC algorithm and EARLlower/EARLupper (p

Abstract Background Recently, the block-sequential regularized expectation maximization (BSREM) reconstruction algorithm was commercially introduced (Q.Clear, GE Healthcare, Milwaukee, WI, USA). However, the combination of noise-penalizing factor (β), acquisition time, and administered activity for optimal image quality has not been established for 18F-fluorocholine (FCH). The aim was to compare image quality and diagnostic performance of different reconstruction protocols for patients with prostate cancer being examined with 18F-FCH on a silicon photomultiplier-based PET-CT. Thirteen patients were included, injected with 4 MBq/kg, and images were acquired after 1 h. Images were reconstructed with frame durations of 1.0, 1.5, and 2.0 min using β of 150, 200, 300, 400, 500, and 550. An ordered subset expectation maximization (OSEM) reconstruction with a frame duration of 2.0 min was used for comparison. Images were quantitatively analyzed regarding standardized uptake values (SUV) in metastatic lymph nodes, local background, and muscle to obtain contrast-to-noise ratios (CNR) as well as the noise level in muscle. Images were analyzed regarding image quality and number of metastatic lymph nodes by two nuclear medicine physicians. Results The highest median CNR was found for BSREM with a β of 300 and a frame duration of 2.0 min. The OSEM reconstruction had the lowest median CNR. Both the noise level and lesion SUVmax decreased with increasing β. For a frame duration of 1.5 min, the median quality score was highest for β 400-500, and for a frame duration of 2.0 min the score was highest for β 300-500. There was no statistically significant difference in the number of suspected lymph node metastases between the different image series for one of the physicians, and for the other physician the number of lymph nodes differed only for one combination of image series. Conclusions To achieve acceptable image quality at 4 MBq/kg 18F-FCH, we propose using a β of 400-550 with a frame duration of 1.5 min. The lower β should be used if a high CNR is desired and the higher if a low noise level is important.

Abstract Background The Bone Scan Index (BSI) is used to quantitatively assess the total tumour burden in bone scans of patients with metastatic prostate cancer. The clinical utility of BSI has recently been validated as a prognostic imaging biomarker. However, the clinical utility of the on-treatment change in BSI is dependent on the reproducibility of bone scans. The objective of this prospective study is to evaluate the intra-patient reproducibility of two bone scan procedures performed at a one-week interval. Methods We prospectively studied prostate cancer patients who were referred for bone scintigraphy at our centres according to clinical routine. All patients underwent two whole-body bone scans: one for clinical routine purposes and a second one as a repeated scan after approximately one week. BSI values were obtained for each bone scintigraph using EXINI boneBSI software. Results A total of 20 patients were enrolled. There was no statistical difference between the BSI values of the first (median = 0.66, range 0–40.77) and second (median = 0.63, range 0–22.98) bone scans (p = 0.41). The median difference in BSI between the clinical routine and repeated scans was − 0.005 (range − 17.79 to 0). The 95% confidence interval for the median value was − 0.1 to 0. A separate analysis was performed for patients with BSI ≤ 10 (n = 17). Differences in BSI were smaller for patients with BSI ≤ 10 compared to the whole cohort (median − 0.1, range − 2.2-0, 95% confidence interval − 0.1 to 0). Conclusions The automated BSI demonstrated high intra-individual reproducibility for BSI ≤ 10 in the two repeated bone scans of patients with prostate cancer. The study supports the use of BSI as a quantitative parameter to evaluate the change in total tumour burden in bone scans.

Abstract Background Sodium fluoride (NaF) positron emission tomography combined with computer tomography (PET/CT) has shown to be more sensitive than the whole-body bone scan in the detection of skeletal uptake due to metastases in prostate cancer. We aimed to calculate a 3D index for NaF PET/CT and investigate its correlation to the bone scan index (BSI) and overall survival (OS) in a group of patients with prostate cancer. Methods NaF PET/CT and bone scans were studied in 48 patients with prostate cancer. Automated segmentation of the thoracic and lumbar spines, sacrum, pelvis, ribs, scapulae, clavicles, and sternum were made in the CT images. Hotspots in the PET images were selected using both a manual and an automated method. The volume of each hotspot localized in the skeleton in the corresponding CT image was calculated. Two PET/CT indices, based on manual (manual PET index) and automatic segmenting using a threshold of SUV 15 (automated PET15 index), were calculated by dividing the sum of all hotspot volumes with the volume of all segmented bones. BSI values were obtained using a software for automated calculations. Results BSI, manual PET index, and automated PET15 index were all significantly associated with OS and concordance indices were 0.68, 0.69, and 0.70, respectively. The median BSI was 0.39 and patients with a BSI >0.39 had a significantly shorter median survival time than patients with a BSI 0.53 had a significantly shorter median survival time than patients with a manual PET index 0.11 had a significantly shorter median survival time than patients with an automated PET15 index

Following publication of the original article [1], the authors flagged the that the Kaplan-Meier curve in Fig. 6 is a duplication of the Kaplan-Meier curve in Fig. 5, which is not correct.