Uncertainty estimation and evaluation of deformation image registration based convolutional neural networks.

Objective.Fast and accurate deformable image registration (DIR), including DIR uncertainty estimation, is essential for safe and reliable clinical deployment. While recent deep learning models have shown promise in predicting DIR with its uncertainty, challenges persist in proper uncertainty evaluation and hyperparameter optimization for these methods. This work aims to develop and evaluate a model that can perform fast DIR and predict its uncertainty in seconds.Approach.This study introduces a novel probabilistic multi-resolution image registration model utilizing convolutional neural networks to estimate a multivariate normal distributed dense displacement field (DDF) in a multimodal image registration problem. To assess the quality of the DDF distribution predicted by the model, we propose a new metric based on the Kullback-Leibler divergence. The performance of our approach was evaluated against three other DIR algorithms (VoxelMorph, Monte Carlo dropout, and Monte Carlo B-spline) capable of predicting uncertainty. The evaluation of the models included not only the quality of the deformation but also the reliability of the estimated uncertainty. Our application investigated the registration of a treatment planning computed tomography (CT) to follow-up cone beam CT for daily adaptive radiotherapy.Main results.The hyperparameter tuning of the models showed a trade-off between the estimated uncertainty's reliability and the deformation's accuracy. In the optimal trade-off, our model excelled in contour propagation and uncertainty estimation (p <0.05) compared to existing uncertainty estimation models. We obtained an average dice similarity coefficient of 0.89 and a KL-divergence of 0.15.Significance.By addressing challenges in DIR uncertainty estimation and evaluation, our work showed that both the DIR and its uncertainty can be reliably predicted, paving the way for safe deployment in a clinical environment.

Detection performance and prognostic value of initial bone marrow involvement in diffuse large B-cell lymphoma: a single centre 18F-FDG PET/CT and bone marrow biopsy evaluation study.

BACKGROUND: Detection of bone marrow involvement (BMI) in diffuse large B-cell lymphoma (DLBCL) typically relies on invasive bone marrow biopsy (BMB) that faces procedure limitations, while 18F-FDG PET/CT imaging offers a noninvasive alternative. The present study assesses the performance of 18F-FDG PET/CT in DLBCL BMI detection, its agreement with BMB, and the impact of BMI on survival outcomes. PATIENTS AND METHODS: This retrospective study analyzes baseline 18F-FDG PET/CT and BMB findings in145 stage II-IV DLBCL patients, evaluating both performance of the two diagnostic procedures and the impact of BMI on survival. RESULTS: DLBCL BMI was detected in 38 patients (26.2%) using PET/CT and in 18 patients (12.4%) using BMB. Concordant results were seen in 79.3% of patients, with 20.7% showing discordant results. Combining PET/CT and BMB data, we identified 29.7% of patients with BMI. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of PET/CT for detecting DLBCL BMI were 88.4%, 100%, 100%, 95.3%, and 96.5%, respectively, while BMB showed lower sensitivity (41.9%) and NPV (46.8%). The median overall survival (OS) was not reached in any gender subgroup, with 5-year OS rates of 82% (total), 84% (female), and 80% (male) (p = 0.461), while different International Prognostic Index (IPI) groups exhibited varied 5-year OS rates: 94% for low risk (LR), 91% for low-intermediate risk (LIR), 84% for high-intermediate risk (HIR), and 65% for high risk (HR) (p = 0.0027). Bone marrow involvement did not impact OS significantly (p = 0.979). CONCLUSIONS: 18F-FDG PET/CT demonstrated superior diagnostic accuracy compared to BMB. While other studies reported poorer overall and BMI 5-year OS in DLBCL, our findings demonstrated favourable survival data.

Breast cancer risk assessment and risk distribution in 3,491 Slovenian women invited for screening at the age of 50; a population-based cross-sectional study.

BACKGROUND: The evidence shows that risk-based strategy could be implemented to avoid unnecessary harm in mammography screening for breast cancer (BC) using age-only criterium. Our study aimed at identifying the uptake of Slovenian women to the BC risk assessment invitation and assessing the number of screening mammographies in case of risk-based screening. PATIENTS AND METHODS: A cross-sectional population-based study enrolled 11,898 women at the age of 50, invited to BC screening. The data on BC risk factors, including breast density from the first 3,491 study responders was collected and BC risk was assessed using the Tyrer-Cuzick algorithm (version 8) to classify women into risk groups (low, population, moderately increased, and high risk group). The number of screening mammographies according to risk stratification was simulated. RESULTS: 57% (6,785) of women returned BC risk questionnaires. When stratifying 3,491 women into risk groups, 34.0% were assessed with low, 62.2% with population, 3.4% with moderately increased, and 0.4% with high 10-year BC risk. In the case of potential personalised screening, the number of screening mammographies would drop by 38.6% compared to the current screening policy. CONCLUSIONS: The study uptake showed the feasibility of risk assessment when inviting women to regular BC screening. 3.8% of Slovenian women were recognised with higher than population 10-year BC risk. According to Slovenian BC guidelines they may be screened more often. Overall, personalised screening would decrease the number of screening mammographies in Slovenia. This information is to be considered when planning the pilot and assessing the feasibility of implementing population risk-based screening.

Uncertainty estimation for deep learning-based pectoral muscle segmentation via Monte Carlo dropout.

Objective. Deep Learning models are often susceptible to failures after deployment. Knowing when your model is producing inadequate predictions is crucial. In this work, we investigate the utility of Monte Carlo (MC) dropout and the efficacy of the proposed uncertainty metric (UM) for flagging of unacceptable pectoral muscle segmentations in mammograms.Approach. Segmentation of pectoral muscle was performed with modified ResNet18 convolutional neural network. MC dropout layers were kept unlocked at inference time. For each mammogram, 50 pectoral muscle segmentations were generated. The mean was used to produce the final segmentation and the standard deviation was applied for the estimation of uncertainty. From each pectoral muscle uncertainty map, the overall UM was calculated. To validate the UM, a correlation between the dice similarity coefficient (DSC) and UM was used. The UM was first validated in a training set (200 mammograms) and finally tested in an independent dataset (300 mammograms). ROC-AUC analysis was performed to test the discriminatory power of the proposed UM for flagging unacceptable segmentations.Main results. The introduction of dropout layers in the model improved segmentation performance (DSC = 0.95 ± 0.07 versus DSC = 0.93 ± 0.10). Strong anti-correlation (r= -0.76,p< 0.001) between the proposed UM and DSC was observed. A high AUC of 0.98 (97% specificity at 100% sensitivity) was obtained for the discrimination of unacceptable segmentations. Qualitative inspection by the radiologist revealed that images with high UM are difficult to segment.Significance. The use of MC dropout at inference time in combination with the proposed UM enables flagging of unacceptable pectoral muscle segmentations from mammograms with excellent discriminatory power.

Challenges and opportunities for implementing hypofractionated radiotherapy in Africa: lessons from the HypoAfrica clinical trial.

The rising cancer incidence and mortality in sub-Saharan Africa (SSA) warrants an increased focus on adopting or developing approaches that can significantly increase access to treatment in the region. One such approach recommended by the recent Lancet Oncology Commission for sub-Saharan Africa is hypofractionated radiotherapy (HFRT), which can substantially increase access to radiotherapy by reducing the overall duration of time (in days) each person spends being treated. Here we highlight challenges in adopting such an approach identified during the implementation of the HypoAfrica clinical trial. The HypoAfrica clinical trial is a longitudinal, multicentre study exploring the feasibility of applying HFRT for prostate cancer in SSA. This study has presented an opportunity for a pragmatic assessment of potential barriers and facilitators to adopting HFRT. Our results highlight three key challenges: quality assurance, study harmonisation and machine maintenance. We describe solutions employed to resolve these challenges and opportunities for longer term solutions that can facilitate scaling-up use of HFRT in SSA in clinical care and multicentre clinical trials. This report provides a valuable reference for the utilisation of radiotherapy approaches that increase access to treatment and the conduct of high-quality large-scale/multi-centre clinical trials involving radiotherapy. Trial registration: Not available yet.

The Value of FET PET/CT in Recurrent Glioma with a Different IDH Mutation Status: The Relationship between Imaging and Molecular Biomarkers.

The evaluation of treatment response remains a challenge in glioma cases because the neuro oncological therapy can lead to the development of treatment-related changes (TRC) that mimic true progression (TP). Positron emission tomography (PET) using O-(2-[18F] fluoroethyl-)-L-tyrosine (18F-FET) has been shown to be a useful tool for detecting TRC and TP. We assessed the diagnostic performance of different 18F-FET PET segmentation approaches and different imaging biomarkers for differentiation between late TRC and TP in glioma patients. Isocitrate dehydrogenase (IDH) status was evaluated as a predictor of disease outcome. In our study, the proportion of TRC in IDH wild type (IDHwt) and IDH mutant (IDHm) subgroups was without significant difference. We found that the diagnostic value of static and dynamic biomarkers of 18F-FET PET for discrimination between TRC and TP depends on the IDH mutation status of the tumor. Dynamic 18F-FET PET acquisition proved helpful in the IDH wild type (IDHwt) subgroup, as opposed to the IDH mutant (IDHm) subgroup, providing an early indication to discontinue dynamic imaging in the IDHm subgroup.

The dose accumulation and the impact of deformable image registration on dose reporting parameters in a moving patient undergoing proton radiotherapy.

INTRODUCTION: Potential changes in patient anatomy during proton radiotherapy may lead to a deviation of the delivered dose. A dose estimate can be computed through a deformable image registration (DIR) driven dose accumulation. The present study evaluates the accumulated dose uncertainties in a patient subject to an inadvertent breathing associated motion. MATERIALS AND METHODS: A virtual lung tumour was inserted into a pair of single participant landmark annotated computed tomography images depicting opposite breathing phases, with the deep inspiration breath-hold the planning reference and the exhale the off-reference geometry. A novel Monte Carlo N-Particle, Version 6 (MCNP6) dose engine was developed, validated and used in treatment plan optimization. Three DIR methods were compared and used to transfer the exhale simulated dose to the reference geometry. Dose conformity and homogeneity measures from International Committee on Radioactivity Units and Measurements (ICRU) reports 78 and 83 were evaluated on simulated dose distributions registered with different DIR algorithms. RESULTS: The MCNP6 dose engine handled patient-like geometries in reasonable dose calculation times. All registration methods were able to align image associated landmarks to distances, comparable to voxel sizes. A moderate deterioration of ICRU measures was encountered in comparing doses in on and off-reference anatomy. There were statistically significant DIR driven differences in ICRU measures, particularly a 10% difference in the relative D98% for planning tumour volume and in the 3 mm/3% gamma passing rate. CONCLUSIONS: T he dose accumulation over two anatomies resulted in a DIR driven uncertainty, important in reporting the associated ICRU measures for quality assurance.

Abnormal metabolic covariance patterns associated with multiple system atrophy and progressive supranuclear palsy.

PURPOSE: Differentiation between neurodegenerative parkinsonisms, whose early clinical presentation is similar, may be improved with metabolic brain imaging. In this study we applied a specific network analysis to 2-[18F]FDG PET brain scans to identify the characteristic metabolic patterns for multiple system atrophy (MSA) and progressive supranuclear palsy (PSP) in a new European cohort. We also developed a new tool to recognize and estimate patients' metabolic brain heterogeneity. METHODS: 20 MSA-P patients, 20 PSP patients and 20 healthy controls (HC) underwent 2-[18F]FDG PET brain imaging. The scaled subprofile model/principal component analysis was applied to identify MSA/PSP-related patterns; MSARP and PSPRP. Additional, 56 MSA, 45 PSP, 116 PD and 61 HC subjects were analyzed for validation. We innovatively applied heat-map analysis to extract and graphically display the pattern's regional sub-scores in individual subjects. RESULTS: MSARP was characterized by hypometabolism in cerebellum and putamen, and PSPRP by hypometabolism in medial prefrontal cortices, nucleus caudatus, frontal cortices and mesencephalon. Patterns' expression discriminated between MSA/PSP patients and HCs as well as between different parkinsonian cohorts (p < 0.001). Both patterns were sensitive and specific (AUC for MSARP/PSPRP: 0.96/0.99). Heat-map analysis showed differences within MSA/PSP subjects and HCs consistent with clinical presentation. CONCLUSIONS: Replication and validation of MSARP and PSPRP confirms robustness of these metabolic biomarkers and supports its application in clinical and research practice. Heat-map analysis gives us an insight into the contribution of various pattern's regions to patterns' expression in individual subjects, which improves our insight into the heterogeneity of studied syndromes.

System resolution versus image uncertainty for positron emission tomography scanners.

Purpose: Quantitative measures derived from positron emission tomography (PET) images are subject to statistical uncertainty, depending critically on system parameters, including the spatial resolution of the scanner. Predictions of statistical uncertainty of quantitative measures were compared with measurements. Approach: Measurements were performed on the dual-ring PET prototype setup at the University of Michigan. The setup consisted of multiple detectors that, in combination, span a system resolution ranging between 1 and 5.5 mm full-width-at-half-maximum (FWHM). A Micro Jaszczak hot-spot phantom with rod diameters between 1.2 and 4.8 mm was imaged and independently reconstructed for different detector combinations. Statistical properties of quantitative measures were evaluated for different reconstructions. Results: Measured signal-to-noise ratios (SNR) of 108 ± 14 , 85 ± 11 , and 40 ± 5 for high (0.92 to 0.98 mm FWHM), medium (1.3 to 1.5 mm FWHM), and low (5.5 mm FWHM) resolution detector configurations and 1 million events in general terms followed predications based on the detector resolution. Conclusions: The unique tomograph configuration allowed for experimental comparison of the impact of spatial resolution on statistical properties of reconstructions in the same setup. An SNR advantage in systems with high resolutions was predicted and confirmed even for object features significantly larger than the detector resolution.

Quantitative imaging biomarkers of immune-related adverse events in immune-checkpoint blockade-treated metastatic melanoma patients: a pilot study.

PURPOSE: To develop quantitative molecular imaging biomarkers of immune-related adverse event (irAE) development in malignant melanoma (MM) patients receiving immune-checkpoint inhibitors (ICI) imaged with 18F-FDG PET/CT. METHODS: 18F-FDG PET/CT images of 58 MM patients treated with anti-PD-1 or anti-CTLA-4 ICI were retrospectively analyzed for indication of irAE. Three target organs, most commonly affected by irAE, were considered: bowel, lung, and thyroid. Patient charts were reviewed to identify which patients experienced irAE, irAE grade, and time to irAE diagnosis. Target organs were segmented using a convolutional neural network (CNN), and novel quantitative imaging biomarkers - SUV percentiles (SUVX%) of 18F-FDG uptake within the target organs - were correlated with the clinical irAE status. Area under the receiver-operating characteristic curve (AUROC) was used to quantify irAE detection performance. Patients who did not experience irAE were used to establish normal ranges for target organ 18F-FDG uptake. RESULTS: A total of 31% (18/58) patients experienced irAE in the three target organs: bowel (n=6), lung (n=5), and thyroid (n=9). Optimal percentiles for identifying irAE were bowel (SUV95%, AUROC=0.79), lung (SUV95%, AUROC=0.98), and thyroid (SUV75%, AUROC=0.88). Optimal cut-offs for irAE detection were bowel (SUV95%>2.7 g/mL), lung (SUV95%>1.7 g/mL), and thyroid (SUV75%>2.1 g/mL). Normal ranges (95% confidence interval) for the SUV percentiles in patients without irAE were bowel [1.74, 2.86 g/mL], lung [0.73, 1.46 g/mL], and thyroid [0.86, 1.99 g/mL]. CONCLUSIONS: Increased 18F-FDG uptake within irAE-affected organs provides predictive information about the development of irAE in MM patients receiving ICI and represents a potential quantitative imaging biomarker for irAE. Some irAE can be detected on 18F-FDG PET/CT well before clinical symptoms appear.

[18F]FDG PET immunotherapy radiomics signature (iRADIOMICS) predicts response of non-small-cell lung cancer patients treated with pembrolizumab.

Background Immune checkpoint inhibitors have changed the paradigm of cancer treatment; however, non-invasive biomarkers of response are still needed to identify candidates for non-responders. We aimed to investigate whether immunotherapy [18F]FDG PET radiomics signature (iRADIOMICS) predicts response of metastatic non-small-cell lung cancer (NSCLC) patients to pembrolizumab better than the current clinical standards. Patients and methods Thirty patients receiving pembrolizumab were scanned with [18F]FDG PET/CT at baseline, month 1 and 4. Associations of six robust primary tumour radiomics features with overall survival were analysed with Mann-Whitney U-test (MWU), Cox proportional hazards regression analysis, and ROC curve analysis. iRADIOMICS was constructed using univariate and multivariate logistic models of the most promising feature(s). Its predictive power was compared to PD-L1 tumour proportion score (TPS) and iRECIST using ROC curve analysis. Prediction accuracies were assessed with 5-fold cross validation. Results The most predictive were baseline radiomics features, e.g. Small Run Emphasis (MWU, p = 0.001; hazard ratio = 0.46, p = 0.007; AUC = 0.85 (95% CI 0.69-1.00)). Multivariate iRADIOMICS was found superior to the current standards in terms of predictive power and timewise with the following AUC (95% CI) and accuracy (standard deviation): iRADIOMICS (baseline), 0.90 (0.78-1.00), 78% (18%); PD-L1 TPS (baseline), 0.60 (0.37-0.83), 53% (18%); iRECIST (month 1), 0.79 (0.62-0.95), 76% (16%); iRECIST (month 4), 0.86 (0.72-1.00), 76% (17%). Conclusions Multivariate iRADIOMICS was identified as a promising imaging biomarker, which could improve management of metastatic NSCLC patients treated with pembrolizumab. The predicted non-responders could be offered other treatment options to improve their overall survival.

Evaluation of a high resolution silicon PET insert module.

Conventional PET systems can be augmented with additional detectors placed in close proximity of the region of interest. We developed a high resolution PET insert module to evaluate the added benefit of such a combination. The insert module consists of two back-to-back 1 mm thick silicon sensors, each segmented into 1040 1 mm2 pads arranged in a 40 by 26 array. A set of 16 VATAGP7.1 ASICs and a custom assembled data acquisition board were used to read out the signal from the insert module. Data were acquired in slice (2D) geometry with a Jaszczak phantom (rod diameters of 1.2-4.8 mm) filled with 18F-FDG and the images were reconstructed with ML-EM method. Both data with full and limited angular coverage from the insert module were considered and three types of coincidence events were combined. The ratio of high-resolution data that substantially improves quality of the reconstructed image for the region near the surface of the insert module was estimated to be about 4%. Results from our previous studies suggest that such ratio could be achieved at a moderate technological expense by using an equivalent of two insert modules (an effective sensor thickness of 4 mm).

A high-resolution PET demonstrator using a silicon "magnifying glass".

To assist ongoing investigations of the limits of the tradeoff between spatial resolution and noise in PET imaging, several PET instruments based on silicon-pad detectors have been developed. The latest is a segment of a dual-ring device to demonstrate that excellent reconstructed image resolution can be achieved with a scanner that uses high-resolution detectors placed close to the object of interest or surrounding a small field-of-view in combination with detectors having modest resolution at larger radius. The outer ring of our demonstrator comprises conventional BGO block detectors scavenged from a clinical PET scanner and located at a 500mm radius around a 50mm diameter field-of-view. The inner detector-in contrast to the high-Z scintillator typically used in PET-is based on silicon-pad detectors located at 70mm nominal radius. Each silicon detector has 512 1.4mm x 1.4mm x 1mm detector elements in a 16 x 32 array and is read out using VATA GP7 ASICs (Gamma Medica-Ideas, Northridge, CA). Even though virtually all interactions of 511 keV annihilation photons in silicon are Compton-scatter, both high spatial resolution and reasonable sensitivity appears possible. The system has demonstrated resolution of ~0.7mm FWHM with Na-22 for coincidences having the highest intrinsic resolution (silicon-silicon) and 5-6mm FWHM for the lowest resolution BGO-BGO coincidences. Spatial resolution for images reconstructed from the mixed silicon-BGO coincidences is ~1.5mm FWHM demonstrating the "magnifying-glass" concept.

A prototype of very high resolution small animal PET scanner using silicon pad detectors.

A very high resolution small animal positron emission tomograph (PET) which can achieve sub-millimeter spatial resolution is being developed using silicon pad detectors. The prototype PET for a single slice instrument consists of two 1 mm thick silicon pad detectors, each containing a 32 x 16 array of 1.4 mm x 1.4 mm pads read out with four VATAGP3 chips which have 128 channels low-noise self triggering ASIC in each chip, coincidence units, a source turntable and tungsten slice collimator. The silicon detectors were located edgewise on opposite sides of a 4 cm field-of-view to maximize efficiency. Energy resolution is dominated by electronic noise, which is 0.98% (1.38 keV) FWHM at 140.5 keV. Coincidence timing resolution is 82.1 ns FWHM and coincidence efficiency was measured to be 1.04 x 10(-3) % from two silicon detectors with annihilation photons of (18)F source Image data were acquired and reconstructed using conventional 2-D filtered-back projection (FBP) and a maximum likelihood expectation maximization (ML-EM) method. Image resolution of approximately 1.45 mm FWHM is obtained from 1-D profile of 1.1 mm diameter (18)F line source image. Even better resolution can be obtained with smaller detector element sizes. While many challenges remain in scaling up the instrument to useful efficiency including densely packed detectors and significantly improved timing resolution, performance of the test setup in terms of easily achieving submillimeter resolution is compelling.

Performance evaluation of a very high resolution small animal PET imager using silicon scatter detectors.

A very high resolution positron emission tomography (PET) scanner for small animal imaging based on the idea of inserting a ring of high-granularity solid-state detectors into a conventional PET scanner is under investigation. A particularly interesting configuration of this concept, which takes the form of a degenerate Compton camera, is shown capable of providing sub-millimeter resolution with good sensitivity. We present a Compton PET system and estimate its performance using a proof-of-concept prototype. A prototype single-slice imaging instrument was constructed with two silicon detectors 1 mm thick, each having 512 1.4 mm x 1.4 mm pads arranged in a 32 x 16 array. The silicon detectors were located edgewise on opposite sides and flanked by two non-position sensitive BGO detectors. The scanner performance was measured for its sensitivity, energy, timing, spatial resolution and resolution uniformity. Using the experimental scanner, energy resolution for the silicon detectors is 1%. However, system energy resolution is dominated by the 23% FWHM BGO resolution. Timing resolution for silicon is 82.1 ns FWHM due to time-walk in trigger devices. Using the scattered photons, time resolution between the BGO detectors is 19.4 ns FWHM. Image resolution of 980 microm FWHM at the center of the field-of-view (FOV) is obtained from a 1D profile of a 0.254 mm diameter (18)F line source image reconstructed using the conventional 2D filtered back-projection (FBP). The 0.4 mm gap between two line sources is resolved in the image reconstructed with both FBP and the maximum likelihood expectation maximization (ML-EM) algorithm. The experimental instrument demonstrates sub-millimeter resolution. A prototype having sensitivity high enough for initial small animal images can be used for in vivo studies of small animal models of metabolism, molecular mechanism and the development of new radiotracers.