Optimizing platelet transfusion through a personalized deep learning risk assessment system for demand management.

ABSTRACT: Platelet demand management (PDM) is a resource-consuming task for physicians and transfusion managers of large hospitals. Inpatient numbers and institutional standards play significant roles in PDM. However, reliance on these factors alone commonly results in platelet shortages. Using data from multiple sources, we developed, validated, tested, and implemented a patient-specific approach to support PDM that uses a deep learning-based risk score to forecast platelet transfusions for each hospitalized patient in the next 24 hours. The models were developed using retrospective electronic health record data of 34 809 patients treated between 2017 and 2022. Static and time-dependent features included demographics, diagnoses, procedures, blood counts, past transfusions, hematotoxic medications, and hospitalization duration. Using an expanding window approach, we created a training and live-prediction pipeline with a 30-day input and 24-hour forecast. Hyperparameter tuning determined the best validation area under the precision-recall curve (AUC-PR) score for long short-term memory deep learning models, which were then tested on independent data sets from the same hospital. The model tailored for hematology and oncology patients exhibited the best performance (AUC-PR, 0.84; area under the receiver operating characteristic curve [ROC-AUC], 0.98), followed by a multispecialty model covering all other patients (AUC-PR, 0.73). The model specific to cardiothoracic surgery had the lowest performance (AUC-PR, 0.42), likely because of unexpected intrasurgery bleedings. To our knowledge, this is the first deep learning-based platelet transfusion predictor enabling individualized 24-hour risk assessments at high AUC-PR. Implemented as a decision-support system, deep-learning forecasts might improve patient care by detecting platelet demand earlier and preventing critical transfusion shortages.

CT-guided High-Dose-Rate Brachytherapy versus Transarterial Chemoembolization in Patients with Unresectable Hepatocellular Carcinoma.

Background CT-guided high-dose-rate (HDR) brachytherapy (hereafter, HDR brachytherapy) has been shown to be safe and effective for patients with unresectable hepatocellular carcinoma (HCC), but studies comparing this therapy with other local-regional therapies are scarce. Purpose To compare patient outcomes of HDR brachytherapy and transarterial chemoembolization (TACE) in patients with unresectable HCC. Materials and Methods This multi-institutional retrospective study included consecutive treatment-naive adult patients with unresectable HCC who underwent either HDR brachytherapy or TACE between January 2010 and December 2022. Overall survival (OS) and progression-free survival (PFS) were compared between patients matched for clinical and tumor characteristics by propensity score matching. Not all patients who underwent TACE had PFS available; thus, a different set of patients was used for PFS and OS analysis for this treatment. Hazard ratios (HRs) were calculated from Kaplan-Meier survival curves. Results After propensity matching, 150 patients who underwent HDR brachytherapy (median age, 71 years [IQR, 63-77 years]; 117 males) and 150 patients who underwent TACE (OS analysis median age, 70 years [IQR, 63-77 years]; 119 male; PFS analysis median age, 68 years [IQR: 63-76 years]; 119 male) were analyzed. Hazard of death was higher in the TACE versus HDR brachytherapy group (HR, 4.04; P < .001). Median estimated PFS was 32.8 months (95% CI: 12.5, 58.7) in the HDR brachytherapy group and 11.6 months (95% CI: 4.9, 22.7) in the TACE group. Hazard of disease progression was higher in the TACE versus HDR brachytherapy group (HR, 2.23; P < .001). Conclusion In selected treatment-naive patients with unresectable HCC, treatment with CT-guided HDR brachytherapy led to improved OS and PFS compared with TACE. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Chapiro in this issue.

Current use of percutaneous image-guided tumor ablation for the therapy of liver tumors: lessons learned from the registry of the German Society for Interventional Radiology and Minimally Invasive Therapy (DeGIR) 2018-2022.

OBJECTIVES: Percutaneous image-guided tumor ablation of liver malignancies has become an indispensable therapeutic procedure. The aim of this evaluation of the prospectively managed multinational registry of the voluntary German Society for Interventional Radiology and Minimally Invasive Therapy (DeGIR) was to analyze its use, technical success, and complications in clinical practice. MATERIALS AND METHODS: All liver tumor ablations from 2018 to 2022 were included. Technical success was defined as complete ablation of the tumor with an ablative margin. RESULTS: A total of 7228 liver tumor ablations from 136 centers in Germany and Austria were analyzed. In total, 31.4% (2268/7228) of patients were female. Median age was 67 years (IQR 58-74 years). Microwave ablation (MWA) was performed in 65.1% (4703/7228), and radiofrequency ablation (RFA) in 32.7% (2361/7228). Of 5229 cases with reported tumor etiology, 60.3% (3152/5229) of ablations were performed for liver metastases and 37.3% (1950/5229) for hepatocellular carcinoma. The median lesion diameter was 19 mm (IQR 12-27 mm). In total, 91.8% (6636/7228) of ablations were technically successful. The rate of technically successful ablations was significantly higher in MWA (93.9%, 4417/4703) than in RFA (87.3%, 2061/2361) (p < 0.0001). The total complication rate was 3.0% (214/7228) and was significantly higher in MWA (4.0%, 189/4703) than in RFA (0.9%, 21/2361, p < 0.0001). Additional needle track ablation did not increase the rate of major complications significantly (24.8% (33/133) vs. 28.4% (23/81), p = 0.56)). CONCLUSION: MWA is the most frequent ablation method. Percutaneous image-guided liver tumor ablations have a high technical success rate, which is higher for MWA than RFA. The complication rate is generally low but is higher for MWA than RFA. CLINICAL RELEVANCE STATEMENT: Percutaneous image-guided liver ablation using microwave ablation and radiofrequency ablation are effective therapeutic procedures with low complication rates for the treatment of primary and secondary liver malignancies. KEY POINTS: • Percutaneous image-guided liver tumor ablations have a high technical success rate, which is higher for microwave ablation than radiofrequency ablation. • Microwave ablation is the most frequent ablation method ahead of radiofrequency ablation. • The complication rate is generally low but is higher for microwave ablation than radiofrequency ablation.

Low bone mineral density is a prognostic factor for elderly patients with HCC undergoing TACE: results from a multicenter study.

OBJECTIVES: Low bone mineral density (BMD) was recently identified as a novel risk factor for patients with hepatocellular carcinoma (HCC). In this multicenter study, we aimed to validate the role of BMD as a prognostic factor for patients with HCC undergoing transarterial chemoembolization (TACE). METHODS: This retrospective multicenter trial included 908 treatment-naïve patients with HCC who were undergoing TACE as a first-line treatment, at six tertiary care centers, between 2010 and 2020. BMD was assessed by measuring the mean Hounsfield units (HUs) in the midvertebral core of the 11th thoracic vertebra, on contrast-enhanced computer tomography performed before treatment. We assessed the influence of BMD on median overall survival (OS) and performed multivariate analysis including established estimates for survival. RESULTS: The median BMD was 145 HU (IQR, 115-175 HU). Patients with a high BMD (≥ 114 HU) had a median OS of 22.2 months, while patients with a low BMD (< 114 HU) had a lower median OS of only 16.2 months (p < .001). Besides albumin, bilirubin, tumor number, and tumor diameter, BMD remained an independent prognostic factor in multivariate analysis. CONCLUSIONS: BMD is an independent predictive factor for survival in elderly patients with HCC undergoing TACE. The integration of BMD into novel scoring systems could potentially improve survival prediction and clinical decision-making. KEY POINTS: • Bone mineral density can be easily assessed in routinely acquired pre-interventional computed tomography scans. • Bone mineral density is an independent predictive factor for survival in elderly patients with HCC undergoing TACE. • Thus, bone mineral density is a novel imaging biomarker for prognosis prediction in elderly patients with HCC undergoing TACE.

Identification of radiomic biomarkers in a set of four skeletal muscle groups on Dixon MRI of the NAKO MR study.

In this work, we propose a processing pipeline for the extraction and identification of meaningful radiomics biomarkers in skeletal muscle tissue as displayed using Dixon-weighted MRI. Diverse and robust radiomics features can be identified that may be of aid in the accurate quantification e.g. varying degrees of sarcopenia in respective muscles of large cohorts. As such, the approach comprises the texture feature extraction from raw data based on well established approaches, such as a nnU-Net neural network and the Pyradiomics toolbox, a subsequent selection according to adequate conditions for the muscle tissue of the general population, and an importance-based ranking to further narrow the amount of meaningful features with respect to auxiliary targets. The performance was investigated with respect to the included auxiliary targets, namely age, body mass index (BMI), and fat fraction (FF). Four skeletal muscles with different fiber architecture were included: the mm. glutaei, m. psoas, as well as the extensors and adductors of the thigh. The selection allowed for a reduction from 1015 available texture features to 65 for age, 53 for BMI, and 36 for FF from the available fat/water contrast images considering all muscles jointly. Further, the dependence of the importance rankings calculated for the auxiliary targets on validation sets (in a cross-validation scheme) was investigated by boxplots. In addition, significant differences between subgroups of respective auxiliary targets as well as between both sexes were shown to be present within the ten lowest ranked features by means of Kruskal-Wallis H-tests and Mann-Whitney U-tests. The prediction performance for the selected features and the ranking scheme were verified on validation sets by a random forest based multi-class classification, with strong area under the curve (AUC) values of the receiver operator characteristic (ROC) of 73.03 ± 0.70 % and 73.63 ± 0.70 % for the water and fat images in age, 80.68 ± 0.30 % and 88.03 ± 0.89 % in BMI, as well as 98.36 ± 0.03 % and 98.52 ± 0.09 % in FF.

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.

Radiation exposure and establishment of diagnostic reference levels of whole-body low-dose CT for the assessment of multiple myeloma with second- and third-generation dual-source CT.

BACKGROUND: In the assessment of diseases causing skeletal lesions such as multiple myeloma (MM), whole-body low-dose computed tomography (WBLDCT) is a sensitive diagnostic imaging modality, which has the potential to replace the conventional radiographic survey. PURPOSE: To optimize radiation protection and examine radiation exposure, and effective and organ doses of WBLDCT using different modern dual-source CT (DSCT) devices, and to establish local diagnostic reference levels (DRL). MATERIAL AND METHODS: In this retrospective study, 281 WBLDCT scans of 232 patients performed between January 2017 and April 2020 either on a second- (A) or third-generation (B) DSCT device could be included. Radiation exposure indices and organ and effective doses were calculated using a commercially available automated dose-tracking software based on Monte-Carlo simulation techniques. RESULTS: The radiation exposure indices and effective doses were distributed as follows (median, interquartile range): (A) second-generation DSCT: volume-weighted CT dose index (CTDIvol) 1.78 mGy (1.47-2.17 mGy); dose length product (DLP) 282.8 mGy·cm (224.6-319.4 mGy·cm), effective dose (ED) 1.87 mSv (1.61-2.17 mSv) and (B) third-generation DSCT: CTDIvol 0.56 mGy (0.47-0.67 mGy), DLP 92.0 mGy·cm (73.7-107.6 mGy·cm), ED 0.61 mSv (0.52-0.69 mSv). Radiation exposure indices and effective and organ doses were significantly lower with third-generation DSCT (P < 0.001). Local DRLs could be set for CTDIvol at 0.75 mGy and DLP at 120 mGy·cm. CONCLUSION: Third-generation DSCT requires significantly lower radiation dose for WBLDCT than second-generation DSCT and has an effective dose below reported doses for radiographic skeletal surveys. To ensure radiation protection, DRLs regarding WBLDCT are required, where our locally determined values may help as benchmarks.

Metal Artefact Reduction Sequences (MARS) in Magnetic Resonance Imaging (MRI) after Total Hip Arthroplasty (THA) : A non-invasive approach for preoperative differentiation between periprosthetic joint infection (PJI) and aseptic complications?

BACKGROUND: In the past, radiographic imaging was of minor relevance in the diagnosis of periprosthetic joint infections (PJI). Since metal artefact reduction sequences (MARS) are available, magnetic resonance imaging (MRI) has become a promising diagnostic tool for the evaluation of hip arthroplasty implants. The purpose of the present study was to evaluate the efficacy of MARS-MRI in comparison to established diagnostic tools to distinguish between aseptic failure and PJI. METHODS: From July 2018 to September 2019, 33 patients classified as having an aseptic joint effusion were recruited into the study. The group included 22 women and 11 men with a mean age of 70.4 ± 13.7 (42-88) years. In the same period, 12 patients were classified as having a PJI. The group consisted of 9 women and 3 men with a mean age of 72.5 ± 10.6 (54-88) years. MARS-MRI was conducted using the optimized parameters at 1.5 T in a coronal and axial STIR (short-tau-inversion recovery), a non-fat-saturated T2 in coronal view and a non-fat-saturated T1 in transverse view in 45 patients with painful hip after total hip arthroplasty (THA). Normally distributed continuous data were shown as mean ± standard deviation (SD) and compared using student's t-test. Non-normally distributed continuous data were shown as mean and compared using the Mann-Whitney U test. RESULTS: Synovial layering and muscle edema were significant features of periprosthetic joint infection, with sensitivities of 100% and specifities of 63.0-75.0%. The combined specifity and sensitivity levels of synovial layering and muscular edema was 88.0% and 90.0%. Granulomatous synovitis was a significant feature for aseptic failure, with 90.0% sensitivity and 57.0% specifity. CONCLUSION: MARS-MRI is as suitable as standard diagnostic tools to distinguish between aseptic failure and PJI in patients with THA. Further studies with larger patient numbers have to prove whether MARS-MRI could be integral part of PJI diagnostic.

Diagnostic reference levels for chest computed tomography in children as a function of patient size.

BACKGROUND: Radiation exposures from computed tomography (CT) in children are inadequately studied. Diagnostic reference levels (DRLs) can help optimise radiation doses. OBJECTIVE: To determine local DRLs for paediatric chest CT performed mainly on modern dual-source, multi-slice CT scanners as a function of patient size. MATERIALS AND METHODS: Five hundred thirty-eight chest CT scans in 345 children under 15 years (y) of age (median age: 8 y, interquartile range [IQR]: 4-13 y) performed on four different CT scanners (38% on third-generation and 43% on second-generation dual-source CT) between November 2013 and December 2020 were retrospectively analysed. Examinations were grouped by water-equivalent diameter as a measure of patient size. DRLs for volume CT dose index (CTDIvol) and dose-length product (DLP) were determined for six different patient sizes and compared to national and European DRLs. RESULTS: The DRLs for CTDIvol and DLP are determined for each patient size group as a function of water-equivalent diameter as follows: (I) < 13 cm (n = 22; median: age 7 months): 0.4 mGy, 7 mGy·cm; (II) 13 cm to less than 17 cm (n = 151; median: age 3 y): 1.2 mGy, 25 mGy·cm; (III) 17 cm to less than 21 cm (n = 211; median: age 8 y): 1.7 mGy, 44 mGy·cm; (IV) 21 cm to less than 25 cm (n = 97; median: age 14 y): 3.0 mGy, 88 mGy·cm; (V) 25 cm to less than 29 cm (n = 42; median: age 14 y): 4.5 mGy, 135 mGy·cm; (VI) ≥ 29 cm (n = 15; median: age 14 y): 8.0 mGy, 241 mGy·cm. Compared with corresponding age and weight groups, our size-based DRLs for DLP are 54% to 71% lower than national and 23% to 85% lower than European DRLs. CONCLUSION: We developed DRLs for paediatric chest CT as a function of patient size with substantially lower values than national and European DRLs. Precise knowledge of size-based DRLs may assist other institutions in further dose optimisation in children.

Radiation exposure, organ and effective dose of CT-guided liver biopsy as a function of lesion depth and size.

Computed tomography (CT)-guided percutaneous biopsies play an important role in the diagnostic workup of liver lesions. Because radiation dose accumulates rapidly due to repeated image acquisition in a relatively small scan area, analysing radiation exposure is critical for improving radiation protection of CT-guided interventions. The aim of this study was to assess the radiation dose of CT-guided liver biopsies and the influence of lesion parameters, and to establish a local diagnostic reference level (DRL). In this observational retrospective cohort study, dose data of 60 CT-guided liver biopsies between September 2016 and July 2017 were analysed. Radiation exposure was reported for volume-weighted CT dose index (CTDIvol), size-specific dose estimate (SSDE), dose-length product (DLP) and effective dose (ED). Radiation dose of CT-guided liver biopsy was (median (interquartile range)): CTDIvol9.91 mGy (8.33-11.45 mGy), SSDE 10.42 mGy (9.39-11.70 mGy), DLP 542 mGy cm (410-733 mGy cm), ED 8.52 mSv (7.17-13.25 mSv). Radiation exposure was significantly higher in biopsies of deep liver lesions compared to superficial lesions (DLP 679 ± 285 mGy cm vs. 497 ± 167 mGy cm,p= 0.0046). No significant dose differences were observed for differences in lesion or needle size. With helical CT spirals additional to the biopsy-guiding axial CT scans, radiation exposure was significantly increased: 797 ± 287 mGy cm vs. 495 ± 162 mGy cm,p< 0.0001. The local DRL is CTDIvol9.91 mGy, DLP 542 mGy cm. Radiation dose is significantly increased in biopsies of deeper liver lesions compared with superficial lesions. Interventions with additional biopsy-guiding CT spirals lead to higher radiation doses. This study provides a detailed analysis of local radiation doses for CT-guided liver biopsies and provides a benchmark for optimising radiation protection in interventional radiology.

Contrast agent dose reduction in computed tomography with deep learning using a conditional generative adversarial network.

OBJECTIVES: To reduce the dose of intravenous iodine-based contrast media (ICM) in CT through virtual contrast-enhanced images using generative adversarial networks. METHODS: Dual-energy CTs in the arterial phase of 85 patients were randomly split into an 80/20 train/test collective. Four different generative adversarial networks (GANs) based on image pairs, which comprised one image with virtually reduced ICM and the original full ICM CT slice, were trained, testing two input formats (2D and 2.5D) and two reduced ICM dose levels (-50% and -80%). The amount of intravenous ICM was reduced by creating virtual non-contrast series using dual-energy and adding the corresponding percentage of the iodine map. The evaluation was based on different scores (L1 loss, SSIM, PSNR, FID), which evaluate the image quality and similarity. Additionally, a visual Turing test (VTT) with three radiologists was used to assess the similarity and pathological consistency. RESULTS: The -80% models reach an SSIM of > 98%, PSNR of > 48, L1 of between 7.5 and 8, and an FID of between 1.6 and 1.7. In comparison, the -50% models reach a SSIM of > 99%, PSNR of > 51, L1 of between 6.0 and 6.1, and an FID between 0.8 and 0.95. For the crucial question of pathological consistency, only the 50% ICM reduction networks achieved 100% consistency, which is required for clinical use. CONCLUSIONS: The required amount of ICM for CT can be reduced by 50% while maintaining image quality and diagnostic accuracy using GANs. Further phantom studies and animal experiments are required to confirm these initial results. KEY POINTS: • The amount of contrast media required for CT can be reduced by 50% using generative adversarial networks. • Not only the image quality but especially the pathological consistency must be evaluated to assess safety. • A too pronounced contrast media reduction could influence the pathological consistency in our collective at 80%.

Non-invasive tumor decoding and phenotyping of cerebral gliomas utilizing multiparametric 18F-FET PET-MRI and MR Fingerprinting.

OBJECTIVES: The introduction of the 2016 WHO classification of CNS tumors has made the combined molecular and histopathological characterization of tumors a pivotal part of glioma patient management. Recent publications on radiogenomics-based prediction of the mutational status have demonstrated the predictive potential of imaging-based, non-invasive tissue characterization algorithms. Hence, the aim of this study was to assess the potential of multiparametric 18F-FET PET-MRI including MR fingerprinting accelerated with machine learning and radiomic algorithms to predict tumor grading and mutational status of patients with cerebral gliomas. MATERIALS AND METHODS: 42 patients with suspected primary brain tumor without prior surgical or systemic treatment or biopsy underwent an 18F-FET PET-MRI examination. To differentiate the mutational status and the WHO grade of the cerebral tumors, support vector machine and random forest were trained with the radiomics signature of the multiparametric PET-MRI data including MR fingerprinting. Surgical sampling served as a gold standard for histopathological reference and assessment of mutational status. RESULTS: The 5-fold cross-validated area under the curve in predicting the ATRX mutation was 85.1%, MGMT mutation was 75.7%, IDH1 was 88.7%, and 1p19q was 97.8%. The area under the curve of differentiating low-grade glioma vs. high-grade glioma was 85.2%. CONCLUSION: 18F-FET PET-MRI and MR fingerprinting enable high-quality imaging-based tumor decoding and phenotyping for differentiation of low-grade vs. high-grade gliomas and for prediction of the mutational status of ATRX, IDH1, and 1p19q. These initial results underline the potential of 18F-FET PET-MRI to serve as an alternative to invasive tissue characterization.

[Artificial Intelligence in radiology : What can be expected in the next few years?] / Künstliche Intelligenz in der Radiologie : Was ist in den nächsten Jahren zu erwarten?

CLINICAL/METHODOLOGICAL ISSUE: Artificial intelligence (AI) is being increasingly used in the field of radiology. The aim of this review is to illustrate the developments expected in the next 5 to 10 years as well as possible advantages and risks. STANDARD RADIOLOGICAL METHODS: Currently, all computed tomography (CT) images are reconstructed using programmed algorithms. Pathologies are detected by the radiologist with a high expenditure of time and evaluated using standardized procedures. METHODOLOGICAL INNOVATIONS: AI can potentially provide a significant improvement to all these standard procedures in the future. CT reconstructions can be significantly enhanced using generative adversarial networks (GAN). Histology can be evaluated using radiomics or deep learning (DL)-based image analysis and the prognosis of the patient can be predicted highly individualized. PERFORMANCE: The performance of the networks is strongly influenced by data quality and requires extensive validation. The ability and willingness of the manufacturers to integrate these into the existing RIS/PACS systems is also decisive. EVALUATION: AI will have a large impact on the daily clinical work of radiologists. However, publications on the risks of the technology and on adequate validation are still lacking. In addition to opening new fields of application, further research regarding possible risks is warranted. PRACTICAL RECOMMENDATIONS: In the next 5 to 10 years, AI will improve and facilitate work in clinical practice. The integration of the applications into the existing RIS/PACS systems is expected to take place via app stores and/or existing teleradiology networks.

AI as a New Frontier in Contrast Media Research: Bridging the Gap Between Contrast Media Reduction, the Contrast-Free Question and New Application Discoveries.

ABSTRACT: Artificial intelligence (AI) techniques are currently harnessed to revolutionize the domain of medical imaging. This review investigates 3 major AI-driven approaches for contrast agent management: new frontiers in contrast agent dose reduction, the contrast-free question, and new applications. By examining recent studies that use AI as a new frontier in contrast media research, we synthesize the current state of the field and provide a comprehensive understanding of the potential and limitations of AI in this context. In doing so, we show the dose limits of reducing the amount of contrast agents and demonstrate why it might not be possible to completely eliminate contrast agents in the future. In addition, we highlight potential new applications to further increase the radiologist's sensitivity at normal doses. At the same time, this review shows which network architectures provide promising approaches and reveals possible artifacts of a paired image-to-image conversion. Furthermore, current US Food and Drug Administration regulatory guidelines regarding AI/machine learning-enabled medical devices are highlighted.

Impact of CT and MRI in the diagnostic workup of malignant triton tumour-a monocentric analysis and review of the literature.

OBJECTIVES: Malignant triton tumours (MTTs) are rare but aggressive subtypes of malignant peripheral nerve sheath tumours (MPNSTs) with a high recurrence rate and 5-year survival of 14%. Systematic imaging data on MTTs are scarce and mainly based on single case reports. Therefore, we aimed to identify typical CT and MRI features to improve early diagnosis rates of this uncommon entity. METHODS: A systematic review on literature published until December 2022 on imaging characteristics of MTTs was performed. Based on that, we conducted a retrospective, monocentric analysis of patients with histopathologically proven MTTs from our department. Explorative data analysis was performed. RESULTS: Initially, 29 studies on 34 patients (31.42 ± 22.6 years, 12 female) were evaluated: Literature described primary MTTs as huge, lobulated tumours (108 ± 99.3 mm) with central necrosis (56% [19/34]), low T1w (81% [17/21]), high T2w signal (90% [19/21]) and inhomogeneous enhancement on MRI (54% [7/13]). Analysis of 16 patients (48.9 ± 13.8 years; 9 female) from our institution revealed comparable results: primary MTTs showed large, lobulated masses (118 mm ± 64.9) with necrotic areas (92% [11/12]). MRI revealed low T1w (100% [7/7]), high T2w signal (100% [7/7]) and inhomogeneous enhancement (86% [6/7]). Local recurrences and soft-tissue metastases mimicked these features, while nonsoft-tissue metastases appeared unspecific. CONCLUSIONS: MTTs show characteristic features on CT and MRI. However, these do not allow a reliable differentiation between MTTs and other MPNSTs based on imaging alone. Therefore, additional histopathological analysis is required. ADVANCES IN KNOWLEDGE: This largest published systematic analysis on MTT imaging revealed typical but unspecific imaging features that do not allow a reliable, imaging-based differentiation between MTTs and other MPNSTs. Hence, additional histopathological analysis remains essential.

The importance of educational tools and a new software solution for visualizing and quantifying report correction in radiology training.

A novel software, DiffTool, was developed in-house to keep track of changes made by board-certified radiologists to preliminary reports created by residents and evaluate its impact on radiological hands-on training. Before (t0) and after (t2-4) the deployment of the software, 18 residents (median age: 29 years; 33% female) completed a standardized questionnaire on professional training. At t2-4 the participants were also requested to respond to three additional questions to evaluate the software. Responses were recorded via a six-point Likert scale ranging from 1 ("strongly agree") to 6 ("strongly disagree"). Prior to the release of the software, 39% (7/18) of the residents strongly agreed with the statement that they manually tracked changes made by board-certified radiologists to each of their radiological reports while 61% were less inclined to agree with that statement. At t2-4, 61% (11/18) stated that they used DiffTool to track differences. Furthermore, we observed an increase from 33% (6/18) to 44% (8/18) of residents who agreed to the statement "I profit from every corrected report". The DiffTool was well accepted among residents with a regular user base of 72% (13/18), while 78% (14/18) considered it a relevant improvement to their training. The results of this study demonstrate the importance of providing a time-efficient way to analyze changes made to preliminary reports as an additive for professional training.

Assessment of image quality and impact of deep learning-based software in non-contrast head CT scans.

In this retrospective study, we aimed to assess the objective and subjective image quality of different reconstruction techniques and a deep learning-based software on non-contrast head computed tomography (CT) images. In total, 152 adult head CT scans (77 female, 75 male; mean age 69.4 ± 18.3 years) obtained from three different CT scanners using different protocols between March and April 2021 were included. CT images were reconstructed using filtered-back projection (FBP), iterative reconstruction (IR), and post-processed using a deep learning-based algorithm (PS). Post-processing significantly reduced noise in FBP-reconstructed images (up to 15.4% reduction) depending on the protocol, leading to improvements in signal-to-noise ratio of up to 19.7%. However, when deep learning-based post-processing was applied to FBP images compared to IR alone, the differences were inconsistent and partly non-significant, which appeared to be protocol or site specific. Subjective assessments showed no significant overall improvement in image quality for all reconstructions and post-processing. Inter-rater reliability was low and preferences varied. Deep learning-based denoising software improved objective image quality compared to FBP in routine head CT. A significant difference compared to IR was observed for only one protocol. Subjective assessments did not indicate a significant clinical impact in terms of improved subjective image quality, likely due to the low noise levels in full-dose images.

Impact of AI-Based Post-Processing on Image Quality of Non-Contrast Computed Tomography of the Chest and Abdomen.

Non-contrast computed tomography (CT) is commonly used for the evaluation of various pathologies including pulmonary infections or urolithiasis but, especially in low-dose protocols, image quality is reduced. To improve this, deep learning-based post-processing approaches are being developed. Therefore, we aimed to compare the objective and subjective image quality of different reconstruction techniques and a deep learning-based software on non-contrast chest and low-dose abdominal CTs. In this retrospective study, non-contrast chest CTs of patients suspected of COVID-19 pneumonia and low-dose abdominal CTs suspected of urolithiasis were analysed. All images were reconstructed using filtered back-projection (FBP) and were post-processed using an artificial intelligence (AI)-based commercial software (PixelShine (PS)). Additional iterative reconstruction (IR) was performed for abdominal CTs. Objective and subjective image quality were evaluated. AI-based post-processing led to an overall significant noise reduction independent of the protocol (chest or abdomen) while maintaining image information (max. difference in SNR 2.59 ± 2.9 and CNR 15.92 ± 8.9, p < 0.001). Post-processing of FBP-reconstructed abdominal images was even superior to IR alone (max. difference in SNR 0.76 ± 0.5, p ≤ 0.001). Subjective assessments verified these results, partly suggesting benefits, especially in soft-tissue imaging (p < 0.001). All in all, the deep learning-based denoising-which was non-inferior to IR-offers an opportunity for image quality improvement especially in institutions using older scanners without IR availability. Further studies are necessary to evaluate potential effects on dose reduction benefits.

MR Imaging Characteristics of Solitary Fibrous Tumors of the Orbit : Case Series of 18 Patients.

PURPOSE: Solitary fibrous tumor (SFT) of the orbit is a rare tumor that was first described in 1994. We aimed to investigate its imaging characteristics that may facilitate the differential diagnosis between SFT and other types of orbital tumors. MATERIAL AND METHODS: Magnetic resonance imaging (MRI) data of patients with immunohistochemically confirmed orbital SFT from 2002 to 2022 at a tertiary care center were retrospectively analyzed. Tumor location, size, morphological characteristics, and contrast enhancement features were evaluated. RESULTS: Of the 18 eligible patients 10 were female (56%) with a mean age of 52 years. Most of the SFTs were oval-shaped (67%) with a sharp margin (83%). The most frequent locations were the laterocranial quadrant (44%), the extraconal space (67%) and the dorsal half of the orbit (67%). A flow void phenomenon was observed in nearly all cases (94%). On the T1-weighted imaging, tumor signal intensity (SI) was significantly lower than that of the retrobulbar fat and appeared predominantly equivalent (82%) to the temporomesial brain cortex, while on T2-weighted imaging its SI remained equivalent (50%) or slightly hyperintense to that of brain cortex. More than half of the lesions showed a homogeneous contrast enhancement pattern with a median SI increase of 2.2-fold compared to baseline precontrast imaging. CONCLUSION: The SFT represents a rare orbital tumor with several characteristic imaging features. It was mostly oval-shaped with a sharp margin and frequently localized in the extraconal space and dorsal half of the orbit. Flow voids indicating hypervascularization were the most common findings.

Addressing the Contrast Media Recognition Challenge: A Fully Automated Machine Learning Approach for Predicting Contrast Phases in CT Imaging.

OBJECTIVES: Accurately acquiring and assigning different contrast-enhanced phases in computed tomography (CT) is relevant for clinicians and for artificial intelligence orchestration to select the most appropriate series for analysis. However, this information is commonly extracted from the CT metadata, which is often wrong. This study aimed at developing an automatic pipeline for classifying intravenous (IV) contrast phases and additionally for identifying contrast media in the gastrointestinal tract (GIT). MATERIALS AND METHODS: This retrospective study used 1200 CT scans collected at the investigating institution between January 4, 2016 and September 12, 2022, and 240 CT scans from multiple centers from The Cancer Imaging Archive for external validation. The open-source segmentation algorithm TotalSegmentator was used to identify regions of interest (pulmonary artery, aorta, stomach, portal/splenic vein, liver, portal vein/hepatic veins, inferior vena cava, duodenum, small bowel, colon, left/right kidney, urinary bladder), and machine learning classifiers were trained with 5-fold cross-validation to classify IV contrast phases (noncontrast, pulmonary arterial, arterial, venous, and urographic) and GIT contrast enhancement. The performance of the ensembles was evaluated using the receiver operating characteristic area under the curve (AUC) and 95% confidence intervals (CIs). RESULTS: For the IV phase classification task, the following AUC scores were obtained for the internal test set: 99.59% [95% CI, 99.58-99.63] for the noncontrast phase, 99.50% [95% CI, 99.49-99.52] for the pulmonary-arterial phase, 99.13% [95% CI, 99.10-99.15] for the arterial phase, 99.8% [95% CI, 99.79-99.81] for the venous phase, and 99.7% [95% CI, 99.68-99.7] for the urographic phase. For the external dataset, a mean AUC of 97.33% [95% CI, 97.27-97.35] and 97.38% [95% CI, 97.34-97.41] was achieved for all contrast phases for the first and second annotators, respectively. Contrast media in the GIT could be identified with an AUC of 99.90% [95% CI, 99.89-99.9] in the internal dataset, whereas in the external dataset, an AUC of 99.73% [95% CI, 99.71-99.73] and 99.31% [95% CI, 99.27-99.33] was achieved with the first and second annotator, respectively. CONCLUSIONS: The integration of open-source segmentation networks and classifiers effectively classified contrast phases and identified GIT contrast enhancement using anatomical landmarks.