Five-minute knee MRI: An AI-based super resolution reconstruction approach for compressed sensing. A validation study on healthy volunteers.

PURPOSE: To investigate the potential of combining Compressed Sensing (CS) and a newly developed AI-based super resolution reconstruction prototype consisting of a series of convolutional neural networks (CNN) for a complete five-minute 2D knee MRI protocol. METHODS: In this prospective study, 20 volunteers were examined using a 3T-MRI-scanner (Ingenia Elition X, Philips). Similar to clinical practice, the protocol consists of a fat-saturated 2D-proton-density-sequence in coronal, sagittal and transversal orientation as well as a sagittal T1-weighted sequence. The sequences were acquired with two different resolutions (standard and low resolution) and the raw data reconstructed with two different reconstruction algorithms: a conventional Compressed SENSE (CS) and a new CNN-based algorithm for denoising and subsequently to interpolate and therewith increase the sharpness of the image (CS-SuperRes). Subjective image quality was evaluated by two blinded radiologists reviewing 8 criteria on a 5-point Likert scale and signal-to-noise ratio calculated as an objective parameter. RESULTS: The protocol reconstructed with CS-SuperRes received higher ratings than the time-equivalent CS reconstructions, statistically significant especially for low resolution acquisitions (e.g., overall image impression: 4.3 ±â€¯0.4 vs. 3.4 ±â€¯0.4, p < 0.05). CS-SuperRes reconstructions for the low resolution acquisition were comparable to traditional CS reconstructions with standard resolution for all parameters, achieving a scan time reduction from 11:01 min to 4:46 min (57 %) for the complete protocol (e.g. overall image impression: 4.3 ±â€¯0.4 vs. 4.0 ±â€¯0.5, p < 0.05). CONCLUSION: The newly-developed AI-based reconstruction algorithm CS-SuperRes allows to reduce scan time by 57% while maintaining unchanged image quality compared to the conventional CS reconstruction.

Value of Magnetic Resonance Imaging for Skeletal Bone Age Assessment in Healthy Male Children.

BACKGROUND: Skeletal bone age assessment for medical reasons is usually performed by conventional x-ray with use of ionizing radiation. Few pilot studies have shown the possible use of magnetic resonance imaging (MRI). PURPOSE: To comprehensively evaluate feasibility and value of MRI for skeletal bone age (SBA) assessment in healthy male children. MATERIALS AND METHODS: In this prospective cross-sectional study, 63 male soccer athletes with mean age of 12.35 ± 1.1 years were examined. All participants underwent 3.0 Tesla MRI with coronal T1-weighted turbo spin echo (TSE), coronal proton density (PD)-weighted turbo spin echo (TSE), and T1-weighted three-dimensional (3D) volume interpolated breath-hold examination (VIBE) sequence. Subsequently, SBA was assessed by 3 independent blinded radiologists with different levels of experience using the common Greulich-Pyle (GP) atlas and the Tanner-Whitehouse (TW2) method. RESULTS: In a mean total acquisition time of 5:04 ± 0:47 min, MR image quality was sufficient in all cases. MRI appraisal was significantly faster ( P < 0.0001) by GP with mean duration of 1:22 ± 0:08 min vs. 7:39 ± 0:28 min by TW. SBA assessment by GP resulted in mean age of 12.8 ± 1.2 years, by TW 13.0 ± 1.4 years. Interrater reliabilities were excellent for both GP (ICC = 0.912 (95% confidence interval [CI] = 0.868-0.944) and TW (ICC = 0.988 (95% CI = 0.980-0.992) and showed statistical significance ( P < 0.001). Subdivided, for GP, ICCs were 0.822 (95% CI = 0.680-0.907) and 0.843 (95% CI = 0.713-0.919) in Under 12 and Under 14 group. For TW, ICCs were 0.978 (95% CI = 0.958-0.989) in Under 12 and 0.979 (95% CI = 0.961-0.989) in Under 14 group. CONCLUSION: MRI is a clinically feasible, rapidly evaluable method to assess skeletal bone age of healthy male children. Using the Greulich-Pyle (GP) atlas or the Tanner-Whitehouse (TW2) method, reliable results are obtained independent of the radiologist's experience level.

Long-term outcomes following percutaneous microwave ablation for colorectal cancer liver metastases.

PURPOSE: To evaluate the overall survival (OS), local progression-free survival (PFS) and prognostic factors of patients with colorectal cancer liver metastases (CRLM) undergoing microwave ablation (MWA). METHOD: A total of 132 patients were retrospectively enrolled who had been treated between 2010 and 2018. For the evaluation of survival rates, all patients were divided according to their indications (curative n = 57 and debulking (patients with additional non-target extrahepatic metastases) n = 75). In total, 257 ablations were evaluated for prognostic factors: number of liver metastases, primary tumor origin (PTO), diameter and volume of metastases, duration and energy of ablation. RESULTS: The OS was 32.1 months with 93.2% of patients free from recurrence at 28.3 months (median follow-up time). The one- year and three-year OS were 82.72% and 41.66%, respectively. The OS and recurrence-free survival of the curative group were statistically significantly higher than the debulking group (p < .001). Statistically significant prognostic factors for OS included the location of the primary tumor (p < .038) and the number of metastases (all p < .017). Metastasis diameter and volume and ablation duration and energy had no significant correlation with survival (p > .05). CONCLUSIONS: Satisfactory OS and local tumor PFS can be achieved in patients with CRLM using MWA with the number of metastases and the location of the primary tumor influencing the outcome of patients. The metastasis's size and the duration and energy used for ablation were not of significant prognostic value.

Quantification of COVID-19 Opacities on Chest CT - Evaluation of a Fully Automatic AI-approach to Noninvasively Differentiate Critical Versus Noncritical Patients.

OBJECTIVES: To evaluate the potential of a fully automatic artificial intelligence (AI)-driven computed tomography (CT) software prototype to quantify severity of COVID-19 infection on chest CT in relationship with clinical and laboratory data. METHODS: We retrospectively analyzed 50 patients with laboratory confirmed COVID-19 infection who had received chest CT between March and July 2020. Pulmonary opacifications were automatically evaluated by an AI-driven software and correlated with clinical and laboratory parameters using Spearman-Rho and linear regression analysis. We divided the patients into sub cohorts with or without necessity of intensive care unit (ICU) treatment. Sub cohort differences were evaluated employing Wilcoxon-Mann-Whitney-Test. RESULTS: We included 50 CT examinations (mean age, 57.24 years), of whom 24 (48%) had an ICU stay. Extent of COVID-19 like opacities on chest CT showed correlations (all p < 0.001 if not otherwise stated) with occurrence of ICU stay (R = 0.74), length of ICU stay (R = 0.81), lethal outcome (R = 0.56) and length of hospital stay (R = 0.33, p < 0.05). The opacities extent was correlated with laboratory parameters: neutrophil count (NEU) (R = 0.60), lactate dehydrogenase (LDH) (R = 0.60), troponin (TNTHS) (R = 0.55) and c-reactive protein (CRP) (R = 0.51). Differences (p < 0.001) between ICU group and non-ICU group concerned longer length of hospital stay (24.04 vs. 10.92 days), higher opacity score (12.50 vs. 4.96) and severity of laboratory data changes such as c-reactive protein (11.64 vs. 5.07 mg/dl, p < 0.01). CONCLUSIONS: Automatically AI-driven quantification of opacities on chest CT correlates with laboratory and clinical data in patients with confirmed COVID-19 infection and may serve as non-invasive predictive marker for clinical course of COVID-19.

Biological Maturity Status in Elite Youth Soccer Players: A Comparison of Pragmatic Diagnostics With Magnetic Resonance Imaging.

The influence of biological maturity status (BMS) on talent identification and development within elite youth soccer is critically debated. During adolescence, maturity-related performance differences within the same age group may cause greater chances of being selected for early maturing players. Therefore, coaches need to consider players' BMS. While standard methods for assessing BMS in adolescents are expensive and time-consuming imaging techniques (i.e., X-ray and MRI), there also exist more pragmatic procedures. This study aimed to evaluate commonly used methods to assess BMS within a highly selected sample of youth soccer players. A total of N = 63 elite male soccer players (U12 and U14) within the German Soccer Association's talent promotion program completed a test battery assessing BMS outcomes. Utilizing MRI diagnostics, players' skeletal age (SAMRI) was determined by radiologists and served as the reference method. Further commonly used methods included skeletal age measured by an ultrasound device (SAUS), the maturity offset (MOMIR), and the percentage of adult height (PAHKR). The relation of these alternative BMS outcomes to SAMRI was examined using different perspectives: performing bivariate correlation analyses (1), modeling BMS as a latent variable (BMSlat) based on the multiple alternative diagnostics (2), and investigating individual differences in agreement (3). (1) Correlations of SAMRI and the further BMS variables ranked from r = 0.80 to r = 0.84 for the total sample and were lower for U12 (0.56 ≤ r ≤ 0.66), and U14 (0.61 ≤ r ≤ 0.74) (2). The latent structural equation modeling (SEM) (R 2 = 51%) revealed a significant influence on BMSlat for MOMIR (ß = 0.51, p <0.05). The additional contribution of PAHKR (ß = 0.27, p = 0.06) and SAUS (ß = -0.03, p = 0.90) was rather small (3). The investigation of individual differences between the reference method and alternative diagnostics indicated a significant bias for MOMIR (p <0.01). The results support the use of economical and time-efficient methods for assessing BMS within elite youth soccer. Bivariate correlation analyses as well as the multivariate latent variable approach highlight the measures' usefulness. However, the observed individual level differences for some of the utilized procedures led to the recommendation for practitioners to use at least two alternative assessment methods in order to receive more reliable information about players' BMS within the talent promotion process.

Comparison of machine learning algorithms to predict clinically significant prostate cancer of the peripheral zone with multiparametric MRI using clinical assessment categories and radiomic features.

OBJECTIVES: To analyze the performance of radiological assessment categories and quantitative computational analysis of apparent diffusion coefficient (ADC) maps using variant machine learning algorithms to differentiate clinically significant versus insignificant prostate cancer (PCa). METHODS: Retrospectively, 73 patients were included in the study. The patients (mean age, 66.3 ± 7.6 years) were examined with multiparametric MRI (mpMRI) prior to radical prostatectomy (n = 33) or targeted biopsy (n = 40). The index lesion was annotated in MRI ADC and the equivalent histologic slides according to the highest Gleason Grade Group (GrG). Volumes of interest (VOIs) were determined for each lesion and normal-appearing peripheral zone. VOIs were processed by radiomic analysis. For the classification of lesions according to their clinical significance (GrG ≥ 3), principal component (PC) analysis, univariate analysis (UA) with consecutive support vector machines, neural networks, and random forest analysis were performed. RESULTS: PC analysis discriminated between benign and malignant prostate tissue. PC evaluation yielded no stratification of PCa lesions according to their clinical significance, but UA revealed differences in clinical assessment categories and radiomic features. We trained three classification models with fifteen feature subsets. We identified a subset of shape features which improved the diagnostic accuracy of the clinical assessment categories (maximum increase in diagnostic accuracy ΔAUC = + 0.05, p < 0.001) while also identifying combinations of features and models which reduced overall accuracy. CONCLUSIONS: The impact of radiomic features to differentiate PCa lesions according to their clinical significance remains controversial. It depends on feature selection and the employed machine learning algorithms. It can result in improvement or reduction of diagnostic performance. KEY POINTS: • Quantitative imaging features differ between normal and malignant tissue of the peripheral zone in prostate cancer. • Radiomic feature analysis of clinical routine multiparametric MRI has the potential to improve the stratification of clinically significant versus insignificant prostate cancer lesions in the peripheral zone. • Certain combinations of standard multiparametric MRI reporting and assessment categories with feature subsets and machine learning algorithms reduced the diagnostic performance over standard clinical assessment categories alone.

Diffusion-Weighted MR Imaging of Primary and Secondary Lung Cancer: Predictive Value for Response to Transpulmonary Chemoembolization and Transarterial Chemoperfusion.

PURPOSE: To examine predictive value of apparent diffusion coefficient (ADC) in diffusion-weighted imaging (DWI) for response of patients with primary and secondary lung neoplasms undergoing transpulmonary chemoembolization (TPCE) and transarterial chemoperfusion (TACP) treatment. MATERIALS AND METHODS: Thirty-one patients (mean age ± SD 64 ± 12.4 y) with 42 lung target lesions (13 primary and 29 secondary) underwent DWI and subsequent ADC analysis on a 1.5T MR imaging scanner before and 30.3 days ± 6.4 after first session of TPCE or TACP. After 3.1 treatment sessions ± 1.4 performed in 2- to 4-week intervals, morphologic response was analyzed by comparing tumor diameter and volume before and after treatment on unenhanced T1-weighted MR images. On a per-lesion basis, response was classified according to Response Evaluation Criteria In Solid Tumors. RESULTS: Threshold ADC increase of 20.7% indicated volume response with 88% sensitivity and 78% specificity (area under the curve [AUC] = 0.84). Differences between ADC changes in volume response groups were significant (P = .002). AUC for volume response predicted by ADC before treatment was 0.77. Median ADC before treatment and mean ADC change were 1.09 × 10-3 mm2/second and 0.36 × 10-3 mm2/second ± 0.23, 1.45 × 10-3 mm2/second and 0.14 × 10-3 mm2/second ± 0.16, and 1.30 × 10-3 mm2/second and 0.06 × 10-3 mm2/second ± 0.19 in partial response, stable disease, and progressive disease groups. In primary lung cancer lesions, strong negative correlation of ADC change with change in diameter (ρ = -.87, P < .001) and volume (ρ = -.66, P = .016) was found. In metastases, respective correlation coefficients were ρ = -.18 (P = .356) and ρ = -.35 (P = .061). CONCLUSIONS: ADC quantification shows considerable diagnostic value for predicting response and monitoring TPCE and TACP treatment of patients with primary and secondary lung neoplasms.

Microwave Ablation (MWA) of Pulmonary Neoplasms: Clinical Performance of High-Frequency MWA With Spatial Energy Control Versus Conventional Low-Frequency MWA.

OBJECTIVE. The objective of our study was to evaluate the clinical performance of a new high-frequency (HF) microwave ablation (MWA) technology with spatial energy control for treatment of lung malignancies in comparison with a conventional low-frequency (LF) MWA technology. MATERIALS AND METHODS. In this retrospective study, 59 consecutive patients (mean age, 58.9 ± 12.6 [SD] years) were treated in 71 sessions using HF spatial-energy-control MWA. Parameters collected were technical success and efficacy, tumor diameter, tumor and ablation volumes, ablation time, output energy, complication rate, 90-day mortality, local tumor progression (LTP), ablative margin size, and ablation zone sphericity. Results were compared with the same parameters retrospectively collected from the last 71 conventional LF-MWA sessions. This group consisted of 56 patients (mean age, 60.3 ± 10.8 years). Statistical comparisons were performed using the Wilcoxon-Mann-Whitney test. RESULTS. Technical success was 98.6% for both technologies; technical efficacy was 97.2% for HF spatial-energy-control MWA and 95.8% for LF-MWA. The 90-day mortality rate was 5.1% (3/59) in the HF spatial-energy-control MWA group and 5.4% (3/56) in the LF-MWA group; for both groups, there were zero intraprocedural deaths. The median ablation time was 8.0 minutes for HF spatial-energy-control MWA and 10.0 minutes for LF-MWA (p < 0.0001). Complications were recorded in 21.1% (15/71) of HF spatial-energy-control MWA sessions and in 31.0% (22/71) of LF-MWA sessions (p = 0.182); of these complications, 4.2% (3/71) were major complications in the HF spatial-energy-control MWA group, and 9.9% (7/71) were major complications in the LF-MWA group. The median deviation from ideal sphericity (1.0) was 0.195 in the HF spatial-energy-control MWA group versus 0.376 in the LF-MWA group (p < 0.0001). Absolute minimal ablative margins per ablation were 7.5 ± 3.6 mm (mean ± SD) in the HF spatial-energy-control MWA group versus 4.2 ± 3.0 mm in the LF-MWA group (p < 0.0001). In the HF spatial-energy-control MWA group, LTP at 12 months was 6.5% (4/62). LTP at 12 months in the LF-MWA group was 12.5% (7/56). Differences in LTP rate (p = 0.137) and time point (p = 0.833) were not significant. CONCLUSION. HF spatial-energy-control MWA technology and conventional LFMWA technology are safe and effective for the treatment of lung malignancies independent of the MWA system used. However, HF spatial-energy-control MWA as an HF and high-energy MWA technique achieves ablation zones that are closer to an ideal sphere and achieves larger ablative margins than LF-MWA (p < 0.0001).

Evaluation of microwave ablation of liver malignancy with enabled constant spatial energy control to achieve a predictable spherical ablation zone.

OBJECTIVES: To evaluate the clinical performance of a new microwave ablation (MWA) system with enabled constant spatial energy control (ECSEC) to achieve spherical ablation zones in the treatment of liver malignancies. MATERIALS AND METHODS: In this retrospective study, 56 hepatic tumours in 48 patients (23 men, 25 women; mean age: 59.6 years) were treated using a new high-frequency MWA-system with ECSEC. Parameters evaluated were technical success, technical efficacy, tumour diameter, tumour and ablation volume, complication rate, 90-day mortality, local tumour progression (LTP) at the 12-month follow-up, ablative margin and ablation zone sphericity. These parameters were compared using the Kruskal-Wallis test with the same parameters collected retrospectively from cohorts of patients treated with conventional high-frequency (HF) MWA (n = 20) or low-frequency (LF) MWA (n = 20). RESULTS: Technical success was achieved in all interventions. The technical efficacy was 100% (ECSEC) vs. 100% (LF-MWA) vs. 95% (HF-MWA). There were no intra-procedural deaths or major complications. Minor complications occurred in 3.57% (2/56), 0% (0/20) and 0% (0/20) of the patients, respectively. The one-year mortality rate was 16.1% (9/56), 15% (3/20) and 10% (2/20), respectively. The LTP was 3.57% (2/56), 5% (1/20) and 5% (1/20), respectively. The median deviation from ideal sphericity (1.0) was 0.135 (ECSEC) vs. 0.344 (LF-MWA) vs. 0.314 (HF-MWA) (p < 0.001). The absolute minimal ablative margin was 8.1 vs. 2.3 vs. 3.1 mm (p < 0.001). CONCLUSIONS: Microwave ablation of liver malignancies is a safe and efficient treatment independent of the system used. Hepatic MWA with ECSEC achieves significantly more spherical ablation zones and higher minimal ablative margins.

Microwave ablation of pancreatic tumors.

OBJECTIVES: To evaluate the clinical performance of percutaneous microwave ablation (MWA) for treatment of locally-advanced-pancreatic-cancer (LAPC). MATERIAL AND METHODS: Twenty-two MWA sessions (August 2015-March 2017) in 20 patients with primary pancreatic cancer (13 men, 7 women, mean-age: 59.9 ± 8.6 years, range: 46-73 years), who had given informed consent, were retrospectively evaluated. All procedures were performed percutaneously under CT-guidance using the same high-frequency (2.45-GHz) MWA device. Tumor location and diameter, ablation diameter and volume, roundness, duration, technical success and efficacy, output energy, complications, and local tumor progression defined as a tumor focus connected to the edge of a previously technically efficient ablation zone were collected. RESULTS: Seventeen pancreatic malignant tumors (77.3%) were located in the pancreatic head and five (22.7%) in the pancreatic tail. Initial Mean Tumor Diameter was 30 ± 6 mm. Technical success and efficacy were idem (100%). No major complications occurred. Two patients (9.1%) showed minor complications of severe local pain related to MWA. Post-ablation diameter was on average 34.4 ± 5.8 mm. Mean ablation volume was 7.8 ± 3.8 cm³. The mean transverse roundness index was 0.74 ± 0.14. Mean ablation time was 2.6 ± 0.96 min. The mean applied energy per treatment was 9627 ± 3953 J. Local tumor progression was documented in one case (10%) of the 10/22 available three-month follow-up imaging studies. CONCLUSION: High-frequency (2.45 GHz) microwave ablation (MWA) for treatment of unresectable and non-metastatic locally-advanced-pancreatic-cancer (LAPC) shows promising results regarding feasibility and safety of percutaneous approach after short-term follow-up and should be further evaluated.