Deep Learning k-Space-to-Image Reconstruction Facilitates High Spatial Resolution and Scan Time Reduction in Diffusion-Weighted Imaging Breast MRI.

BACKGROUND: For time-consuming diffusion-weighted imaging (DWI) of the breast, deep learning-based imaging acceleration appears particularly promising. PURPOSE: To investigate a combined k-space-to-image reconstruction approach for scan time reduction and improved spatial resolution in breast DWI. STUDY TYPE: Retrospective. POPULATION: 133 women (age 49.7 ± 12.1 years) underwent multiparametric breast MRI. FIELD STRENGTH/SEQUENCE: 3.0T/T2 turbo spin echo, T1 3D gradient echo, DWI (800 and 1600 sec/mm2 ). ASSESSMENT: DWI data were retrospectively processed using deep learning-based k-space-to-image reconstruction (DL-DWI) and an additional super-resolution algorithm (SRDL-DWI). In addition to signal-to-noise ratio and apparent diffusion coefficient (ADC) comparisons among standard, DL- and SRDL-DWI, a range of quantitative similarity (e.g., structural similarity index [SSIM]) and error metrics (e.g., normalized root mean square error [NRMSE], symmetric mean absolute percent error [SMAPE], log accuracy error [LOGAC]) was calculated to analyze structural variations. Subjective image evaluation was performed independently by three radiologists on a seven-point rating scale. STATISTICAL TESTS: Friedman's rank-based analysis of variance with Bonferroni-corrected pairwise post-hoc tests. P < 0.05 was considered significant. RESULTS: Both DL- and SRDL-DWI allowed for a 39% reduction in simulated scan time over standard DWI (5 vs. 3 minutes). The highest image quality ratings were assigned to SRDL-DWI with good interreader agreement (ICC 0.834; 95% confidence interval 0.818-0.848). Irrespective of b-value, both standard and DL-DWI produced superior SNR compared to SRDL-DWI. ADC values were slightly higher in SRDL-DWI (+0.5%) and DL-DWI (+3.4%) than in standard DWI. Structural similarity was excellent between DL-/SRDL-DWI and standard DWI for either b value (SSIM ≥ 0.86). Calculation of error metrics (NRMSE ≤ 0.05, SMAPE ≤ 0.02, and LOGAC ≤ 0.04) supported the assumption of low voxel-wise error. DATA CONCLUSION: Deep learning-based k-space-to-image reconstruction reduces simulated scan time of breast DWI by 39% without influencing structural similarity. Additionally, super-resolution interpolation allows for substantial improvement of subjective image quality. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 1.

Not all that looks fractured is broken-multipartite humeral epicondyles in children.

OBJECTIVE: Multipartite epicondyles may mimic fractures in the setting of pediatric elbow trauma. This study examines the prevalence of multipartite epicondyles during skeletal development and their association with pediatric elbow fractures. MATERIALS AND METHODS: In this retrospective analysis, 4282 elbow radiographs of 1265 elbows of 1210 patients aged 0-17 years were reviewed. The radiographs were analyzed by two radiologists in consensus reading, and the number of visible portions of the medial and lateral epicondyles was noted. For elbows in which epicondylar ossification was not yet visible, the epicondyles were already fused with the humerus or could not be sufficiently evaluated due to projection issues or because osteosynthesis material was excluded. In total, 187 elbows were included for the lateral and 715 for the medial epicondyle analyses. RESULTS: No multipartite medial epicondyles were found in patients without history of elbow fracture, whereas 9% of these patients had multipartite lateral epicondyles (p < 0.01). Current or previous elbow fractures increased the prevalence of multipartite epicondyles, with significant lateral predominance (medial epicondyle + 9% vs. lateral + 24%, p < 0.0001). Including all patients regardless of a history of elbow fracture, multipartite medial epicondyles were observed in 3% and multipartite lateral epicondyles in 18% (p < 0.0001). There was no gender difference in the prevalence of multipartition of either epicondyle, regardless of a trauma history. CONCLUSION: Multipartite medial epicondyles occur in patients with current or previous elbow fractures only, whereas multipartite lateral epicondyles may be constitutional. Elbow fractures increase the prevalence of multipartite epicondyles on both sides, with significant lateral predominance. KEY POINTS: • Multipartite medial epicondyles should be considered of traumatic origin. • Multipartite lateral epicondyles may be constitutional. • Elbow fractures increase the prevalence of multipartite epicondyles on both sides with lateral predominance.

Fibroblast growth factor receptor 1 gene amplification and protein expression in human lung cancer.

BACKGROUND: Targeting fibroblast growth factor receptor 1 (FGFR1) is a potential treatment for squamous cell lung cancer (SQCLC). So far, treatment decision in clinical studies is based on gene amplification. However, only a minority of patients have shown durable response. Furthermore, former studies have revealed contrasting results regarding the impact of FGFR1 amplification and expression on patient's prognosis. AIMS: Here, we analyzed prevalence and correlation of FGFR1 gene amplification and protein expression in human lung cancer and their impact on overall survival. MATERIALS & METHODS: FGFR1 gene amplification and protein expression were analyzed by fluorescence in situ hybridization and immunohistochemistry (IHC) in 208 SQCLC and 45 small cell lung cancers (SCLC). Furthermore, FGFR1 protein expression was analyzed in 121 pulmonary adenocarcinomas (ACs). Amplification and expression were correlated to each other, clinicopathological characteristics, and overall survival. RESULTS: FGFR1 was amplified in 23% of SQCLC and 8% of SCLC. Amplification was correlated to males (P = .027) but not to overall survival. Specificity of immunostaining was verified by cellular CRISPR/Cas9 FGFR1 knockout. FGFR1 was strongly expressed in 9% of SQCLC, 35% of AC, and 4% of SCLC. Expression was correlated to females (P = .0187) and to the absence of lymph node metastasis in SQCLC (P = .018) with no significant correlation to overall survival. Interestingly, no significant correlation between amplification and expression was detected. DISCUSSION: FGFR1 gene amplification does not seem to correlate to protein expression. CONCLUSION: We believe that patient selection for FGFR1 inhibitors in clinical studies should be reconsidered. Neither FGFR1 amplification nor expression influences patient's prognosis.

Expression and prognostic impact of alpha thalassemia/mental retardation X-linked and death domain-associated protein in human lung cancer.

Molecular characterization of lung cancer specimens after radical surgery offers additional prognostic information and may help to guide adjuvant therapeutic procedures. The transcriptional regulators alpha thalassemia/mental retardation X-linked (ATRX) and death domain-associated protein (DAXX) have recently been described in different cancer entities as a useful prognostic biomarker. This study was initiated to explore their protein expression patterns and prognostic value in patients with operable lung cancer disease.The protein abundance (in the following text also named protein expression) of ATRX and DAXX were analyzed by immunohistochemistry in 194 samples of squamous cell lung carcinoma (SQCLC), 111 samples of pulmonary adenocarcinoma (AC) and 40 samples of small cell lung cancer (SCLC). The protein levels of ATRX and DAXX were correlated with clinicopathological characteristics and patient outcome.ATRX showed strong protein expression in 16.2% of AC, 11.9% of SQCLC, and 42.5% of SCLC. DAXX was highly expressed in 54.9% of AC, 76.2% of SQCLC, and 82.5% of SCLC. Immunostaining of both ATRX and DAXX were seen in 14.4% of AC, 11.3% of SQCLC, and 42.5% of SCLC. High protein expression of ATRX was a favorable prognostic marker for patients with AC (hazard ratio 0.38, P = .02). Sub-group analyses showed a significant correlation between ATRX and the clinical stage of SQCLC and SCLC. Histological grading and ATRX were also significantly associated in cases of SQCLC.The presence of ATRX and DAXX are correlated with lung cancer histology. Strong ATRX protein expression is associated with a significantly longer overall survival in patients with AC.

Comparative proteomics reveals a diagnostic signature for pulmonary head-and-neck cancer metastasis.

Patients with head-and-neck cancer can develop both lung metastasis and primary lung cancer during the course of their disease. Despite the clinical importance of discrimination, reliable diagnostic biomarkers are still lacking. Here, we have characterised a cohort of squamous cell lung (SQCLC) and head-and-neck (HNSCC) carcinomas by quantitative proteomics. In a training cohort, we quantified 4,957 proteins in 44 SQCLC and 30 HNSCC tumours. A total of 518 proteins were found to be differentially expressed between SQCLC and HNSCC, and some of these were identified as genetic dependencies in either of the two tumour types. Using supervised machine learning, we inferred a proteomic signature for the classification of squamous cell carcinomas as either SQCLC or HNSCC, with diagnostic accuracies of 90.5% and 86.8% in cross- and independent validations, respectively. Furthermore, application of this signature to a cohort of pulmonary squamous cell carcinomas of unknown origin leads to a significant prognostic separation. This study not only provides a diagnostic proteomic signature for classification of secondary lung tumours in HNSCC patients, but also represents a proteomic resource for HNSCC and SQCLC.