Magnetic Resonance Imaging (MRI) is an exceptional diagnostic tool known for its ability to provide superior soft tissue contrast. Despite its proven efficacy, traditional MRI methods have some inherent limitations, including relatively longer scan times and the requirement for specialized expertise in data analysis. These factors can, at times, create challenges in the widespread adoption of MRI in certain research and clinical scenarios. Deep learning (DL) methods for MRI reconstruction and analysis offer a promising solution to address this issue. While these DL techniques have been validated using standard image quality metrics, they fall short in assessing clinically relevant details. This hinders their clinical reliability and practical application. Although radiologists have previously compared the diagnostic equivalence of accelerated DL-reconstructed images to conventional ones for evaluating knee internal derangement, it remains uncertain whether DL detectors can accurately identify clinically important details when reconstruction models are used. Furthermore, the artifacts or hallucinations generated by DL reconstructions in knee MRI have not been examined in a clinical setting. Thus, this study aims to determine the performance of DL detectors on retrospectively accelerated DL-reconstructed knee MRI, comparing them to conventional imaging and expert evaluations for detecting meniscal tears. Our investigation yields three significant contributions. First, an in-depth analysis of DL reconstruction highlights the presence of hallucinations in the femur, tibia, and false positive artifacts, indicating that the overall reconstruction quality does not directly affect pathological features. Second, the results of DL detectors demonstrate that their performance aligns well with image quality assessment metrics and expert scores. This finding validates the reliability of the detection outcomes. Finally, we propose an integrated (i.e. reconstruction + detection) process for meniscal tears on fastMRI+ data and achieved state-of-the-art results with average precision scores of 0.69 and 0.67 at 4- and 8-fold accelerations, respectively.

Background: The prediction of high-flow nasal oxygen (HFNO) failure in patients with coronavirus disease-2019 (COVID-19) having acute respiratory failure (ARF) may prevent delayed intubation and decrease mortality. Aims: To define the related risk factors to HFNO failure and hospital mortality Study Design: Retrospective cohort study. Methods: To this study. 85 critically ill patients (>= 18 years) with COVID- I 9 related acute kidney injury who were treated with HFNO were enrolled. Treatment success was defined as the de-escalation of the oxygenation support to the conventional oxygen therapies. HFNO therapy failure was determined as the need for invasive mechanical ventilation or death. The patients were divided into HFNO-failure (HFNO-F) and HFNO-success (HFNO-S) groups. Electronic medical records and laboratory data were screened for all patients. Respiratory rate oxygenation (ROX) index on the first hour and chest computed tomography (CT) severity score were calculated. Factors related to HFNO therapy failure and mortality were defined. Results: This study assessed 85 patients (median age 67 years, 69.4% male) who were divided into two groups as HFNO success (n = 33) and HFNO failure (n = 52). The respiratory rate oxygenation (ROX) was measured at I hour and the computed tomography (CT) score indicated HFNO failure and intubation, with an area under the receiver operating characteristic of 0.695 for the ROX index and 0.628 for the CT score. A ROX index of 15 in the first hour of therapy were the predictors of HFNO failure and intubation. Age. Acute Physiology and Chronic Health Evaluation II score, arterial blood gas findings "(i.e., partial pressure of oxygen [PaO2]. PaO2 [fraction of inspired oxygenYSO(2) [oxygen saturation] ratio)", and D-dimer levels were also associated with HFNO failure; however. based on logistic regression analysis, a calculated ROX on the first hour of therapy of 15 (OR = 2.83, 95% CI = 1.01-7.88, P = 0.001) were the only independent risk factors. In logistic regression analysis, a ROX calculated on the first hour of therapy of 15 (OR 2.83. 95% CI = 1.01-7.88, P = <0.001) were the independent risk factors for the HFNO failure. The intensive care unit and hospital mortality rates were 80.2% and 82.7%, respectively. in the HFNO failure group. Conclusion: The early prediction of HFNO therapy failure is essential considering the high mortality rate in patients with HFNO therapy failure. Using the ROX index and the chest CT severity score combined with the other clinical parameters may reduce mortality. Additionally multi-centre observational studies are needed to define the predictive value of ROX and chest CT score not only for COVID-19 but also other causes of ARF.

To date, the coronavirus disease 2019 (COVID-19) caused more than 2.6 million deaths all around the world. Risk factors for mortality remain unclear. The primary aim was to determine the independent risk factors for 28-day mortality. In this retrospective cohort study, critically ill patients (≥ 18 years) who were admitted to the intensive care unit due to COVID-19 were included. Patient characteristics, laboratory data, radiologic findings, treatments, and complications were analyzed in the study. A total of 249 patients (median age 71, 69.1% male) were included in the study. 28-day mortality was 67.9% (n = 169). The median age of deceased patients was 75 (66–81). Of them, 68.6% were male. Cerebrovascular disease, dementia, chronic kidney disease, and malignancy were significantly higher in the deceased group. In the multivariate analysis, sepsis/septic shock (OR, 15.16, 95% CI, 3.96–58.11, p < 0.001), acute kidney injury (OR, 4.73, 95% CI, 1.55–14.46,p = 0.006), acute cardiac injury (OR, 9.76, 95% CI, 1.84–51.83, p = 0.007), and chest CT score higher than 15 (OR, 4.49, 95% CI, 1.51-13.38, p = 0.007) were independent risk factors for 28-day mortality. Early detection of the risk factors and the use of chest CT score might improve the outcomes in patients with COVID-19.

Neoadjuvant chemoradiotherapy (CRT) is known to increase sphincter preservation rates and decrease the risk of postoperative recurrence in patients with locally advanced rectal tumors. However, the response to CRT in patients with locally advanced rectal cancer (LARC) varies significantly. The objective of this study was to compare the performance of models based on radiomics features of the tumor alone, the mesorectum alone, and a combination of both in predicting tumor response to neoadjuvant CRT in LARC. This retrospective study included 101 patients with LARC. Patients were categorized as responders (modified Ryan score 0-1) and non-responders (modified Ryan score 2-3). Pre-CRT magnetic resonance imaging evaluations included tumor-T2 weighted imaging (T2WI), tumor-diffusion weighted imaging (DWI), tumor-apparent diffusion coefficient (ADC) maps, and mesorectum-T2WI. The first radiologist segmented the tumor and mesorectum from T2-weighted images, and the second radiologist performed tumor segmentation using DWI and ADC maps. Feature reproducibility was assessed by calculating the intraclass correlation coefficient (ICC) using a two-way mixed-effects model with absolute agreement for single measurements [ICC(3,1)]. Radiomic features with ICC values <0.60 were excluded from further analysis. Subsequently, the least absolute shrinkage and selection operator method was applied to select the most relevant radiomic features. The top five features with the highest coefficients were selected for model training. To address class imbalance between groups, the synthetic minority over-sampling technique was applied exclusively to the training folds during cross-validation. Thereafter, classification learner models were developed using 10-fold cross-validation to achieve the highest performance. The performance metrics of the final models, including accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC), were calculated to evaluate the classification performance. Among the 101 patients, 36 were classified as responders and 65 as non-responders. A total of 25 radiomic features from the tumor and 20 from the mesorectum were found to be statistically significant (P < 0.05). The AUC values for predicting treatment response were 0.781 for the tumor-only model (random forest), 0.726 for the mesorectum-only model (logistic regression), and 0.837 for the combined model (logistic regression). Radiomic features derived from both the tumor and mesorectum demonstrated complementary prognostic value in predicting treatment response. The inclusion of mesorectal features substantially improved model performance, with the combined model achieving the highest AUC value. These findings highlight the added predictive contribution of the mesorectum as a key peritumoral structure in radiomics-based assessment. Currently, the response of locally advanced rectal tumors to neoadjuvant therapy cannot be reliably predicted using conventional methods. Recently, the significance of the mesorectum in predicting treatment response has gained attention, although the number of studies focusing on this area remains limited. In our study, we performed radiomics analyses of both the tumor tissue and the mesorectum to predict neoadjuvant treatment response.