Background: The ultrasound is one of the most used medical imaging investigations worldwide. It is non-invasive and effective in assessing liver tumors or other types of parenchymal changes. Methods: The aim of the study was to build a deep learning model for image segmentation in ultrasound video investigations. The dataset used in the study was provided by the University of Medicine and Pharmacy Craiova, Romania and contained 50 video examinations from 49 patients. The mean age of the patients in the cohort was 69.57. Regarding presence of a subjacent liver disease, 36.73% had liver cirrhosis and 16.32% had chronic viral hepatitis (5 patients: chronic hepatitis C and 3 patients: chronic hepatitis B). Frames were extracted and cropped from each examination and an expert gastroenterologist labelled the lesions in each frame. After labelling, the labels were exported as binary images. A deep learning segmentation model (U-Net) was trained with focal Tversky loss as a loss function. Two models were obtained with two different sets of parameters for the loss function. The performance metrics observed were intersection over union and recall and precision. Results: Analyzing the intersection over union metric, the first segmentation model obtained performed better compared to the second model: 0.8392 (model 1) vs. 0.7990 (model 2). The inference time for both models was between 32.15 milliseconds and 77.59 milliseconds. Conclusions: Two segmentation models were obtained in the study. The models performed similarly during training and validation. However, one model was trained to focus on hard-to-predict labels. The proposed segmentation models can represent a first step in automatically extracting time-intensity curves from CEUS examinations.

The aim of this study was to assess the role of immunocyte-derived ratios (IDRs), such as the systemic immune-inflammation index (SII), neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and lymphocyte-to-monocyte ratio (LMR), as markers for the postoperative recovery of gastrointestinal function following colorectal cancer surgery. A retrospective analysis was conducted on a consecutive cohort of 260 patients who underwent radical colorectal cancer surgery within the timeframe spanning from January 2016 to December 2022. Data concerning the postoperative recovery of gastrointestinal function included the I-FEED score, time to pass flatus, toleration for liquids in the first 48 h, and the need for nasogastric tube reinsertion in the immediate postoperative period. A special emphasis was allocated towards the examination of IDRs and their interrelation with the postoperative gastrointestinal functional parameters. The I-FEED score exhibited a positive correlation with the NLR, SII, and PLR. The univariate analysis indicated that all IDRs, multiorgan resection, hemoglobin and protein levels, regional nodal extent of the tumor (N), and obesity significantly affected nasogastric tube reinsertion. The multivariate analysis showed that the SII and N1 stages were risk factors for nasogastric tube reinsertion after colorectal cancer surgery. The SII and multiorgan resection were the only classifiers that remained significant in the multivariable analysis for the toleration for liquids. In summation, certain preoperative IDRs, such as the SII, PLR, and NLR, may hold potential as predictive determinants for postoperative gastrointestinal functional recovery following colorectal cancer surgery.

Background: Contrast-enhanced ultrasound (CEUS) is an important imaging modality in the diagnosis of liver tumors. By using contrast agent, a more detailed image is obtained. Time-intensity curves (TIC) can be extracted using a specialized software, and then the signal can be analyzed for further investigations. Methods: The purpose of the study was to build an automated method for extracting TICs and classifying liver lesions in CEUS liver investigations. The cohort contained 50 anonymized video investigations from 49 patients. Besides the CEUS investigations, clinical data from the patients were provided. A method comprising three modules was proposed. The first module, a lesion segmentation deep learning (DL) model, handled the prediction of masks frame-by-frame (region of interest). The second module performed dilation on the mask, and after applying colormap to the image, it extracted the TIC and the parameters from the TIC (area under the curve, time to peak, mean transit time, and maximum intensity). The third module, a feed-forward neural network, predicted the final diagnosis. It was trained on the TIC parameters extracted by the second model, together with other data: gender, age, hepatitis history, and cirrhosis history. Results: For the feed-forward classifier, five classes were chosen: hepatocarcinoma, metastasis, other malignant lesions, hemangioma, and other benign lesions. Being a multiclass classifier, appropriate performance metrics were observed: categorical accuracy, F1 micro, F1 macro, and Matthews correlation coefficient. The results showed that due to class imbalance, in some cases, the classifier was not able to predict with high accuracy a specific lesion from the minority classes. However, on the majority classes, the classifier can predict the lesion type with high accuracy. Conclusions: The main goal of the study was to develop an automated method of classifying liver lesions in CEUS video investigations. Being modular, the system can be a useful tool for gastroenterologists or medical students: either as a second opinion system or a tool to automatically extract TICs.

In patients diagnosed with multiple myeloma (MM), the primary complaints at the time of diagnosis are often related to bone involvement, significantly impacting quality of life and increasing both morbidity and mortality. Obesity is associated with a chronic inflammatory state that results in the production of various cytokines and adipokines, which may promote bone destruction. Adiponectin, an adipokine predominantly secreted by adipocytes, is notably diminished in circulation among individuals with obesity, a phenomenon that has also been observed in MM. This reduction may contribute to the disruption of an already compromised bone architecture. The increase in adipose tissue is associated with heightened leptin production, a key adipokine, which can play a significant role in the pathophysiology of MM and its related bone complications. Obesity is associated with hyperinsulinemia and increased levels of free IGF-1. In MM, IGF-1 plays a critical role as a growth factor, produced by both myeloma cells and osteoclasts within the bone marrow microenvironment. Our gathered data indicates a significant relationship between the adipokines produced by adipose tissue and the bone matrix, particularly in the context of obesity and MM. However, it is important to note that the existing body of research on this topic is relatively sparse, with the majority of studies conducted on murine models rather than human subjects. This limitation highlights a critical need for further investigation to elucidate the precise mechanisms that contribute to bone destruction under these conditions.

Background/Objectives: Inflammatory and hematologic indices derived from routine blood tests have been increasingly investigated as prognostic biomarkers in multiple myeloma (MM). However, their clinical utility remains inconsistent, and data on novel composite indices, such as the mean corpuscular volume-to-lymphocyte ratio (MCVL) and the cumulative inflammatory index (IIC), are lacking in MM. Methods: We conducted a retrospective study including 122 patients with newly diagnosed MM. Hematologic and inflammatory indices were evaluated at baseline and after four cycles of induction therapy. Associations with progression-free survival (PFS) and overall survival (OS) were assessed using Kaplan–Meier analysis, Cox regression models, and receiver operating characteristic (ROC) curve analysis. Results: Baseline inflammatory biomarkers, including NLR, PLR, MLR, SII, as well as MCVL and IIC, were not significantly associated with PFS or OS. ROC analysis demonstrated poor discriminative ability for all evaluated markers at both baseline and post-induction timepoints (AUC values close to or below 0.50). In contrast, post-induction inflammatory indices, particularly PLR, MLR, AISI, and SIRI, were significantly associated with PFS in both univariable and multivariable Cox regression analyses. Neither baseline nor post-induction MCVL and IIC showed independent prognostic value. Conclusions: Baseline inflammatory and erythrocyte-derived indices, including the novel composite markers MCVL and IIC, have limited prognostic utility in MM. In contrast, dynamic changes in inflammatory biomarkers during treatment may provide more clinically relevant information regarding disease progression. These findings support the integration of longitudinal biomarker assessment into future risk stratification models in MM.

Background/Objectives: Inflammatory and hematologic indices derived from routine blood tests have been increasingly investigated as prognostic biomarkers in multiple myeloma (MM). However, their clinical utility remains inconsistent, and data on novel composite indices, such as the mean corpuscular volume-to-lymphocyte ratio (MCVL) and the cumulative inflammatory index (IIC), are lacking in MM. Methods: We conducted a retrospective study including 122 patients with newly diagnosed MM. Hematologic and inflammatory indices were evaluated at baseline and after four cycles of induction therapy. Associations with progression-free survival (PFS) and overall survival (OS) were assessed using Kaplan–Meier analysis, Cox regression models, and receiver operating characteristic (ROC) curve analysis. Results: Baseline inflammatory biomarkers, including neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), monocyte-to-lymphocyte ratio (MLR), systemic immune–inflammation index (SII), MCVL, and IIC, were not significantly associated with PFS or OS. ROC analysis demonstrated poor discriminative ability for all evaluated markers at both baseline and post-induction timepoints (AUC values close to or below 0.50). In contrast, post-induction inflammatory indices, particularly PLR, MLR, AISI, and SIRI, were significantly associated with PFS in both univariable and multivariable Cox regression analyses. Neither baseline nor post-induction MCVL and IIC showed independent prognostic value. Conclusions: Baseline inflammatory and erythrocyte-derived indices, including the novel composite markers MCVL and IIC, have limited prognostic utility in MM. In contrast, dynamic changes in inflammatory biomarkers during treatment may provide more clinically relevant information regarding disease progression. These findings support integrating longitudinal biomarker assessment into future risk stratification models for MM.