Background: The accurate segmentation of the appendix with well-defined boundaries is critical for diagnosing conditions such as acute appendicitis. The manual identification of the appendix is time-consuming and highly dependent on the expertise of the radiologist. Method: In this study, we propose a fully automated approach to the detection of the appendix using deep learning architecture based on the U-Net with specific training parameters in CT scans. The proposed U-Net architecture is trained on an annotated original dataset of abdominal CT scans to segment the appendix efficiently and with high performance. In addition, to extend the training set, data augmentation techniques are applied for the created dataset. Results: In experimental studies, the proposed U-Net model is implemented using hyperparameter optimization and the performance of the model is evaluated using key metrics to measure diagnostic reliability. The trained U-Net model achieved the segmentation performance for the detection of the appendix in CT slices with a Dice Similarity Coefficient (DSC), Volumetric Overlap Error (VOE), Average Symmetric Surface Distance (ASSD), Hausdorff Distance 95 (HD95), Precision (PRE) and Recall (REC) of 85.94%, 23.29%, 1.24 mm, 5.43 mm, 86.83% and 86.62%, respectively. Moreover, our model outperforms other methods by leveraging the U-Net’s ability to capture spatial context through encoder–decoder structures and skip connections, providing a correct segmentation output. Conclusions: The proposed U-Net model showed reliable performance in segmenting the appendix region, with some limitations in cases where the appendix was close to other structures. These improvements highlight the potential of deep learning to significantly improve clinical outcomes in appendix detection.

Spleen abscess is a rare and serious condition. Splenectomy and imaging-guided percutaneous catheter drainage (PCD) are the methods used in the treatment, but there is still a debate about the appropriate treatment for the patient. The results of 16 patients treated for spleen abscesses in our clinic between 2012 and 2021 were reviewed. The patients were divided into two groups according to splenectomy and PCD. In the study, PCD was performed in 11 patients (68.75%), but three of these patients required splenectomy due to inadequate drainage. The patients who underwent splenectomy were significantly younger than the patients who underwent PCD (p < 0.05). One patient underwent PCD and 2 patients underwent splenectomy after PCD died. Spleen abscess is a serious clinical picture that requires a multidisciplinary approach and is life-threatening. New clinical studies are needed for a treatment algorithm that will provide good results.

Background: A leading cause of emergency abdominal surgery, appendicitis is a common condition affecting millions of people worldwide. Automatic and accurate segmentation of the appendix from medical imaging is a challenging task, due to its small size, variability in shape, and proximity to other anatomical structures. Methods: In this study, we propose a backbone-enriched Mask R-CNN architecture (MaskAppendix) on the Detectron platform, enhanced with Gradient-weighted Class Activation Mapping (Grad-CAM), for precise appendix segmentation on computed tomography (CT) scans. In the proposed MaskAppendix deep learning model, ResNet101 network is used as the backbone. By integrating Grad-CAM into the MaskAppendix network, our model improves feature localization, allowing it to better capture subtle variations in appendix morphology. Results: We conduct extensive experiments on a dataset of abdominal CT scans, demonstrating that our method achieves state-of-the-art performance in appendix segmentation, outperforming traditional segmentation techniques in terms of both accuracy and robustness. In the automatic segmentation of the appendix region in CT slices, a DSC score of 87.17% was achieved with the proposed approach, and the results obtained have the potential to improve clinical diagnostic accuracy. Conclusions: This framework provides an effective tool for aiding clinicians in the diagnosis of appendicitis and other related conditions, reducing the potential for diagnostic errors and enhancing clinical workflow efficiency.

With a 5-year survival of ˂ 10%, pancreatic cancer is one of the leading causes of cancer-related deaths. Given the role of the distribution of tumor-infiltrating lymphocyte (TILs) subtypes in the tumor and its microenvironment in predicting prognosis, the development of new targeted therapies based on T-cell adaptive response has gained considerable attention. This study aimed to examine the peritumoral spread of TILs and its relationship with other prognostic parameters and survival. This study included 60 patients with pancreatic cancer who had undergone surgery with follow-up between 2011 and 2021. Demographic characteristics, tumor histopathological features, peritumoral TILs counts, and intratumoral programmed cell death protein-1 (PD-1) and programmed death ligand − 1 (PD-L1) positivity were evaluated. Furthermore, overall survival and their efficacy in predicting survival according to TNM stage were analyzed. The number of cluster differentiation-3 positive (CD3 P) TILs increased with advancing pathological T stage. CD3 P and CD8 P TIL counts were higher in patients with peripancreatic fatty tissue invasion. Patients with PD-L1 positivity and higher TIL counts had better survival rates. PD-L1-negative patients with a low CD8 positive/total lymph node count (P/T) ratio had a longer survival. Moreover, patients with poorly differentiated tumors with low CD3 P/T and CD8 P/T ratios had a longer survival. The CD3 P/T and CD8 P/T ratios were compatible with the automatic and manual measurements. Age, tumor differentiation, N stage, and peritumoral TIL count and subtype, when evaluated together with the presence of PD-L1 in the tumor tissue, may have prognostic significance for survival in patients with pancreatic cancer.

Objective: Sigmoid volvulus is most commonly seen in patients between 60 and 80 years old. The management of volvulus depends on its location and clinical presentation. The fundamental aspects of treatment include evaluating the viability of the colon, relieving the obstruction, and preventing the possibility of recurrence. We aimed to present the clinicopathological characteristics of geriatric colonic volvulus patients treated in a single center. Methods: Patients diagnosed with colonic volvulus and treated in this hospital were included in the study. Mortality rates of patients who underwent and did not undergo preoperative colonoscopic detorsion were compared statistically. In addition, diseases that affect the quality of life and cause deterioration in bowel movements and habits were determined, and these diseases' effect on mortality was evaluated. Results: Forty-four patients who underwent emergency surgery due to volvulus were included in our study. There was sigmoid colon perforation in two patients and cecum perforation in 1 patient. Two patients had cecal volvulus, and right hemicolectomy was performed in these patients; anastomosis was performed in one, and ileostomy was performed in the other. Sigmoid resection was performed in 36 patients, subtotal colectomy in 5 patients, right hemicolectomy in 2 patients, and sigmoidopexy with laparotomy and reduction in 1 patient. Thirteen patients (29.5%) underwent preoperative colonoscopy, and in eight cases, the procedure was conducted a day before the surgery, with the operation being carried out semi-urgently the next day. Conclusion: Intestinal volvulus is a rare condition that can occur in any part of the large intestine. However, it is a severe medical issue that requires prompt diagnosis and treatment due to the possibility of intestinal damage and mortality.

(1) Background: In our study, we aimed to determine the accuracy rates of imaging methods for sigmoid, rectosigmoid colon, and rectum cancer. (2) Methods: Patients with tumors located in the rectosigmoid colon, sigmoid colon, and rectum who were operated on were included. Upon admission, we examined the patients’ first diagnostic colonoscopies and their preoperative repeat control colonoscopies and computed tomography (CT) report. (3) Results: In this study, 23 patients (57.5%) were male. The overall accuracy rates were 80.0% (32/40) in colonoscopy, 65.0% (26/40) in preoperative CT, and 87.5% (35/40) in retro CT, and the differences among the examination methods were statistically significant (p = 0.049). The sensitivity levels decreased to 50.0% for colonoscopy and preoperative CT and 75.0% for retro CT in rectosigmoid colon tumors. In rectal tumors, the sensitivity levels were 75.0% in colonoscopy, 60.0% in preoperative CT, and 80.0% in retro CT. In two patients, the tumor location was given incorrectly, and postoperative pathological evaluations indicated T3N0 tumors; the initially planned treatment was thus changed to include radiotherapy in addition to chemotherapy in the postoperative period because the tumor was located in the middle rectum. (4) Conclusions: Accuracy in tumor localization in sigmoid, rectosigmoid, and rectum tumors still needs to be improved, which could be accomplished with prospective studies. CT evaluations for cancer localization in this patient group should be re-evaluated by a radiologist.