UDBRNet: A novel uncertainty driven boundary refined network for organ at risk segmentation.

Organ segmentation has become a preliminary task for computer-aided intervention, diagnosis, radiation therapy, and critical robotic surgery. Automatic organ segmentation from medical images is a challenging task due to the inconsistent shape and size of different organs. Besides this, low contrast at the edges of organs due to similar types of tissue confuses the network's ability to segment the contour of organs properly. In this paper, we propose a novel convolution neural network based uncertainty-driven boundary-refined segmentation network (UDBRNet) that segments the organs from CT images. The CT images are segmented first and produce multiple segmentation masks from multi-line segmentation decoder. Uncertain regions are identified from multiple masks and the boundaries of the organs are refined based on uncertainty data. Our method achieves remarkable performance, boasting dice accuracies of 0.80, 0.95, 0.92, and 0.94 for Esophagus, Heart, Trachea, and Aorta respectively on the SegThor dataset, and 0.71, 0.89, 0.85, 0.97, and 0.97 for Esophagus, Spinal Cord, Heart, Left-Lung, and Right-Lung respectively on the LCTSC dataset. These results demonstrate the superiority of our uncertainty-driven boundary refinement technique over state-of-the-art segmentation networks such as UNet, Attention UNet, FC-denseNet, BASNet, UNet++, R2UNet, TransUNet, and DS-TransUNet. UDBRNet presents a promising network for more precise organ segmentation, particularly in challenging, uncertain conditions. The source code of our proposed method will be available at https://github.com/riadhassan/UDBRNet.

Comparing the success rate of external dacryocystorhinostomy with anterior flap versus flap excision in managing chronic dacryocystitis.

Background: Nasolacrimal duct obstruction (NLDO) is characterized by epiphora and recurrent episodes of acute dacryocystitis. Despite the temporary effect of antibiotics in the acute phase, it is primarily managed by dacryocystorhinostomy (DCR). There is a new modification of external DCR that is performed without either anterior or posterior flaps. This study aimed to compare the outcomes of flapless and single-flap external DCR in adult patients with chronic symptomatic dacryocystitis secondary to NLDO. Methods: In this retrospective, non-randomized, interventional, comparative study of patients with chronic dacryocystitis secondary to primary acquired NLDO, we compared the surgical outcomes and complication rates of flapless external DCR to those of external DCR with only anterior flap suturing. We excluded patients who declined participation and those with soft stops, nasal problems, lid margin abnormalities, lid malposition or laxity, previous lacrimal surgery, lacrimal fistula, trauma involving the lacrimal drainage system, lack of adequate follow-up, or severe septal deviation or turbinate hypertrophy. Anatomical and functional success rates were determined at the last follow-up visit and were compared. Postoperative complications were recorded and compared between groups. Results: We included 53 patients with a male-to-female ratio of 16 (30.2%) to 37 (69.8%); 25 eyes underwent flapless DCR (group 1) and 28 eyes underwent anterior flap suturing DCR (group 2). The two groups had comparable demographic characteristics (all P > 0.05). Furthermore, anatomical (92.0% in group 1 and 92.9% in group 2) and functional (84.0% in group 1 and 92.9% in group 2) success rates at final follow-up were comparable between groups (both P > 0.05). At the one-month postoperative examination, premature tube extrusion was more often reported in group 1 (12.0%) compared to group 2 (7.1%). At the two-month follow-up examination, tube extrusion was noted in 4.0% in group 1 and 0.0% in group 2, yet the difference failed to attain statistical significance (P > 0.05). Conclusions: We found that neither surgical method was superior in terms of anatomical or functional success rate at a maximum of one year after external DCR. Flapless DCR is a simple, effective, and reproducible alternative to the single anterior flap suturing technique for managing NLDO in adults with chronic dacryocystitis. However, further randomized clinical trials with larger sample sizes and longer follow-up periods are recommended before generalization can be justified.

Clinical characteristics of pediatric hidradenitis suppurativa: a cross-sectional multicenter study of 140 patients.

Hidradenitis suppurativa (HS) rarely affects pediatric patients. The literature on pediatric HS patients is scarce. This is a cross-sectional study based on case note review or interviews and clinical examination of 140 pediatric patients undergoing secondary or tertiary level care. Patients were predominantly female (75.5%, n = 105) with a median age of 16. 39% reported 1st-degree relative with HS. Median BMI percentile was 88, and 11% were smokers (n = 15). Median modified Sartorius score was 8.5. Notable comorbidities found were acne (32.8%, n = 45), hirsutism (19.3%, n = 27), and pilonidal cysts (16.4%, n = 23). Resorcinol (n = 27) and clindamycin (n = 25) were the most frequently used topical treatments. Patients were treated with tetracycline (n = 32), or oral clindamycin and rifampicin in combination (n = 29). Surgical excision was performed in 18 patients, deroofing in five and incision in seven patients. Obesity seemed to be prominent in the pediatric population and correlated to parent BMI, suggesting a potential for preventive measures for the family. Disease management appeared to be similar to that of adult HS, bearing in mind that the younger the patient, the milder the disease in majority of cases.