Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models.

Hospitals, especially their emergency services, receive a high number of wrist fracture cases. For correct diagnosis and proper treatment of these, images obtained from various medical equipment must be viewed by physicians, along with the patient's medical records and physical examination. The aim of this study is to perform fracture detection by use of deep-learning on wrist X-ray images to support physicians in the diagnosis of these fractures, particularly in the emergency services. Using SABL, RegNet, RetinaNet, PAA, Libra R-CNN, FSAF, Faster R-CNN, Dynamic R-CNN and DCN deep-learning-based object detection models with various backbones, 20 different fracture detection procedures were performed on Gazi University Hospital's dataset of wrist X-ray images. To further improve these procedures, five different ensemble models were developed and then used to reform an ensemble model to develop a unique detection model, 'wrist fracture detection-combo (WFD-C)'. From 26 different models for fracture detection, the highest detection result obtained was 0.8639 average precision (AP50) in the WFD-C model. Huawei Turkey R&D Center supports this study within the scope of the ongoing cooperation project coded 071813 between Gazi University, Huawei and Medskor.

Comparision of the apoptotic effects on lymphoblasts and on increase of myeloid lineage cells of a short-time, high-dose methylprednisolone and the conventional-dose prednisolone treatments in children with acute lymphoblastic leukemia.

The authors compare the apoptotic effect on the lymphoblasts and the proliferative effect on the myeloid lineage cells of a short-course high-dose methylprednisolone (HDMP) and the conventional-dose prednisolone treatments in children with acute lymphoblastic leukemia (ALL). The patients were divided into 2 groups. Group I (n = 10) received HDMP (30 mg/kg/day for 7 days) in a single dose before 6 a.m. perorally. Group II (n = 10) received prednisolone (2 mg/kg/day for 7 days) in 3 doses. The apoptotic percentages of lymphpblasts and the percentages of blasts and myeloid lineage cells were determined after performing the bone marrow aspiration (BMA) at diagnosis on the 0th, 3rd, and 7th days of the treatments in all patients. The mean apoptotic percentages of the lymphoblasts on the 3rd day were significantly higher than those on the 0th and 7th days in both groups (p < .05). The highest apoptosis was determined on the 3rd day in group I. The mean percentages of the blast cells on the 7th day were significantly lower than those on the 0th and the 3rd days in both groups (p < .05). The lowest lymphoblast percentage was determined on the 7th day in group I. The mean percentages of the CD13+ and CD33+ cells on the 7th day were significantly higher than those on the 0th and the 3rd days in both groups (p < .05). The highest percentages of the CD13+ and CD33+ cells were found on the 7th day in group I. Prednisolone and HDMP showed no proliferative effect on the CD14+ cells. These findings indicate that a short-course HDMP treatment shows a more effective apoptosis on the lymphoblasts and on the increase of the myeloid lineage cells when compared to the prednisolone treatment. The authors suggest that HDMP may be used in the treatment of patients with ALL instead of prednisolone.