Mask R-CNN-based building extraction from VHR satellite data in operational humanitarian action: An example related to Covid-19 response in Khartoum, Sudan.

Within the constraints of operational work supporting humanitarian organizations in their response to the Covid-19 pandemic, we conducted building extraction for Khartoum, Sudan. We extracted approximately 1.2 million dwellings and buildings, using a Mask R-CNN deep learning approach from a Pléiades very high-resolution satellite image with 0.5 m pixel resolution. Starting from an untrained network, we digitized a few hundred samples and iteratively increased the number of samples by validating initial classification results and adding them to the sample collection. We were able to strike a balance between the need for timely information and the accuracy of the result by combining the output from three different models, each aiming at distinctive types of buildings, in a post-processing workflow. We obtained a recall of 0.78, precision of 0.77 and F 1 score of 0.78, and were able to deliver first results in only 10 days after the initial request. The procedure shows the great potential of convolutional neural network frameworks in combination with GIS routines for dwelling extraction even in an operational setting.

Peroneal tendon dislocation in talus fracture and diagnostic value of fleck sign.

INTRODUCTION: Talus fractures are not uncommon and one of the serious fractures in the foot and ankle. Peroneal tendon dislocation is one of the commonly missed soft tissue injuries which may have significant impact on the outcomes including persistent pain and swelling. They have been reported to be associated with calcaneum as well as talus fractures. AIM: To report the incidence of peroneal tendon dislocation in talus fracture and the significance of fleck sign in the diagnosis of peroneal tendon dislocation. METHODS: We retrospectively reviewed 93 consecutive talus fractures in the period between 1/1/2011 to 1/11/2018. Inclusion criteria were: The patient underwent open reduction and internal fixation, had pre-operative CT scan that is available for review and three view ankle plain radiographs. Two independent authors review the radiographs for peroneal tendon dislocation, fleck sign and fracture classification, if any. Any dispute was resolved by the senior author.Patient records were reviewed for laterality, age, sex,mode of injury, associated injuries and operative interventions. 50 ankles met the inclusion criteria. 49 were males, mean age was 32.5 year and the predominant mode of injury was a fall from height. RESULTS: Peroneal tendon dislocation was found in ten patients out of 50 (20%). Risk of dislocation increased with severity of the fracture and neck fractures. Most of the dislocations were missed by surgeons and radiologist, and no additional procedures were done to address such an injury. The Fleck sign had a statistically significant correlation with peroneal tendons dislocations (p=.005) CONCLUSION: Peroneal tendons dislocation is associated with as high as 20% of talus fractures. The authors recommend carefully reviewing CT scans by surgeons and radiologists alike to avoid missing such injury and allow for appropriate surgical approach utilization. The Fleck sign is a highly specific radiographic sign that has a statistically significant correlation with PT dislocation and hence we recommend intra-operative assessment of peroneal tendons in patients with the fleck sign.

Correction to: Early versus late intramedullary nailing for traumatic femur fracture management: meta-analysis.

Following the publication of this article [1], the authors reported that they had submitted an incorrect version of Figs. 2, 3 and 4.

Early versus late intramedullary nailing for traumatic femur fracture management: meta-analysis.

INTRODUCTION: There is no consensus yet on the impact of timing of femur fracture (FF) internal fixation on the patient outcomes. This meta-analysis was conducted to evaluate the contemporary data in patients with traumatic FF undergoing intramedullary nail fixation (IMN). METHODS: English language literature was searched with publication limits set from 1994 to 2016 using PubMed, Scopus, MEDLINE (OVID), EMBASE (OVID), Web of Science, and Cochrane Central Register of Controlled Trials (CENTRAL). Studies included randomized controlled trials (RCTs), prospective observational or retrospective cohort studies, and case-control studies comparing early versus late femoral shaft fractures IMN fixation. Variable times were used across studies to distinguish between early and late IMN, but 24 h was the most frequently used cutoff. The quality assessment of the reviewed studies was performed with two instruments. Observational studies were assessed with the Newcastle-Ottawa Quality Assessment Scale. RCTs were assessed with the Cochrane Risk of Bias Tool. RESULTS: We have searched 1151 references. Screening of titles and abstracts eliminated 1098 references. We retrieved 53 articles for full-text screening, 15 of which met study eligibility criteria. CONCLUSIONS: This meta-analysis addresses the utility of IMN in patients with FF based on the current evidence; however, the modality and timing to intervene remain controversial. While we find large pooled effects in favor of early IMN, for reasons discussed, we have little confidence in the effect estimate. Moreover, the available data do not fill all the gaps in this regard; therefore, a tailored algorithm for management of FF would be of value especially in polytrauma patients.

An unusual osteomyelitis caused by Moraxella osloensis: A case report.

INTRODUCTION: Moraxella osloensis is a gram-negative coccobacillus, that is saprophytic on skin and mucosa, and rarely causing human infections. Reported cases of human infections usually occur in immunocompromised patients. PRESENTATION OF CASE: We report the second case of M. osloensis-caused-osteomyelitis in literature, occurring in a young healthy man. The organism was identified by sequencing analysis of the 16S ribosomal RNA gene. Our patient was treated successfully with surgical debridement and intravenous third-generation cephalosporins. DISCUSSION: M. osloensis has been rarely reported to cause local or invasive infections. Our case report is the second case in literature and it is different from the previously reported case in that our patient has no chronic medical problems, no history of trauma, with unique presentation and features on the MRI and intraoperative finding. CONCLUSION: Proper diagnosis is essential for appropriate treatment of osteomyelitis. RNA gene sequence analysis is the primary method of M. osloensis diagnosis. M. osloensis is usually susceptible to simple antibiotics.

Early and late intramedullary nailing of femur fracture: A single center experience.

BACKGROUND: Femur fracture (FF) is a common injury, and intramedullary nailing (IMN) is the standard surgical fixation. However, the time of intervention remains controversial. We aimed to describe the reamed IMN (rIMN) timing and hospital outcomes in trauma patients presenting with FF. MATERIALS AND METHODS: A retrospective analysis was conducted for all patients admitted with FF and they underwent fixation at level 1 trauma unit between January 2010 and January 2012. Patients were divided into Group I with early rIMN (<12 h) and Group II with late rIMN (≥12 h). Patients' demographics, clinical presentations, mechanism of injury, pulmonary complications, organ failure, length of stay, and mortality were described. RESULTS: A total of 307 eligible patients with FF were identified (156 patients in Group I and 151 patients in Group II). Patients in Group II were older (36 ± 18 vs. 29 ± 9; P = 0.001) and had higher rate of polytrauma (35% vs. 18%, P = 0.001), head injury (5% vs. 12%, P = 0.68) and bilateral FF (10.7% vs. 5.1%; P = 0.07) in comparison to Group I. Group II had longer stay in Intensive Care Unit (7 [1-56] vs. 2 [1-17] days; P = 0.009) and hospital (13 [2-236] vs. 9 [1-367]; P = 0.001). There were no significant differences in outcomes between the two groups in terms of sepsis, renal failure, fat embolism, adult respiratory distress syndrome and death. CONCLUSIONS: Based on this analysis, we believe that early rIMN is safe in appropriately selected cases. In patients with traumatic FFs, early rIMN is associated with low hospital complications and shorter hospital stay. The rate of pulmonary complications is almost the same in the early and late group. Further prospective randomized studies with large sample size would be ideal using the information garnered from the present study.

Thigh compartment syndrome complicated by sciatic nerve palsy, rhabdomyolysis, and acute renal failure.

We reported a rare case of thigh compartment syndrome (TCS) complicated by sciatic nerve palsy, rhabdomyolysis, and acute renal failure in an alcoholic patient. Intensive care measures and immediate posteromedial decompressive fasciotomy were performed. These timely interventions resulted in improvement of the nerve injury and restoration of the kidney function.