Vision Transformers for Lung Segmentation on CXR Images.

Accurate segmentation of the lungs in CXR images is the basis for an automated CXR image analysis system. It helps radiologists in detecting lung areas, subtle signs of disease and improving the diagnosis process for patients. However, precise semantic segmentation of lungs is considered a challenging case due to the presence of the edge rib cage, wide variation of lung shape, and lungs affected by diseases. In this paper, we address the problem of lung segmentation in healthy and unhealthy CXR images. Five models were developed and used in detecting and segmenting lung regions. Two loss functions and three benchmark datasets were employed to evaluate these models. Experimental results showed that the proposed models were able to extract salient global and local features from the input CXR images. The best performing model achieved an F1 score of 97.47%, outperforming recent published models. They proved their ability to separate lung regions from the rib cage and clavicle edges and segment varying lung shape depending on age and gender, as well as challenging cases of lungs affected by anomalies such as tuberculosis and the presence of nodules.

Infected popliteal pseudoaneurysm in a youth basketball player: A case report and brief review of the literature.

INTRODUCTION: An infected popliteal pseudoaneurysm has never been described in the pediatric population. Physicians need to be aware of its presentation and management, in order to diagnose and treat this medical condition adequately. METHODS: We describe the case of a 14-year-old boy who developed myositis and cellulitis centered at the popliteal fossa after playing basketball. A treatment of intravenous cefazolin was started. 5 days later, he experienced a knee pain flare-up, which turned out to be a popliteal pyomyositis with a pseudoaneurysm of the popliteal artery. A saphenous vein graft bypass of the popliteal artery and an excision of the popliteal pseudoaneurysm were performed. Intravenous cefazolin was continued for 6 weeks and prophylactic acetylsalicylic acid for 6 months. RESULTS AND CONCLUSION: This case highlighted the importance of repeating radiologic investigations if a patient suffering from soft tissue infection has persistent pain after several days of appropriate antibiotics. A popliteal pseudoaneurysm can be diagnosed with ultrasound imaging and treated with a popliteal-popliteal bypass. Our patient needed a catheter-guided dilation of the anastomosis at the vein graft 6 months post-surgery, and then evolved favorably and went back to playing basketball 6 months post-dilation.

Deep Learning and Transformer Approaches for UAV-Based Wildfire Detection and Segmentation.

Wildfires are a worldwide natural disaster causing important economic damages and loss of lives. Experts predict that wildfires will increase in the coming years mainly due to climate change. Early detection and prediction of fire spread can help reduce affected areas and improve firefighting. Numerous systems were developed to detect fire. Recently, Unmanned Aerial Vehicles were employed to tackle this problem due to their high flexibility, their low-cost, and their ability to cover wide areas during the day or night. However, they are still limited by challenging problems such as small fire size, background complexity, and image degradation. To deal with the aforementioned limitations, we adapted and optimized Deep Learning methods to detect wildfire at an early stage. A novel deep ensemble learning method, which combines EfficientNet-B5 and DenseNet-201 models, is proposed to identify and classify wildfire using aerial images. In addition, two vision transformers (TransUNet and TransFire) and a deep convolutional model (EfficientSeg) were employed to segment wildfire regions and determine the precise fire regions. The obtained results are promising and show the efficiency of using Deep Learning and vision transformers for wildfire classification and segmentation. The proposed model for wildfire classification obtained an accuracy of 85.12% and outperformed many state-of-the-art works. It proved its ability in classifying wildfire even small fire areas. The best semantic segmentation models achieved an F1-score of 99.9% for TransUNet architecture and 99.82% for TransFire architecture superior to recent published models. More specifically, we demonstrated the ability of these models to extract the finer details of wildfire using aerial images. They can further overcome current model limitations, such as background complexity and small wildfire areas.

Microsurgical and Endovascular Management of Congenital Iliac Aneurysms in the Neonatal Period: Two Cases and a Literature Review.

INTRODUCTION: Congenital aneurysms of major arteries are very rare diagnoses and prognosis can be poor if treatment is not initiated rapidly. This is the presentation of two cases of infants with congenital iliac aneurysms who underwent treatment in the neonatal period. The report then proceeds with a literature review of paediatric iliac aneurysms. REPORT: Case 1: A female neonate was diagnosed antenatally with right common iliac (CIA) and internal iliac (IIA) artery aneurysms. Embolisation on day of life (DOL) eight was impossible because of partial thrombosis. The infant was subsequently observed for several months and the aneurysm was injected percutaneously with thrombin on DOL 78. A small residual aneurysm was coil embolised at five months of age. Satisfactory results were observed at one year follow up. Case 2: A female neonate was diagnosed antenatally on routine third trimester ultrasound with voluminous, bilateral CIA aneurysms. The patient underwent surgery on DOL 9 for aneurysm resection and microsurgical vascular reconstruction. The intervention was successful with triphasic flow through the anastomoses on colour Doppler ultrasound at six week follow up. DISCUSSION: Ten cases of congenital iliac aneurysms have been reported previously, with just two diagnosed in the neonatal period and eight undergoing surgical intervention. Definitive management to avoid aneurysm rupture or thrombosis should be timed carefully, and sometimes delayed with watchful waiting, to maximise success and minimise complications. Surgery is the key treatment modality, but endovascular intervention can be considered in selected cases. Congenital iliac aneurysms should be addressed at the safest time for the patient. Following resection, primary microvascular anastomosis is the ideal reconstructive technique, but other options for neonates have been described. Endovascular treatment should be considered for anatomically amenable saccular aneurysms.

Erratum to: Neonatal Microsurgical Repair of a Congenital Abdominal Aortic Aneurysm with a Cadaveric Graft.

[This corrects the article DOI: 10.1055/s-0041-1723019.].

Neonatal Microsurgical Repair of a Congenital Abdominal Aortic Aneurysm with a Cadaveric Graft.

Congenital abdominal aortic aneurysms (AAA) are an extremely rare entity. We present the case of a female fetus diagnosed with an AAA on routine prenatal ultrasound. A postnatal computed tomography angiogram revealed an infrarenal AAA with a narrow proximal neck. Surgery was performed on day of life 14 using a cadaveric femoral artery graft. The proximal anastomosis was performed under the microscope given the severity of the aortic stenosis and the proximity of the renal arteries. The patient's postoperative course was uneventful and she is developing normally 1 year after surgery. The graft remains permeable, albeit with evidence of proximal and distal stenosis and graft calcification on imaging.

Outcomes of vulnerable elderly patients undergoing elective major surgery: a prospective cohort study.

PURPOSE: Identifying patients at risk of postoperative complications and trying to prevent these complications are the essence of preoperative evaluation. While not overtly frail or disabled, vulnerable patients with mild frailty may be missed by routine assessments and may still have a worse postoperative course. METHODS: We performed a prospective cohort study evaluating vulnerability in older patients undergoing elective surgery. Vulnerability was assessed using the Clinical Frailty Scale. Our primary outcome was postoperative hospital length of stay (LOS) and our secondary outcome was non-home hospital discharge. We performed multivariable analyses to assess the association between vulnerability and our primary and secondary outcome. RESULTS: Between 1 January 2017 and 1 January 2018, 271 older patients with a median [interquartile range (IQR)] age of 72 [69-76] yr underwent frailty assessment prior to surgery. Eighty-eight (32.5%) of the cohort were classified as vulnerable. The median [IQR] duration of hospital LOS was 4 [2-7] days for vulnerable patients, 4 [2-6] days for robust patients, and 7 [3-10] days for frail patients. After adjusting for confounders, hospital LOS was not longer for vulnerable patients than for robust patients, but was associated with a higher rate of non-home discharge (odds ratio, 3.7; 95% confidence interval, 1.1 to 12.9; P = 0.04). CONCLUSIONS: Vulnerability was not associated with a longer hospital LOS but with higher risk of non-home discharge. Vulnerable patients might benefit from early identification and advanced planning with earlier transfer to rehabilitation centres.

RéSUMé: OBJECTIF: L'identification des patients à risque de complications postopératoires et la prévention de ces complications constituent le fondement de l'évaluation préopératoire. Sans être ouvertement fragiles ou handicapés, les patients vulnérables avec une fragilité légère pourraient passer entre les mailles des évaluations de routine et tout de même souffrir d'un parcours postopératoire plus difficile. MéTHODE: Nous avons réalisé une étude de cohorte prospective évaluant la vulnérabilité des patients âgés subissant une chirurgie élective. La vulnérabilité a été évaluée à l'aide de l'Échelle Clinical Frailty Scale. Notre critère d'évaluation principal était la durée de séjour hospitalier postopératoire; notre critère d'évaluation secondaire était le congé de l'hôpital sans retour au foyer. Nous avons réalisé des analyses multivariées afin d'évaluer l'association entre la vulnérabilité et nos critères d'évaluation principal et secondaire. RéSULTATS: Entre le 1er janvier 2017 et le 1er janvier 2018, 271 patients d'un âge médian [écart interquartile (ÉIQ)] de 72 [69­76] ans ont passé une évaluation de fragilité avant leur chirurgie. Quatre-vingt-huit personnes (32,5 %) de la cohorte ont été catégorisées comme vulnérables. La durée médiane [ÉIQ] de séjour hospitalier était de 4 [2­7] jours pour les patients vulnérables, 4 [2­6] pour les patients robustes, et 7 [3­10] pour les patients fragiles. Après l'ajustement pour tenir compte des facteurs confondants, la durée de séjour hospitalier n'était pas plus longue pour les patients vulnérables que pour les patients robustes, mais était associée à un taux plus élevé de congé sans retour au foyer (rapport de cotes, 3,7; intervalle de confiance 95 %, 1,1 à 12,9; P = 0,04). CONCLUSION: La vulnérabilité n'a pas été associée à une durée de séjour hospitalier plus longue mais à un risque plus élevé de congé sans retour au foyer. Les patients vulnérables pourraient bénéficier d'une identification précoce et d'une planification avancée avec un transfert plus rapide vers les centres de réadaptation.