A fully convolutional neural network for new T2-w lesion detection in multiple sclerosis

•

A deep learning model for new T2-w lesions detection in multiple sclerosis is presented.

•

Combining a learning-based registration network with a segmentation one increases the performance.

•

The proposed model decreases false-positives while increasing true-positives.

•

Better performance compared to other supervised and unsupervised state-of-the-art approaches.

Introduction: Longitudinal magnetic resonance imaging (MRI) has an important role in multiple sclerosis (MS) diagnosis and follow-up. Specifically, the presence of new T2-w lesions on brain MR scans is considered a predictive biomarker for the disease. In this study, we propose a fully convolutional neural network (FCNN) to detect new T2-w lesions in longitudinal brain MR images.

Methods: One year apart, multichannel brain MR scans (T1-w, T2-w, PD-w, and FLAIR) were obtained for 60 patients, 36 of them with new T2-w lesions. Modalities from both temporal points were preprocessed and linearly coregistered. Afterwards, an FCNN, whose inputs were from the baseline and follow-up images, was trained to detect new MS lesions. The first part of the network consisted of U-Net blocks that learned the deformation fields (DFs) and nonlinearly registered the baseline image to the follow-up image for each input modality. The learned DFs together with the baseline and follow-up images were then fed to the second part, another U-Net that performed the final detection and segmentation of new T2-w lesions. The model was trained end-to-end, simultaneously learning both the DFs and the new T2-w lesions, using a combined loss function. We evaluated the performance of the model following a leave-one-out cross-validation scheme.

Results: In terms of the detection of new lesions, we obtained a mean Dice similarity coefficient of 0.83 with a true positive rate of 83.09% and a false positive detection rate of 9.36%. In terms of segmentation, we obtained a mean Dice similarity coefficient of 0.55. The performance of our model was significantly better compared to the state-of-the-art methods (p < 0.05).

Conclusions: Our proposal shows the benefits of combining a learning-based registration network with a segmentation network. Compared to other methods, the proposed model decreases the number of false positives. During testing, the proposed model operates faster than the other two state-of-the-art methods based on the DF obtained by Demons.

P617Early global longitudinal strain predicts late infarct size in patients with anterior ST-segment elevation myocardial infarction treated with a primary percutaneous coronary intervention

Background

Late infarct size (IS) after STEMI is a determinant of subsequent mortality. Late Gadolinium enhancement in cardiac magnetic resonance imaging (LGE-CMRI) is the gold standard for IS measurement, however, it is not readily accessible in many areas.

Aims

To evaluate the value of early baseline 2D-echocardiographic global longitudinal strain (GLS) for prediction of late IS after STEMI.

Methods

From October 2017 to July 2018, we studied 100 patients with their 1st anterior STEMI treated with a PPCI. Baseline GLS calculation was performed within 48 hours of admission. The average value of the 9 segments supplied by the LAD was assessed separately (anterior GLS). Infarct size was assessed 3 months later using LGE-CMRI, and large infarcts were defined as ≥20% LV myocardium covered by scar.

Results

Based on CMRI, patients were divided into 2 groups; 57 patients with large infarcts (group I) and 43 patients with small infarcts (group II). Both groups were matched in all baseline demographics and risk factors. There was a good and significant correlation between GLS and the degree of myocardium affected by scar (r=−0.840, P<0.001). This correlation was even higher for anterior GLS (r=−0.867, P<0.001). ROC analysis showed a cut-off point of GLS (−13%) that identified large late IS with a sensitivity and specificity of 66.7% and 88.4% respectively (AUC= 0.85). For anterior GLS, the cut-off point was −9.6% (Sensitivity 94%, specificity 86%, AUC= 0.9).

Baseline 2D-GLS & Late LGE-CMRI

Conclusion

Baseline GLS significantly predicts and correlates well with late IS after anterior STEMI.

Un syndrome de Budd-Chiari associé à une thrombose veineuse portomésentérique : mode de révélation inhabituel d’une hémoglobinurie paroxystique nocturne

Le syndrome de Budd-Chiari (SBC) est une maladie vasculaire du foie faisant suite souvent à une thrombose veineuse sus-hépatique. L’hémoglobinurie paroxystique nocturne (HPN), affection clonale acquise rare, réalise une des conditions prothrombotiques bien connues prédisposant au SBC primitif. L’association SBC–HPN est souvent rapportée sous forme de cas cliniques isolés ou de petites séries présentant des spécificités pronostiques et thérapeutiques. Nous rapportons le cas d’une fille de 27 ans ayant une HPN révélée dans le cadre du bilan étiologique d’un SBC, associé à des thromboses veineuses portale, mésentérique et à une embolie pulmonaire.

Critical care usage after major gastrointestinal and liver surgery: a prospective, multicentre observational study

BACKGROUND

Patient selection for critical care admission must balance patient safety with optimal resource allocation. This study aimed to determine the relationship between critical care admission, and postoperative mortality after abdominal surgery.

METHODS

This prespecified secondary analysis of a multicentre, prospective, observational study included consecutive patients enrolled in the DISCOVER study from UK and Republic of Ireland undergoing major gastrointestinal and liver surgery between October and December 2014. The primary outcome was 30-day mortality. Multivariate logistic regression was used to explore associations between critical care admission (planned and unplanned) and mortality, and inter-centre variation in critical care admission after emergency laparotomy.

RESULTS

Of 4529 patients included, 37.8% (n=1713) underwent planned critical care admissions from theatre. Some 3.1% (n=86/2816) admitted to ward-level care subsequently underwent unplanned critical care admission. Overall 30-day mortality was 2.9% (n=133/4519), and the risk-adjusted association between 30-day mortality and critical care admission was higher in unplanned [odds ratio (OR): 8.65, 95% confidence interval (CI): 3.51-19.97) than planned admissions (OR: 2.32, 95% CI: 1.43-3.85). Some 26.7% of patients (n=1210/4529) underwent emergency laparotomies. After adjustment, 49.3% (95% CI: 46.8-51.9%, P<0.001) were predicted to have planned critical care admissions, with 7% (n=10/145) of centres outside the 95% CI.

CONCLUSIONS

After risk adjustment, no 30-day survival benefit was identified for either planned or unplanned postoperative admissions to critical care within this cohort. This likely represents appropriate admission of the highest-risk patients. Planned admissions in selected, intermediate-risk patients may present a strategy to mitigate the risk of unplanned admission. Substantial inter-centre variation exists in planned critical care admissions after emergency laparotomies.

Detection of Mycobacterium avium subsp. paratuberculosis in an Egyptian mixed breeding farm and comparative molecular characterisation of isolates from cattle, camels and cats – a case report

The present study records and investigates an outbreak of Johne’s Disease in a mixed breeding camel – cattle farm and the possible role of non-domestic non-ruminants animals in the epidemiology of Mycobacterium avium subspecies paratuberculosis in Egypt. For this reason, faecal samples were collected from 24 dairy cattle and from 15 one humped Arabian camels suffering from diarrhoea. Moreover, intestinal tissue samples were provided from 7 cats and 2 rats that were caught from the same farm and were euthanized before necropsy. Samples were examined using traditional culture and IS900 PCR techniques together with the application of BstEII-IS900 RFLP for typing of obtained isolates. Interestingly, MAP was recovered from cattle (n=8) and from camels (n=3) and non-domestic cats (n=3) reared under local conditions in this farm in Egypt. The obtained results highlight the potential role of cats in the epidemiology of MAP, a subject which needs further investigation and might have a public health importance, catsbeing common members of many families.