Automatic severity grade classification of diabetic retinopathy using deformable ladder Bi attention U-net and deep adaptive CNN.

Long-term exposure to diabetes mellitus leads to the formation of diabetic retinopathy (DR), which can cause vision loss in working-age adults. Early stage diagnosis of DR is highly essential for preventing vision loss and preserving vision in people with diabetes. The motivation behind the severity grade classification of DR is to develop an automated system that can assist ophthalmologists and healthcare professionals in the diagnosis and management of DR. However, existing methods suffer from variability in image quality, similar structures of the normal and lesion regions, high dimensional features, variability in disease manifestations, small datasets, high training loss, model complexity, and overfitting, which leads to high misclassification errors in the severity grading system. Hence, there is a need to develop an automated system using improved deep learning techniques to provide a reliable and consistent grading of DR severity with high classification accuracy using fundus images. To solve these issues, we proposes a Deformable Ladder Bi attention U-shaped encoder-decoder network and Deep Adaptive Convolutional Neural Network (DLBUnet-DACNN) for accurate severity classification of DR. The DLBUnet performs lesion segmentation that can be divided into three parts: the encoder, the central processing module and the decoder. In the encoder part, deformable convolution is used instead of convolution to learn different shapes of the lesion by understanding the offset location. Afterwards, Ladder Atrous Spatial Pyramidal Pooling (LASPP) using variable dilation rates is introduced in the central processing module. LASPP enhance the tiny lesion features and variable dilation rates avoid gridding effects and can learn better global context information. Then the decoder part uses a bi-attention layer contains spatial and channel attention, which can learn contour and edges of the lesion accurately. Finally, the severity of DR is classified using a DACNN by extracting the discriminative features from the segmentation results. Experiments are conducted on the Messidor-2, Kaggle, and Messidor datasets. Our proposed method DLBUnet-DACNN achieves better results in terms of accuracy of 98.2, recall of 0.987, kappa coefficient of 0.993, precision of 0.98, F1-score of 0.981, Matthews Correlation Coefficient (MCC) of 0.93 and Classification Success Index (CSI) of 0.96 when compared to existing methods.

Halobacterium sp. SP1(1) as a starter culture for accelerating fish sauce fermentation.

AIMS: Application of Halobacterium sp. SP1(1) for the acceleration of fish sauce fermentation. METHODS AND RESULTS: Traditional fish sauce fermentation was mimicked using Halobacterium sp. SP1(1) as starter culture. Protease activity, peptide release and α-amino content (parameters used to monitor the progress of the fermentation) were high at day 10 in tests and day 20 in un-inoculated controls. The total protein and nitrogen contents were also high in tests compared with controls. The amino acid profile observed at the end of fermentation in experimental samples, when compared with the commercial sauce preparation, was found to be better with respect to flavour and aroma contributing amino acids as well as essential amino acid lysine. Microflora analysis of the final fish sauce revealed the absence of any nonhalophilic or halotolerant micro-organisms. The protease-producing halophilic isolates obtained from the fish sauce of eviscerated and uneviscerated controls were identified as Halobacterium sp. F1 and F2, respectively, by 16S rDNA sequence analysis. CONCLUSIONS: Exogenous augmentation of Halobacterium sp. SP1(1) accelerated the fish sauce fermentation process with an additive effect on the existing natural microflora present in the fish during fermentation. Halobacterium sp SP1(1), therefore, can be used as an important starter culture for accelerating the fish fermentation process, which is attributed to its extracellular protease. SIGNIFICANCE AND IMPACT OF THE STUDY: The present study is the first report on use of Halobacterium species as a starter culture for accelerating fish sauce fermentation. Use of halobacterial starter cultures may revolutionize the process in fish sauce industries by reducing the fermentation time and making the process more economical with improved nutritive value of product.

What are the clinical outcome and cost-effectiveness of endoscopy undertaken by nurses when compared with doctors? A Multi-Institution Nurse Endoscopy Trial (MINuET).

OBJECTIVES: To compare the clinical outcome and cost-effectiveness of doctors and nurses undertaking upper and lower gastrointestinal endoscopy. DESIGN: The study was a pragmatic randomised controlled trial. Zelen's randomisation before consent was used to minimise distortion of existing practice in the participating sites. An economic evaluation was conducted alongside the trial, assessing the relative cost-effectiveness of nurses and doctors. SETTING: The study was undertaken in 23 hospitals in England, Scotland and Wales. In six hospitals nurses undertook both upper and lower gastrointestinal endoscopy, yielding a total of 29 'centres'. The study was coordinated and managed from Swansea. Randomisation, data management and analysis were undertaken at York. Analysis was by intention-to-scope. PARTICIPANTS: Sixty-seven doctors and 30 nurses took part in the study. Of 4964 potentially eligible patients, 4128 (83%) were randomised. Of these, 1888 (45%) were recruited to the study from 29 July 2002 to 30 June 2003. INTERVENTIONS: The procedures under study were diagnostic upper gastrointestinal endoscopy and flexible sigmoidoscopy undertaken by nurses or doctors, with or without sedation, using the preparation, techniques and protocols of participating hospitals. MAIN OUTCOME MEASURES: Primary outcome measure was the Gastrointestinal Symptom Rating Questionnaire (GSRQ). The secondary outcome measures were EuroQol (EQ5D), Gastrointestinal Endoscopy Satisfaction Questionnaire (GESQ), State-Trait Anxiety Inventory (STAI), cost-effectiveness, immediate and delayed complications, quality of examination by blinded assessment of endoscopic video recordings, quality of procedure reports, patients' preferences for operator 1 year after endoscopy, and new diagnoses at 1 year. RESULTS: The two groups were well matched at baseline for demographic and clinical characteristics. Significantly more patients changed from a planned endoscopy by a doctor to a nurse than vice versa, mainly for staffing reasons. There was no significant difference between the two groups in the primary or secondary outcome measures at 1 day, 1 month or 1 year after endoscopy, with the exception of patient satisfaction at 1 day, which favoured nurses. Nurses were significantly more thorough in the examination of stomach and oesophagus, but no different from doctors in the examination of duodenum and colon. There was no significant difference in costs to the NHS or patients, although doctors cost slightly more. Although quality of life measures showed improvement in some scores in the doctor group, this did not reach traditional levels of statistical significance. Even so, the economic evaluation, taking account of uncertainty in both costs and quality of life, suggests that endoscopy by doctors has an 87% chance of being more cost-effective than endoscopy by nurses. CONCLUSIONS: There is no statistically significant difference between doctors and nurses in their clinical effectiveness in diagnostic endoscopy. However, nurses are significantly more thorough in the examination of oesophagus and stomach, and patients are significantly more satisfied after endoscopy by a nurse. Endoscopy by doctors is associated with better outcome at 1 year at higher cost, but overall is likely to be cost-effective. Further research is needed to evaluate the clinical outcome and cost-effectiveness of nurses undertaking a greater role in other settings, to monitor the cost-effectiveness of nurse endoscopists as they become more experienced and to assess, the effect of increasing the number of nurse endoscopists on waiting times for patients, and the career implications and opportunities for nurses who become trained endoscopists. Evaluation of the clinical outcome and cost-effectiveness of diagnostic endoscopy for all current indications is also needed.

Review article: how and when to use ciclosporin in ulcerative colitis.

Although colectomy for ulcerative colitis is curative, long-term quality of life is reduced. Intravenous ciclosporin 4 mg/kg/day has significant toxicity. There is now evidence that low-dose ciclosporin (2 mg/kg daily by intravenous infusion, or 5-6 mg/kg daily in a twice daily oral dosage) has an acceptable safety profile, even when used in combination with corticosteroids. Drug dosage should be adjusted to the levels of 150-250 ng/mL initially (random levels during intravenous infusion, or trough levels for oral use). Ciclosporin should be considered not only in those who have failed 7 days of corticosteroids, but also in fulminant colitis at day 3, if not responding to corticosteroids. The drug should be avoided in frail or elderly patients with significant comorbidity, and also where colectomy is likely to be necessary in the short to medium term. Ciclosporin should not be continued for more than 7 days, unless there is a definite response. A 70-80% initial response is likely, and responders are discharged on oral ciclosporin, adding thiopurines and tailing prednisolone rapidly. The drug should be continued for 3 months. The likelihood of avoiding colectomy over 2-3 years is 40-50%. More studies are needed to evaluate the use of oral ciclosporin in corticosteroid-refractory colitis in out-patients, and to assess whether monotherapy (without corticosteroids) is significantly safer, without loss of efficacy.

GOAL: a simplified mental test for emergency medical admissions.

BACKGROUND: Several scoring systems are used in screening for cognitive impairment, but none are suited to the busy medical assessment environment. AIM: To construct, validate and assess the reliability of a simple scale (Gwent Orientation and Awareness Listing, GOAL) for this purpose, and to examine its application in consecutive emergency admissions in two general hospitals. DESIGN: Prospective cohort studies. METHODS: The validity and reliability of GOAL was assessed in three studies of patients aged > or =65 years who had been pronounced medically fit for discharge. The evaluation studies were carried out over 4-week medical intake periods in each participating hospital. RESULTS: Correlation of GOAL with the standard 30-point Mini-Mental State Examination was 0.89, and the inter-observer reliability was 0.90. Based on Receiver Operating Characteristics Curves, patients scoring <8 on GOAL were deemed to be cognitively impaired. Assessment by GOAL took half the time required for the widely used Abbreviated Mental Test Score. Of 1037 consecutive patients admitted to two hospitals' acute medical intakes and remaining for >24 h, 952 were able and willing to be scored by GOAL, and of these 201 (21%) 'failed', with a score of <8. DISCUSSION: Loss of orientation and awareness is common among patients admitted via medical intakes. GOAL is a practical brief screen for identifying and following-up these patients.

Regression of primary high-grade gastric B-cell lymphoma following Helicobacter pylori eradication.

The causative association between Helicobacter pylori and gastric mucosal inflammation is well established. The inflammatory process leads to the acquisition of mucosa-associated lymphoid tissue (MALT) by the stomach. Evidence links H. pylori gastritis with the development of low-grade primary gastric lymphoma with a phenotype specific for lymphoma of MALT type. It is now accepted that primary low-grade MALT lymphomas regress with H. pylori eradication therapy. However, the response of primary, diffuse, large-cell gastric lymphoma to H. pylori eradication therapy is still not established. We report a case of a primary high-grade gastric lymphoma regressing after H. pylori eradication therapy.