Stain normalization gives greater generalizability than stain jittering in neural network training for the classification of coeliac disease in duodenal biopsy whole slide images.

Around 1% of the population of the UK and North America have a diagnosis of coeliac disease (CD), due to a damaging immune response to the small intestine. Assessing whether a patient has CD relies primarily on the examination of a duodenal biopsy, an unavoidably subjective process with poor inter-observer concordance. Wei et al. [11] developed a neural network-based method for diagnosing CD using a dataset of duodenal biopsy whole slide images (WSIs). As all training and validation data came from one source, there was no guarantee that their results would generalize to WSIs obtained from different scanners and laboratories. In this study, the effects of applying stain normalization and jittering to the training data were compared. We trained a deep neural network on 331 WSIs obtained with a Ventana scanner (WSIs; CD: n=190; normal: n=141) to classify presence of CD. In order to test the effects of stain processing when validating on WSIs scanned on varying scanners and from varying laboratories, the neural network was validated on 4 datasets: WSIs of slides scanned on a Ventana scanner (WSIs; CD: n=48; normal: n=35), WSIs of the same slides rescanned on a Hamamatsu scanner (WSIs; CD: n=48; normal: n=35), WSIs of the same slides rescanned on an Aperio scanner (WSIs; CD: n=48; normal: n=35), and WSIs of different slides scanned on an Aperio scanner (WSIs; CD: n=38; normal: n=37). Without stain processing, the F1 scores of the neural network were 0.947, 0.619, 0.746, and 0.727 when validating on the Ventana validation WSIs, Hamamatsu and Aperio rescans of the Ventana validation WSIs, and Aperio WSIs from a different source respectively. With stain normalization, the performance of the neural network improved significantly with respective F1 scores 0.982, 0.943, 0.903, and 0.847. Stain jittering resulted in a better performance than stain normalization when validating on data from the same source F1 score 1.000, but resulted in poorer performance than stain normalization when validating on WSIs from different scanners (F1 scores 0.939, 0.814, and 0.747). This study shows the importance of stain processing, in particular stain normalization, when training machine learning models on duodenal biopsy WSIs to ensure generalizability between different scanners and laboratories.

Risk factors for TB in Australia and their association with delayed treatment completion.

BACKGROUND: Australia has a low incidence of TB and has committed to eliminating the disease. Identification of risk factors associated with TB is critical to achieving this goal.METHODS: We undertook a prospective cohort study involving persons receiving TB treatment in four Australian jurisdictions. Risk factors and their association with delayed treatment completion (treatment delayed by at least 1 month) were analysed using univariate analyses and multivariate logistic regression.RESULTS: Baseline surveys were completed for 402 persons with TB. Most (86.1%) were born overseas. Exposure to a person with TB was reported by 19.4%. Diabetes mellitus (10.2%), homelessness (9.2%), cigarette smoking (8.7%), excess alcohol consumption (6.0%) and mental illness (6.2%) were other common risk factors. At follow-up, 24.8% of patients had delayed treatment completion, which was associated with adverse events (34.1%, aOR 6.67, 95% CI 3.36-13.27), excess alcohol consumption (6.0%, aOR 21.94, 95% CI 6.03-79.85) and HIV co-infection (2.7%, aOR 8.10, 95% CI 1.16-56.60).CONCLUSIONS: We identified risk factors for TB and their association with delayed treatment completion, not all of which are routinely collected for surveillance purposes. Recognition of these risk factors should facilitate patient-centred care and assist Australia in reaching TB elimination.

Clinical standards for the diagnosis, treatment and prevention of TB infection.

BACKGROUND: Tuberculosis (TB) preventive therapy (TPT) decreases the risk of developing TB disease and its associated morbidity and mortality. The aim of these clinical standards is to guide the assessment, management of TB infection (TBI) and implementation of TPT.METHODS: A panel of global experts in the field of TB care was identified; 41 participated in a Delphi process. A 5-point Likert scale was used to score the initial standards. After rounds of revision, the document was approved with 100% agreement.RESULTS: Eight clinical standards were defined: Standard 1, all individuals belonging to at-risk groups for TB should undergo testing for TBI; Standard 2, all individual candidates for TPT (including caregivers of children) should undergo a counselling/health education session; Standard 3, testing for TBI: timing and test of choice should be optimised; Standard 4, TB disease should be excluded prior to initiation of TPT; Standard 5, all candidates for TPT should undergo a set of baseline examinations; Standard 6, all individuals initiating TPT should receive one of the recommended regimens; Standard 7, all individuals who have started TPT should be monitored; Standard 8, a TBI screening and testing register should be kept to inform the cascade of care.CONCLUSION: This is the first consensus-based set of Clinical Standards for TBI. This document guides clinicians, programme managers and public health officers in planning and implementing adequate measures to assess and manage TBI.

Active case-finding in contacts of people with TB.

BACKGROUND: Exposure to people with TB substantially elevates a person's risk of tuberculous infection and TB disease. Systematic screening of TB contacts enables the early detection and treatment of co-prevalent disease, and the opportunity to prevent future TB disease. However, scale-up of contact investigation in high TB transmission settings remains limited.METHODS: We undertook a narrative review to evaluate the evidence for contact investigation and identify strategies that TB programmes may consider when introducing contact investigation and management.RESULTS: Selection of contacts for priority screening depends upon their proximity and duration of exposure, along with their susceptibility to develop TB. Screening algorithms can be tailored to the target population, the availability of diagnostic tests and preventive therapy, and healthcare worker expertise. Contact investigation may be performed in the household or at communal locations. Local contact investigation policies should support vulnerable patients, and ensure that drop-out during screening can be mitigated. Ethical issues should be anticipated and addressed in each setting.CONCLUSION: Contact investigation is an important strategy for TB elimination. While its epidemiological impact will be greatest in lower-transmission settings, the early detection and prevention of TB have important benefits for contacts and their communities.

Preventive therapy for latent tuberculosis infection-the promise and the challenges.

Around one third of the world's population may harbour latent tuberculosis infection (LTBI), an asymptomatic immunological state that confers a heightened risk of subsequently developing tuberculosis (TB). Effectively treating LTBI will be essential if the End TB Strategy is to be realized. This review evaluates the evidence in relation to the effectiveness of preventive antibiotic therapy to treat LTBI due to both drug-susceptible and drug-resistant bacteria. Current national and international preventive therapy guidelines are summarized, as well as ongoing randomized trials evaluating regimens to prevent drug-resistant TB. Populations that may benefit most from screening and treatment for LTBI include close contacts of patients with TB (particularly children under 5 years of age) and individuals with substantial immunological impairment. The risks and benefits of treatment must be carefully balanced for each individual. Electronic decision support tools offer one way in which clinicians can help patients to make informed decisions. Modelling studies indicate that the expanded use of preventive therapy will be essential to achieving substantial reductions in the global TB burden. However, the widespread scale-up of screening and treatment will require careful consideration of cost-effectiveness, while ensuring the drivers of ongoing disease transmission are also addressed.