Deep neural network-based segmentation of normal and abnormal pancreas on abdominal CT: evaluation of global and local accuracies.

PURPOSE: Delay in diagnosis can contribute to poor outcomes in pancreatic ductal adenocarcinoma (PDAC), and new tools for early detection are required. Recent application of artificial intelligence to cancer imaging has demonstrated great potential in detecting subtle early lesions. The aim of the study was to evaluate global and local accuracies of deep neural network (DNN) segmentation of normal and abnormal pancreas with pancreatic mass. METHODS: Our previously developed and reported residual deep supervision network for segmentation of PDAC was applied to segment pancreas using CT images of potential renal donors (normal pancreas) and patients with suspected PDAC (abnormal pancreas). Accuracy of DNN pancreas segmentation was assessed using DICE simulation coefficient (DSC), average symmetric surface distance (ASSD), and Hausdorff distance 95% percentile (HD95) as compared to manual segmentation. Furthermore, two radiologists semi-quantitatively assessed local accuracies and estimated volume of correctly segmented pancreas. RESULTS: Forty-two normal and 49 abnormal CTs were assessed. Average DSC was 87.4 ± 3.1% and 85.5 ± 3.2%, ASSD 0.97 ± 0.30 and 1.34 ± 0.65, HD95 4.28 ± 2.36 and 6.31 ± 6.31 for normal and abnormal pancreas, respectively. Semi-quantitatively, ≥95% of pancreas volume was correctly segmented in 95.2% and 53.1% of normal and abnormal pancreas by both radiologists, and 97.6% and 75.5% by at least one radiologist. Most common segmentation errors were made on pancreatic and duodenal borders in both groups, and related to pancreatic tumor including duct dilatation, atrophy, tumor infiltration and collateral vessels. CONCLUSION: Pancreas DNN segmentation is accurate in a majority of cases, however, minor manual editing may be necessary; particularly in abnormal pancreas.

Hearing function after betahistine therapy in patients with Ménière's disease / Função auditiva após terapia com beta-histina em pacientes com doença de Ménière

ABSTRACT INTRODUCTION: Preventing or reversing hearing loss is challenging in Ménière's disease. Betahistine, as a histamine agonist, has been tried in controlling vertigo in patients with Ménière's disease, but its effectiveness on hearing problems is not known. OBJECTIVE: To examine the effect of betahistine on hearing function in not-previously-treated patients with Ménière's disease and to define possible contributors in this regard. METHODS: A total of 200 not-previously-treated patients with definite unilateral Ménière's disease received betahistine by mouth (initial dose, 16 mg three times a day; maintenance dose, 24-48 mg daily in divided doses). Changes in indicators of hearing status before and six months after treatment were documented. Hearing loss was considered as the mean hearing level >25 dB HL at five frequencies. RESULTS: The mean duration of disease was 3.37 years. Six months after treatment the mean hearing level decreased by 6.35 dB compared to that at the baseline (p < 0.001). Both patients' age and the duration of disease correlated negatively with the improvement in hearing function. Post treatment hearing loss was independently associated with age, the initial hearing level and the chronicity of disease. The corresponding optimal cut-off points for predicating a persistent hearing loss 6 months after treatment were 47 years, 38 dB HL, and 1.4 years, respectively. CONCLUSION: Oral betahistine was significantly effective in preventing/reversing hearing deterioration in patients with Ménière's disease. Age, the hearing level on admission, and the disease duration were independent predictors of hearing status after treatment.

Resumo Introdução: Prevenir ou reverter a perda auditiva é um desafio na doença de Ménière. A betahistina, um agonista de histamina, tem sido testada no controle de vertigem em pacientes com doença de Ménière, mas sua eficácia em problemas de audição ainda não é conhecida. Objetivo: Analisar o efeito da betahistina na função auditiva em pacientes com doença de Ménière não tratados previamente, e definir possíveis contribuintes a esse respeito. Método: Um total de 200 pacientes sem tratamento prévio, e com diagnóstico definido de doença de Ménière unilateral, recebeu beta-histina por via oral (dose inicial de 16 mg três vezes ao dia; dose de manutenção de 24-48 mg por dia, em doses divididas). Alterações dolimiar auditivo antes e após seis meses de tratamento foram documentadas. Considerou-se como perda auditiva uma média do nível de audição > 25 dB NA em cinco frequências. Resultados: A média de duração da doença foi de 3,37 anos. Seis meses após o tratamento, a média do limiar auditivo diminuiu em 6,35 dB, em comparação com o valor da linha de base (p < 0,001). Tanto a idade dos pacientes quanto a duração da doença apresentaram correlação negativa com a melhora da função auditiva. A perda auditiva após o tratamento foi independentemente associada à idade, ao nível inicial de audição e à cronicidade da doença. Os pontos de corte ótimos correspondentes para prever uma perda auditiva persistente seis meses após o tratamento foram 47 anos, 38 dB HL e 1,4 ano, respectivamente. Conclusão: A betahistina oral foi significantemente eficaz na prevenção/reversão da deterioração auditiva em pacientes com doença de Ménière. Idade, nível de audição na admissão e duração da doença foram fatores preditivos independentes da condição auditiva após o tratamento.