Validation of a deep learning computer aided system for CT based lung nodule detection, classification, and growth rate estimation in a routine clinical population.

OBJECTIVE: In this study, we evaluated a commercially available computer assisted diagnosis system (CAD). The deep learning algorithm of the CAD was trained with a lung cancer screening cohort and developed for detection, classification, quantification, and growth of actionable pulmonary nodules on chest CT scans. Here, we evaluated the CAD in a retrospective cohort of a routine clinical population. MATERIALS AND METHODS: In total, a number of 337 scans of 314 different subjects with reported nodules of 3-30 mm in size were included into the evaluation. Two independent thoracic radiologists alternately reviewed scans with or without CAD assistance to detect, classify, segment, and register pulmonary nodules. A third, more experienced, radiologist served as an adjudicator. In addition, the cohort was analyzed by the CAD alone. The study cohort was divided into five different groups: 1) 178 CT studies without reported pulmonary nodules, 2) 95 studies with 1-10 pulmonary nodules, 23 studies from the same patients with 3) baseline and 4) follow-up studies, and 5) 18 CT studies with subsolid nodules. A reference standard for nodules was based on majority consensus with the third thoracic radiologist as required. Sensitivity, false positive (FP) rate and Dice inter-reader coefficient were calculated. RESULTS: After analysis of 470 pulmonary nodules, the sensitivity readings for radiologists without CAD and radiologist with CAD, were 71.9% (95% CI: 66.0%, 77.0%) and 80.3% (95% CI: 75.2%, 85.0%) (p < 0.01), with average FP rate of 0.11 and 0.16 per CT scan, respectively. Accuracy and kappa of CAD for classifying solid vs sub-solid nodules was 94.2% and 0.77, respectively. Average inter-reader Dice coefficient for nodule segmentation was 0.83 (95% CI: 0.39, 0.96) and 0.86 (95% CI: 0.51, 0.95) for CAD versus readers. Mean growth percentage discrepancy of readers and CAD alone was 1.30 (95% CI: 1.02, 2.21) and 1.35 (95% CI: 1.01, 4.99), respectively. CONCLUSION: The applied CAD significantly increased radiologist's detection of actionable nodules yet also minimally increasing the false positive rate. The CAD can automatically classify and quantify nodules and calculate nodule growth rate in a cohort of a routine clinical population. Results suggest this Deep Learning software has the potential to assist chest radiologists in the tasks of pulmonary nodule detection and management within their routine clinical practice.

Preventing constipation in critically ill patients.

In 2003 an audit was carried out on an ICU which demonstrated that the incidence of constipation was high and that this could contribute to the failure to wean patients from mechanical ventilation (Mostafa et al, 2003). A protocol was introduced to standardise the assessment and management of constipation. This article explores why patients in intensive care are at risk of constipation and presents the results of a second audit, carried out after the protocol was introduced, to assess its impact on patients.

Strategies to promote sexual health.

This article examines trends in sexually transmitted infections in the UK. Screening, treatment and education of adults and adolescents are discussed. Suggestions are made for improvements to sexual health, as outlined in The National Strategy for Sexual Health and HIV (Department of Health 2001).

Incidental meandering right pulmonary vein, literature review and proposed nomenclature revision.

We report a case of an anomalous pulmonary vein on chest X-ray resembling a scimitar sign in an 80-year-old female undergoing investigation of syncope. Multislice computed tomography (CT) with multiplanar reformatting and maximum intensity projections demonstrated an aberrant right inferior pulmonary vein coursing inferomedially towards the diaphragm before turning superiorly and draining normally into the left atrium. The diagnosis of an incidental meandering right pulmonary vein was established. The case is used to review the literature on this rare pulmonary anomaly, including pathogenesis, its relationship with scimitar syndrome and scimitar variant, and diagnosis, with an emphasis on the role modern CT techniques can play in non-invasive diagnosis. A revision to the nomenclature of pulmonary vascular anomalies is proposed to help reduce confusion in the literature.

Comparison of differential renal function using technetium-99m mercaptoacetyltriglycine (MAG3) and technetium-99m dimercaptosuccinic acid (DMSA) renography in a paediatric population.

BACKGROUND: In children who have undergone both 99mTc-DMSA and 99mTc-MAG3 studies for the assessment of differential renal function (DRF) and drainage, respectively, we have noticed good agreement between the calculated DRF values, and hypothesized that there is no significant difference in DRF values calculated from these tests. Therefore, both tests may not always be necessary. OBJECTIVE: To determine whether there is a statistically significant difference between DRF values calculated using 99mTc-DMSA and those calculated using 99mTc-MAG3. MATERIALS AND METHODS: We retrospectively identified children imaged with 99mTc-DMSA and 99mTc-MAG3. We recorded DRF values, age, indication, and renal pelvis diameter. For the 99mTc-DMSA studies we recorded the imaging time after injection. For the 99mTc-MAG3 studies we recorded the delay between injection and data acquisition, diuretic use and evidence of delayed drainage or reflux. RESULTS: We identified 100 episodes in 92 children where both 99mTc-DMSA and 99mTc-MAG3 scans had been performed within a few days. The commonest indication was urinary tract infection or pelviureteric junction obstruction. The mean age of the children was 6.96 years. A significant but clinically acceptable trend was seen between abnormal DRF and difference between tests. A significant link was found with the difference between tests and the time of imaging after DMSA injection, and also with scarring. No significant effect was caused by renal pelvis dilatation, delayed drainage, frusemide administration, or delayed 99mTc-MAG3 imaging. CONCLUSION: If a 99mTc-MAG3 study has been performed then a 99mTc-DMSA study is unnecessary provided DRF is normal on the 99mTc-MAG3 study and there is no scarring. A change in practice would lead to considerable savings in time, cost and radiation burden.

Prospective evaluation of unsuspected pulmonary embolism on contrast enhanced multidetector CT (MDCT) scanning.

AIM: To quantify the incidence of unsuspected pulmonary emboli (PE) in an unselected inpatient population undergoing contrast enhanced multidetector CT (MDCT) scanning of the thorax and to assess aetiological factors in their development. METHODS: All inpatients undergoing MDCT scanning of the thorax over a 10 month period were prospectively identified. Patients with previous or suspected current PE were excluded. CT scans were reviewed and the degree of contrast enhancement and presence of PE recorded. Where PE was found, the level of the most proximal thrombus was identified. Patient age, length of admission, slice scan thickness and clinical indication were noted. RESULTS: 547 inpatients who had undergone MDCT scanning were identified. Following exclusions 487 remained, 28 of whom (5.7%) had PE. Unsuspected PE was more common with increasing age, occurring in 9.2% (20/218) of all patients over 70 years and 16.7% (11/66) of those over 80 years (p<0.001). Eighteen of the 28 positive scans (64.3%) were at the segmental or subsegmental level. No other aetiological factor was identified which significantly increased the incidence of unsuspected PE. No significant difference was noted between 4-slice and 16-slice MDCT. Nine of the cases of incidental PE (32.1%) were not identified by the original reporting radiologists. CONCLUSION: PE is an unsuspected finding on contrast enhanced MDCT scanning of the thorax in 5.7% of all inpatients. The incidence is higher in older patients. Most are peripheral and >30% are missed on initial review. PE should be routinely sought in all contrast enhanced MDCT scans of the chest, irrespective of the indication for the CT scan.