Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation

Convolutional neural networks (CNNs) have been successfully applied to chest x-ray (CXR) images. Moreover, annotated bounding boxes have been shown to improve the interpretability of a CNN in terms of localizing abnormalities. However, only a few relatively small CXR datasets containing bounding boxes are available, and collecting them is very costly. Opportunely, eye-tracking (ET) data can be collected during the clinical workflow of a radiologist. We use ET data recorded from radiologists while dictating CXR reports to train CNNs. We extract snippets from the ET data by associating them with the dictation of keywords and use them to supervise the localization of specific abnormalities. We show that this method can improve a model's interpretability without impacting its image-level classification.

Lung ultrasound to guide the administration of exogenous pulmonary surfactant in respiratory distress syndrome of newborn infants: A retrospective investigation study

BACKGROUND

Respiratory distress syndrome (RDS) is a common disease that seriously endangers the life and safety of newborns, especially premature infants. Exogenous pulmonary surfactant (PS) is the specific agent for the treatment of neonatal RDS. Lung ultrasound (LUS) has been successfully used in the diagnosis of RDS, but its value in guiding the application of PS is still unclear. This paper explored whether the application of PS under LUS monitoring has some advantages, including (1) decreasing the misdiagnosis rate of RDS and decreasing probability of using PS, and (2) reducing the dose of PS without reducing the therapeutic effect.

METHODS

This study included two parts. Part 1: To decide whether the LUS is good to differentiate RDS from other lung diseases in the premature infants. All patients who were diagnosed with RDS and required PS treatment based on conventional criteria were routinely examined by LUS. Then, according to LUS findings, we decided whether they needed to receive PS treatment. Part 2: To see the dose reduction of surfactant is applicable. In RDS patients diagnosed based on LUS presentation and treated with Curosurf (Chiesi Pharmaceutical, Parma, Italy), the dose of Curosurf was compared with that recommended by the European RDS management guidelines.

RESULTS

(1) Since March 2017, 385 newborn infants admitted to our neonatal intensive care unit met the traditional diagnostic criteria of RDS. Of these, only 269 cases were diagnosed with RDS and needed PS treatment according to LUS manifestations. The other 116 infants who did not meet the criteria for ultrasound diagnosis of RDS did not receive PS supplementation but obtained good outcomes, that is LUS findings decreased a misdiagnosis rate of RDS by 30.1% and subsequently resulted in a 30.1% reduction in PS use. (2) Among the 269 RDS patients diagnosed based on LUS findings, 148 were treated with Curosurf (another 121 RDS infants who received domestic PS treatment were not included in the study group), and the average dose was 105.4 ± 24.3 mg/kg per time, which is significantly lower than the dose of 200 mg/kg per time recommended by the European RDS guidelines. (3) The mortality rate of RDS patients was 0%, and no patients had ventilator-associated pneumonia or bronchopulmonary dysplasia in this study.

CONCLUSION

LUS can decrease the misdiagnosis rate of RDS, thereby decreasing the probability of using PS and decreasing the dose of PS, and can help RDS infants to achieve better outcomes.

Issues with implementing a high-quality lung cancer screening program

After a comprehensive review of the evidence, the United States Preventive Services Task Force recently endorsed screening with low-dose computed tomography as an early detection approach that has the potential to significantly reduce deaths due to lung cancer. Prudent implementation of lung cancer screening as a high-quality preventive health service is a complex challenge. The clinical evaluation and management of high-risk cohorts in the absence of symptoms mandates an approach that differs significantly from that of symptom-detected lung cancer. As with other cancer screenings, it is essential to provide to informed at-risk individuals a safe, high-quality, cost-effective, and accessible service. In this review, the components of a successful screening program are discussed as we begin to disseminate lung cancer screening as a national resource to improve outcomes with this lethal cancer. This information about lung cancer screening will assist clinicians with communications about the potential benefits and harms of this service for high-risk individuals considering participation in the screening process.