Mycobacterium tuberculosis Infection in School Contacts of Tuberculosis Cases: A Systematic Review and Meta-Analysis.

Substantial tuberculosis transmission occurs outside of households, and tuberculosis surveillance in schools has recently been proposed. However, the yield of tuberculosis outcomes from school contacts is not well characterized. We assessed the prevalence of Mycobacterium tuberculosis infection among close school contacts by performing a systematic review. We searched PubMed, Elsevier, China National Knowledge Infrastructure, and Wanfang databases. Studies reporting the number of children who were tested overall and who tested positive were included. Subgroup analyses were performed by study location, index case bacteriological status, type of school, and other relevant factors. In total, 28 studies including 54,707 school contacts screened for M. tuberculosis infection were eligible and included in the analysis. Overall, the prevalence of M. tuberculosis infection determined by the QuantiFERON Gold in-tube test was 33.2% (95% CI, 0.0-73.0%). The prevalences of M. tuberculosis infection based on the tuberculin skin test (TST) using 5 mm, 10 mm, and 15 mm as cutoffs were 27.2% (95% CI, 15.1-39.3%), 24.3% (95% CI, 15.3-33.4%), and 12.7% (95% CI, 6.3-19.0%), respectively. The pooled prevalence of M. tuberculosis infection (using a TST ≥5-mm cutoff) was lower in studies from China (22.8%; 95% CI, 16.8-28.8%) than other regions (36.7%; 95% CI, 18.1-55.2%). The pooled prevalence of M. tuberculosis infection was higher when the index was bacteriologically positive (43.6% [95% CI, 16.5-70.8%] versus 23.8% [95% CI, 16.2-31.4%]). These results suggest that contact investigation and general surveillance in schools from high-burden settings merit consideration as means to improve early case detection in children.

Multi-Grained Radiology Report Generation With Sentence-Level Image-Language Contrastive Learning.

The automatic generation of accurate radiology reports is of great clinical importance and has drawn growing research interest. However, it is still a challenging task due to the imbalance between normal and abnormal descriptions and the multi-sentence and multi-topic nature of radiology reports. These features result in significant challenges to generating accurate descriptions for medical images, especially the important abnormal findings. Previous methods to tackle these problems rely heavily on extra manual annotations, which are expensive to acquire. We propose a multi-grained report generation framework incorporating sentence-level image-sentence contrastive learning, which does not require any extra labeling but effectively learns knowledge from the image-report pairs. We first introduce contrastive learning as an auxiliary task for image feature learning. Different from previous contrastive methods, we exploit the multi-topic nature of imaging reports and perform fine-grained contrastive learning by extracting sentence topics and contents and contrasting between sentence contents and refined image contents guided by sentence topics. This forces the model to learn distinct abnormal image features for each specific topic. During generation, we use two decoders to first generate coarse sentence topics and then the fine-grained text of each sentence. We directly supervise the intermediate topics using sentence topics learned by our contrastive objective. This strengthens the generation constraint and enables independent fine-tuning of the decoders using reinforcement learning, which further boosts model performance. Experiments on two large-scale datasets MIMIC-CXR and IU-Xray demonstrate that our approach outperforms existing state-of-the-art methods, evaluated by both language generation metrics and clinical accuracy.

Automatic intracranial abnormality detection and localization in head CT scans by learning from free-text reports.

Deep learning has yielded promising results for medical image diagnosis but relies heavily on manual image annotations, which are expensive to acquire. We present Cross-DL, a cross-modality learning framework for intracranial abnormality detection and localization in head computed tomography (CT) scans by learning from free-text imaging reports. Cross-DL has a discretizer that automatically extracts discrete labels of abnormality types and locations from reports, which are utilized to train an image analyzer by a dynamic multi-instance learning approach. Benefiting from the low annotation cost and a consequent large-scale training set of 28,472 CT scans, Cross-DL achieves accurate performance, with an average area under the receiver operating characteristic curve (AUROC) of 0.956 (95% confidence interval: 0.952-0.959) in detecting 4 abnormality types in 17 regions while accurately localizing abnormalities at the voxel level. An intracranial hemorrhage classification experiment on the external dataset CQ500 achieves an AUROC of 0.928 (0.905-0.951). The model can also help review prioritization.