Computer-aided reading (CAR) of medical images is becoming increasingly common, but few studies exist for CAR in tuberculosis (TB). We designed a prospective study evaluating CAR for chest radiography (CXR) as a triage tool before Xpert MTB/RIF (Xpert).Consecutively enrolled adults in Dhaka, Bangladesh, with TB symptoms received CXR and Xpert. Each image was scored by CAR and graded by a radiologist. We compared CAR with the radiologist for sensitivity and specificity, area under the receiver operating characteristic curve (AUC), and calculated the potential Xpert tests saved.A total of 18 036 individuals were enrolled. TB prevalence by Xpert was 15%. The radiologist graded 49% of CXRs as abnormal, resulting in 91% sensitivity and 58% specificity. At a similar sensitivity, CAR had a lower specificity (41%), saving fewer (36%) Xpert tests. The AUC for CAR was 0.74 (95% CI 0.73–0.75). CAR performance declined with increasing age. The radiologist grading was superior across all sub-analyses.Using CAR can save Xpert tests, but the radiologist's specificity was superior. Differentiated CAR thresholds may be required for different populations. Access to, and costs of, human readers must be considered when deciding to use CAR software. More studies are needed to evaluate CAR using different screening approaches.

Multi-modal learning, particularly among imaging and linguistic modalities, has made amazing strides in many high-level fundamental visual understanding problems, ranging from language grounding to dense event captioning. However, much of the research has been limited to approaches that either do not take audio corresponding to video into account at all, or those that model the audiovisual correlations in service of sound or sound source localization. In this paper, we present the evidence, that audio signals can carry surprising amount of information when it comes to high-level visual-lingual tasks. Specifically, we focus on the problem of weakly-supervised dense event captioning in videos and show that audio on its own can nearly rival performance of a state-of-the-art visual model and, combined with video, can improve on the state-of-theart performance. Extensive experiments on the ActivityNet Captions dataset show that our proposed multi-modal approach outperforms state-of-the-art unimodal methods, as well as validate specific feature representation and architecture design choices.

BackgroundSputum smear microscopy is fast and inexpensive technique for detecting tuberculosis (TB) in high incidence areas but has low sensitivity. Physical and chemical sputum processing along with centrifugation have been found to show promise in overcoming this limitation. Our objective was to compare the sensitivity of smear microscopy obtained with smears made directly from respiratory specimens to those from concentrated specimens.MethodsBy active screening, 915 TB suspects were identified from Dhaka Central Jail and sputum specimens were aseptically collected. Direct smears were prepared by taking a small portion of the purulent part of the sputum with a sterile loop. The specimens were then processed by a standard N-acetyl-L-cysteine-NaOH digestion-decontamination method to prepare concentrated specimens. Both smears were then air dried, heat fixed, and stained by the Ziehl-Neelsen staining technique. The stained slides were examined under oil immersion and were graded following International Union Against Tuberculosis and Lung Diseases guidelines. All the specimens were inoculated into Lowenstein-Jensen (L-J) media and culture results were considered as gold standard to calculate sensitivity.ResultsOf 915 specimens, 73 (8%) specimens were positive both on direct and concentrated methods, one sample was positive on direct microscopy but was negative on concentrated method. An extra 14 (1.5%) samples were positive on concentrated method which were negative on direct smear. In L-J media 105 specimens were found positive for TB bacilli and of them, 74 (70.5%) and 87 (82.9%) were positive in direct and concentrated smear, respectively. The sensitivity of direct and concentrated smear microscopy was different when using positive culture as the gold standard (71% vs. 83%).ConclusionsThe results showed that concentrated technique increases the sensitivity of microscopy up to 12%. Therefore, the national programs in high TB burden countries may consider incorporating the technique into their guidelines at least in the district and higher level laboratories to improve case finding strategy.

No abstract