Surgical tool detection is attracting increasing attention from the medical image analysis community. The goal generally is not to precisely locate tools in images, but rather to indicate which tools are being used by the surgeon at each instant. The main motivation for annotating tool usage is to design efficient solutions for surgical workflow analysis, with potential applications in report generation, surgical training and even real-time decision support. Most existing tool annotation algorithms focus on laparoscopic surgeries. However, with 19 million interventions per year, the most common surgical procedure in the world is cataract surgery. The CATARACTS challenge was organized in 2017 to evaluate tool annotation algorithms in the specific context of cataract surgery. It relies on more than nine hours of videos, from 50 cataract surgeries, in which the presence of 21 surgical tools was manually annotated by two experts. With 14 participating teams, this challenge can be considered a success. As might be expected, the submitted solutions are based on deep learning. This paper thoroughly evaluates these solutions: in particular, the quality of their annotations are compared to that of human interpretations. Next, lessons learnt from the differential analysis of these solutions are discussed. We expect that they will guide the design of efficient surgery monitoring tools in the near future.

Background: Talaromyces marneffei, also named Penicillium marneffei, is an opportunistic pathogen that can cause systemic or limited infection in human beings. This infection is especially common in human immunodeficiency virus (HIV)-infected hosts; however, it has also been recently reported in HIV-negative hosts. Here, we report a very rarely seen case of T. marneffei pulmonary infection in a non-HIV-infected patient with signal transducer and activator of transcription 3 ( STAT3) mutation. Case presentation: A 34-year-old woman was admitted to our hospital for uncontrollable nonproductive cough and dyspnea with exercise. She had been immunocompromised since infancy. Computerized tomography scan showed multiple ground glass opacities with multiple bullae in both lungs. Next generation sequencing (NGS) of the bronchoalveolar lavage fluid identified T. marneffei nucleotide sequences. Culture of bronchoscopy specimens further verified the results. The patient was HIV negative, and blood gene detection indicated STAT3 mutation. To date, following the application of itraconazole, the patient has recovered satisfactorily. Conclusion: In clinical practice, T. marneffei infection among HIV-negative individuals is relatively rare, and we found that patients who are congenitally immunocompromised due to STAT3 mutation may be potential hosts. Early diagnosis and timely treatment are expected to improve the prognosis of T. marneffei infection. NGS is a powerful technique that may play an important role in this progress. The reviews of this paper are available via the supplemental material section.

No abstract

Media-adventitia (MA) border delineates the outer appearance of arterial wall in intravascular ultrasound (IVUS) image. The detection of MA border is a challenging topic due to many difficulties such as complicated intravascular structures, intrinsic artifacts and image noises. We propose a classification-based MA border detection method with an embedded feature selection technique. The feature selection technique is based on Fractional-order Darwinian particle swarm optimization (FODPSO) algorithm. By employing feature selection, 293-dimension features including multi-scale features, gray-scale features and morphological feature are reducing to 37-dimension. The border detection method with feature selection is tested on a public dataset extracted from in-vivo pullbacks of human coronary arteries, which contains 77 IVUS images. Three indicators, Jaccard (JACC), Hausdorff Distance (HD) and Percentage of Area Difference (PAD), are measured for quantitative evaluation. Detection with 293-dimension features obtains JACC 0.79, HD 1.41 and PAD 0.16, while detection with 37-dimension features obtains JACC 0.83, HD 1.27 and PAD 0.12, indicating that the FODPSO-based feature selection method improves MA border detection by JACC 0.04, HD 0.14 and PAD 0.04. Furthermore, the proposed border detection method acquires better performances compared with two other automatic methods conducted on the same dataset available in literature.