Dynamically Synthetic Images for Federated Learning of medical images.

BACKGROUND: To develop deep learning models for medical diagnosis, it is important to collect more medical data from several medical institutions. Due to the regulations for privacy concerns, it is infeasible to collect data from various medical institutions to one institution for centralized learning. Federated Learning (FL) provides a feasible approach to jointly train the deep learning model with data stored in various medical institutions instead of collected together. However, the resulting FL models could be biased towards institutions with larger training datasets. METHODOLOGY: In this study, we propose the applicable method of Dynamically Synthetic Images for Federated Learning (DSIFL) that aims to integrate the information of local institutions with heterogeneous types of data. The main technique of DSIFL is to develop a synthetic method that can dynamically adjust the number of synthetic images similar to local data that are misclassified by the current model. The resulting global model can handle the diversity in heterogeneous types of data collected in local medical institutions by including the training of synthetic images similar to misclassified cases in local collections. RESULTS: In model performance evaluation metrics, we focus on the accuracy of each client's dataset. Finally, the accuracy of the model of DSIFL in the experiments can achieve the higher accuracy of the FL approach. CONCLUSION: In this study, we propose the framework of DSIFL that achieves improvements over the conventional FL approach. We conduct empirical studies with two kinds of medical images. We compare the performance by variants of FL vs. DSIFL approaches. The performance by individual training is used as the baseline, whereas the performance by centralized learning is used as the target for the comparison studies. The empirical findings suggest that the DSIFL has improved performance over the FL via the technique of dynamically synthetic images in training.

Learning and recognition of on-premise signs from weakly labeled street view images.

Camera-enabled mobile devices are commonly used as interaction platforms for linking the user's virtual and physical worlds in numerous research and commercial applications, such as serving an augmented reality interface for mobile information retrieval. The various application scenarios give rise to a key technique of daily life visual object recognition. On-premise signs (OPSs), a popular form of commercial advertising, are widely used in our living life. The OPSs often exhibit great visual diversity (e.g., appearing in arbitrary size), accompanied with complex environmental conditions (e.g., foreground and background clutter). Observing that such real-world characteristics are lacking in most of the existing image data sets, in this paper, we first proposed an OPS data set, namely OPS-62, in which totally 4649 OPS images of 62 different businesses are collected from Google's Street View. Further, for addressing the problem of real-world OPS learning and recognition, we developed a probabilistic framework based on the distributional clustering, in which we proposed to exploit the distributional information of each visual feature (the distribution of its associated OPS labels) as a reliable selection criterion for building discriminative OPS models. Experiments on the OPS-62 data set demonstrated the outperformance of our approach over the state-of-the-art probabilistic latent semantic analysis models for more accurate recognitions and less false alarms, with a significant 151.28% relative improvement in the average recognition rate. Meanwhile, our approach is simple, linear, and can be executed in a parallel fashion, making it practical and scalable for large-scale multimedia applications.

Necrotizing fasciitis caused by Shewanella putrefaciens in a uremic patient.

Shewanella putrefaciens rarely causes infections in humans. This report describes a case of necrotizing fasciitis caused by S. putrefaciens in a uremic patient who recovered in spite of inadequate antibiotic treatment. S. putrefaciens is a possible causative organism of necrotizing fasciitis, and the absence of any sign of systemic infection cannot rule out the possibility of invasive infection in uremic patients. Surgical intervention is important in such cases.

Clinical manifestations of strongyloidiasis in southern Taiwan.

The diagnosis and management of strongyloidiasis present a continuous challenge in developing countries including Taiwan. In this study, the clinical characteristics and microbiological findings of 27 patients with Strongyloides stercoralis infection were retrospectively analyzed. Intestinal infection was identified in 17 patients and hyperinfection syndrome or disseminated disease in 10 (including 2 autopsy cases). The most frequent clinical findings were diarrhea (74%), fever (70%), abdominal pain (59%), cough (37%), dyspnea (33%), and constipation (26%). The common initial laboratory abnormalities were leukocytosis (81%), anemia (67%), liver function impairment (52%), and eosinophilia (44%). Most of the 27 patients had comorbid conditions, including malnutrition in 20 (74%), corticosteroid dependence in 15 (55%), chronic obstructive pulmonary disease in 9 (33%), chronic liver disease or cirrhosis in 8 (30%), and peptic ulcer disease in 7 (26%). There was no difference in the time interval from symptom onset to diagnosis between the intestinal infection group and the hyperinfection/disseminated group (22 +/- 15 vs 17 +/- 9 days). Larvae of S. stercoralis were identified in the stool of 24 patients, in the sputum smear of 5, in the gastric biopsy of one, and on histology of autopsy specimens in 2. Twenty-six patients received antiparasitic drug therapy of variable duration (mebendazole in 24, albendazole in 2, combined therapy in one). The overall cure rate was 52% (14/27). Relapse occurred in 4 patients. The overall mortality was 26% (7/27). There was a high mortality (up to 50%) in the hyperinfection/disseminated disease group. In conclusion, diagnosis of strongyloidiasis is often delayed and overlooked because of nonspecific symptoms. Physicians in endemic regions should include strongyloidiasis in the differential diagnosis when patients present with gastrointestinal and/or pulmonary symptoms with peripheral eosinophilia.