Medical image retrieval with query-dependent feature fusion based on one-class SVM

Due to the huge growth of the World Wide Web, medical images are now available in large numbers in online repositories, and there exists the need to retrieval the images through automatically extracting visual information of the medical images, which is commonly known as content-based image retrieval (CBIR). Since each feature extracted from images just characterizes certain aspect of image content, multiple features are necessarily employed to improve the retrieval performance. Meanwhile, experiments demonstrate that a special feature is not equally important for different image queries. Most of existed feature fusion methods for image retrieval only utilize query independent feature fusion or rely on explicit user weighting. In this paper, we present a novel query dependent feature fusion method for medical image retrieval based on one class support vector machine. Having considered that a special feature is not equally important for different image queries, the proposed query dependent feature fusion method can learn different feature fusion models for different image queries only based on multiply image samples provided by the user, and the learned feature fusion models can reflect the different importances of a special feature for different image queries. The experimental results on the IRMA medical image collection demonstrate that the proposed method can improve the retrieval performance effectively and can outperform existed feature fusion methods for image retrieval.

QDFA : query-dependent feature aggregation for medical image retrieval

We propose a novel query-dependent feature aggregation (QDFA) method for medical image retrieval. The QDFA method can learn an optimal feature aggregation function for a multi-example query, which takes into account multiple features and multiple examples with different importance. The experiments demonstrate that the QDFA method outperforms three other feature aggregation methods.

A new query dependent feature fusion approach for medical image retrieval based on one-class SVM

With the development of the internet, medical images are now available in large numbers in online repositories, and there exists the need to retrieval the medical images in the content-based ways through automatically extracting visual information of the medical images. Since a single feature extracted from images just characterizes certain aspect of image content, multiple features are necessarily employed to improve the retrieval performance. Furthermore, a special feature is not equally important for different image queries since a special feature has different importance in reflecting the content of different images. However, most existed feature fusion methods for image retrieval only utilize query independent feature fusion or rely on explicit user weighting. In this paper, based on multiply query samples provided by the user, we present a novel query dependent feature fusion method for medical image retrieval based on one class support vector machine. The proposed query dependent feature fusion method for medical image retrieval can learn different feature fusion models for different image queries, and the learned feature fusion models can reflect the different importance of a special feature for different image queries. The experimental results on the IRMA medical image collection demonstrate that the proposed method can improve the retrieval performance effectively and can outperform existed feature fusion methods for image retrieval.

SMS-based medical diagnostic telemetry data transmission protocol for medical sensors

People with special medical monitoring needs can, these days, be sent home and remotely monitored through the use of data logging medical sensors and a transmission base-station. While this can improve quality of life by allowing the patient to spend most of their time at home, most current technologies rely on hardwired landline technology or expensive mobile data transmissions to transmit data to a medical facility. The aim of this paper is to investigate and develop an approach to increase the freedom of a monitored patient and decrease costs by utilising mobile technologies and SMS messaging to transmit data from patient to medico. To this end, we evaluated the capabilities of SMS and propose a generic communications protocol which can work within the constraints of the SMS format, but provide the necessary redundancy and robustness to be used for the transmission of non-critical medical telemetry from data logging medical sensors.

The role of the medical emergency team in end-of-life care : a multicenter, prospective, observational study

Objective: To investigate the role of medical emergency teams in end-of-life care planning.

Design: One month prospective audit of medical emergency team calls.

Setting: Seven university-affiliated hospitals in Australia, Canada, and Sweden.

Patients: Five hundred eighteen patients who received a medical emergency team call over 1 month.

Interventions: None.

Measurements and Main Results: There were 652 medical emergency team calls in 518 patients, with multiple calls in 99 (19.1%) patients. There were 161 (31.1%) patients with limitations of medical therapy during the study period. The limitation of medical therapy was instituted in 105 (20.3%) and 56 (10.8%) patients before and after the medical emergency team call, respectively. In 78 patients who died with a limitation of medical therapy in place, the last medical emergency team review was on the day of death in 29.5% of patients, and within 2 days in another 28.2%. Compared with patients who did not have a limitation of medical therapy, those with a limitation of medical therapy were older (80 vs. 66 yrs; p < .001), less likely to be male (44.1% vs. 55.7%; p .014), more likely to be medical admissions (70.8% vs. 51.3%; p < .001), and less likely to be admitted from home (74.5% vs. 92.2%, p < .001). In addition, those with a limitation of medical therapy were less likely to be discharged home (22.4% vs. 63.6%; p < .001) and more likely to die in hospital (48.4% vs. 12.3%; p < .001). There was a trend for increased likelihood of calls associated with limitations of medical therapy to occur out of hours (51.0% vs. 43.8%, p .089).

Conclusions: Issues around end-of-life care and limitations of medical therapy arose in approximately one-third of calls, suggesting a mismatch between patient needs for end-of-life care and resources at participating hospitals. These calls frequently occur in elderly medical patients and out of hours. Many such patients do not return home, and half die in hospital. There is a need for improved advanced care planning in our hospitals, and to confirm our findings in other organizations.