Diagnostic Accuracy of Intraoperative Brain Smear: A Meta-Analysis of Studies from Resource-Limited Settings.

BACKGROUND: Intraoperative brain smear is an easy, rapid, and cost-effective technique for immediate diagnosis of brain tumors. Earlier studies have gauged its application on limited number of samples, but its diagnostic accuracy especially in low-resource settings, where its practice would be extremely helpful, is still undetermined. To investigate the diagnostic accuracy of intraoperative brain smear in resource-limited settings for diagnosis of brain tumors. METHODS: A systematic search was conducted on PubMed, Google Scholar, Scopus, Cumulative Index to Nursing and Allied Health Literature (CINAHL), and Embase for all articles utilizing intraoperative brain smears that were extracted. Studies from low- and middle-income countries (LMICs) with test performance characteristics were selected and subsequent values were summarized using a hierarchical summary receiver operating characteristic (ROC) curve via STATA and pooled using a random-effects model on MetaDiSc 2.0. RESULTS: Twelve studies consisting of 1124 patients were identified. Six studies included both adult and pediatric population groups, while 4 investigated adults and 2 included pediatric patients. The pooled diagnostic odds ratio (OR) was calculated to be 212.52 (CI: [104.27-433.13]) of Bivariable pooled specificity and sensitivity were 92% (CI: [86%-96%]) and 96% (CI: [93%-98%]), respectively. CONCLUSIONS: Our study shows that intraoperative brain smear is not only an accurate and sensitive diagnostic modality in resource-rich settings, but it is also equally useful in resource-limited settings, making it an ideal method for rapid diagnosis.

An automatic nuclei segmentation method based on deep convolutional neural networks for histopathology images.

BACKGROUND: Since nuclei segmentation in histopathology images can provide key information for identifying the presence or stage of a disease, the images need to be assessed carefully. However, color variation in histopathology images, and various structures of nuclei are two major obstacles in accurately segmenting and analyzing histopathology images. Several machine learning methods heavily rely on hand-crafted features which have limitations due to manual thresholding. RESULTS: To obtain robust results, deep learning based methods have been proposed. Deep convolutional neural networks (DCNN) used for automatically extracting features from raw image data have been proven to achieve great performance. Inspired by such achievements, we propose a nuclei segmentation method based on DCNNs. To normalize the color of histopathology images, we use a deep convolutional Gaussian mixture color normalization model which is able to cluster pixels while considering the structures of nuclei. To segment nuclei, we use Mask R-CNN which achieves state-of-the-art object segmentation performance in the field of computer vision. In addition, we perform multiple inference as a post-processing step to boost segmentation performance. We evaluate our segmentation method on two different datasets. The first dataset consists of histopathology images of various organ while the other consists histopathology images of the same organ. Performance of our segmentation method is measured in various experimental setups at the object-level and the pixel-level. In addition, we compare the performance of our method with that of existing state-of-the-art methods. The experimental results show that our nuclei segmentation method outperforms the existing methods. CONCLUSIONS: We propose a nuclei segmentation method based on DCNNs for histopathology images. The proposed method which uses Mask R-CNN with color normalization and multiple inference post-processing provides robust nuclei segmentation results. Our method also can facilitate downstream nuclei morphological analyses as it provides high-quality features extracted from histopathology images.

Efficient quantitative assessment of facial paralysis using iris segmentation and active contour-based key points detection with hybrid classifier.

BACKGROUND: Facial palsy or paralysis (FP) is a symptom that loses voluntary muscles movement in one side of the human face, which could be very devastating in the part of the patients. Traditional methods are solely dependent to clinician's judgment and therefore time consuming and subjective in nature. Hence, a quantitative assessment system becomes apparently invaluable for physicians to begin the rehabilitation process; and to produce a reliable and robust method is challenging and still underway. METHODS: We introduce a novel approach for a quantitative assessment of facial paralysis that tackles classification problem for FP type and degree of severity. Specifically, a novel method of quantitative assessment is presented: an algorithm that extracts the human iris and detects facial landmarks; and a hybrid approach combining the rule-based and machine learning algorithm to analyze and prognosticate facial paralysis using the captured images. A method combining the optimized Daugman's algorithm and Localized Active Contour (LAC) model is proposed to efficiently extract the iris and facial landmark or key points. To improve the performance of LAC, appropriate parameters of initial evolving curve for facial features' segmentation are automatically selected. The symmetry score is measured by the ratio between features extracted from the two sides of the face. Hybrid classifiers (i.e. rule-based with regularized logistic regression) were employed for discriminating healthy and unhealthy subjects, FP type classification, and for facial paralysis grading based on House-Brackmann (H-B) scale. RESULTS: Quantitative analysis was performed to evaluate the performance of the proposed approach. Experiments show that the proposed method demonstrates its efficiency. CONCLUSIONS: Facial movement feature extraction on facial images based on iris segmentation and LAC-based key point detection along with a hybrid classifier provides a more efficient way of addressing classification problem on facial palsy type and degree of severity. Combining iris segmentation and key point-based method has several merits that are essential for our real application. Aside from the facial key points, iris segmentation provides significant contribution as it describes the changes of the iris exposure while performing some facial expressions. It reveals the significant difference between the healthy side and the severe palsy side when raising eyebrows with both eyes directed upward, and can model the typical changes in the iris region.

Role of GIS in social sector planning: can developing countries benefit from the examples of primary health care (PHC) planning in Britain?

Social sector planning requires rational approaches where community needs are identified by referring to relative deprivation among localities and resources are allocated to address inequalities. Geographical information system (GIS) has been widely argued and used as a base for rational planning for equal resource allocation in social sectors around the globe. Devolution of primary health care is global strategy that needs pains taking efforts to implement it. GIS is one of the most important tools used around the world in decentralization process of primary health care. This paper examines the scope of GIS in social sector planning by concentration on primary health care delivery system in Pakistan. The work is based on example of the UK's decentralization process and further evidence from US. This paper argues that to achieve benefits of well informed decision making to meet the communities' needs GIS is an essential tool to support social sector planning and can be used without any difficulty in any environment. There is increasing trend in the use of Health Management Information System (HMIS) in Pakistan with ample internet connectivity which provides well established infrastructure in Pakistan to implement GIS for health care, however there is need for change in attitude towards empowering localities especially with reference to decentralization of decision making. This paper provides GIS as a tool for primary health care planning in Pakistan as a starting point in defining localities and preparing locality profiles for need identification that could help developing countries in implementing the change.