Automated detection of malarial retinopathy-associated retinal hemorrhages

Retinal imaging technologies in cerebral malaria: a systematic review

BACKGROUND

Cerebral malaria (CM) continues to present a major health challenge, particularly in sub-Saharan Africa. CM is associated with a characteristic malarial retinopathy (MR) with diagnostic and prognostic significance. Advances in retinal imaging have allowed researchers to better characterize the changes seen in MR and to make inferences about the pathophysiology of the disease. The study aimed to explore the role of retinal imaging in diagnosis and prognostication in CM; establish insights into pathophysiology of CM from retinal imaging; establish future research directions.

METHODS

The literature was systematically reviewed using the African Index Medicus, MEDLINE, Scopus and Web of Science databases. A total of 35 full texts were included in the final analysis. The descriptive nature of the included studies and heterogeneity precluded meta-analysis.

RESULTS

Available research clearly shows retinal imaging is useful both as a clinical tool for the assessment of CM and as a scientific instrument to aid the understanding of the condition. Modalities which can be performed at the bedside, such as fundus photography and optical coherence tomography, are best positioned to take advantage of artificial intelligence-assisted image analysis, unlocking the clinical potential of retinal imaging for real-time diagnosis in low-resource environments where extensively trained clinicians may be few in number, and for guiding adjunctive therapies as they develop.

CONCLUSIONS

Further research into retinal imaging technologies in CM is justified. In particular, co-ordinated interdisciplinary work shows promise in unpicking the pathophysiology of a complex disease.

Uncovering the role of transient receptor potential channels in pterygium: a machine learning approach

OBJECTIVES

We aimed at identifying the role of transient receptor potential (TRP) channels in pterygium.

METHODS

Based on microarray data GSE83627 and GSE2513, differentially expressed genes (DEGs) were screened and 20 hub genes were selected. After gene correlation analysis, 5 TRP-related genes were obtained and functional analyses of gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) were performed. Multifactor regulatory network including mRNA, microRNAs (miRNAs) and transcription factors (TFs) was constructed. The 5 gene TRP signature for pterygium was validated by multiple machine learning (ML) programs including support vector classifiers (SVC), random forest (RF), and k-nearest neighbors (KNN). Additionally, we outlined the immune microenvironment and analyzed the candidate drugs. Finally, in vitro experiments were performed using human conjunctival epithelial cells (CjECs) to confirm the bioinformatics results.

RESULTS

Five TRP-related genes (MCOLN1, MCOLN3, TRPM3, TRPM6, and TRPM8) were validated by ML algorithms. Functional analyses revealed the participation of lysosome and TRP-regulated inflammatory pathways. A comprehensive immune infiltration landscape and TFs-miRNAs-mRNAs network was studied, which indicated several therapeutic targets (LEF1 and hsa-miR-455-3p). Through correlation analysis, MCOLN3 was proposed as the most promising immune-related biomarker. In vitro experiments further verified the reliability of our in silico results and demonstrated that the 5 TRP-related genes could influence the proliferation and proinflammatory signaling in conjunctival tissue contributing to the pathogenesis of pterygium.

CONCLUSIONS

Our study suggested that TRP channels played an essential role in the pathogenesis of pterygium. The identified pivotal biomarkers (especially MCOLN3) and pathways provide novel directions for future mechanistic and therapeutic studies for pterygium.

Automated malarial retinopathy detection using transfer learning and multi-camera retinal images

Cerebral malaria (CM) is a fatal syndrome found commonly in children less than 5 years old in Sub-saharan Africa and Asia. The retinal signs associated with CM are known as malarial retinopathy (MR), and they include highly specific retinal lesions such as whitening and hemorrhages. Detecting these lesions allows the detection of CM with high specificity. Up to 23% of CM, patients are over-diagnosed due to the presence of clinical symptoms also related to pneumonia, meningitis, or others. Therefore, patients go untreated for these pathologies, resulting in death or neurological disability. It is essential to have a low-cost and high-specificity diagnostic technique for CM detection, for which We developed a method based on transfer learning (TL). Models pre-trained with TL select the good quality retinal images, which are fed into another TL model to detect CM. This approach shows a 96% specificity with low-cost retinal cameras.

[Ocular changes as a diagnostic tool for malaria]

BACKGROUND

According to the WHO Malaria Report 2019 a total of 229 million people fall ill with malaria each year and two thirds of deaths involve children under 5 years of age.

AIM

To review the fundus changes in the context of malaria and the importance of ophthalmoscopy in the diagnosis.

MATERIAL AND METHODS

Summary of changes in cerebral malaria visible on fundus examination, possible underlying pathomechanisms and the value of ophthalmoscopy in practice.

RESULTS

Retinal findings in malaria include white or gray staining of the retina (retinal whitening), color change of retinal vessels (orange or white staining), hemorrhages often with a white center, such as Roth's spot and papilledema.

DISCUSSION

The retinal changes in malaria are specific and may help to differentiate malaria from other causes of coma and fever. Smartphone-based fundus photography and artificial intelligence could support malaria diagnostics particularly in resource-poor regions.

Deep Learning and its Application for Healthcare Delivery in Low and Middle Income Countries

As anyone who has witnessed firsthand knows, healthcare delivery in low-resource settings is fundamentally different from more affluent settings. Artificial Intelligence, including Machine Learning and more specifically Deep Learning, has made amazing advances over the past decade. Significant resources are now dedicated to problems in the field of medicine, but with the potential to further the digital divide by neglecting underserved areas and their specific context. In the general case, Deep Learning remains a complex technology requiring deep technical expertise. This paper explores advances within the narrower field of deep learning image analysis that reduces barriers to adoption and allows individuals with less specialized software skills to effectively employ these techniques. This enables a next wave of innovation, driven largely by problem domain expertise and the creative application of this technology to unaddressed concerns in LMIC settings. The paper also explores the central role of NGOs in problem identification, data acquisition and curation, and integration of new technologies into healthcare systems.

[Retinal manifestations of neuro-malaria or "malarial retinopathy" in Yaoundé]

AIM

Contribute to the improvement of diagnostic and prognostic approaches to treating children with neuro-malaria in Yaoundé.

PATIENTS AND METHOD

A prospective and analytical study carried out in 2 hospitals of Yaoundé from October 2015 to March 2016. All patients aged 3 months to 15 years hospitalized for neuro-malaria in one of the 2 hospitals benefited from a fundus examination. The variables studied were: age, sex, Glasgow or Blantyre score, fundus examination and parasitaemia. For statistical analysis, we used the software R 3.3.0, Chi², exact of Fisher or Kolmogorov-Smirnov tests with a significance P<5%.

RESULTS

Out of the 178 children hospitalized during the study period, 44 had neuro-malaria (24.71%) and 26 (46 diseased eyes) among them presented retinal lesions at a frequency of 14.60%. The mean age was 5.54±3.49 years with a sex ratio of 1.09. The under 5-years-old were the most affected with 31 (70.45%) cases. The fundus lesions of 26 (59.09%) were retinal hemorrhages in 24 (54.54%), retinal whitening and vessel discoloration in 8 (18.18%) respectively. Papillary edema was associated in 4 (9.09%). Macular involvement was noted in 9 cases. These lesions were correlated with age, depth of coma, duration, and clinical course. The rate of parasitaemia did not affect their occurrence.

CONCLUSION

Retinal lesions are frequent and serious during neuro-malaria in our environment, especially in children under five. They must therefore be an emphasis in the systematic exam to rule it out for a better prognostic evaluation and a fast and adequate multidisciplinary management.

Automated Detection of Malarial Retinopathy in Retinal Fundus Images obtained in Clinical Settings

Cerebral malaria (CM) is a life-threatening clinical syndrome associated with 5-10% of malarial infection cases, most prevalent in Africa. About 23% of cerebral malaria cases are misdiagnosed as false positives, leading to inappropriate treatment and loss of lives. Malarial retinopathy (MR) is a retinal manifestation of CM that presents with a highly specific set of lesions. The detection of MR can reduce the false positive diagnosis of CM and alert physicians to investigate for other possible causes of the clinical symptoms and apply a more appropriate clinical intervention of underlying diseases. In order to facilitate easily accessible and affordable means of MR detection, we have developed an automated software system that detects the retinal lesions specific to MR, whitening and hemorrhages, using retinal color fundus images. The individual lesion detection algorithms were combined into an MR detection model using partial least square classifier. The classifier model was trained and tested on retinal image dataset obtained from 64 patients presenting with clinical signs of CM (44 with MR, 20 without MR). The MR detection model yielded specificity of 92% and sensitivity of 68%, with an AUC of 0.82. The proposed MR detection system demonstrates potential for broad screening of MR and can be integrated with a low-cost and portable retinal camera, to provide a bed-side tool for confirming CM diagnosis.

Automated Detection of Malarial Retinopathy in Digital Fundus Images for Improved Diagnosis in Malawian Children with Clinically Defined Cerebral Malaria

Cerebral malaria (CM), a complication of malaria infection, is the cause of the majority of malaria-associated deaths in African children. The standard clinical case definition for CM misclassifies ~25% of patients, but when malarial retinopathy (MR) is added to the clinical case definition, the specificity improves from 61% to 95%. Ocular fundoscopy requires expensive equipment and technical expertise not often available in malaria endemic settings, so we developed an automated software system to analyze retinal color images for MR lesions: retinal whitening, vessel discoloration, and white-centered hemorrhages. The individual lesion detection algorithms were combined using a partial least square classifier to determine the presence or absence of MR. We used a retrospective retinal image dataset of 86 pediatric patients with clinically defined CM (70 with MR and 16 without) to evaluate the algorithm performance. Our goal was to reduce the false positive rate of CM diagnosis, and so the algorithms were tuned at high specificity. This yielded sensitivity/specificity of 95%/100% for the detection of MR overall, and 65%/94% for retinal whitening, 62%/100% for vessel discoloration, and 73%/96% for hemorrhages. This automated system for detecting MR using retinal color images has the potential to improve the accuracy of CM diagnosis.

Method of Quantifying Size of Retinal Hemorrhages in Eyes with Branch Retinal Vein Occlusion Using 14-Square Grid: Interrater and Intrarater Reliability

Purpose. To describe a method of quantifying the size of the retinal hemorrhages in branch retinal vein occlusion (BRVO) and to determine the interrater and intrarater reliabilities of these measurements. Methods. Thirty-five fundus photographs from 35 consecutive eyes with BRVO were studied. The fundus images were analyzed with Power-Point® software, and a grid of 14 squares was laid over the fundus image. Raters were asked to judge the percentage of each of the 14 squares that was covered by the hemorrhages, and the average of the 14 squares was taken to be the relative size of the retinal hemorrhage. Results. Interrater reliability between three raters was higher when a grid with 14 squares was used (intraclass correlation coefficient (ICC), 0.96) than that when a box with no grid was used (ICC, 0.78). Intrarater reliability, which was calculated by the retinal hemorrhage area measured on two different days, was also higher (ICC, 0.97) than that with no grid (ICC, 0.86). Interrater reliability for five fundus pictures with poor image quality was also good when a grid with 14 squares was used (ICC, 0.88). Conclusions. Although our method is subjective, excellent interrater and intrarater reliabilities indicate that this method can be adapted for clinical use.

Random Forests for Dura Mater Microvasculature Segmentation Using Epifluorescence Images

Automatic segmentation of microvascular structures is a critical step in quantitatively characterizing vessel remodeling and other physiological changes in the dura mater or other tissues. We developed a supervised random forest (RF) classifier for segmenting thin vessel structures using multiscale features based on Hessian, oriented second derivatives, Laplacian of Gaussian and line features. The latter multiscale line detector feature helps in detecting and connecting faint vessel structures that would otherwise be missed. Experimental results on epifluorescence imagery show that the RF approach produces foreground vessel regions that are almost 20 and 25 percent better than Niblack and Otsu threshold-based segmentations respectively.

A novel ultrasound based approach for lesion segmentation and its applications in gynecological laparoscopic surgery

Laparoscopic ultrasound (LUS) has been widely utilized as a surgical aide in general, urological, and gynecological applications. Our study summarizes the clinical applications of laparoscopic ultrasonography in laparoscopic gynecologic surgery. Retrospective analyses were performed on 42 women subjects using laparoscopic surgery during laparoscopic extirpation and excision of gynecological tumors in our hospital from August 2011 to August 2013. Specifically, the Esaote 7.5 × 10 MHz laparoscopic transducer was used to detect small residual lesions, as well as to assess, locate and guide in removing the lesions during laparoscopic operations. The findings of LUS were compared with those of preoperative trans-vaginal ultrasound, postoperative, and pathohistological examinations. In addition, a novel method for lesion segmentation was proposed in order to facilitate the laparoscopic gynecologic surgery. In our experiment, laparoscopic operation was performed using a higher frequency and more close to pelvic organs via laparoscopic access. LUS facilitates the ability of gynaecologists to find small residual lesions under laparoscopic visualization and their accurate diagnosis. LUS also helps to locate residual lesions precisely and provides guidance for the removal of residual tumor and eliminate its recurrence effectively. Our experiment provides a safer and more valuable assistance for clinical applications in laparoscopic gynecological surgery that are superior to trans-abdominal ultrasound and trans-vaginal ultrasound.

Automated detection of leakage in fluorescein angiography images with application to malarial retinopathy

The detection and assessment of leakage in retinal fluorescein angiogram images is important for the management of a wide range of retinal diseases. We have developed a framework that can automatically detect three types of leakage (large focal, punctate focal, and vessel segment leakage) and validated it on images from patients with malarial retinopathy. This framework comprises three steps: vessel segmentation, saliency feature generation and leakage detection. We tested the effectiveness of this framework by applying it to images from 20 patients with large focal leak, 10 patients with punctate focal leak, and 5,846 vessel segments from 10 patients with vessel leakage. The sensitivity in detecting large focal, punctate focal and vessel segment leakage are 95%, 82% and 81%, respectively, when compared to manual annotation by expert human observers. Our framework has the potential to become a powerful new tool for studying malarial retinopathy, and other conditions involving retinal leakage.

Quantitative measurement of retinal hemorrhages in suspected victims of child abuse

PURPOSE

Child abuse is one of the leading causes of death in early childhood. The presence of retinal hemorrhages often supports the diagnosis. The purpose of this study was to determine whether the specific measurement of retinal hemorrhages when present on fundus photography correlates with other clinical findings typically seen in children suspected of having been abused.

METHODS

The medical records of children with retinal hemorrhages who were suspected of being victims of abusive head trauma from June 2003 to June 2013 and who had widefield retinal photography performed were retrospectively reviewed. Data collected included hemorrhage-covered percentage (HCP) of the central retina (posterior pole or 40° circle centered on fovea) measured by ImageJ in relation to death, length of hospital stay, presence of abnormal findings on neuroimaging or skeletal survey, and definite versus possible abuse.

RESULTS

Significant difference in retinal hemorrhage measured on fundus photography was found in patients with axial skeletal fracture (P = 0.016), signs of severe brain trauma on neuroimaging (P = 0.014) and definite versus possible abuse (P = 0.023). No correlation of quantitative measurement of the retinal hemorrhage to length of hospital stay, death, or the presence of skull fracture was found in this cohort.

CONCLUSIONS

The quantitative measurement of total retinal hemorrhage when present on fundus photography centered on posterior pole in children suspected of having been abused correlated with some but not all findings typically seen in abused children.

Retinal hemorrhage in abusive head trauma: finding a common language

PURPOSE

To assess the performance of a refined Web-based tool for documenting retinal hemorrhage characteristics in suspected abusive head trauma.

METHODS

Using a comprehensive tabular secure platform, with access to digital images in color, black and white, and 4-zone system schematic overlay, four pediatric ophthalmologists performed pilot testing with 80 images for tool refinement. In a second phase, retinal hemorrhages were documented by number, zone, and type. Interobserver agreement was calculated using the Fleiss kappa coefficient. Intraobserver agreement was calculated using Cohen's kappa statistic. We used surface area mapping software for further analysis.

RESULTS

Interobserver agreement was good (kappa 0.4-0.6) and very good (kappa 0.6-0.8) for all questions in Zone A (peripapillary). For zones C (midperiphery) and D (peripheral retina), agreement was very good for all questions except number of hemorrhages, for which agreement was good. Zone B (macula) showed good and fair agreement except for superficial hemorrhage, for which agreement was poor. There was very good intraobserver agreement for number (kappa 0.68, 0.65, 0.67) and type of hemorrhages in zones A, B, and C. Surface area mapping results revealed no significant differences between zones A and B. Zones C and D had significantly less hemorrhage than A and B.

CONCLUSIONS

Our tool performed with good or very good interobserver and intraobserver agreement in almost all domains. We attribute zone B underperformance to the significant increased area covered by hemorrhages compared to zones C and D and the lack of contrast with normal anatomical structures in zone A.