Deep Learning Based Sub-Retinal Fluid Segmentation in Central Serous Chorioretinopathy Optical Coherence Tomography Scans.

Development of an automated sub-retinal fluid segmentation technique from optical coherence tomography (OCT) scans is faced with challenges such as noise and motion artifacts present in OCT images, variation in size, shape and location of fluid pockets within the retina. The ability of a fully convolutional neural network to automatically learn significant low level features to differentiate subtle spatial variations makes it suitable for retinal fluid segmentation task. Hence, a fully convolutional neural network has been proposed in this work for the automatic segmentation of sub-retinal fluid in OCT scans of central serous chorioretinopathy (CSC) pathology. The proposed method has been evaluated on a dataset of 15 OCT volumes and an average Dice rate, Precision and Recall of 0.91, 0.93 and 0.89 respectively has been achieved over the test set.

Depthwise Separable Convolutional Neural Network Model for Intra-Retinal Cyst Segmentation.

Intra-retinal cysts (IRCs) are significant in detecting several ocular and retinal pathologies. Segmentation and quantification of IRCs from optical coherence tomography (OCT) scans is a challenging task due to present of speckle noise and scan intensity variations across the vendors. This work proposes a convolutional neural network (CNN) model with an encoder-decoder pair architecture for IRC segmentation across different cross-vendor OCT scans. Since deep CNN models have high computational complexity due to a large number of parameters, the proposed method of depthwise separable convolutional filters aids model generalizability and prevents model over-fitting. Also, the swish activation function is employed to prevent the vanishing gradient problem. The optima cyst segmentation challenge (OCSC) dataset with four different vendor OCT device scans is used to evaluate the proposed model. Our model achieves a mean Dice score of 0.74 and mean recall/precision rate of 0.72/0.82 across different imaging vendors and it outperforms existing algorithms on the OCSC dataset.

Segmentation of Intra-Retinal Cysts From Optical Coherence Tomography Images Using a Fully Convolutional Neural Network Model.

Optical coherence tomography (OCT) is an imaging modality that is used extensively for ophthalmic diagnosis, near-histological visualization, and quantification of retinal abnormalities such as cysts, exudates, retinal layer disorganization, etc. Intra-retinal cysts (IRCs) occur in several macular disorders such as, diabetic macular edema, retinal vascular disorders, age-related macular degeneration, and inflammatory disorders. Automated segmentation of IRCs poses challenges owing to variations in the acquisition system scan intensities, speckle noise, and imaging artifacts. Several segmentation methods have been proposed in the literature for IRC segmentation on vendor-specific OCT images that lack generalizability across imaging systems. In this paper, we propose a fully convolutional network (FCN) model for vendor-independent IRC segmentation. The proposed method counteracts image noise variabilities and trains FCN models on OCT sub-images from the OPTIMA cyst segmentation challenge dataset (with four different vendor-specific images, namely, Cirrus, Nidek, Spectralis, and Topcon). Further, optimal data augmentation and model hyperparametrization are shown to prevent over-fitting for IRC area segmentation. The proposed method is evaluated on the test dataset with a recall/precision rate of 0.66/0.79 across imaging vendors. The Dice correlation coefficient of the proposed method outperforms that of the published algorithms in the OPTIMA cyst segmentation challenge with a Dice rate of 0.71 across the vendors.

A benchmark study of automated intra-retinal cyst segmentation algorithms using optical coherence tomography B-scans.

(BACKGROUND AND OBJECTIVES): Retinal cysts are formed by accumulation of fluid in the retina caused by leakages from inflammation or vitreous fractures. Analysis of the retinal cystic spaces holds significance in detection and treatment of several ocular diseases like age-related macular degeneration, diabetic macular edema etc. Thus, segmentation of intra-retinal cysts and quantification of cystic spaces are vital for retinal pathology and severity detection. In the recent years, automated segmentation of intra-retinal cysts using optical coherence tomography B-scans has gained significant importance in the field of retinal image analysis. The objective of this paper is to compare different intra-retinal cyst segmentation algorithms for comparative analysis and benchmarking purposes. (METHODS): In this work, we employ a modular approach for standardizing the different segmentation algorithms. Further, we analyze the variations in automated cyst segmentation performances and method scalability across image acquisition systems by using the publicly available cyst segmentation challenge dataset (OPTIMA cyst segmentation challenge). (RESULTS): Several key automated methods are comparatively analyzed using quantitative and qualitative experiments. Our analysis demonstrates the significance of variations in signal-to-noise ratio (SNR), retinal layer morphology and post-processing steps on the automated cyst segmentation processes. (CONCLUSION): This benchmarking study provides insights towards the scalability of automated processes across vendor-specific imaging modalities to provide guidance for retinal pathology diagnostics and treatment processes.

Automated segmentation of intra-retinal cysts from optical coherence tomography scans using marker controlled watershed transform.

Optical Coherence Tomography (OCT) has emerged as a major diagnostic modality for retinal imaging. Although OCT generates gross volumetric data, manual analysis of the images for locating or quantifying retinal cysts is a time consuming process. Recently semi- and fully-automatic methods for locating and segmenting retinal cysts have been proposed in the literature. Our paper proposes a fully automatic method for intra-retinal cyst segmentation using marker controlled watershed transform on B-scan images obtained on OCT scanning. Markers are obtained using k-means clustering and used as sources for topographical based watershed transform for final segmentation. Proposed method was evaluated both quantitatively and qualitatively on Optima Cyst Challenge dataset against ground truth obtained from two graders. Experimental results show that the proposed method outperformed other recently proposed methods. Our algorithm achieved a recall rate of 82% while preserving precision rate of 77%, and gave a higher correlation rate of 96% with ground truth obtained from two graders.

Hoffa's fracture with ipsilateral fibular fracture in a 16-year-old girl: An approach to a rare injury.

Hoffa's fracture is an uncommon fracture of the femoral condyle with coronal orientation of the fracture line. The mechanism of injury in pediatric Hoffa's fracture is road traffic accident, sports injury, and trivial injury. Clinical examination and proper imaging is important for diagnosis of pediatric Hoffa's fracture because of high chances of missing these injuries which can lead to nonunion and malunion at the fracture site. Open reduction and anatomical reduction of intraarticular fragment is the gold standard treatment of these fractures. We present a rare case of Hoffa's fracture in a 16-year-old girl with asso ciated ipsilateral fibular fracture.

Vaccination Related Pain: Comparison of Two Injection Techniques.

OBJECTIVE: To compare the acute pain response during immunization in infants using a slow "standard" injection technique vs. "pragmatic" technique. METHODS: In this randomised controlled trial, source of data were 200 healthy infants of age group 6 wk to one and half years, receiving routine intramuscular vaccination. They were divided randomly using computer generated random numbers into 'Standard group' receiving immunization using standard slow technique with aspiration and 'Pragmatic group' receiving immunization using "pragmatic" technique without aspiration. The entire vaccination procedure was videotaped. Videos were scored for pain using modified behavioral pain scale (MBPS) by 2 clinical psychologists and the mean score was considered for analysis. Pain was scored within 15 s of the immunization, were measured and described the child's maximal pain response to the injection. Cry time was measured by a different person from the start of cry till it ends. Entire data was entered in a preformed proforma. The Z test for two sample population means was used for statistical analysis. RESULTS: Standard technique of vaccination needs longer time to administer (5-10 s) when compared to pragmatic technique (1-2 s). Mean post vaccination MBPS in standard group was 8.4 (SD - 0.75) and in pragmatic group was 7.8 (SD - 1.17) which was statistically significant (p - 0.00). Mean crying duration in pragmatic group was less (32.1 s) than standard group (37.37 s). CONCLUSIONS: The "standard" slow technique was significantly more painful and took longer to administer than the "pragmatic" rapid technique. Cry duration is lesser in pragmaticgroup than standard group, but it is statistically not significant.

Analysis of short-term results of monsieur's tunica albuginea urethroplasty as a definitive procedure for pan-anterior urethral stricture.

CONTEXT: Long anterior urethral strictures are fairly common in developing world and the treatment is equally challenging. AIM: To assess the results and efficacy of Monsieur's Tunica Albuginea Urethroplasty (TAU) for anterior urethral stricture. SETTINGS AND DESIGN: We analyzed the results in 10 consecutive patients with pan-anterior urethral stricture, who underwent Monsieur's urethroplasty. MATERIALS AND METHODS: The procedure involves mobilization of strictured urethra and laying it open with a dorsal slit. Edges of the slit-open urethra are sutured to edges of the urethral groove to the tunica of corporal bodies with catheter in situ. Results were assessed postoperatively 3, 6, 9 and 12 months. Patients were categorized as success and failure by comparative analysis of patient satisfaction along with urethroscopy, retrograde urethrogram, uroflowmetry. All patients were taken for post-operative urethroscopic analysis at 6 months to allow better understanding of both successful and failed cases. RESULTS: Mean follow-up of 15.2 (11-19) months showed an 80% success rate. Mean uroflow rate showed Qmax 24.5 cc/sec with 8 cases showing no residual or recurrent stricture. Two cases failed and required intervention. Urethroscopic visualization of the reconstruction site showed wide, patent and distensible neourethra appearing epithelized over roof formed by tunica albuginea of the corpora cavernosa in successful cases. CONCLUSION: Monsieur's TAU is effective technique in treatment of anterior urethral stricture especially cases with unavailable buccal mucosa, with results fairly acceptable at the end of one year.

A quantitative comparison between free uroflow variables and urodynamic data, and the effect of the size of urodynamic catheters on its interpretation.

OBJECTIVE: To assess the effect of the urodynamic catheter on the urinary flow rate and residual volume in various urodynamic diagnoses, and compare the outcome when using a smaller catheter, as the effect of this catheter on free uroflow variables is mostly studied in patients with bladder outlet obstruction (BOO) and little is known about its effect in other urodynamic diagnoses. PATIENTS AND METHODS: In all, 319 men undergoing a pressure-flow study (PFS) with a 5 F filling and 5 F measuring bladder catheter were subdivided into three groups based on a urodynamic diagnosis, i.e. normal PFS (group 1), BOO (group 2) and detrusor underactivity (DU, group 3). Another group (4) comprised 61 patients who had a PFS with the filling catheter removed before the voiding phase. The effect of the catheters on the maximum urinary flow rate (Qmax) and the postvoid residual volume (PVR) was analysed statistically and compared among the groups. We also compared the free-flow variables with the clinical and urodynamic variables. RESULTS: Groups 1-3 (with two catheters) had a significantly lower Qmax and higher PVR than those voiding with one catheter (group 4). The reduction in Qmax was highest in group 3 (41.9%) and least in group 2 (21%). Group 4 showed no significant change in Qmax in cases with BOO and a normal PFS but a significant decline in those with DU (19.6%). The PVR was positively associated with the bladder capacity and negatively with detrusor contractility, but no association with a urodynamic diagnosis of BOO or any specific symptom. CONCLUSION: Detrusor contractility was the strongest predictor of the obstructive effect caused by the catheter. This study justifies the use of a single 5 F catheter at the time of voiding, although that can also cause a reduction in flow in patients with DU.

Immature gastric teratoma in an infant.

Gastric teratomas are very rare tumors accounting for less than 1 % of all teratomas of infants and children. Little more than 100 cases of gastric teratomas are reported in the literature; out of which, very few of them are of immature variety. Complete excision of the gastric teratoma carries a good prognosis. We hereby report a case of immature gastric teratoma in a 3-month-old baby.

Coinfection with dengue and chikungunya--a case report.

Dengue fever outbreaks are reported from India since last 10 years. Since 2005, chikungunya is also causing massive outbreaks in India and other parts of Asia. Both viruses are transmitted by aedes genus and both viruses can re-emerge in many regions due to climatic changes. The clinical presentation of both arthropod borne diseases are similar. Here a concomitant infection of chikungunya and dengue is reported in an 8-year-old child.