This paper proposes a method for automatic classification of spectral domain OCT data for the identification of patients with retinal diseases such as Diabetic Macular Edema (DME). We address this issue as an anomaly detection problem and propose a method that not only allows the classification of the OCT volume, but also allows the identification of the individual diseased B-scans inside the volume. Our approach is based on modeling the appearance of normal OCT images with a Gaussian Mixture Model (GMM) and detecting abnormal OCT images as outliers. The classification of an OCT volume is based on the number of detected outliers. Experimental results with two different datasets show that the proposed method achieves a sensitivity and a specificity of 80% and 93% on the first dataset, and 100% and 80% on the second one. Moreover, the experiments show that the proposed method achieves better classification performance than other recently published works.
Congenital chylothorax is rare in preterm infants. While most cases respond to conservative treatment, a few require surgery. Treatment with intravenous octreotide has been reported to have varying success in preterm infants. A fetus was diagnosed with bilateral hydrothoraces at 29 weeks of gestation and repeated thoracocentesis was performed antenatally to allow growth of the lungs. She was delivered electively at 32 weeks by caesarean section. Hydrops fetalis was confirmed and chest tubes were inserted bilaterally soon after birth. Intravenous octreotide was commenced on day 4 of life, titrated to a maximum of 10 μg/kg/hr for a total of 28 days. Hydrothorax resolved at day 30 and total parenteral nutrition was given for a total of 37 days. She was successfully extubated on day 40 of life and discharged on day 80. On review at 6 months of age, she was thriving and developing normally.