Semi-supervised segmentation of retinoblastoma tumors in fundus images.

Retinoblastoma is a rare form of cancer that predominantly affects young children as the primary intraocular malignancy. Studies conducted in developed and some developing countries have revealed that early detection can successfully cure over 90% of children with retinoblastoma. An unusual white reflection in the pupil is the most common presenting symptom. Depending on the tumor size, shape, and location, medical experts may opt for different approaches and treatments, with the results varying significantly due to the high reliance on prior knowledge and experience. This study aims to present a model based on semi-supervised machine learning that will yield segmentation results comparable to those achieved by medical experts. First, the Gaussian mixture model is utilized to detect abnormalities in approximately 4200 fundus images. Due to the high computational cost of this process, the results of this approach are then used to train a cost-effective model for the same purpose. The proposed model demonstrated promising results in extracting highly detailed boundaries in fundus images. Using the Sørensen-Dice coefficient as the comparison metric for segmentation tasks, an average accuracy of 93% on evaluation data was achieved.

Usefulness of subtraction images for accurate diagnosis of pituitary microadenomas in dynamic contrast-enhanced magnetic resonance imaging.

BACKGROUND: Dynamic contrast-enhanced magnetic resonance imaging (MRI) is the modality of choice for the diagnosis of pituitary microadenomas; however, it may be associated with a relatively high false-negative rate, especially in small lesions. PURPOSE: To evaluate the usefulness of subtraction images for enhancing the visual detection of pituitary microadenomas. MATERIAL AND METHODS: In total, 50 patients with clinically established diagnosis hyperprolactinemia, acromegaly, and Cushing's disease were enrolled. Ten patients referred for brain MRI for reasons other than pituitary abnormality were selected as control group. Routine dynamic MRI of the pituitary gland and obtained subtraction MRI scans were scrutinized separately on different sessions by an experienced radiologist blinded to the study design and patient's data. The investigator's opinion on the presence or absence of a lesion and lesion size were collected. RESULTS: In patients with pituitary microadenoma, dynamic MRI images were reported positive in 42 (84%) patients and negative in 8 (16%). Subtraction images were described as positive in all patients (100%)-including all patients with negative dynamic MRI-and the difference was statistically significant (P=0.016). Undetected lesions on dynamic MRI had a mean size of 2.84 ± 1.79 mm (median= 2.20 mm, interquartile range=1.62-4.62 mm) and a significant inverse correlation was noted between lesion size and negative report of dynamic MRI (P=0.018). Brain MRI scans in the control group were reported negative for pituitary microadenoma in both dynamic contrast-enhanced and subtraction images. CONCLUSION: Subtraction images can successfully identify all lesions detectable with conventional dynamic MRI as well as improving visualization of lesions undetected on dynamic MRI, especially in small lesions.

Differentiating features of OCT angiography in diabetic macular edema.

The purpose of current study was to evaluate different optical coherence tomography angiography (OCTA) metrics in eyes with diabetic retinopathy with and without diabetic macular edema (DME). In this retrospective study, macular OCTA images of eyes with non-proliferative or proliferative diabetic retinopathy were evaluated. Vascular density, vascular complexity and non-perfusion densities were compared between eyes with and without DME. One-hundred-thirty-eight eyes of 92 diabetic patients including 49 eyes with DME were included. In multivariate analysis, the presence of DME was positively associated with geometric perfusion deficit (GPD) in superficial capillary plexus (SCP), capillary non-perfusion (CNP) of SCP, and GPD in deep capillary plexus (DCP) (all P < 0.05). In eyes with DME, central foveal thickness was associated with VD ratio (SCP/DCP) (P = 0.001) and FAZ area (P = 0.001). In conclusion, in eyes with diabetic retinopathy, the presence of DME was associated with more extensive capillary non-perfusion compared to those with no macular edema.