Autonomous screening for laser photocoagulation in fundus images using deep learning.

BACKGROUND: Diabetic retinopathy (DR) is a leading cause of blindness in adults worldwide. Artificial intelligence (AI) with autonomous deep learning algorithms has been increasingly used in retinal image analysis, particularly for the screening of referrable DR. An established treatment for proliferative DR is panretinal or focal laser photocoagulation. Training autonomous models to discern laser patterns can be important in disease management and follow-up. METHODS: A deep learning model was trained for laser treatment detection using the EyePACs dataset. Data was randomly assigned, by participant, into development (n=18 945) and validation (n=2105) sets. Analysis was conducted at the single image, eye, and patient levels. The model was then used to filter input for three independent AI models for retinal indications; changes in model efficacy were measured using area under the receiver operating characteristic curve (AUC) and mean absolute error (MAE). RESULTS: On the task of laser photocoagulation detection: AUCs of 0.981, 0.95, and 0.979 were achieved at the patient, image, and eye levels, respectively. When analysing independent models, efficacy was shown to improve across the board after filtering. Diabetic macular oedema detection on images with artefacts was AUC 0.932 vs AUC 0.955 on those without. Participant sex detection on images with artefacts was AUC 0.872 vs AUC 0.922 on those without. Participant age detection on images with artefacts was MAE 5.33 vs MAE 3.81 on those without. CONCLUSION: The proposed model for laser treatment detection achieved high performance on all analysis metrics and has been demonstrated to positively affect the efficacy of different AI models, suggesting that laser detection can generally improve AI-powered applications for fundus images.

Connectivity maps based analysis of EEG for the advanced diagnosis of schizophrenia attributes.

This article presents a novel connectivity analysis method that is suitable for multi-node networks such as EEG, MEG or EcOG electrode recordings. Its diagnostic power and ability to interpret brain states in schizophrenia is demonstrated on a set of 50 subjects that constituted of 25 healthy and 25 diagnosed with schizophrenia and treated with medication. The method can also be used for the automatic detection of schizophrenia; it exhibits higher sensitivity than state-of-the-art methods with no false positives. The detection is based on an analysis from a minute long pattern-recognition computer task. Moreover, this connectivity analysis leads naturally to an optimal choice of electrodes and hence to highly statistically significant results that are based on data from only 3-5 electrodes. The method is general and can be used for the diagnosis of other psychiatric conditions, provided an appropriate computer task is devised.

Schizophrenia detection and classification by advanced analysis of EEG recordings using a single electrode approach.

Electroencephalographic (EEG) analysis has emerged as a powerful tool for brain state interpretation and diagnosis, but not for the diagnosis of mental disorders; this may be explained by its low spatial resolution or depth sensitivity. This paper concerns the diagnosis of schizophrenia using EEG, which currently suffers from several cardinal problems: it heavily depends on assumptions, conditions and prior knowledge regarding the patient. Additionally, the diagnostic experiments take hours, and the accuracy of the analysis is low or unreliable. This article presents the "TFFO" (Time-Frequency transformation followed by Feature-Optimization), a novel approach for schizophrenia detection showing great success in classification accuracy with no false positives. The methodology is designed for single electrode recording, and it attempts to make the data acquisition process feasible and quick for most patients.