FundusQ-Net: A regression quality assessment deep learning algorithm for fundus images quality grading.

OBJECTIVE: Ophthalmological pathologies such as glaucoma, diabetic retinopathy and age-related macular degeneration are major causes of blindness and vision impairment. There is a need for novel decision support tools that can simplify and speed up the diagnosis of these pathologies. A key step in this process is to automatically estimate the quality of the fundus images to make sure these are interpretable by a human operator or a machine learning model. We present a novel fundus image quality scale and deep learning (DL) model that can estimate fundus image quality relative to this new scale. METHODS: A total of 1245 images were graded for quality by two ophthalmologists within the range 1-10, with a resolution of 0.5. A DL regression model was trained for fundus image quality assessment. The architecture used was Inception-V3. The model was developed using a total of 89,947 images from 6 databases, of which 1245 were labeled by the specialists and the remaining 88,702 images were used for pre-training and semi-supervised learning. The final DL model was evaluated on an internal test set (n=209) as well as an external test set (n=194). RESULTS: The final DL model, denoted FundusQ-Net, achieved a mean absolute error of 0.61 (0.54-0.68) on the internal test set. When evaluated as a binary classification model on the public DRIMDB database as an external test set the model obtained an accuracy of 99%. SIGNIFICANCE: the proposed algorithm provides a new robust tool for automated quality grading of fundus images.

A Whole-Cell Bacterial Biosensor for Blood Markers Detection in Urine.

The early detection of blood in urine (hematuria) can play a crucial role in the treatment of serious diseases (e.g., infections, kidney disease, schistosomiasis, and cancer). Therefore, the development of low-cost portable biosensors for blood detection in urine has become necessary. Here, we designed an ultrasensitive whole-cell bacterial biosensor interfaced with an optoelectronic measurement module for heme detection in urine. Heme is a red blood cells (RBCs) component that is liberated from lysed cells. The bacterial biosensor includes Escherichia coli cells carrying a heme-sensitive synthetic promoter integrated with a luciferase reporter (luxCDABE) from Photorhabdus luminescens. To improve the bacterial biosensor performance, we re-engineered the genetic structure of luxCDABE operon by splitting it into two parts (luxCDE and luxAB). The luxCDE genes were regulated by the heme-sensitive promoter, and the luxAB genes were regulated by either constitutive or inducible promoters. We examined the genetic circuit's performance in synthetic urine diluent supplied with heme and in human urine supplied with lysed blood. Finally, we interfaced the bacterial biosensor with a light detection setup based on a commercial optical measurement single-photon avalanche photodiode (SPAD). The whole-cell biosensor was tested in human urine with lysed blood, demonstrating a low-cost, portable, and easy-to-use hematuria detection with an ON-to-OFF ratio of 6.5-fold for blood levels from 5 × 104 to 5 × 105 RBC per mL of human urine.

Tissue post-classification using the measured acoustic signals during 355 nm laser atherectomy procedures.

The current laser atherectomy technologies to treat patients with challenging (to-cross) total chronic occlusions with a step-by-step (SBS) approach (without leading guide wire), are lacking real-time signal monitoring of the ablated tissues, and carry the risk for vessel perforation. We present first time post-classification of ablated tissues using acoustic signals recorded by a microphone placed nearby during five atherectomy procedures using 355 nm solid-state Auryon laser device performed with an SBS approach, some with highly severe calcification. Using our machine-learning algorithm, the classification results of these ablation signals recordings from five patients showed 93.7% classification accuracy with arterial vs nonarterial wall material. While still very preliminary and requiring a larger study and thereafter as commercial device, the results of these first acoustic post-classification in SBS cases are very promising. This study implies, as a general statement, that online recording of the acoustic signals using a noncontact microphone, may potentially serve for an online classification of the ablated tissue in SBS cases. This technology could be used to confirm correct positioning in the vasculature, and by this, to potentially further reduce the risk of perforation using 355 nm laser atherectomy in such procedures.