The ongoing race of biomedical applications has given momentum to the development of graphene quantum dots (GQDs). GQDs are zero-dimensional fluorescent carbon-nanomaterials, with a pronounced quantum confinement effect, and abundant edge states and functional groups. Despite their potential applications, mass-scale synthesis of single crystalline graphene quantum dots (GQDs) with high quantum yields derived via a direct green synthesis approach from bio-wastes is a major challenge. Hitherto, green extract (i.e. sugarcane molasses) driven single crystalline sulphur-doped GQDs (S-GQDs) with a longer decay time, high quantum yield, and excellent biocompatibility have remained unexplored in the bioimaging arena. At the same time, this agro-industrial waste has value in terms of both products and byproducts i.e. zero waste generation resulting in reduced human footprint on the environment. For the first time, we present a facile, large-scale, one-step, economical, template- and catalyst-free synthesis of sustainable, highly crystalline S-GQDs via a hydrothermal route from second generation (2G) bio-wastes. Mechanistic insight into the formation of S-GQDs from their precursor was obtained using powder X-ray diffraction patterns (PXRD). S-GQDs directly obtained from bio-wastes without surface passivation showed the highest quantum yield (QY) ∼ 47% obtained to date. The wide and symmetric emission spectrum of these S-GQDs is instrumental for sensitive detection as labelling nanoprobes. Moreover, their non-toxic behavior, in vitro and in vivo, has a future in quick point-of-care screening and real-time bioimaging. Thus, the as-synthesized bio-waste derived S-GQDs accomplished the purpose of an advanced environmentally friendly and sustainable material which is non-toxic, viable, safe, and cheap. This unprecedented work advances the synthesis of high-quality S-GQDs from bio-waste, which provides a breakthrough in the bioimaging field.

The 3D image segmentation is the process of partitioning a digital 3D volumes into multiple segments. This paper presents a fully automatic method for high resolution 3D volumetric segmentation of medical image data using modern supervised deep learning approach. We introduce 3D Dense-U-Net neural network architecture implementing densely connected layers. It has been optimized for graphic process unit accelerated high resolution image processing on currently available hardware (Nvidia GTX 1080ti). The method has been evaluated on MRI brain 3D volumetric dataset and CT thoracic scan dataset for spine segmentation. In contrast with many previous methods, our approach is capable of precise segmentation of the input image data in the original resolution, without any pre-processing of the input image. It can process image data in 3D and has achieved accuracy of 99.72% on MRI brain dataset, which outperformed results achieved by human expert. On lumbar and thoracic vertebrae CT dataset it has achieved the accuracy of 99.80%. The architecture proposed in this paper can also be easily applied to any task already using U-Net network as a segmentation algorithm to enhance its results. Complete source code was released online under open-source license.

Visually impaired people face numerous difficulties in their daily life, and technological interventions may assist them to meet these challenges. This paper proposes an artificial intelligence-based fully automatic assistive technology to recognize different objects, and auditory inputs are provided to the user in real time, which gives better understanding to the visually impaired person about their surroundings. A deep-learning model is trained with multiple images of objects that are highly relevant to the visually impaired person. Training images are augmented and manually annotated to bring more robustness to the trained model. In addition to computer vision-based techniques for object recognition, a distance-measuring sensor is integrated to make the device more comprehensive by recognizing obstacles while navigating from one place to another. The auditory information that is conveyed to the user after scene segmentation and obstacle identification is optimized to obtain more information in less time for faster processing of video frames. The average accuracy of this proposed method is 95.19% and 99.69% for object detection and recognition, respectively. The time complexity is low, allowing a user to perceive the surrounding scene in real time.