Search

Magnetic anchoring technology provides a new development opportunity for current minimally invasive surgery. The magnetic anchoring abdominal video system based on this technology can effectively improve the operability and minimally invasiveness of single-port laparoscopic surgery. The development history of magnetically anchored abdominal video system was reviewed, and the design features and deficiencies of various types of magnetically anchored video devices were compared and analyzed. The evolution characteristics of the magnetic anchored video system are explained from minimally invasive and intelligent perspectives, and the challenges and opportunities of magnetic anchored video system are summarized and prospected.

Deep networks have been shown to achieve impressive accuracy for some medical image analysis tasks where large datasets and annotations are available. However, tasks involving learning over new sets of classes arriving over extended time is a different and difficult challenge due to the tendency of reduction in performance over old classes while adapting to new ones. Controlling such a 'forgetting' is vital for deployed algorithms to evolve with new arrivals of data incrementally. Usually, incremental learning approaches rely on expert knowledge in the form of manual annotations or active feedback. In this paper, we explore the role that other forms of expert knowledge might play in making deep networks in medical image analysis immune to forgetting over extended time. We introduce a novel framework for mitigation of this forgetting effect in deep networks considering the case of combining ultrasound video with point-of-gaze tracked for expert sonographers during model training. This is used along with a novel weighted distillation strategy to reduce the propagation of effects due to class imbalance.

In medical imaging, manual annotations can be expensive to acquire and sometimes infeasible to access, making conventional deep learning-based models difficult to scale. As a result, it would be beneficial if useful representations could be derived from raw data without the need for manual annotations. In this paper, we propose to address the problem of self-supervised representation learning with multi-modal ultrasound video-speech raw data. For this case, we assume that there is a high correlation between the ultrasound video and the corresponding narrative speech audio of the sonographer. In order to learn meaningful representations, the model needs to identify such correlation and at the same time understand the underlying anatomical features. We designed a framework to model the correspondence between video and audio without any kind of human annotations. Within this framework, we introduce cross-modal contrastive learning and an affinity-aware self-paced learning scheme to enhance correlation modelling. Experimental evaluations on multi-modal fetal ultrasound video and audio show that the proposed approach is able to learn strong representations and transfers well to downstream tasks of standard plane detection and eye-gaze prediction.

Water has been labeled as a devil in fabrication and stability of perovskite solar cells. The inherent cognition impels researchers to prepare perovskite films in water-controlled conditions. Herein, water is used as a green solvent to prepare CsPbBr 3 films through a two-step spin-coating method. Due to the high solubility of CsBr but low solubility of PbBr 2 in water, it provides a possibility to deposit CsBr onto PbBr 2 from water solution without destroying the film. Here, high-quality CsPbBr 3 films are fabricated by spin-coating concentrated CsBr/H 2 O solution onto the PbBr 2 film followed by annealing. As a result, the solar cells basing on a configuration of FTO/TiO 2 /CsPbBr 3 /Carbon exhibit a power conversion efficiency of 6.12%. This work provides a simple and easy way to prepare high-quality CsPbBr 3 films for efficient solar cells. It makes a solid step toward reducing the solvent toxicity in the fabrication process of perovskite solar cells. It also breaks the forbidden zone for fabricating perovskite films from water and updates the inherent understanding of water in the research study of perovskite solar cells.

Image representations are commonly learned from class labels, which are a simplistic approximation of human image understanding. In this paper we demonstrate that transferable representations of images can be learned without manual annotations by modeling human visual attention. The basis of our analyses is a unique gaze tracking dataset of sonographers performing routine clinical fetal anomaly screenings. Models of sonographer visual attention are learned by training a convolutional neural network (CNN) to predict gaze on ultrasound video frames through visual saliency prediction or gaze-point regression. We evaluate the transferability of the learned representations to the task of ultrasound standard plane detection in two contexts. Firstly, we perform transfer learning by fine-tuning the CNN with a limited number of labeled standard plane images. We find that fine-tuning the saliency predictor is superior to training from random initialization, with an average F1-score improvement of 9.6% overall and 15.3% for the cardiac planes. Secondly, we train a simple softmax regression on the feature activations of each CNN layer in order to evaluate the representations independently of transfer learning hyper-parameters. We find that the attention models derive strong representations, approaching the precision of a fully-supervised baseline model for all but the last layer.

Abiotic stresses such as water deficit, salt, and heat are major environmental factors that negatively affect plant growth, development, and productivity. Previous studies showed that overexpression of the Arabidopsis vacuolar H + -pyrophosphatase gene AVP1 increases salt and water deficit stress tolerance and overexpression of the rice SUMO E3 ligase gene OsSIZ1 improves heat and water deficit stress tolerance in transgenic plants. In this report, the effects of co-overexpression of AVP1 and OsSIZ1 in Arabidopsis on abiotic stress tolerance were studied. It was found that AVP1/OsSIZ1 co-overexpressing plants performed significantly better than AVP1-overexpressing plants and OsSIZ1-overexpressing plants, and produced 100% more seed than wild-type plants under single stress or multiple stress conditions. The increased stress tolerance in AVP1/OsSIZ1 co-overexpressing plants was substantially larger than the increased stress tolerance in AVP1-overexpressing plants and OsSIZ1-overexpressing plants under every abiotic stress condition tested. This research provides the proof-of-concept that crop yields might be substantially improved using this approach.

Recent automated medical image analysis methods have attained state-of-the-art performance but have relied on memory and compute-intensive deep learning models. Reducing model size without significant loss in performance metrics is crucial for time and memory-efficient automated image-based decision-making. Traditional deep learning based image analysis only uses expert knowledge in the form of manual annotations. Recently, there has been interest in introducing other forms of expert knowledge into deep learning architecture design. This is the approach considered in the paper where we propose to combine ultrasound video with point-of-gaze tracked for expert sonographers as they scan to train memory-efficient ultrasound image analysis models. Specifically we develop teacher-student knowledge transfer models for the exemplar task of frame classification for the fetal abdomen, head, and femur. The best performing memory-efficient models attain performance within 5% of conventional models that are 1000× larger in size.

We present a novel multi-task convolutional neural network called Multi-task SonoEyeNet ( M-SEN ) that learns to generate clinically relevant visual attention maps using sonographer gaze tracking data on input ultrasound (US) video frames so as to assist standardized abdominal circumference (AC) plane detection. Our architecture consists of a generator and a discriminator, which are trained in an adversarial scheme. The generator learns sonographer attention on a given US video frame to predict the frame label (standardized AC plane / background). The discriminator further fine-tunes the predicted attention map by encouraging it to mimick the ground-truth sonographer attention map. The novel model expands the potential clinical usefulness of a previous model by eliminating the requirement of input gaze tracking data during inference without compromising its plane detection performance (Precision: 96.8, Recall: 96.2, F-1 score: 96.5).

The treatment of malignant primary brain tumors is challenging. Concomitant radiochemotherapy has become the standard clinical treatment for malignant glioma, but there are two critical challenges to overcome in order to increase efficacy. First, glioma is known to have increased resistant to radiation due to its intra-tumoral hypoxia. In addition, the blood-brain barrier (BBB) restricts the distribution of the chemotherapeutic agent to the brain. Therefore, we developed a hypoxic radiosensitizer-prodrug liposome (MLP), in order to deliver DOX to the tumor and to overcome the above challenges, achieving a synergistic chemo-/radiotherapy treatment of malignant glioma. In this study, hypoxic radiosensitizer nitroimidazoles were conjugated with lipid molecules with a hydrolysable ester bond to form MDH. MDH was mixed together with DSPE-PEG2000 and cholesterol to make MLP liposomes, which were found to have strong radiosensitivity and to promote cargo release under hypoxic conditions, due to the properties of nitroimidazoles under hypoxic conditions. MLP/DOX was found to have distinct advantages, including precise and stealthy pharmacokinetics and efficient passive uptake by the tumor. Furthermore, the combination of MLP/DOX and radiotherapy (RT) significantly inhibited glioma growth as assessed by in vivo bioluminescence imaging. These findings suggest that MLP is a promising candidate as a DOX delivery system to enhance the antitumor treatment effects on glioma, owing to synergistic chemo-/radiotherapy., (Copyright © 2017 Elsevier Ltd. All rights reserved.)