Computer-aided polyp detection in gastric gastroscopy has been the subject of research over the past few decades. However, despite significant advances, automatic polyp detection in real time is still an unsolved problem. In this paper, we report on a convolutional neural network (CNN) for polyp detection that is constructed based on Single Shot MultiBox Detector (SSD) architecture and which we call SSD for Gastric Polyps (SSD-GPNet). To take full advantages of feature maps’ information from the feature pyramid and to acquire higher accuracy, we re-use information that is abandoned by Max-Pooling layers. In other words, we reuse the lost data from the pooling layers and concatenate that data as extra feature maps to contribute to classification and detection. Meanwhile, in the feature pyramid, we concatenate feature maps of the lower layers and feature maps that are deconvolved from upper layers to make explicit relationships between layers and to effectively increase the number of channels. The results show that our enhanced SSD for gastric polyp detection can realize real-time polyp detection with 50 frames per second (FPS) and can improve the mean average precision (mAP) from 88.5% to 90.4%, with only a little loss in time-performance. And the further experiment shows that SSD-GPNet has excellent performance in improving polyp detection recalls over 10% (p = 0.00053), especially in small polyp detection. This can help endoscopic physicians more easily find missed polyps and decrease the gastric polyp miss rate. It may be applicable in daily clinical practice to reduce the burden on physicians.

INTRODUCTION: Patients with atrophic gastritis (AG) or gastric intestinal metaplasia (GIM) have elevated risk of gastric adenocarcinoma. Endoscopic screening and surveillance have been implemented in high incidence countries. The study aimed to evaluate the accuracy of a deep convolutional neural network (CNN) for simultaneous recognition of AG and GIM. METHODS: Archived endoscopic white light images with corresponding gastric biopsies were collected from 14 hospitals located in different regions of China. Corresponding images by anatomic sites containing AG, GIM, and chronic non-AG were categorized using pathology reports. The participants were randomly assigned (8:1:1) to the training cohort for developing the CNN model (TResNet), the validation cohort for fine-tuning, and the test cohort for evaluating the diagnostic accuracy. The area under the curve (AUC), sensitivity, specificity, and accuracy with 95% confidence interval (CI) were calculated. RESULTS: A total of 7,037 endoscopic images from 2,741 participants were used to develop the CNN for recognition of AG and/or GIM. The AUC for recognizing AG was 0.98 (95% CI 0.97–0.99) with sensitivity, specificity, and accuracy of 96.2% (95% CI 94.2%–97.6%), 96.4% (95% CI 94.8%–97.9%), and 96.4% (95% CI 94.4%–97.8%), respectively. The AUC for recognizing GIM was 0.99 (95% CI 0.98–1.00) with sensitivity, specificity, and accuracy of 97.9% (95% CI 96.2%–98.9%), 97.5% (95% CI 95.8%–98.6%), and 97.6% (95% CI 95.8%–98.6%), respectively. DISCUSSION: CNN using endoscopic white light images achieved high diagnostic accuracy in recognizing AG and GIM.

Cardiovascular disease (CVD) has become the primary cause of global deaths and inflicts an enormous healthcare burden on both developed and developing countries. Frequent monitoring of CVD-associated risk factors such as the level of lipids (e.g., triglyceride (TG) and total cholesterol (TC)) and lipoproteins (e.g., low-density lipoprotein (LDL) and high-density lipoprotein (HDL)) can effectively help prevent disease progression and improve clinical outcomes. However, measurement of these risk factors is generally integrated into an automated analyzer, which is prohibitively expensive and highly instrument-dependent for routine testing in primary care settings. As such, a variety of rapid, simple and portable nanomaterial-based biosensors have been developed for measuring the level of lipids (TG and TC) and lipoproteins (LDL and HDL) towards the management of CVD at the point-of-care (POC). In this review, we first summarize traditional methods for measurement of lipids and lipoproteins, and then present the latest advances in developing nanomaterial-based biosensors that can potentially monitor the risk factors of CVD at the POC.

Deep learning based computer-aided diagnosis technology demonstrates an encouraging performance in aspect of polyp lesion detection on reducing the miss rate of polyps during colonoscopies. However, to date, few studies have been conducted for tracking polyps that have been detected in colonoscopy videos, which is an essential and intuitive issue in clinical intelligent video analysis task (e.g. lesion counting, lesion retrieval, report generation). In the paradigm of conventional tracking-by-detection system, detection task for lesion localization is separated from the tracking task for cropped lesions re-identification. In the multi object tracking problem, each target is supposed to be tracked by invoking a tracker after the detector, which introduces multiple inferences and leads to external resource and time consumption. To tackle these problems, we proposed a plug-in module named instance tracking head (ITH) for synchronous polyp detection and tracking, which can be simply inserted into object detection frameworks. It embeds a feature-based polyp tracking procedure into the detector frameworks to achieve multi-task model training. ITH and detection head share the model backbone for low level feature extraction, and then low level feature flows into the separate branches for task-driven model training. For feature maps from the same receptive field, the region of interest head assigns these features to the detection head and the ITH, respectively, and outputs the object category, bounding box coordinates, and instance feature embedding simultaneously for each specific polyp target. We also proposed a method based on similarity metric learning. The method makes full use of the prior boxes in the object detector to provide richer and denser instance training pairs, to improve the performance of the model evaluation on the tracking task. Compared with advanced tracking-by-detection paradigm methods, detectors with proposed ITH can obtain comparative tracking performance but approximate 30% faster speed. Optimized model based on Scaled-YOLOv4 detector with ITH illustrates good trade-off between detection (mAP 91.70%) and tracking (MOTA 92.50% and Rank-1 Acc 88.31%) task at the frame rate of 66 FPS. The proposed structure demonstrates the potential to aid clinicians in real-time detection with online tracking or offline retargeting of polyp instances during colonoscopies.

Esophagogastroduodenoscopy (EGD) has been widely applied for gastrointestinal (GI) examinations. However, there is a lack of mature technology to evaluate the quality of the EGD inspection process. In this Letter, the authors design a multi‐task anatomy detection convolutional neural network (MT‐AD‐CNN) to evaluate the EGD inspection quality by combining the detection task of the upper digestive tract with ten anatomical structures and the classification task of informative video frames. The authors’ model is able to eliminate non‐informative frames of the gastroscopic videos and detect the anatomies in real time. Specifically, a sub‐branch is added to the detection network to classify NBI images, informative and non‐informative images. By doing so, the detected box will be only displayed on the informative frames, which can reduce the false‐positive rate. They can determine the video frames on which each anatomical location is effectively examined, so that they can analyse the diagnosis quality. Their method reaches the performance of 93.74% mean average precision for the detection task and 98.77% accuracy for the classification task. Their model can reflect the detailed circumstance of the gastroscopy examination process, which shows application potential in improving the quality of examinations.

Background: This study investigated the clinical efficacy of combined posteromedial and posterolateral approaches for repair of 2-part posterior malleolar fractures associated with medial and lateral malleolar fractures. Methods: This case series report included 27 Weber B with Haraguchi type II patients with medial and lateral malleolar fractures combined with 2-part posterior malleolar fractures. Patients were treated with open reduction and internal fixation through a combination of posteromedial and posterolateral approaches from January 2015 to January 2018. There were 11 males and 16 females, with an average age of 61.5 years (range, 53-67 years). The procedures were performed on prone patients under spinal anesthesia. The medial, lateral, and posterior malleolar fractures were exposed through posteromedial and posterolateral approaches performed at the same time. The lateral malleolar fracture was fixed using a plate, the medial malleolar fracture was fixed using screws, and the posterior malleolar fracture was fixed using a plate or cannulated screws according to the size of the fragments. We performed follow-up on 22 patients for an average of 30 months (range, 18-48 months). Results: Primary healing of the incisions was achieved in all cases, and no infection was found. The mean time of bone union was 12.5 weeks (range, 10-15 weeks). The mean time from the operation to full weightbearing was 13 weeks (range, 11-16 weeks). We used the American Orthopaedic Foot & Ankle Society (AOFAS) Ankle-Hindfoot Scale to score patient outcomes; the mean score was 85.4 (range, 80-92) at the final follow-up. No significant pain was found at the final follow-up. Conclusion: This study showed that satisfactory outcomes were achieved with combined posteromedial and posterolateral approaches. Therefore, we believe this approach was a good alternative strategy to repair 2-part posterior malleolar fractures associated with medial and lateral malleolar fractures. Level of Evidence: Level IV, retrospective case series.