Search

Sarcopenia is not only a major cause of disability but also a risk factor for obesity and diabetes in elderly persons. Exercise is an effective method for improving the sarcopenic condition by inducing the secretion of interleukin (IL)-6, which has the capacities to both promote muscle hypertrophy and regulate lipid metabolism and glucose homeostasis, by skeletal muscle. We previously showed that mesenchymal stem cells (MSCs) promote IL-6 secretion by lipopolysaccharide-stimulated C2C12 mouse skeletal muscle myotubes via paracrine mechanisms. Therefore, in this study, we investigated the effect of paracrine actions of MSCs on IL-6 and proinflammatory cytokine expression in contractile C2C12 myotubes by applying electrical stimulation. IL-6 secretion by C2C12 myotubes was increased by electrical stimulation, and a more significant increase in IL-6 secretion was observed in electrically stimulated C2C12 myotubes cultured in conditioned medium from MSCs. The activation of nuclear factor-κB in C2C12 myotubes was also promoted by the combination of conditioned medium from MSCs and electrical stimulation. Moreover, the increases in tumor necrosis factor-α and IL-1β mRNA expression in C2C12 myotubes induced by electrical stimulation were suppressed by culture in conditioned medium from MSCs. The present findings suggest that MSCs transplantation or injection of their extracellular vesicles improve the therapeutic effect of exercise against sarcopenia without exacerbating inflammation.

Background Dermal backflow (DBF), which refers to lymphatic reflux due to lymphatic valve insufficiency, is a diagnostic finding in lymphedema. However, the three-dimensional structure of DBF remains unknown. Photoacoustic lymphangiography (PAL) is a new technique that enables the visualization of the distribution of light-absorbing molecules, such as hemoglobin or indocyanine green (ICG), and can provide three-dimensional images of superficial lymphatic vessels and the venous system. This study reports the use of PAL to visualize DBF structures in the extremities of patients with lymphedema after cancer surgery. Methods Patients with a clinical or lymphographic diagnosis of lymphedema who previously underwent surgery for cancer at one of two participating hospitals were included in this study. PAL was performed using the PAI-05 system. ICG was administered subcutaneously in the affected hand or foot, and ICG fluorescence lymphography was performed using a nearinfrared camera system prior to PAL. Results Between April 2018 and January 2019, 21 patients were enrolled and examined using PAL. The DBF was composed of dense, interconnecting, three-dimensional lymphatic vessels. It was classified into three patterns according to the composition of the lymphatic vessels: a linear structure of lymphatic collectors (pattern 1), a network of lymphatic capillaries and lymphatic collectors in an underlying layer (pattern 2), and lymphatic capillaries and precollectors with no lymphatic collectors (pattern 3). Conclusions PAL showed the structure of DBF more precisely than ICG fluorescence lymphography. The use of PAL to visualize DBF assists in understanding the pathophysiology and assessing the severity of cancer-related lymphedema.

Multi-camera multi-person (MCMP) tracking and re-identification (ReID) are essential tasks in safety, pedestrian analysis, and so on; however, most research focuses on outdoor scenarios because they are much more complicated to deal with occlusions and misidentification in a crowded room with obstacles. Moreover, it is challenging to complete the two tasks in one framework. We present a trajectory-based method, integrating tracking and ReID tasks. First, the poses of all surgical members captured by each camera are detected frame-by-frame; then, the detected poses are exploited to track the trajectories of all members for each camera; finally, these trajectories of different cameras are clustered to re-identify the members in the operating room across all cameras. Compared to other MCMP tracking and ReID methods, the proposed one mainly exploits trajectories, taking texture features that are less distinguishable in the operating room scenario as auxiliary cues. We also integrate temporal information during ReID, which is more reliable than the state-of-the-art framework where ReID is conducted frame-by-frame. In addition, our framework requires no training before deployment in new scenarios. We also created an annotated MCMP dataset with actual operating room videos. Our experiments prove the effectiveness of the proposed trajectory-based ReID algorithm. The proposed framework achieves 85.44% accuracy in the ReID task, outperforming the state-of-the-art framework in our operating room dataset.

BackgroundFibrotic scars are common in both human and mouse skin wounds. However, wound-induced hair neogenesis in the murine wounding models often results in regenerative repair response. Herein, we aimed to uncover cellular functional heterogeneity in dermis between fibrotic and regenerative wound healing fates.MethodsThe expression matrix of single-cell RNA sequencing (scRNA-seq) data of fibrotic and regenerative wound dermal cells was filtered, normalized, and scaled; underwent principal components analysis; and further analyzed by Uniform Manifold Approximation and Projection (UMAP) for dimension reduction with the Seurat package. Cell types were annotated, and cell–cell communications were analyzed. The core cell population myofibroblast was identified and the biological functions of ligand and receptor genes between myofibroblast and macrophage were evaluated. Specific genes between fibrotic and regenerative myofibroblast and macrophage were identified. Temporal dynamics of myofibroblast and macrophage were reconstructed with the Monocle tool.ResultsAcross dermal cells, there were six cell types, namely, EN1-negative myofibroblasts, EN1-positive myofibroblasts, hematopoietic cells, macrophages, pericytes, and endothelial cells. Ligand and receptor genes between myofibroblasts and macrophages mainly modulated cell proliferation and migration, tube development, and the TGF-β pathway. Specific genes that were differentially expressed in fibrotic compared to regenerative myofibroblasts or macrophages were separately identified. Specific genes between fibrotic and regenerative myofibroblasts were involved in the mRNA metabolic process and organelle organization. Specific genes between fibrotic and regenerative macrophages participated in regulating immunity and phagocytosis. We then observed the underlying evolution of myofibroblasts or macrophages.ConclusionCollectively, our findings reveal that myofibroblasts and macrophages may alter the skin wound healing fate through modulating critical signaling pathways.

Recording surgery is an important technique for education and the evaluation of medical treatments. However, capturing targets such as the surgical field, surgical tools, and the surgeon’s hands, is almost impossible since these targets are heavily occluded by the surgeon’s head and body during a surgery. We used a recording system in which multiple cameras are installed in the surgical lump, supposing at least one camera would capture the target without occlusion. As this system records multiple video sequences, we address the task to select a best view camera automatically. Recently, learning-based approaches in a fully supervised manner have been proposed for this task, but these previous approaches completely rely on manual annotation of the training data. In this paper, we focus on the eye tracker mounted on the surgeon’s head, which can capture the recording targets without occlusion. Employing this first-person-view video synchronized with multiple videos of the surgical lump, we propose a novel camera selection approach using a self-supervised learning framework. In experiments, we created a dataset composed of four different breast surgery. Our extended experiments showed that our approach successfully switched to the best camera view without manual annotation and achieved competitive accuracy compared with conventional supervised methods. Also, our approach yielded effective visual representations comparable to state-of-the-art self-supervised learning frameworks.

Mounting multi-view cameras within a surgical light is a practical choice since some cameras are expected to observe surgery with few occlusions. Such multi-view videos must be reassembled for easy reference. A typical way is to reconstruct the surgery in 3D. However, the geometrical relationship among cameras is changed because each camera independently moves every time the lighting is reconfigured (i.e., every time surgeons touch the surgical light). Moreover, feature matching between surgical images is potentially challenging because of missing rich features. To address the challenge, we propose a feature-matching strategy that enables robust calibration of the multi-view camera system by collecting a set of a small number of matches over time while the cameras stay stationary. Our approach would enable conversion from multi-view videos to a 3D video. However, surgical videos are long and, thus, the cost of the conversion rapidly grows. Therefore, we implement a video player where only selected frames are converted to minimize time and data until playbacks. We demonstrate that sufficient calibration quality with real surgical videos can lead to a promising 3D mesh and a recently emerged 3D multi-layer representation. We reviewed comments from surgeons to discuss the differences between those 3D representations on an autostereoscopic display with respect to medical usage.

Cutaneous melanoma refers to a common skin tumor that is dangerous to health with a great risk of metastasis. Previous researches reported that autophagy is associated with the progression of cutaneous melanoma. Nevertheless, the role played by genes with a relation to autophagy (ARG) in the prediction of the course of metastatic cutaneous melanoma is still largely unknown. We observed that thirteen ARGs showed relations to overall survival (OS) in the Cox regression investigation based on a single variate. We developed 2-gene signature, which stratified metastatic cutaneous melanoma cases to groups at great and small risks. Cases suffering from metastatic cutaneous melanoma in the group at great risks had power OS compared with cases at small risks. The risk score, T phase, N phase, and age were proved to be individual factors in terms of the prediction of OS. Besides, the risk scores identified by the two ARGs were significantly correlated with metastatic cutaneous melanoma. Receiver operating characteristic (ROC) curve analysis demonstrated accurate predicting performance exhibited by the 2-gene signature. We also found that the immunization and stromal scores achieved by the group based on large risks were higher compared with those achieved by the group based on small risks. The metastatic cutaneous melanoma cases achieving the score based on small risks acquired greater expression of immune checkpoint molecules as compared with the high-risk group. In conclusion, the 2-ARG gene signature indicated a novel prognostic indicator for prognosis prediction of metastatic cutaneous melanoma, which served as an important tool for guiding the clinical treatment of cutaneous melanoma.

Background Detailed visualization of the lymphatic vessels would greatly assist in the diagnosis and monitoring of lymphatic diseases and aid in preoperative planning of lymphedema surgery and postoperative evaluation. Purpose To evaluate the usefulness of photoacoustic imaging (PAI) for obtaining three-dimensional images of both lymphatic vessels and surrounding venules. Materials and Methods In this prospective study, the authors recruited healthy participants from March 2018 to January 2019 and imaged lymphatic vessels in the lower limbs. Indocyanine green (5.0 mg/mL) was injected into the subcutaneous tissue of the first and fourth web spaces of the toes and below the lateral malleolus. After confirmation of the lymphatic flow with near-infrared fluorescence (NIRF) imaging as the reference standard, PAI was performed over a field of view of 270 × 180 mm. Subsequently, the number of enhancing lymphatic vessels was counted in both proximal and distal areas of the calf and compared between PAI and NIRF. Results Images of the lower limbs were obtained with PAI and NIRF in 15 participants (three men, 12 women; average age, 42 years ± 12 [standard deviation]). All participants exhibited a linear pattern on NIRF images, which is generally considered a reflection of good lymphatic function. A greater number of lymphatic vessels were observed with PAI than with NIRF in both the distal (mean: 3.6 vessels ± 1.2 vs 2.0 vessels ± 1.1, respectively; P < .05) and proximal (mean: 6.5 vessels ± 2.6 vs 2.6 vessels ± 1.6; P < .05) regions of the calf. Conclusion Compared with near-infrared fluorescence imaging, photoacoustic imaging provided a detailed, three-dimensional representation of the lymphatic vessels and facilitated an increased understanding of their relationship with the surrounding venules. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Lillis and Krishnamurthy in this issue.

Lymphaticovenular anastomosis (LVA) is a widely performed surgical procedure for the treatment of lymphedema. For good LVA outcomes, identifying lymphatic vessels and venules is crucial. Photoacoustic lymphangiography (PAL) is a new technology for visualizing lymphatic vessels. It can depict lymphatic vessels at high resolution; therefore, this study focused on how to apply PAL for lymphatic surgery. To visualize lymphatic vessels, indocyanine green was injected as a color agent. PAI-05 was used as the photoacoustic imaging device. Lymphatic vessels and veins were visualized at 797- and 835-nm wavelengths. First, it was confirmed whether the branching of the vasculature as depicted by the PAL was consistent with the actual branching of the vasculature as confirmed intraoperatively. Second, to use PAL images for surgical planning, preoperative photoacoustic images were superimposed onto the patient limb through augmented reality (AR) glasses (MOVERIO Smart Glass BT-30E). Lymphatics and venule markings drawn using AR glasses were consistent with the actual intraoperative images obtained during LVA. To anastomose multiple lymphatic vessels, a site with abundant venous branching was selected as the incision site; and selecting the incision site became easier. The anatomical morphology obtained by PAL matched the surgical field. AR-based marking could be very useful in future LVA.

Background Lymphatic vessels are difficult to identify using existing modalities as because of their small diameter and the transparency of the lymph fluid flowing through them. Methods Here, we introduce photoacoustic lymphangiography (PAL), a new modality widely used for lymphedema treatment, to observe limb lymphatic vessels. The photoacoustic imaging system used in this study can simultaneously visualize lymphatic vessels and veins with a high resolution (0.2 mm) and can also observe their three-dimensional relationship with each other. Results High-resolution images of the lymphatic vessels, detailed structure of the dermal back flow, and the three-dimensional positional relationship between the lymphatic vessels and veins were observed by PAL. Conclusion The clear image provided by PAL could have a major application in pre- and postoperative use during lymphaticovenular anastomosis for lymphedema treatment.

In the medical field, surgical videos can be used to introduce surgical skills. Medical students and residents watch the videos to study the surgical skills and increase learning speed by compensating for the lack of experience in surgical rooms due to limited opportunity to join in surgery. To record egocentric surgical videos by a wearable camera is a solution to record surgical skills of a surgeon in detail. However, most egocentric surgical videos are of quite long duration. For example, in the case of tumor removal in breast surgery, a video recording time often reaches 2[Formula: see text]h. With that length, it is time consuming to see important scenes in the video, particularly because many surgical videos include nonessential scenes such as sterilization and preparation of tools. For extracting specific scenes from a long video, we can apply scene estimation by machine learning. Furthermore, it is important to know where the surgeon is looking to observe the area of the incision in detail. In particular, it is vital to be able to zoom in on key elements, allowing viewers to see the incision area and the fine details of the necessary surgical skills. In this study, we aimed to highlight incision scenes from egocentric surgical videos in the spatiotemporal domain by utilizing two neural networks for the temporal and spatial highlights. For the temporal highlights, we designed a neural network that estimates the incision scenes by learning gaze speed, hand movements, number of hands, and background movements in egocentric surgical videos. For the spatial highlights, in order to estimate the important area to zoom in, we designed a neural network that learns the surgeon’s gaze on natural features of surgical scenes to form a probability map as a representation of the estimated gaze area. The estimated gaze area was also used to calculate the appropriate zoom-in position and zoom-in ratio. To control the highlighted parameters in accord with user preferences, we also made a user interface that allows for the selection of playback speed gain and zoom ratio gain. For the evaluation, we verified the performance of the networks by a quantitative assessment and conducted a user study with medical doctors by showing an actual surgical video to obtain a qualitative assessment on the proposed system.

This work presents a method for identifying surgical field states using time-of-flight (ToF) sensors equipped with a surgical light. It is important to understand the surgical field state in a smart surgical room. In this study, we aimed to identify surgical field states by using 28 ToF sensors with a surgical light installed on each. In the experimental condition, we obtained a sensor dataset by changing the number of people, posture, and movement state of a person under the surgical light. The identification accuracy of the proposed system was evaluated by applying machine learning techniques. This system can be realized simply by attaching ToF sensors to the surface of an existing surgical light.

Photoacoustic imaging is a new technique that uses the photoacoustic effect. In photoacoustic lymphangiography (PAL), images of the lymphatic vessels can be visualized using light-absorbing contrast agents. In the present study, we investigated the efficacy of PAL for lymphedema staging.We performed PAL of the lower extremities and examined the clinical implications of using PAL for staging lymphedema by comparing the PAL images with those obtained using lymphoscintigraphy. Of 47 patients with lymphedema who had been outpatients or hospitalized at our institution between May 2018 and September 2020 and had undergone PAL, 15 with 18 limbs who had also undergone lymphoscintigraphy were included in the present study. The lymphoscintigraphy findings were classified using the Maegawa classification. We also investigated whether PAL could clearly visualize the lymphatic vessels and concisely reflect the disease state by counting the number of lymphatic vessels observed using PAL.The PAL findings were categorized into three groups: collecting lymphatic vessels, dermal backflow (DBF), and no lymphatic vessels. The collecting lymphatic vessels group corresponded to types 2 and 3 in the Maegawa classification; DBF corresponded to types 3 and 4, and the no lymphatic vessels group corresponded to type 4. The number of lymphatic vessels visualized using PAL was similar to that with lymphoscintigraphy. As the disease progressed, the number of lymphatic vessels observed decreased, increased DBF was detected, and, eventually, the lymphatic vessels were not visible, corresponding to the general changes observed via lymphoscintigraphy with stage progression.The findings from PAL and lymphoscintigraphy tended to correspond, suggesting that PAL could be useful for lymphedema staging.

Detecting surgical tools is an essential task for analyzing and evaluating surgical videos. However, most studies focus on minimally invasive surgery (MIS) and cataract surgery. Mainly because of a lack of a large, diverse, and well-annotated dataset, research in the area of open surgery has been limited so far. Open surgery video analysis is challenging because of its properties: varied number and roles of people (e.g., main surgeon, assistant surgeons, and nurses), a complex interaction of tools and hands, various operative environments, and lighting conditions. In this paper, to handle these limitations and difficulties, we introduce an egocentric open surgery dataset that includes 15 open surgeries recorded with a head-mounted camera. More than 67k bounding boxes are labeled to 19k images with 31 surgical tool categories. Finally, we present a surgical tool detection baseline model based on recent advances in object detection. The results of our new dataset show that our presented dataset provides enough interesting challenges for future methods and that it can serve as a strong benchmark to address the study of tool detection in open surgery.

Objective Photoacoustic imaging (PAI) is a new technique that can evaluate the vascular system using photoacoustic effects. The present study compared the ability of the new photoacoustic lymphangiography (PAL) method and more standard near-infrared fluorescence (NIRF) to image the lymphatic system in patients with secondary lymphedema following gynecological cancer surgery. Methods Patients with secondary lymphedema in the lower extremities following gynecologic cancer surgery, who were assessed using PAL between May 2018 and January 2019 were recruited. NIRF was performed first using 5.0 mg/mL of indocyanine green injected using a 0.2-cc 30-gauge needle. Correlations between NIRF and PAL findings on patient images were subsequently examined. Results Seventeen patients with secondary lymphedema were enrolled. The mean age of the patients was 61 ± 11 years. The imaging sites were the medial lower leg in 15 patients, the posterior lower leg in nine patients, the lateral lower leg in seven patients, the medial knee in four patients, and other areas in three patients. A total of 38 pictures were obtained. Five distinct lymphatic patterns were observed over the entire sample using PAL: straight, winding, spiderweb, nebulous, and black-out pattern Eighteen of the 24 limbs (75%) that exhibited a linear pattern in NIRF exhibited a straight pattern in PAL, and 19 of the 20 limbs (95%) that exhibited a splash pattern in NIRF exhibited a winding or spider web pattern in PAL. Eight limbs exhibiting diffuse patterns without linear or splash patterns with NIRF were all nebulous or black-out patterns in PAL. This suggests that more severe lymphatic degeneration was associated with poorer visualization in PAL. Conclusions NIRF plays an important role in lymphedema treatment. In the present study, various PAL patterns were compared with those observed using NIRF. PAL provided clearer images including transectional views, which were not available using NIRF, and may promote further understanding of the changes in the lymphatic structure and function in patients with secondary lymphedema.

This paper presents progress in the automation of cell and tissue systems and attempts toward the in situ feedback control of organs-on-a-chip. Our study aims to achieve feedback control of a cell and tissue system by a personal computer (PC), whereas most studies on organs-on-a-chip focus on the automation of status monitoring. The implemented system is composed of subsystems including automated culture, stimulation, and monitoring. The monitoring function provides imaging as well as sampling and dispensing in combination with an external analyzer. Individual subsystems can be combined accordingly. First, monitoring of skeletal muscle (SM) and adipose tissues using this system was demonstrated. The highlight of this paper is the application of the system to the feedback control of the lipid droplet (LD) size, where biochemical stimulation using insulin and adrenaline is controlled by a PC according to the obtained LD imaging data. In this study, the system demonstrated its function of maintaining the desired size of LDs. Our results expand the possibility of PC-controllable cell and tissue systems by addressing the challenge of feedback control of organs-on-a-chip. The PC-controllable cell and tissue systems will contribute to living systems-on-a-chip based on homeostasis phenomena involving interactions between organs or tissues.

Lymphedema occurs when interstitial fluid and fibroadipose tissues accumulate abnormally because of decreased drainage of lymphatic fluid as a result of injury, infection, or congenital abnormalities of the lymphatic system drainage pathway. An accurate anatomical map of the lymphatic vasculature is needed not only for understanding the pathophysiology of lymphedema but also for surgical planning. However, because of their limited spatial resolution, no imaging modalities are currently able to noninvasively provide a clear visualization of the lymphatic vessels. Photoacoustic imaging is an emerging medical imaging technique that provides unique scalability of optical resolution and acoustic depth of penetration. Moreover, light-absorbing biomolecules, including oxy- and deoxyhemoglobin, lipids, water, and melanin, can be imaged. Using exogenous contrast agents that are taken up by lymphatic vessels, e.g., indocyanine green, photoacoustic lymphangiography, which has a higher spatial resolution than previous imaging modalities, is possible. Using a new prototype of a photoacoustic imaging system with a wide field of view developed by a Japanese research group, high-resolution three-dimensional structural information of the vasculatures was successfully obtained over a large area in both healthy and lymphedematous extremities. Anatomical information on the lymphatic vessels and adjacent veins provided by photoacoustic lymphangiography is helpful for the management of lymphedema. In particular, such knowledge will facilitate the planning of microsurgical lymphaticovenular anastomoses to bypass the excess fluid component by joining with the circulatory system peripherally. Although challenges remain to establish its implementation in clinical practice, photoacoustic lymphangiography may contribute to improved treatments for lymphedema patients in the near future.

Detecting surgical tools is an essential task for the analysis and evaluation of surgical videos. However, in open surgery such as plastic surgery, it is difficult to detect them because there are surgical tools with similar shapes, such as scissors and needle holders. Unlike endoscopic surgery, the tips of the tools are often hidden in the operating field and are not captured clearly due to low camera resolution, whereas the movements of the tools and hands can be captured. As a result that the different uses of each tool require different hand movements, it is possible to use hand movement data to classify the two types of tools. We combined three modules for localization, selection, and classification, for the detection of the two tools. In the localization module, we employed the Faster R-CNN to detect surgical tools and target hands, and in the classification module, we extracted hand movement information by combining ResNet-18 and LSTM to classify two tools. We created a dataset in which seven different types of open surgery were recorded, and we provided the annotation of surgical tool detection. Our experiments show that our approach successfully detected the two different tools and outperformed the two baseline methods.

Objective Aging is one of the causes of primary lymphedema. However, the effects of aging on the lymphatic system are still not completely understood. We investigated the effects of aging on the lymphatic vessels in the lower extremities of healthy volunteers using photoacoustic imaging. Methods Healthy volunteers who underwent photoacoustic lymphangiography between March 2018 and January 2019 were enrolled. To visualize lymphatics, indocyanine green (ICG, 5.0 mg/mL) was injected subcutaneously into the first and fourth web spaces of the foot and under the lateral malleolus. Subsequently, near-infrared fluorescence lymphography was performed to confirm good ICG flow, and photoacoustic lymphangiography was performed on the medial side of the lower leg. Ti sapphire laser irradiation at 797 and 835 nm, the optimal wavelengths for visualizing ICG and blood, was applied. The number of lymphatic vessels shown at areas 10 cm (L10) and 20 cm (L20) cranially from the internal malleolus was counted. Results Nineteen healthy volunteers (4 males and 15 females) were enrolled in the study. Their mean age was 42.9 ± 12.8 years. One volunteer was bilaterally imaged; 15 left lower limbs and 5 right lower limbs were imaged. The number of lymphatic vessels visualized increased with age. There were strong positive correlations between age and L10 (R = 0.729, P Conclusions Photoacoustic imaging indicates that the number of lymphatic vessels increases with age. Lymphatic stasis resulted in visualization of not only normal drainage pathways but also nonfunctional lymphatic pathways.

Supplemental Digital Content is available in the text., Summary: It is difficult to evaluate the postoperative patency of lymphaticovenular anastomosis, but this evaluation is essential for determining surgical results. When using the current standard modality, near-infrared fluorescent lymphography, it is difficult to observe patency if the anastomotic point is veiled by dermal backflow. In this study, we used a new photoacoustic imaging device, PAI-05, to check the patency of anastomosis. We performed photoacoustic lymphangiography after lymphaticovenular anastomosis surgery. By digitally subtracting the superficial area, we can examine an area deeper than the dermal backflow, which is not visible by near-infrared fluorescent lymphography. The connection between the lymphatic vessel and the venule observed in the image is an indication of the patency of anastomosis. However, in a non-patent anastomosed site, the lymphatic vessel has a gap that separates it from the venule at the anastomosed site. Although photoacoustic lymphangiography cannot be used to visualize the lymphatic vessels that are not contrasted by indocyanine green, the resulting high-resolution images and clear anastomosis evaluation afforded by it will contribute to the development of future lymphedema treatments.

Supplemental Digital Content is available in the text.

Supplemental Digital Content is available in the text.

There has been a substantial amount of research involving computer methods and technology for the detection and recognition of diabetic foot ulcers (DFUs), but there is a lack of systematic comparisons of state-of-the-art deep learning object detection frameworks applied to this problem. DFUC2020 provided participants with a comprehensive dataset consisting of 2,000 images for training and 2,000 images for testing. This paper summarises the results of DFUC2020 by comparing the deep learning-based algorithms proposed by the winning teams: Faster R-CNN, three variants of Faster R-CNN and an ensemble method; YOLOv3; YOLOv5; EfficientDet; and a new Cascade Attention Network. For each deep learning method, we provide a detailed description of model architecture, parameter settings for training and additional stages including pre-processing, data augmentation and post-processing. We provide a comprehensive evaluation for each method. All the methods required a data augmentation stage to increase the number of images available for training and a post-processing stage to remove false positives. The best performance was obtained from Deformable Convolution, a variant of Faster R-CNN, with a mean average precision (mAP) of 0.6940 and an F1-Score of 0.7434. Finally, we demonstrate that the ensemble method based on different deep learning methods can enhanced the F1-Score but not the mAP., Comment: 19 pages, 18 figures, 10 tables

Recording surgery in operating rooms is an essential task for education and evaluation of medical treatment. However, recording the desired targets, such as the surgery field, surgical tools, or doctor’s hands, is difficult because the targets are heavily occluded during surgery. We use a recording system in which multiple cameras are embedded in the surgical lamp, and we assume that at least one camera is recording the target without occlusion at any given time. As the embedded cameras obtain multiple video sequences, we address the task of selecting the camera with the best view of the surgery. Unlike the conventional method, which selects the camera based on the area size of the surgery field, we propose a deep neural network that predicts the camera selection probability from multiple video sequences by learning the supervision of the expert annotation. We created a dataset in which six different types of plastic surgery are recorded, and we provided the annotation of camera switching. Our experiments show that our approach successfully switched between cameras and outperformed three baseline methods.

Recording medical surgery operations is important for sharing the various operating techniques. In most operating rooms, fixed surgery cameras are already installed, but it is almost impossible to capture the surgical field because of occlusion by the surgeon’s head and body. In order to capture the surgical field in real surgery operations, we proposed the installation of multiple cameras in a surgical lighting system, so that at least one camera can capture the target surgical field even when the surgeon’s head and body occlude other cameras. In this paper, we present a method for automatic viewpoint selection from multi-view surgical videos, so that the surgical field can always be recorded in the output video. We employ a method for learning-based object detection from videos for automatic evaluation of the surgical field area from multiple input videos. By selecting the viewpoint with the largest area of the surgical field, we can virtually reduce the area of the surgeon’s head and hands. In general, frequent camera switching degrades the video quality of view (QoV). Therefore, we apply the Dijkstra method widely used in the shortest path problem as a combinatorial optimization method for this problem. Our camera scheduling method is that the camera switching is not performed for a certain period of time, and the surgical field observed in the entire video is maximized.

Photoacoustic lymphangiography, which is based on photoacoustic technology, is an optical imaging that visualizes the distribution of light absorbing tissue components like hemoglobin or melanin, as well as optical absorption contrast imaging agents like indocyanine green (ICG) in the lymphatic channels, with high spatial resolution. In this report, we introduce the three-dimensional (3D) images of human lymphatic vessels obtained with photoacoustic lymphangiography.We used the 3D photoacoustic visualization system (PAI-05). Some healthy subjects and lymphedema patients were recruited. To image the lymphatic structures of the limbs ICG was administered subcutaneously as in fluorescence lymphangiography. Photoacoustic images were acquired by irradiating the tissue using a laser at wavelengths of near-infrared region. On the same occasion, fluorescence images were also recorded.The lymphatic vessels up to the diameter of 0.2 mm could be observed three-dimensionally with the venules around them. In the patient-group, dermal backflow patterns were often observed as dense interconnecting 3D structures of lymphatic vessels. Collecting vessels passing below the dermis were also observed, which were not observed by fluorescence lymphography.Photoacoustic lymphangiography provided the detailed observation of each lymphatic vessel, leading to deeper understanding of 3D structures and physiological state of the vessel.