微创腔镜影像系 统应用于妇产科临床教学的体会

以腔镜技术为主要代表的微创外科是21世纪外科学发展的主旋律。将微创外科的理念与实践纳入妇产科的临床教学工作符合教学实际和时代要求。腔镜外科技术的发展及应用,完善了盆宫腔疾病诊断及治疗的影像资料, 提供了真实、生动、直观及多层次的教学素材。与传统临床教学方法相比,微创腔镜影像辅助教学法有助于学生掌握盆宫腔内脏解剖结构及妇产科疾病的病理改变;提高了医学生学习兴趣及主动性。同时,微创外科腔镜影像系统积累的直观真实、可重复的临床诊疗案例大大丰富了教学内容,提升教学效果。      

Minimally invasive surgery

During the last 10 years, minimally invasive surgery has influenced the techniques used in every specialty of surgical medicine. This development has not only led to the replacement of conventional procedures with minimally invasive ones, but has also stimulated surgeons to reevaluate conventional approaches with regard to perioperative parameters such as pain medication. However, two major drawbacks have emerged with the introduction of this new technique: firstly, the prolonged learning curve for most surgeons, in comparison with the learning process in open surgery; and secondly, increased costs due to investment in the equipment required and the use of disposable instruments, as well as longer operating times. In the various health-care systems around the world, these increased costs are not always compensated for by shorter hospital stays. This review focuses on major areas of indication for minimally invasive surgery in the gastrointestinal tract. These include functional disorders of the upper and lower gastrointestinal tract, obesity surgery, minimally invasive techniques in gastric and hepatobiliary surgery and in other solid organs, and laparoscopic colorectal surgery. The shortening of the hospitalization period has led to increasing use of outpatient laparoscopic surgery, and many centers specializing in day-care surgery are using these techniques. The frontiers are being pushed even further, as the size of the instruments is reduced to achieve better cosmetic results. Clinical research has also focused on the topic of expanding the indications for minimally invasive approaches in the elderly and in high-risk patients, to take advantage of the shorter hospital stays and reduced surgical trauma that are possible. A considerable amount of basic research has been carried out on the stress response during and after minimally invasive procedures, and an improved immune response with the minimally invasive approach has been observed, leading to better results after extensive oncological procedures. Robotic surgery and telesurgery involve new computer-aided methods that allow greater precision in surgical technique, as well as offering an opportunity to supply surgical skill and expertise remotely, over long distances. Minimally invasive surgical techniques are thus now fully established in routine use, and the indications are continuing to expand.     

Live laparoscopic video retrieval with compressed uncertainty

Searching through large volumes of medical data to retrieve relevant information is a challenging yet crucial task for clinical care. However the primitive and most common approach to retrieval, involving text in the form of keywords, is severely limited when dealing with complex media formats. Content-based retrieval offers a way to overcome this limitation, by using rich media as the query itself. Surgical video-to-video retrieval in particular is a new and largely unexplored research problem with high clinical value, especially in the real-time case: using real-time video hashing, search can be achieved directly inside of the operating room. Indeed, the process of hashing converts large data entries into compact binary arrays or hashes, enabling large-scale search operations at a very fast rate. However, due to fluctuations over the course of a video, not all bits in a given hash are equally reliable. In this work, we propose a method capable of mitigating this uncertainty while maintaining a light computational footprint. We present superior retrieval results (3%–4% top 10 mean average precision) on a multi-task evaluation protocol for surgery, using cholecystectomy phases, bypass phases, and coming from an entirely new dataset introduced here, surgical events across six different surgery types. Success on this multi-task benchmark shows the generalizability of our approach for surgical video retrieval.     

Siam-U-Net: encoder-decoder siamese network for knee cartilage tracking in ultrasound images

The tracking of the knee femoral condyle cartilage during ultrasound-guided minimally invasive procedures is important to avoid damaging this structure during such interventions. In this study, we propose a new deep learning method to track, accurately and efficiently, the femoral condyle cartilage in ultrasound sequences, which were acquired under several clinical conditions, mimicking realistic surgical setups. Our solution, that we name Siam-U-Net, requires minimal user initialization and combines a deep learning segmentation method with a siamese framework for tracking the cartilage in temporal and spatio-temporal sequences of 2D ultrasound images. Through extensive performance validation given by the Dice Similarity Coefficient, we demonstrate that our algorithm is able to track the femoral condyle cartilage with an accuracy which is comparable to experienced surgeons. It is additionally shown that the proposed method outperforms state-of-the-art segmentation models and trackers in the localization of the cartilage. We claim that the proposed solution has the potential for ultrasound guidance in minimally invasive knee procedures.     

Lumbar disc surgery in historical perspective

The development of microscopy, laser technology, endoscopy, and video and image guidance systems has provided the foundation on which minimally invasive spinal surgery is based. Minimally invasive treatments have been undertaken in all areas of the spinal axis since the 20th century. Lumbar disc disease has been treated using chemonucleolysis, percutaneous discectomy, laser discectomy, intradiscal thermoablation, and minimally invasive microdiscectomy techniques.     

Automatic segmentation of occluded vasculature via pulsatile motion analysis in endoscopic robot-assisted partial nephrectomy video

Hilar dissection is an important and delicate stage in partial nephrectomy, during which surgeons remove connective tissue surrounding renal vasculature. Serious complications arise when the occluded blood vessels, concealed by fat, are missed in the endoscopic view and as a result are not appropriately clamped. Such complications may include catastrophic blood loss from internal bleeding and associated occlusion of the surgical view during the excision of the cancerous mass (due to heavy bleeding), both of which may compromise the visibility of surgical margins or even result in a conversion from a minimally invasive to an open intervention. To aid in vessel discovery, we propose a novel automatic method to segment occluded vasculature from labeling minute pulsatile motion that is otherwise imperceptible with the naked eye. Our segmentation technique extracts subtle tissue motions using a technique adapted from phase-based video magnification, in which we measure motion from periodic changes in local phase information albeit for labeling rather than magnification. Based on measuring local phase through spatial decomposition of each frame of the endoscopic video using complex wavelet pairs, our approach assigns segmentation labels by detecting regions exhibiting temporal local phase changes matching the heart rate. We demonstrate how our technique is a practical solution for time-critical surgical applications by presenting quantitative and qualitative performance evaluations of our vessel detection algorithms with a retrospective study of fifteen clinical robot-assisted partial nephrectomies.     

In vivo comparison of hip mechanics for minimally invasive versus traditional total hip arthroplasty

BACKGROUND: Minimally invasive surgery has been developed to reduce incision length, muscle damage, and rehabilitation time. However, reduced exposure of anatomical landmarks may result in technical errors and inferior implant survivorship. The objective of this study was to compare in vivo motions and hip joint contact forces during gait in total hip arthroplasty subjects, performed with either minimally invasive surgery or standard surgical approaches. METHODS: Fifteen subjects implanted using either minimally invasive surgery anterolateral, minimally invasive surgery posterolateral, or traditional posterolateral total hip arthroplasty were evaluated using fluoroscopy while performing gait on a treadmill. Kinematics, obtained using 3D-to-2D image registration technique, were input as temporal functions in a 3D inverse dynamic mathematical model that determines in vivo soft tissue and hip contact forces. FINDINGS: The subjects implanted with posterolateral and anterolateral minimally invasive surgery demonstrated significantly less separation than those implanted with the traditional approach (P<0.01). The minimally invasive surgery subjects also experienced lower average maximum peak forces, with 3.2 body weight for the anterolateral minimally invasive surgery and 2.9 body weight for the posterolateral minimally invasive surgery subjects, compared to 3.5 body weight for the traditional subjects (P=0.02 and P=0.03, respectively). INTERPRETATION: This is the first study to compare in vivo weight-bearing kinematics, separation and kinetics for traditional, anterolateral minimally invasive surgery and posterolateral minimally invasive surgery total hip arthroplasty subject groups. Our data indicated in all analyzed parameters differences between the minimally invasive surgery and the traditional groups, with favorable results for the minimally invasive surgery subjects. This may be related, to a reduction in stabilizing soft tissues after a minimally invasive surgery procedure, leading to lower bearing surface forces at the femoral head--acetabular cup interface.     

Minimally invasive surgical options in pediatric heart surgery

Surgery for congenital heart disease has changed considerably during the last decade. Improved surgical results in patients with simple congenital heart disease and new interventional cardiology procedures have stimulated the surgeon to adopt minimally invasive techniques with the aim of reducing the patient's surgical insult and obtaining good functional and cosmetic results. As a consequence, new surgical techniques and special equipment for minimally invasive heart procedures have been developed and refined in recent years. This article reports on our institutional protocols for minimally invasive surgery in children and adults with congenital heart disease.     

Practical camera evaluation: A review of principles

Summary

Background: Modern video systems are essential to minimally invasive surgery. Methods: We discuss general precepts that must be considered when planning to acquire such a system for one's operating rooms. One possible approach to objective camera evaluation is described. Multivariate analysis was performed. Results: There was a statistical preference for two independent variables: chip number and digitization. Of these, digitized enhancement was more significant. Conclusions: As cost and versatility become increasingly important in the purchase of surgical video systems, multi-disciplinary evaluations to determine a preferred system can prove valuable to an institution.     

Contrastive domain adaptation with consistency match for automated pneumonia diagnosis

Pneumonia can be difficult to diagnose since its symptoms are too variable, and the radiographic signs are often very similar to those seen in other illnesses such as a cold or influenza. Deep neural networks have shown promising performance in automated pneumonia diagnosis using chest X-ray radiography, allowing mass screening and early intervention to reduce the severe cases and death toll. However, they usually require many well-labelled chest X-ray images for training to achieve high diagnostic accuracy. To reduce the need for training data and annotation resources, we propose a novel method called Contrastive Domain Adaptation with Consistency Match (CDACM). It transfers the knowledge from different but relevant datasets to the unlabelled small-size target dataset and improves the semantic quality of the learnt representations. Specifically, we design a conditional domain adversarial network to exploit discriminative information conveyed in the predictions to mitigate the domain gap between the source and target datasets. Furthermore, due to the small scale of the target dataset, we construct a feature cloud for each target sample and leverage contrastive learning to extract more discriminative features. Lastly, we propose adaptive feature cloud expansion to push the decision boundary to a low-density area. Unlike most existing transfer learning methods that aim only to mitigate the domain gap, our method instead simultaneously considers the domain gap and the data deficiency problem of the target dataset. The conditional domain adaptation and the feature cloud generation of our method are learning jointly to extract discriminative features in an end-to-end manner. Besides, the adaptive feature cloud expansion improves the model’s generalisation ability in the target domain. Extensive experiments on pneumonia and COVID-19 diagnosis tasks demonstrate that our method outperforms several state-of-the-art unsupervised domain adaptation approaches, which verifies the effectiveness of CDACM for automated pneumonia diagnosis using chest X-ray imaging.     

机器人手术系统在妇科领域的应用

随着医学进步和手术器械设备的日益更新及改善,机器人手术作为一种新兴的微创手术方式逐渐应用于妇科领域,与开腹手术及传统腹腔镜手术相比,具有三维视野高清、机械臂可自由旋转、操作精细准确、学习曲线短等优势。     

Automatic feature generation in endoscopic images

Motivation

Fiber optic endoscopy is essential for minimally invasive surgery, but endoscopic images are very challenging for computer vision algorithms, since they contain many effects like tissue deformations, specular reflections, smoke, variable illumination and field of view. We developed a method to extract features from endoscopic images usable for scene analysis and classification. These features could be used with data from other sensors for workflow analysis and recognition.

Materials and methods

Evolutionary reinforcement learning that automatically computes good features, making it possible to classify endoscopic images into their respective surgical phases. It is especially designed to abstract the relevant information from the highly noisy images automatically.

Results

Automatic feature extraction was used to classify images from endoscopic cholecystectomies into their respective surgical phases. These automatically computed features perform better than some classical features from computer vision. The automated feature extraction process enables reasonable classification rates for complex and difficult images where no good features are known.

Conclusion

We developed an automatic method that extracts features from images for use in classification. The method was applied to endoscopic images yielding promising results and demonstrating its feasibility under demanding conditions.     

Deep learning with 4D spatio-temporal data representations for OCT-based force estimation

Estimating the forces acting between instruments and tissue is a challenging problem for robot-assisted minimally-invasive surgery. Recently, numerous vision-based methods have been proposed to replace electro-mechanical approaches. Moreover, optical coherence tomography (OCT) and deep learning have been used for estimating forces based on deformation observed in volumetric image data. The method demonstrated the advantage of deep learning with 3D volumetric data over 2D depth images for force estimation. In this work, we extend the problem of deep learning-based force estimation to 4D spatio-temporal data with streams of 3D OCT volumes. For this purpose, we design and evaluate several methods extending spatio-temporal deep learning to 4D which is largely unexplored so far. Furthermore, we provide an in-depth analysis of multi-dimensional image data representations for force estimation, comparing our 4D approach to previous, lower-dimensional methods. Also, we analyze the effect of temporal information and we study the prediction of short-term future force values, which could facilitate safety features. For our 4D force estimation architectures, we find that efficient decoupling of spatial and temporal processing is advantageous. We show that using 4D spatio-temporal data outperforms all previously used data representations with a mean absolute error of 10.7 mN. We find that temporal information is valuable for force estimation and we demonstrate the feasibility of force prediction.     

Transformer-based unsupervised contrastive learning for histopathological image classification

A large-scale and well-annotated dataset is a key factor for the success of deep learning in medical image analysis. However, assembling such large annotations is very challenging, especially for histopathological images with unique characteristics (e.g., gigapixel image size, multiple cancer types, and wide staining variations). To alleviate this issue, self-supervised learning (SSL) could be a promising solution that relies only on unlabeled data to generate informative representations and generalizes well to various downstream tasks even with limited annotations. In this work, we propose a novel SSL strategy called semantically-relevant contrastive learning (SRCL), which compares relevance between instances to mine more positive pairs. Compared to the two views from an instance in traditional contrastive learning, our SRCL aligns multiple positive instances with similar visual concepts, which increases the diversity of positives and then results in more informative representations. We employ a hybrid model (CTransPath) as the backbone, which is designed by integrating a convolutional neural network (CNN) and a multi-scale Swin Transformer architecture. The CTransPath is pretrained on massively unlabeled histopathological images that could serve as a collaborative local–global feature extractor to learn universal feature representations more suitable for tasks in the histopathology image domain. The effectiveness of our SRCL-pretrained CTransPath is investigated on five types of downstream tasks (patch retrieval, patch classification, weakly-supervised whole-slide image classification, mitosis detection, and colorectal adenocarcinoma gland segmentation), covering nine public datasets. The results show that our SRCL-based visual representations not only achieve state-of-the-art performance in each dataset, but are also more robust and transferable than other SSL methods and ImageNet pretraining (both supervised and self-supervised methods). Our code and pretrained model are available at https://github.com/Xiyue-Wang/TransPath.     

超声引导下微创治疗乳腺脓肿的价值

目的探讨超声引导下微创治疗乳腺脓肿的临床价值。方法 2008年1月至2011年1月我院收治56例乳腺脓肿患者共78个脓肿病灶。单侧乳房脓肿34例,双侧乳房脓肿22例。脓肿最大为9cm×7cm×4cm,最小为3cm×3cm×2cm。30例患者共42个脓肿病灶采用超声引导下微创治疗,26例患者共36个脓肿病灶采用传统手术治疗。结果行超声引导下微创治疗患者术后切口愈合及术腔完全闭合时间为7～9d,行传统手术治疗患者为9～20d,差异有统计学意义(P=0.045)。行超声引导下微创治疗患者术后切口瘢痕长度为0.3～0.5cm,小于行传统手术治疗患者的3～5cm。行超声引导下微创治疗患者一次手术治疗成功率为97.6%(41/42),行传统手术治疗患者一次手术治疗成功率为83.3%(30/36),差异有统计学意义(P=0.044);行超声引导下微创治疗患者术后均无复发(0/41),行传统手术治疗患者术后复发率为13.33%(4/30),差异有统计学意义(P=0.028)。结论超声引导下微创治疗乳腺脓肿可缩短术后切口愈合及术腔完全闭合时间,瘢痕小,一次手术治疗成功率较高,术后复发率低,是临床治疗乳腺脓肿的较好方法 。     

Deep learning with convolutional neural network for objective skill evaluation in robot-assisted surgery

Purpose

With the advent of robot-assisted surgery, the role of data-driven approaches to integrate statistics and machine learning is growing rapidly with prominent interests in objective surgical skill assessment. However, most existing work requires translating robot motion kinematics into intermediate features or gesture segments that are expensive to extract, lack efficiency, and require significant domain-specific knowledge.

Methods

We propose an analytical deep learning framework for skill assessment in surgical training. A deep convolutional neural network is implemented to map multivariate time series data of the motion kinematics to individual skill levels.

Results

We perform experiments on the public minimally invasive surgical robotic dataset, JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS). Our proposed learning model achieved competitive accuracies of 92.5%, 95.4%, and 91.3%, in the standard training tasks: Suturing, Needle-passing, and Knot-tying, respectively. Without the need of engineered features or carefully tuned gesture segmentation, our model can successfully decode skill information from raw motion profiles via end-to-end learning. Meanwhile, the proposed model is able to reliably interpret skills within a 1–3 second window, without needing an observation of entire training trial.

Conclusion

This study highlights the potential of deep architectures for efficient online skill assessment in modern surgical training.

     

FUN-SIS: A Fully UNsupervised approach for Surgical Instrument Segmentation

Automatic surgical instrument segmentation of endoscopic images is a crucial building block of many computer-assistance applications for minimally invasive surgery. So far, state-of-the-art approaches completely rely on the availability of a ground-truth supervision signal, obtained via manual annotation, thus expensive to collect at large scale. In this paper, we present FUN-SIS, a Fully-UNsupervised approach for binary Surgical Instrument Segmentation. FUN-SIS trains a per-frame segmentation model on completely unlabelled endoscopic videos, by solely relying on implicit motion information and instrument shape-priors. We define shape-priors as realistic segmentation masks of the instruments, not necessarily coming from the same dataset/domain as the videos. The shape-priors can be collected in various and convenient ways, such as recycling existing annotations from other datasets. We leverage them as part of a novel generative-adversarial approach, allowing to perform unsupervised instrument segmentation of optical-flow images during training. We then use the obtained instrument masks as pseudo-labels in order to train a per-frame segmentation model; to this aim, we develop a learning-from-noisy-labels architecture, designed to extract a clean supervision signal from these pseudo-labels, leveraging their peculiar noise properties. We validate the proposed contributions on three surgical datasets, including the MICCAI 2017 EndoVis Robotic Instrument Segmentation Challenge dataset. The obtained fully-unsupervised results for surgical instrument segmentation are almost on par with the ones of fully-supervised state-of-the-art approaches. This suggests the tremendous potential of the proposed method to leverage the great amount of unlabelled data produced in the context of minimally invasive surgery.     

Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the HeiChole benchmark

PurposeSurgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase the safety of the operation through context-sensitive warnings and semi-autonomous robotic assistance or improve training of surgeons via data-driven feedback. In surgical workflow analysis up to 91% average precision has been reported for phase recognition on an open data single-center video dataset. In this work we investigated the generalizability of phase recognition algorithms in a multicenter setting including more difficult recognition tasks such as surgical action and surgical skill.MethodsTo achieve this goal, a dataset with 33 laparoscopic cholecystectomy videos from three surgical centers with a total operation time of 22 h was created. Labels included framewise annotation of seven surgical phases with 250 phase transitions, 5514 occurences of four surgical actions, 6980 occurences of 21 surgical instruments from seven instrument categories and 495 skill classifications in five skill dimensions. The dataset was used in the 2019 international Endoscopic Vision challenge, sub-challenge for surgical workflow and skill analysis. Here, 12 research teams trained and submitted their machine learning algorithms for recognition of phase, action, instrument and/or skill assessment.ResultsF1-scores were achieved for phase recognition between 23.9% and 67.7% (n = 9 teams), for instrument presence detection between 38.5% and 63.8% (n = 8 teams), but for action recognition only between 21.8% and 23.3% (n = 5 teams). The average absolute error for skill assessment was 0.78 (n = 1 team).ConclusionSurgical workflow and skill analysis are promising technologies to support the surgical team, but there is still room for improvement, as shown by our comparison of machine learning algorithms. This novel HeiChole benchmark can be used for comparable evaluation and validation of future work. In future studies, it is of utmost importance to create more open, high-quality datasets in order to allow the development of artificial intelligence and cognitive robotics in surgery.     

胸骨抬举法辅助经剑突下胸腔镜微创手术治疗胸腺病变的初步尝试

目的:探讨胸骨抬举法辅助经剑突下胸腔镜微创手术治疗胸腺病变的临床疗效。方法:2016年3月至2016年7月对连续24例胸腺病变患者采用经剑突下胸腔镜微创切除术,其中后12例加用术中胸骨抬举法辅助(研究组)。比较两组患者围手术期相关临床指标。结果:研究组患者手术时间少于对照组[(80.3±14.9)min vs(96.2±17.3)min],差异有统计学意义(P0.01)。两组患者在出血量、中转开胸率、并发症、术后住院时间和术后疼痛评分方面差异无统计学意义。结论:胸骨抬举法辅助经剑突下胸腔镜治疗胸腺疾病简便经济、安全可靠、疗效满意,值得临床推广。     

Semi-supervised learning with progressive unlabeled data excavation for label-efficient surgical workflow recognition

Surgical workflow recognition is a fundamental task in computer-assisted surgery and a key component of various applications in operating rooms. Existing deep learning models have achieved promising results for surgical workflow recognition, heavily relying on a large amount of annotated videos. However, obtaining annotation is time-consuming and requires the domain knowledge of surgeons. In this paper, we propose a novel two-stage Semi-Supervised Learning method for label-efficient Surgical workflow recognition, named as SurgSSL. Our proposed SurgSSL progressively leverages the inherent knowledge held in the unlabeled data to a larger extent: from implicit unlabeled data excavation via motion knowledge excavation, to explicit unlabeled data excavation via pre-knowledge pseudo labeling. Specifically, we first propose a novel intra-sequence Visual and Temporal Dynamic Consistency (VTDC) scheme for implicit excavation. It enforces prediction consistency of the same data under perturbations in both spatial and temporal spaces, encouraging model to capture rich motion knowledge. We further perform explicit excavation by optimizing the model towards our pre-knowledge pseudo label. It is naturally generated by the VTDC regularized model with prior knowledge of unlabeled data encoded, and demonstrates superior reliability for model supervision compared with the label generated by existing methods. We extensively evaluate our method on two public surgical datasets of Cholec80 and M2CAI challenge dataset. Our method surpasses the state-of-the-art semi-supervised methods by a large margin, e.g., improving 10.5% Accuracy under the severest annotation regime of M2CAI dataset. Using only 50% labeled videos on Cholec80, our approach achieves competitive performance compared with full-data training method.