Purpose
A profound education of novice surgeons is crucial to ensure that surgical interventions are effective and safe. One important aspect is the teaching of technical skills for minimally ...invasive or robot-assisted procedures. This includes the objective and preferably automatic assessment of surgical skill. Recent studies presented good results for automatic, objective skill evaluation by collecting and analyzing motion data such as trajectories of surgical instruments. However, obtaining the motion data generally requires additional equipment for instrument tracking or the availability of a robotic surgery system to capture kinematic data. In contrast, we investigate a method for automatic, objective skill assessment that requires video data only. This has the advantage that video can be collected effortlessly during minimally invasive and robot-assisted training scenarios.
Methods
Our method builds on recent advances in deep learning-based video classification. Specifically, we propose to use an inflated 3D ConvNet to classify snippets, i.e., stacks of a few consecutive frames, extracted from surgical video. The network is extended into a temporal segment network during training.
Results
We evaluate the method on the publicly available JIGSAWS dataset, which consists of recordings of basic robot-assisted surgery tasks performed on a dry lab bench-top model. Our approach achieves high skill classification accuracies ranging from 95.1 to 100.0%.
Conclusions
Our results demonstrate the feasibility of deep learning-based assessment of technical skill from surgical video. Notably, the 3D ConvNet is able to learn meaningful patterns directly from the data, alleviating the need for manual feature engineering. Further evaluation will require more annotated data for training and testing.
International challenges have become the standard for validation of biomedical image analysis methods. Given their scientific impact, it is surprising that a critical analysis of common practices ...related to the organization of challenges has not yet been performed. In this paper, we present a comprehensive analysis of biomedical image analysis challenges conducted up to now. We demonstrate the importance of challenges and show that the lack of quality control has critical consequences. First, reproducibility and interpretation of the results is often hampered as only a fraction of relevant information is typically provided. Second, the rank of an algorithm is generally not robust to a number of variables such as the test data used for validation, the ranking scheme applied and the observers that make the reference annotations. To overcome these problems, we recommend best practice guidelines and define open research questions to be addressed in the future.
Colonoscopy is the gold standard for colon cancer screening though some polyps are still missed, thus preventing early disease detection and treatment. Several computational systems have been ...proposed to assist polyp detection during colonoscopy but so far without consistent evaluation. The lack of publicly available annotated databases has made it difficult to compare methods and to assess if they achieve performance levels acceptable for clinical use. The Automatic Polyp Detection sub-challenge, conducted as part of the Endoscopic Vision Challenge (http://endovis.grand-challenge.org) at the international conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2015, was an effort to address this need. In this paper, we report the results of this comparative evaluation of polyp detection methods, as well as describe additional experiments to further explore differences between methods. We define performance metrics and provide evaluation databases that allow comparison of multiple methodologies. Results show that convolutional neural networks are the state of the art. Nevertheless, it is also demonstrated that combining different methodologies can lead to an improved overall performance.
Recent technological advances have made Virtual Reality (VR) attractive in both research and real world applications such as training, rehabilitation, and gaming. Although these other fields ...benefited from VR technology, it remains unclear whether VR contributes to better spatial understanding and training in the context of surgical planning. In this study, we evaluated the use of VR by comparing the recall of spatial information in two learning conditions: a head-mounted display (HMD) and a desktop screen (DT). Specifically, we explored (a) a scene understanding and then (b) a direction estimation task using two 3D models (i.e., a liver and a pyramid). In the scene understanding task, participants had to navigate the rendered the 3D models by means of rotation, zoom and transparency in order to substantially identify the spatial relationships among its internal objects. In the subsequent direction estimation task, participants had to point at a previously identified target object, i.e., internal sphere, on a materialized 3D-printed version of the model using a tracked pointing tool. Results showed that the learning condition (HMD or DT) did not influence participants' memory and confidence ratings of the models. In contrast, the model type, that is, whether the model to be recalled was a liver or a pyramid significantly affected participants' memory about the internal structure of the model. Furthermore, localizing the internal position of the target sphere was also unaffected by participants' previous experience of the model via HMD or DT. Overall, results provide novel insights on the use of VR in a surgical planning scenario and have paramount implications in medical learning by shedding light on the mental model we make to recall spatial structures.
Clinically relevant postoperative pancreatic fistula (CR-POPF) can significantly affect the treatment course and outcome in pancreatic cancer patients. Preoperative prediction of CR-POPF can aid the ...surgical decision-making process and lead to better perioperative management of patients. In this retrospective study of 108 pancreatic head resection patients, we present risk models for the prediction of CR-POPF that use combinations of preoperative computed tomography (CT)-based radiomic features, mesh-based volumes of annotated intra- and peripancreatic structures and preoperative clinical data. The risk signatures were evaluated and analysed in detail by visualising feature expression maps and by comparing significant features to the established CR-POPF risk measures. Out of the risk models that were developed in this study, the combined radiomic and clinical signature performed best with an average area under receiver operating characteristic curve (AUC) of 0.86 and a balanced accuracy score of 0.76 on validation data. The following pre-operative features showed significant correlation with outcome in this signature (Formula: see text) - texture and morphology of the healthy pancreatic segment, intensity volume histogram-based feature of the pancreatic duct segment, morphology of the combined segment, and BMI. The predictions of this pre-operative signature showed strong correlation (Spearman correlation co-efficient, Formula: see text) with the intraoperative updated alternative fistula risk score (ua-FRS), which is the clinical gold standard for intraoperative CR-POPF risk stratification. These results indicate that the proposed combined radiomic and clinical signature developed solely based on preoperatively available clinical and routine imaging data can perform on par with the current state-of-the-art intraoperative models for CR-POPF risk stratification.
Clinically relevant postoperative pancreatic fistula (CR-POPF) is a common severe surgical complication after pancreatic surgery. Current risk stratification systems mostly rely on intraoperatively ...assessed factors like manually determined gland texture or blood loss. We developed a preoperatively available image-based risk score predicting CR-POPF as a complication of pancreatic head resection. Frequency of CR-POPF and occurrence of salvage completion pancreatectomy during the hospital stay were associated with an intraoperative surgical (sFRS) and image-based preoperative CT-based (rFRS) fistula risk score, both considering pancreatic gland texture, pancreatic duct diameter and pathology, in 195 patients undergoing pancreatic head resection. Based on its association with fistula-related outcome, radiologically estimated pancreatic remnant volume was included in a preoperative (preFRS) score for POPF risk stratification. Intraoperatively assessed pancreatic duct diameter (p < 0.001), gland texture (p < 0.001) and high-risk pathology (p < 0.001) as well as radiographically determined pancreatic duct diameter (p < 0.001), gland texture (p < 0.001), high-risk pathology (p = 0.001), and estimated pancreatic remnant volume (p < 0.001) correlated with the risk of CR-POPF development. PreFRS predicted the risk of CR-POPF development (AUC = 0.83) and correlated with the risk of rescue completion pancreatectomy. In summary, preFRS facilitates preoperative POPF risk stratification in patients undergoing pancreatic head resection, enabling individualized therapeutic approaches and optimized perioperative management.
Object detection and image segmentation of regions of interest provide the foundation for numerous pipelines across disciplines. Robust and accurate computer vision methods are needed to properly ...solve image-based tasks. Multiple algorithms have been developed to solely detect edges in images. Constrained to the problem of creating a thin, one-pixel wide, edge from a predicted object boundary, we require an algorithm that removes pixels while preserving the topology. Thanks to skeletonize algorithms, an object boundary is transformed into an edge; contrasting uncertainty with exact positions.
To extract edges from boundaries generated from different algorithms, we present a computational pipeline that relies on: a novel skeletonize algorithm, a non-exhaustive discrete parameter search to find the optimal parameter combination of a specific post-processing pipeline, and an extensive evaluation using three data sets from the medical and natural image domains (kidney boundaries, NYU-Depth V2, BSDS 500). While the skeletonize algorithm was compared to classical topological skeletons, the validity of our post-processing algorithm was evaluated by integrating the original post-processing methods from six different works.
Using the state of the art metrics, precision and recall based Signed Distance Error (SDE) and the Intersection over Union bounding box (IOU-box), our results indicate that the SDE metric for these edges is improved up to 2.3 times.
Our work provides guidance for parameter tuning and algorithm selection in the post-processing of predicted object boundaries.
Purpose
The course of surgical procedures is often unpredictable, making it difficult to estimate the duration of procedures beforehand. This uncertainty makes scheduling surgical procedures a ...difficult task. A context-aware method that analyses the workflow of an intervention online and automatically predicts the remaining duration would alleviate these problems. As basis for such an estimate, information regarding the current state of the intervention is a requirement.
Methods
Today, the operating room contains a diverse range of sensors. During laparoscopic interventions, the endoscopic video stream is an ideal source of such information. Extracting quantitative information from the video is challenging though, due to its high dimensionality. Other surgical devices (e.g., insufflator, lights, etc.) provide data streams which are, in contrast to the video stream, more compact and easier to quantify. Though whether such streams offer sufficient information for estimating the duration of surgery is uncertain. In this paper, we propose and compare methods, based on convolutional neural networks, for continuously predicting the duration of laparoscopic interventions based on unlabeled data, such as from endoscopic image and surgical device streams.
Results
The methods are evaluated on 80 recorded laparoscopic interventions of various types, for which surgical device data and the endoscopic video streams are available. Here the combined method performs best with an overall average error of 37% and an average halftime error of approximately 28%.
Conclusion
In this paper, we present, to our knowledge, the first approach for online procedure duration prediction using unlabeled endoscopic video data and surgical device data in a laparoscopic setting. Furthermore, we show that a method incorporating both vision and device data performs better than methods based only on vision, while methods only based on tool usage and surgical device data perform poorly, showing the importance of the visual channel.
Physics‐based shape matching for intraoperative image guidance Suwelack, Stefan; Röhl, Sebastian; Bodenstedt, Sebastian ...
Medical physics (Lancaster),
November 2014, 2014-Nov, 2014-11-00, 20141101, 2014-11-01, Letnik:
41, Številka:
11
Journal Article
Recenzirano
Purpose:
Soft‐tissue deformations can severely degrade the validity of preoperative planning data during computer assisted interventions. Intraoperative imaging such as stereo endoscopic, ...time‐of‐flight or, laser range scanner data can be used to compensate these movements. In this context, the intraoperative surface has to be matched to the preoperative model. The shape matching is especially challenging in the intraoperative setting due to noisy sensor data, only partially visible surfaces, ambiguous shape descriptors, and real‐time requirements.
Methods:
A novel physics‐based shape matching (PBSM) approach to register intraoperatively acquired surface meshes to preoperative planning data is proposed. The key idea of the method is to describe the nonrigid registration process as an electrostatic–elastic problem, where an elastic body (preoperative model) that is electrically charged slides into an oppositely charged rigid shape (intraoperative surface). It is shown that the corresponding energy functional can be efficiently solved using the finite element (FE) method. It is also demonstrated how PBSM can be combined with rigid registration schemes for robust nonrigid registration of arbitrarily aligned surfaces. Furthermore, it is shown how the approach can be combined with landmark based methods and outline its application to image guidance in laparoscopic interventions.
Results:
A profound analysis of the PBSM scheme based on in silico and phantom data is presented. Simulation studies on several liver models show that the approach is robust to the initial rigid registration and to parameter variations. The studies also reveal that the method achieves submillimeter registration accuracy (mean error between 0.32 and 0.46 mm). An unoptimized, single core implementation of the approach achieves near real‐time performance (2 TPS, 7–19 s total registration time). It outperforms established methods in terms of speed and accuracy. Furthermore, it is shown that the method is able to accurately match partial surfaces. Finally, a phantom experiment demonstrates how the method can be combined with stereo endoscopic imaging to provide nonrigid registration during laparoscopic interventions.
Conclusions:
The PBSM approach for surface matching is fast, robust, and accurate. As the technique is based on a preoperative volumetric FE model, it naturally recovers the position of volumetric structures (e.g., tumors and vessels). It cannot only be used to recover soft‐tissue deformations from intraoperative surface models but can also be combined with landmark data from volumetric imaging. In addition to applications in laparoscopic surgery, the method might prove useful in other areas that require soft‐tissue registration from sparse intraoperative sensor data (e.g., radiation therapy).
Image-based tracking of medical instruments is an integral part of surgical data science applications. Previous research has addressed the tasks of detecting, segmenting and tracking medical ...instruments based on laparoscopic video data. However, the proposed methods still tend to fail when applied to challenging images and do not generalize well to data they have not been trained on. This paper introduces the Heidelberg Colorectal (HeiCo) data set - the first publicly available data set enabling comprehensive benchmarking of medical instrument detection and segmentation algorithms with a specific emphasis on method robustness and generalization capabilities. Our data set comprises 30 laparoscopic videos and corresponding sensor data from medical devices in the operating room for three different types of laparoscopic surgery. Annotations include surgical phase labels for all video frames as well as information on instrument presence and corresponding instance-wise segmentation masks for surgical instruments (if any) in more than 10,000 individual frames. The data has successfully been used to organize international competitions within the Endoscopic Vision Challenges 2017 and 2019.