Image-Based Smoke Detection in Laparoscopic Videos

Leibetseder, Andreas; Primus, Manfred Jürgen; Petscharnig, Stefan; Schoeffmann, Klaus

doi:10.1007/978-3-319-67543-5_7

Cited by 13 publications

(14 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accuracy F1-Score RGB 0.60 0.60 IMSHARP 0.58 0.58 BF [40] 0.60 0.59 GF [14] 0.60 0.59 WLS [12] 0 Comparison with the saturation histogram based classification methodologies. We compare FC AVG with the saturation histogram based classification methodologies Saturation Analysis (SAN) and Saturation Peak Analysis (SPA) [9,30]. SAN and SPA codes are provided by [9,30] 6 .…”

Section: Methodsmentioning

confidence: 99%

“…The performance of their CNN models on Cholec80 [36] dataset are very similar to that of SAN or SPA. While DL shows its promising performance on smoke classification [9,30], to the best of our knowledge there is no work that does image enhancement for smoke classification. Therefore, we limit to comparisons with the non deep learning based methods only in our experimental section.…”

Section: Introductionmentioning

confidence: 98%

“…biological particles, which may be harmful for surgeons and patients [4][5][6]. Therefore, it is of vital importance to remove the smoke by computer vision algorithms [7] and by smoke evacuation techniques [8,9]. In order to employ a desmoking technique, as a prior knowledge it is essential to know if the image contains smoke or not.…”

Section: Introductionmentioning

confidence: 99%

“…In the medical imaging community, researchers have shown that the formation of smoke and the lighting condition for laparoscopic surgery images are very different, which limits the "in the wild" smoke detection methodologies applicability in medical domain [9,30]. Recently, Chou et al [31] explore temporal differences information that is motion blur and block analysis between current and previous frames as features for smoke detection.…”

Section: Introductionmentioning

confidence: 99%

“…They extract different features from optical flow estimated by Kanade-Lucas-Tomasi (KLT) algorithm [33], and then a support vector machine (SVM) is trained to classify each shot. Leibetseder et al in [9,30] propose saturation histogram based classification methodologies Saturation Peak Analysis (SPA) and Saturation Analysis (SAN) and deep learning (DL) techniques. In [30], Leibetseder et al train three variants of convolutional neural network (CNN) models: Google-LeNet [34] trained with RGB images (GLN RGB) and saturation channels only (GLN SAT), and a modified AlexNet [35] trained on RGB images (ALEX RGB).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Can Image Enhancement be Beneficial to Find Smoke Images in Laparoscopic Surgery?

Wang

Sharma

Fan

et al. 2018

cic

View full text Add to dashboard Cite

Laparoscopic surgery has a limited field of view. Laser ablation in a laproscopic surgery causes smoke, which inevitably influences the surgeon's visibility. Therefore, it is of vital importance to remove the smoke, such that a clear visualization is possible. In order to employ a desmoking technique, one needs to know beforehand if the image contains smoke or not, to this date, there exists no accurate method that could classify the smoke/non-smoke images completely. In this work, we propose a new enhancement method which enhances the informative details in the RGB images for discrimination of smoke/non-smoke images. Our proposed method utilizes weighted least squares optimization framework (WLS). For feature extraction, we use statistical features based on bivariate histogram distribution of gradient magnitude (GM) and Laplacian of Gaussian (LoG). We then train a SVM classifier with binary smoke/non-smoke classification task. We demonstrate the effectiveness of our method on Cholec80 dataset. Experiments using our proposed enhancement method show promising results with improvements of 4% in accuracy and 4% in F1-Score over the baseline performance of RGB images. In addition, our approach improves over the saturation histogram based classification methodologies Saturation Analysis (SAN) and Saturation Peak Analysis (SPA) by 1/5% and 1/6% in accuracy/F1-Score metrics.We can employ our enhancement method in replacement of RGB images for classifier training e.g., CNN architectures, which in turn can lead to more accurate classification. Code will be released for public use.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Can Image Enhancement be Beneficial to Find Smoke Images in Laparoscopic Surgery?

Wang

Sharma

Fan

et al. 2018

cic

View full text Add to dashboard Cite

show abstract

Intraoperative surgery room management: A deep learning perspective

Tanzi

Piazzolla

Vezzetti

2020

Robotics Computer Surgery

View full text Add to dashboard Cite

Purpose: The current study aimed to systematically review the literature addressing the use of deep learning (DL) methods in intraoperative surgery applications, focusing on the data collection, the objectives of these tools and, more technically, the DLbased paradigms utilized. Methods: A literature search with classic databases was performed: we identified, with the use of specific keywords, a total of 996 papers. Among them, we selected 52 for effective analysis, focusing on articles published after January 2015. Results: The preliminary results of the implementation of DL in clinical setting are encouraging. Almost all the surgery sub-fields have seen the advent of artificial intelligence (AI) applications and the results outperformed the previous techniques in the majority of the cases. From these results, a conceptualization of an intelligent operating room (IOR) is also presented. Conclusion: This evaluation outlined how AI and, in particular, DL are revolutionizing the surgery field, with numerous applications, such as context detection and room management. This process is evolving years by years into the realization of an IOR, equipped with technologies perfectly suited to drastically improve the surgical workflow.

show abstract