2017 Robotic Instrument Segmentation Challenge

Allan, Max; Shvets, A. A.; Kurmann, Thomas; Zhang, Zichen; Duggal, Rahul; Su, Yun-Hsuan; Rieke, Nicola; Laina, Iro; Kalavakonda, Niveditha; Bodenstedt, Sebastian; Herrera, L.; Li, Wenqi; Iglovikov, Vladimir I.; Luo, Han; Yang, Jian; Stoyanov, Danail; Maier‐Hein, Klaus H.; Speidel, Stefanie; Azizian, Mahdi

doi:10.48550/arxiv.1902.06426

Cited by 51 publications

(121 citation statements)

References 0 publications

Supporting

Mentioning

121

Contrasting

Order By: Relevance

“…For scanpath, compare the top rank and all average instruments priority between ground-truth and prediction. Overall evaluation is done by using cross-validation and testing dataset of MICCAI endoscopic vision challenge [2].…”

Section: Resultsmentioning

confidence: 99%

“…Subsequently, a holistically nested CNN approach ToolNet [19], FCN with affine transformation, joint CNN, and recurrent neural network (RNN) are utilized to track the surgical instrument. Nonetheless, the performance of these models is not satisfactory, especially for the instrument type segmentation [2]. Moreover, with less computational resources, achieving multiple tasks from a single model is more competent.…”

Section: A Related Workmentioning

confidence: 99%

“…This work is done using the robotic instrument segmentation dataset of MICCAI endoscopic vision challenge [2]. This dataset contains 10 sequences recorded with a resolution of 1920 x 1080 using da Vinci surgical systems [1].…”

Section: A Datasetmentioning

confidence: 99%

“…of Instrumentation and Control Engineering, NIT Trichy, India C. M. Lim is with Dept. of Otolaryngology, Singapore General Hospital, Singapore of the reduction of instrument size and actuation mechanisms, complicated surgical environment with shadows, adverse lighting, partial occlusion, and smoke [2]. Therefore, enabling visual perception based endoscope automation while tracking and segmentation of the instruments in robotic surgery is crucial to enhance surgical outcomes.…”

Section: Introductionmentioning

confidence: 99%

“…By considering these factors, we propose a spatio-temporal multi-task learning (ST-MTL) model for surgical instrument segmentation and saliency detection in this work. Task-aware temporal attention map and corresponding scanpath are generated on the MICCAI 2017 surgical instrument segmentation dataset [2] to train our ST-MTL model.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

ST-MTL: Spatio-Temporal multitask learning model to predict scanpath while tracking instruments in robotic surgery

Islam

Lim

et al. 2021

Medical Image Analysis

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: A Related Workmentioning

confidence: 99%

Section: A Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

ST-MTL: Spatio-Temporal multitask learning model to predict scanpath while tracking instruments in robotic surgery

Islam

Lim

et al. 2021

Medical Image Analysis

View full text Add to dashboard Cite

Automated detection of left ventricle in arterial input function images for inline perfusion mapping using deep learning: A study of 15,000 patients

Xue

Tseng

Knott

et al. 2020

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose Quantification of myocardial perfusion has the potential to improve the detection of regional and global flow reduction. Significant effort has been made to automate the workflow, where one essential step is the arterial input function (AIF) extraction. Failure to accurately identify the left ventricle (LV) prevents AIF estimation required for quantification, therefore high detection accuracy is required. This study presents a robust LV detection method using the convolutional neural network (CNN). Methods CNN models were trained by assembling 25,027 scans (N = 12,984 patients) from three hospitals, seven scanners. Performance was evaluated using a hold‐out test set of 5721 scans (N = 2805 patients). Model inputs were a time series of AIF images (2D+T). Two variations were investigated: (1) two classes (2CS) for background and foreground (LV mask), and (2) three classes (3CS) for background, LV, and RV. The final model was deployed on MRI scanners using the Gadgetron reconstruction software framework. Results Model loading on the MRI scanner took ~340 ms and applying the model took ~180 ms. The 3CS model successfully detected the LV in 99.98% of all test cases (1 failure out of 5721). The mean Dice ratio for 3CS was 0.87 ± 0.08 with 92.0% of all cases having Dice >0.75. The 2CS model gave a lower Dice ratio of 0.82 ± 0.22 (P < 1e−5). There was no significant difference in foot‐time, peak‐time, first‐pass duration, peak value, and area‐under‐curve (P > .2) comparing automatically extracted AIF signals with signals from manually drawn contours. Conclusions A CNN‐based solution to detect the LV blood pool from the arterial input function image series was developed, validated, and deployed. A high LV detection accuracy of 99.98% was achieved.

show abstract

Unpaired deep adversarial learning for multi‐class segmentation of instruments in robot‐assisted surgical videos

Nema

Vachhani

2023

Robotics Computer Surgery

View full text Add to dashboard Cite

Purpose Image segmentation of instruments in the raw surgical videos is a critical component of intraoperative assistance softwares. Challenges include addressing rendered overlays occluding the instrument while providing pivotal input to instrument tracking frameworks and, train the segmentation process with limited labelled data available from surgical videos. Method The proposed adversarial network, InstruSegNet uses unpaired training (eliminating need for massive paired data) for automated multi‐class surgical instrument segmentation in raw surgical videos with complex backgrounds. The proposed method is applied for single/multiple robotic and rigid instruments and optimised on least square Generative Adversarial Networks loss. Result Promising validation has been conducted on the publicly available dataset. Proposed approach for multi‐class segmentation of robotic and rigid instruments meets outstanding performance in terms of accuracy and surpasses the existing methods. Application This work facilitates segmenting instrument information without manual interventions from raw videos providing means to code surgeon's actions for developing intelligent assistance software.

show abstract

2017 Robotic Instrument Segmentation Challenge

Cited by 51 publications

References 0 publications

ST-MTL: Spatio-Temporal multitask learning model to predict scanpath while tracking instruments in robotic surgery

ST-MTL: Spatio-Temporal multitask learning model to predict scanpath while tracking instruments in robotic surgery

Automated detection of left ventricle in arterial input function images for inline perfusion mapping using deep learning: A study of 15,000 patients

Unpaired deep adversarial learning for multi‐class segmentation of instruments in robot‐assisted surgical videos

Contact Info

Product

Resources

About