Dataset Information

Deep-learned placental vessel segmentation for intraoperative video enhancement in fetoscopic surgery.

ABSTRACT: INTRODUCTION:Twin-to-twin transfusion syndrome (TTTS) is a potentially lethal condition that affects pregnancies in which twins share a single placenta. The definitive treatment for TTTS is fetoscopic laser photocoagulation, a procedure in which placental blood vessels are selectively cauterized. Challenges in this procedure include difficulty in quickly identifying placental blood vessels due to the many artifacts in the endoscopic video that the surgeon uses for navigation. We propose using deep-learned segmentations of blood vessels to create masks that can be recombined with the original fetoscopic video frame in such a way that the location of placental blood vessels is discernable at a glance. METHODS:In a process approved by an institutional review board, intraoperative videos were acquired from ten fetoscopic laser photocoagulation surgeries performed at Yale New Haven Hospital. A total of 345 video frames were selected from these videos at regularly spaced time intervals. The video frames were segmented once by an expert human rater (a clinician) and once by a novice, but trained human rater (an undergraduate student). The segmentations were used to train a fully convolutional neural network of 25 layers. RESULTS:The neural network was able to produce segmentations with a high similarity to ground truth segmentations produced by an expert human rater (sensitivity?=?92.15%?±?10.69%) and produced segmentations that were significantly more accurate than those produced by a novice human rater (sensitivity?=?56.87%?±?21.64%; p?

SUBMITTER: Sadda P

PROVIDER: S-EPMC6438174 | biostudies-literature | 2019 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep-learned placental vessel segmentation for intraoperative video enhancement in fetoscopic surgery.

Sadda Praneeth P Imamoglu Metehan M Dombrowski Michael M Papademetris Xenophon X Bahtiyar Mert O MO Onofrey John J

International journal of computer assisted radiology and surgery 20181127 2

<h4>Introduction</h4>Twin-to-twin transfusion syndrome (TTTS) is a potentially lethal condition that affects pregnancies in which twins share a single placenta. The definitive treatment for TTTS is fetoscopic laser photocoagulation, a procedure in which placental blood vessels are selectively cauterized. Challenges in this procedure include difficulty in quickly identifying placental blood vessels due to the many artifacts in the endoscopic video that the surgeon uses for navigation. We propose ...[more]

PMID: 30484115

Similar Datasets

Project description:Objective: Reliable quantification of white matter hyperintensities (WHMs) resulting from cerebral small vessel diseases (CSVD) is essential for understanding their clinical impact. We aim to develop and clinically validate a deep learning system for automatic segmentation of CSVD-WMH from fluid-attenuated inversion recovery (FLAIR) imaging using large multicenter data. Method: A FLAIR imaging dataset of 1,156 patients diagnosed with CSVD associated WMH (median age, 54 years; 653 males) obtained between September 2018 and September 2019 from Beijing Tiantan Hospital was retrospectively analyzed in this study. Locations of CSVD-WMH on the FLAIR scans were manually marked by two experienced neurologists. Using the manually labeled data of 996 patients (development set), a U-shaped novel 2D convolutional neural network (CNN) architecture was trained for automatic segmentation of CSVD-WMH. The segmentation performance of the network was evaluated with per pixel and lesion level dice scores using an independent internal test set (n = 160) and a multi-center external test set (n = 90, three medical centers). The clinical suitability of the segmentation results, classified as acceptable, acceptable with minor revision, acceptable with major revision, and not acceptable, was analyzed by three independent neuroradiologists. The inter-neuroradiologists agreement rate was assessed by the Kendall-W test. Results: On the internal and external test sets, the proposed CNN architecture achieved per pixel and lesion level dice scores of 0.72 (external test set), and they were significantly better than the state-of-the-art deep learning architectures proposed for WMH segmentation. In the clinical evaluation, neuroradiologists observed the segmentation results for 95% of the patients were acceptable or acceptable with a minor revision. Conclusions: A deep learning system can be used for automated, objective, and clinically meaningful segmentation of CSVD-WMH with high accuracy.

Project description:To study causes and implications of intraoperative conversion to thoracotomy during video-assisted thoracoscopic surgery (VATS) lobectomy.We performed an institutional review of patients undergoing lobectomy for known or suspected lung cancer with root cause analysis of every conversion from VATS to open thoracotomy.Between 2004 and 2012, 1227 patients underwent lobectomy. Of these, 517 procedures (42%) were completed via VATS, 87 procedures (7%) were converted to open procedures, and 623 procedures (51%) were performed via planned thoracotomy. Patients undergoing thoracotomy were younger and had a higher incidence of prior lung cancers. Planned thoracotomy and conversion group patients had higher clinical T stage than patients in the VATS group, whereas the planned thoracotomy group had higher pathologic stage than patients in the other groups. Postoperative complications were more frequent in patients in the conversion group (46%) than in the VATS group (23%; P < .001), but similar to the open group (42%; P = .56). Validating a previous classification of causes for conversion, 22 out of 87 conversions (25%) were due to vascular causes, 56 conversions (64%) were for anatomy (eg, adhesions or tumor size), and 8 conversions (9%) were the result of lymph nodes. No specific imaging variables predicted conversion. Within the conversion groups, emergent (20 out of 87; 23%) and planned (67 out of 87; 77%) conversion groups were similar in patient and tumor characteristics and incidence of perioperative morbidity. The conversion rate for VATS lobectomy dropped from 21 out of 74 (28%), to 29 out of 194 (15%), to 37 out of 336 (11%) (P < .001) over 3-year intervals. Over the same periods, the proportion of operations started via VATS increased significantly.With increasing experience, a higher proportion of lobectomy operations can be completed thoracoscopically. VATS should be strongly considered as the initial approach for the majority of patients undergoing lobectomy.

Dataset Information

Deep-learned placental vessel segmentation for intraoperative video enhancement in fetoscopic surgery.

Publications

Deep-learned placental vessel segmentation for intraoperative video enhancement in fetoscopic surgery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets