Digital Image Analysis with Fully Connected Convolutional Neural Network to Facilitate Hysteroscopic Fibroid Resection

Török, Péter; Harangi, Balázs

doi:10.1159/000490563

Cited by 9 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current use of deep learning in hysteroscopic images is mainly focused on the classification of endometrial cancer, with a few studies on endometrial fibroids [ 16 , 17 ]. For example, Török et al used a fully convolutional CNN to identify the plane between myoma and the normal myometrium, achieving a pixel-wise segmentation accuracy of 86.19% after training the network on 13 cases of video data for 140 epochs [ 22 ]. Deep learning research on uterine lesions has mainly focused on MRIs and ultrasound images.…”

Section: Discussionmentioning

confidence: 99%

Automated Detection of Endometrial Polyps from Hysteroscopic Videos Using Deep Learning

Zhao

Yuan

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Endometrial polyps are common gynecological lesions. The standard treatment for this condition is hysteroscopic polypectomy. However, this procedure may be accompanied by misdetection of endometrial polyps. To improve the diagnostic accuracy and reduce the risk of misdetection, a deep learning model based on YOLOX is proposed to detect endometrial polyps in real time. Group normalization is employed to improve its performance with large hysteroscopic images. In addition, we propose a video adjacent-frame association algorithm to address the problem of unstable polyp detection. Our proposed model was trained on a dataset of 11,839 images from 323 cases provided by a hospital and was tested on two datasets of 431 cases from two hospitals. The results show that the lesion-based sensitivity of the model reached 100% and 92.0% for the two test sets, compared with 95.83% and 77.33%, respectively, for the original YOLOX model. This demonstrates that the improved model may be used effectively as a diagnostic tool during clinical hysteroscopic procedures to reduce the risk of missing endometrial polyps.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated Detection of Endometrial Polyps from Hysteroscopic Videos Using Deep Learning

Zhao

Yuan

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…An important help for better assessing the pseudocapsule could be brought by computer-aided imaging. A recent study of Török et al [6] showed a very good accuracy, of more than 86%, using fully convolutional neural networking and highresolution endoscopic image, which is promising for faster and safer future resections.…”

Section: Limits For Office Hysteroscopic Myomectomymentioning

confidence: 99%

New Hysteroscopic Approaches to Uterine Fibroids

Socolov¹,

Păvăleanu²,

Socolov³

et al. 2020

Leiomyoma

View full text Add to dashboard Cite

The hysteroscopic myomectomy is a very important application of the gynecologic endoscopy, as it allows minimal invasive removal of the type 0, 1, and 2 fibroids with minimal damage to the uterine wall. In the last decade, new developments of this method allowed an even less invasive approach, with possibility of ambulatory procedure. We discuss the importance of these new developments, based very much on the pseudocapsule of the myoma, and analyze the literature data regarding the outcome. The cold loop resection is a technique that could be used in type 1 and type 2 myomas, with less complications and limitations than the classical electrical resectoscope. Another development, more useful for type 0 and 1 myoma, is the hysteroscopic morcellator, similar to the laparoscopic one, but providing a faster and safer procedure. We also update the complications of hysteroscopic myomectomy and their management, including long-term and obstetrical complications related to hysteroscopic myomectomy. In conclusion, new developments and studies show that hysteroscopic myomectomy has become a valid endoscopic technique ready to be used by many specialists.

show abstract

“…There exist datasets of labelled laparoscopy images for supervised learning based detection of surgical actions [12], surgical phases [21,19] and anatomical structures [12]. These datasets are procedure specific, namely cholecystectomy [21,12,19] and fibroid resection [20,12]. There exist datasets for semantic segmentation of robotic surgical instruments, stereo correspondence and reconstruction in endoscopy [10].…”

Section: Related Workmentioning

confidence: 99%

“…The third missing part for OC2D is a dataset, specifically in laparoscopy. Existing datasets [21,12,19,20] do not comprise labels for anatomical structures and the type of occlusion. We propose a dataset of 3818 carefully labelled laparoscopy images of the uterus meant to address gynecologic surgery.…”

Section: Introductionmentioning

confidence: 99%

Detecting the occluding contours of the uterus to automatise augmented laparoscopy: score, loss, dataset, evaluation and user study

et al. 2020

View full text Add to dashboard Cite

The registration of a preoperative 3D model, reconstructed for example from MRI, to intraoperative laparoscopy 2D images, is the main challenge to achieve augmented reality in laparoscopy. The current systems have a major limitation: they require that the surgeon manually marks the occluding contours during surgery. This requires the surgeon to fully comprehend the nontrivial concept of occluding contours and surgeon time, directly impacting acceptance and usability. To overcome this limitation, we propose a complete framework for object-class occluding contour detection (OC2D), with application to uterus surgery. Methods. Our first contribution is a new distance-based evaluation score complying with all the relevant performance criteria. Our second contribution is a loss function combining cross-entropy and two new penalties designed to boost 1-pixel thickness responses. This allows us to train a U-Net end-to-end, outperforming all competing methods, which tends to produce thick responses. Our third contribution is a dataset of 3818 carefully labelled laparoscopy images of the uterus, which was used to train and evaluate our detector. Results. Evaluation shows that the proposed detector has a similar false negative rate to existing methods but substantially reduces both false positive rate and response thickness. Finally, we ran a user-study to evaluate the impact of OC2D against manually marked occluding contours in augmented laparoscopy. We used 10 recorded gynecologic laparoscopies and involved 5 surgeons. Using OC2D led to a reduction of 3 minutes and 53 seconds in surgeon time without sacrificing registration accuracy. Conclusions. We provide a new set of criteria and a distance-based measure to evaluate an OC2D method. We propose an OC2D method which outperforms the state of the art methods. The results obtained from the user study indicate that fully automatic augmented laparoscopy is feasible.

show abstract

Digital Image Analysis with Fully Connected Convolutional Neural Network to Facilitate Hysteroscopic Fibroid Resection

Cited by 9 publications

References 11 publications

Automated Detection of Endometrial Polyps from Hysteroscopic Videos Using Deep Learning

Automated Detection of Endometrial Polyps from Hysteroscopic Videos Using Deep Learning

New Hysteroscopic Approaches to Uterine Fibroids

Detecting the occluding contours of the uterus to automatise augmented laparoscopy: score, loss, dataset, evaluation and user study

Contact Info

Product

Resources

About