Effect of interpolation on specular reflections in texture‐based automatic colonic polyp detection

Kacmaz, Rukiye Nur; Yılmaz, Bülent; Aydın, Zafer

doi:10.1002/ima.22457

Cited by 7 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, through vaginal mirror screening for cervical cancer, specular reflection may change the appearance of the tissue and interfere with the performance of the segmentation of the cervical lesions area algorithm [ 5 , 6 , 7 ]. In colonoscopy imaging research, the detection of polyps and colorectal cancer may be affected by specular reflection [ 8 , 9 ]. Laryngeal cancer is detected by the laryngeal mirror, and the interference caused by specular reflection may cause the correct classification of laryngeal cancer tissue to fail [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

Specular Reflections Detection and Removal for Endoscopic Images Based on Brightness Classification

Nie

Chen

et al. 2023

Sensors

View full text Add to dashboard Cite

Specular Reflections often exist in the endoscopic image, which not only hurts many computer vision algorithms but also seriously interferes with the observation and judgment of the surgeon. The information behind the recovery specular reflection areas is a necessary pre-processing step in medical image analysis and application. The existing highlight detection method is usually only suitable for medium-brightness images. The existing highlight removal method is only applicable to images without large specular regions, when dealing with high-resolution medical images with complex texture information, not only does it have a poor recovery effect, but the algorithm operation efficiency is also low. To overcome these limitations, this paper proposes a specular reflection detection and removal method for endoscopic images based on brightness classification. It can effectively detect the specular regions in endoscopic images of different brightness and can improve the operating efficiency of the algorithm while restoring the texture structure information of the high-resolution image. In addition to achieving image brightness classification and enhancing the brightness component of low-brightness images, this method also includes two new steps: In the highlight detection phase, the adaptive threshold function that changes with the brightness of the image is used to detect absolute highlights. During the highlight recovery phase, the priority function of the exemplar-based image inpainting algorithm was modified to ensure reasonable and correct repairs. At the same time, local priority computing and adaptive local search strategies were used to improve algorithm efficiency and reduce error matching. The experimental results show that compared with the other state-of-the-art, our method shows better performance in terms of qualitative and quantitative evaluations, and the algorithm efficiency is greatly improved when processing high-resolution endoscopy images.

show abstract

Section: Introductionmentioning

confidence: 99%

Specular Reflections Detection and Removal for Endoscopic Images Based on Brightness Classification

Nie

Chen

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In contrast, learning-based methods obtains the prior knowledge directly from training samples [ 8 , 9 , 10 ] during learning process without assumption of the data distribution. In non-learning methods, linear interpolation methods such as bilinear and bi-cubic approaches [ 6 , 7 ] are often used for SR. These methods are easy in implementation, however, they usually yield solutions with overly smooth textures.…”

Section: Introductionmentioning

confidence: 99%

FNSAM: Image super-resolution using a feedback network with self-attention mechanism

Huang¹,

Wang²,

Li³

2023

THC

View full text Add to dashboard Cite

BACKGROUND: High-resolution (HR) magnetic resonance imaging (MRI) provides rich pathological information which is of great significance in diagnosis and treatment of brain lesions. However, obtaining HR brain MRI images comes at the cost of extending scan time and using sophisticated expensive instruments. OBJECTIVE: This study aims to reconstruct HR MRI images from low-resolution (LR) images by developing a deep learning based super-resolution (SR) method. METHODS: We propose a feedback network with self-attention mechanism (FNSAM) for SR reconstruction of brain MRI images. Specifically, a feedback network is built to correct shallow features by using a recurrent neural network (RNN) and the self-attention mechanism (SAM) is integrated into the feedback network for extraction of important information as the feedback signal, which promotes image hierarchy. RESULTS: Experimental results show that the proposed FNSAM obtains more reasonable SR reconstruction of brain MRI images both in peak signal to noise ratio (PSNR) and structural similarity (SSIM) than some state-of-the-arts. CONCLUSION: Our proposed method is suitable for SR reconstruction of MRI images.

show abstract

“…The considered tasks in this paper include sparse feature matching, optical flow, camera motion estimation, and stereo disparity calculation. While previous works have studied some of these tasks in isolation (Ali et al, 2021;Kaçmaz et al, 2020;, we assess the specular highlight processing pipeline for all tasks.…”

Section: Introductionmentioning

confidence: 99%

A Temporal Learning Approach to Inpainting Endoscopic Specularities and Its effect on Image Correspondence

Daher¹,

Júnior²,

Stoyanov³

2022

Proceedings of the 14th Hamlyn Symposium on Medical Robotics 2022

View full text Add to dashboard Cite

Computer vision has been utilized to analyze mini- mally invasive surgery videos and aid with polyp detec- tion, tool localization, and organ 3D modelling tasks. However, irregular light patterns such as saturation, specular highlights, or extreme contrasts occlude texture and hinder these tasks. In this work, specular highlights were removed and the occluded data was reconstructed. To do that, an unsupervised temporal generative ad- versarial network (GAN) was used to inpaint specular highlights spatially and temporally. Due to the absence of a dataset with ground truth occluded textures, the network was trained on the in-vivo gastric endoscopy dataset (Hyper-Kvasir [1]) with specular highlight masks that were automatically created and processed to act as pseudo ground truths. Ablation studies and direct comparison with other methods were used to show the improved results of our system. In addition, the results on various datasets show the generalizability of our net- work on different environments and procedures as shown in Fig. 1. Finally, experiments also show the positive effect of inpainting on other computer vision tasks under the umbrella of 3D reconstruction and localization in endoscopy including feature matching as well as optical flow and disparity estimation.

show abstract

Effect of interpolation on specular reflections in texture‐based automatic colonic polyp detection

Cited by 7 publications

References 22 publications

Specular Reflections Detection and Removal for Endoscopic Images Based on Brightness Classification

Specular Reflections Detection and Removal for Endoscopic Images Based on Brightness Classification

FNSAM: Image super-resolution using a feedback network with self-attention mechanism

A Temporal Learning Approach to Inpainting Endoscopic Specularities and Its effect on Image Correspondence

Contact Info

Product

Resources

About