• Journal of Biomedical Engineering Research
• /
• v.44 no.2
• /
• pp.118-124
• /
• 2023

Many recent studies have reported that the quality of input learning data was vital to the detection of regions of interest. However, due to a lack of research on the quality of learning data on lesion detetcting using gastroscopy, we aimed to quantify the impact of quality difference in endoscopic images to lesion detection models using Image Quality Assessment (IQA) algorithms. Through IQA methods such as BRISQUE (Blind/Referenceless Image Spatial Quality Evaluation), Laplacian Score, and PSNR (Peak Signal-To-Noise) algorithm on 430 sheets of high quality data (HQD) and 430 sheets of low quality data (PQD), we showed that there were significant differences between high and low quality images in lesion detecting through BRISQUE and Laplacian scores (p<0.05). The PSNR value showed 10.62±1.76 dB on average, illustrating the lower lesion detection performance of PQD than HQD. In addition, F1-Score of HQD showed higher detection performance at 77.42±3.36% while F1-Score of PQD showed 66.82±9.07%. Through this study, we hope to contribute to future gastroscopy lesion detection assistance systems that involve IQA algorithms by emphasizing the importance of using high quality data over lower quality data.

• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.839-841
• /
• 1999

This paper presents the method of 3D reconstruction of the depth information from the endoscopic stereo scopic images. After camera modeling to find camera parameters, we performed feature-point based stereo matching to find depth information. Acquired some depth information is finally 3D reconstructed using the NURBS(Non Uniform Rational B-Spline) algorithm. The final result image is helpful for the understanding of depth information visually.

• Korean Journal of Bronchoesophagology
• /
• v.17 no.2
• /
• pp.108-111
• /
• 2011

Epiglottic cysts cause stridor mimicking asthma and hinder intubation in surgery. A huge cyst can obstruct the airway, making laryngeal examinations impossible. Before surgery, complete visualization of the larynx is necessary for the successful excision of a cyst. If laryngeal examination fails, computed tomography (CT) scanning can provide detailed information. Virtual endoscopy based on CT data reconstruction can yield a detailed three-dimensional image of the larynx. Here, we report two cases of epiglottic cysts along with virtual endoscopic findings and surgical photographs.

• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.265-266
• /
• 1998

This paper describes a depth extraction algorithm in the stereo endoscopic images using adaptive window. First, The relation between the 3D coordinates in the world and the 2D coordinates in the image plane is estimated using camera calibration. Next, stereo matching is performed to find the conjugate pairs in the left and right images. To improve the precision of the matching result, adaptive window which can be varied on the shape as well as on the size according to the area characteristics is used. Finally, the result from the stereo matching and that of camera modeling are combined to extract the real depth information.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2228-2230
• /
• 1998

This paper presents the development of depth extraction algorithm for the stereoscopic endoscope data using a stereo matching method. generally, the purpose of existing stereo algorithms is to reconstruct stereo object surface and depth map. but the main purpose of our processing is to give exact depth feeling to doctor showing depth information in some points. for this purpose, this paper presents two stereo matching algorithms which are to measure exact depth. one is using variable window, and the other is reference points-based algorithm for a fast processing.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2818-2820
• /
• 2001

This paper presents the method of 3D reconstruction of the depth information from the endoscopic stereo scopic images. After camera modeling to find camera parameters, we performed feature-point based stereo matching to find depth information. Acquired some depth information is finally 3D reconstructed using the NURBS(Non Uniform Rational B-Spline) algorithm. The final result image is helpful for the understanding of depth information visually.

• Journal of Korean Neurosurgical Society
• /
• v.39 no.4
• /
• pp.292-295
• /
• 2006

Isolated fourth ventricle[IFV] is a rare entity producing symptoms of a progressive posterior fossa mass lesion. It is mainly reported in a patient who undergo shunt placement as its late complication. However, its surgical management has been difficult and its optional treatment remains controversial. We had an occasion to admit 19-year-old female to our hospital due to hydrocephalus : she had a history of meningitis when she was 2 years old. Ten years later she was diagnosed as hydrocephalus and managed by lateral ventriculo-peritoneal shunting procedure. Seven years after the procedure, the patient presented with headache, nausea, truncal ataxia and nystagmus. Computed tomography and magnetic resonance image scan demonstrated markedly enlarged fourth ventricle : and thus, neuroendoscopic aqueductoplasty and aqueductal stent insertion was performed. The authors present a case of an IFV after lateral ventriculo-peritoneal shunting for hydrocephalus, which was treated successfully with a neuroendoscopic surgery. The technique of this procedure is described below.

• Archives of Craniofacial Surgery
• /
• v.12 no.1
• /
• pp.1-5
• /
• 2011

Purpose: The management of frontal sinus fractures and frontal sinus outflow tract (=FSOT) injuries is controversial. Traditional treatments include frontal sinus obliteration with a variety of material grafts, which all employ complicated algorithms for treatment planning. A simplified algorithm aiming for frontal sinus ventilation, however, can be achieved through the advanced technology of image guided endoscopic surgery and instruments. The authors explain this simplified treatment algorithm of frontal sinus fractures. Methods: The authors reviewed articles on the management of frontal sinus fractures. Results: Complicated treatment planning algorithms of frontal sinus fractures aiming for obliteration were replaced with a simplified algorithm aiming for ventilation of the frontal sinus. Conclusion: The authors suggest that a simplified algorithm can replace the complicated algorithms in selective cases.

• Journal of Digestive Cancer Research
• /
• v.10 no.2
• /
• pp.56-64
• /
• 2022

Narrow-band imaging (NBI) is the most widely used image-enhanced endoscopic technique. The superficial microanatomy of gastric mucosa can be visualized when used with a magnifying endoscopy with narrow-band imaging (ME-NBI). The diagnostic criteria for early gastric cancer (EGC), using the classification system for microvascular and microsurface pattern of ME-NBI, have been developed, and their usefulness has been proven in the differential diagnosis of small depressed cancer from focal gastritis and in lateral extent delineation of EGC. Some studies reported on the prediction of histologic differentiation and invasion depth of gastric cancer using ME-NBI; however, its application is limited in clinical practice, and further well-designed studies are necessary. Clinicians should understand the ME-NBI classification system and acquire appropriate diagnostic skills through various experiences and training to improve the quality of endoscopy for EGC diagnosis.

• Journal of Digestive Cancer Research
• /
• v.11 no.3
• /
• pp.130-140
• /
• 2023

Gastric cancer (GC) is one of the most common malignant tumors worldwide, with a 5-year survival rate of < 40%. The diagnosis and treatment decisions of GC rely on human experts' judgments on medical images; therefore, the accuracy can be hindered by image condition, objective criterion, limited experience, and interobserver discrepancy. In recent years, several applications of artificial intelligence (AI) have emerged in the GC field based on improvement of computational power and deep learning algorithms. AI can support various clinical practices in endoscopic examination, pathologic confirmation, radiologic staging, and prognosis prediction. This review has systematically summarized the current status of AI applications after a comprehensive literature search. Although the current approaches are challenged by data scarcity and poor interpretability, future directions of this field are likely to overcome the risk and enhance their accuracy and applicability in clinical practice.