• Imaging Science in Dentistry
• /
• 제48권2호
• /
• pp.121-125
• /
• 2018

Purpose: Detecting laryngeal cartilages (triticeous and thyroid cartilages) on panoramic radiographs is important because they may be confused with carotid artery calcifications in the bifurcation region, which are a risk factor for stroke. This study assessed the efficiency of panoramic radiography in the diagnosis of calcified laryngeal cartilages using cone-beam computed tomography (CBCT) as the reference standard. Materials and Methods: A total of 312 regions(142 bilateral, 10 left, 18 right) in 170 patients(140 males, 30 females) were examined. Panoramic radiographs were examined by an oral and maxillofacial radiologist with 11 years of experience. CBCT scans were reviewed by 2 other oral and maxillofacial radiologists. The kappa coefficient(${\kappa}$) was calculated to determine the level of intra-observer agreement and to determine the level of agreement between the 2 methods. Diagnostic indicators(sensitivity, specificity, accuracy, and false positive and false negative rates) were also calculated. P values <.05 were considered to indicate statistical significance. Results: Eighty-two images were re-examined to determine the intra-observer agreement level, and the kappa coefficient was calculated as 0.709 (P<.05). Statistically significant and acceptable agreement was found between the panoramic and CBCT images (${\kappa}=0.684$ and P<.05). The sensitivity, specificity, diagnostic accuracy rate, the false positive rate, and the false negative rate of the panoramic radiographs were 85.4%, 83.5%, 84.6%, 16.5%, and 14.6%, respectively. Conclusion: In most cases, calcified laryngeal cartilages could be diagnosed on panoramic radiographs. However, due to variation in the calcifications, diagnosis may be difficult.

• 한국농공학회논문집
• /
• 제61권3호
• /
• pp.55-65
• /
• 2019

Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structure as it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized for it. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack's image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with or without crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualization of crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were applied for each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizing crack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under 100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, and regarding to the false negative error, the case using 50 data per category showed the best result.

• Korean Journal of Radiology
• /
• 제21권7호
• /
• pp.891-899
• /
• 2020

Objective: To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. Materials and Methods: We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). Results: All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. Conclusion: We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

• Journal of Yeungnam Medical Science
• /
• 제20권2호
• /
• pp.117-128
• /
• 2003

Thallium-201 scintigraphy is used to discriminate the malignant bone tumor from the benign by qualitatively and quantitatively, and to predict the response of preoperative chemotherapy in osteosarcoma, by comparing the changes of thallium uptake ratio after chemotherapy to the tumor necrosis ratio. Thallium-201 scintigraphy scan should be done prior to surgical biopsy. PICKER Prism 2000 gamma camera with high resolution parallel hole collimator is usually used for scanning. The patient is injected with 2-3mCi of Tl-201 and the early phase is checked in 30 minutes and delayed phase in 3 hours. The scan images are visually evaluated by a blinded nuclear medicine physician. We could evaluate true positive, true negative, false positive and false negative by the comparison of results with those of biopsy, and calculate positive and negative predictive value(%), sensitivity(%), specificity(%) and diagnostic accuracy(%). For the quantitative analysis of thallium uptake, we drew the region of interest on the tumor side and contralateral normal side as mirror image, and calculated the uptake ratio with dividing the amount of gamma count in tumor side by normal side. We could calculate the percent changes of thallium uptake ratio in early and delayed phase, and compare them to the ratio of tumor necrosis. Thallium-201 scintigraphy proved as useful imaging study to discriminate malignant bone tumor from benign, but had exception in giant cell tumor and low grade malignant bone tumors. We can use T1-201 scan to differentiate the benign from the malignant tumor, and to evaluate the response of preoperative chemotherapy or radiotherapy, and to determine the residual tumor or local recurrence. For the better result, we need to have a more detail information about false positive cases and a more objective and quantitative reading technique.

• Korean Journal of Otorhinolaryngology-Head and Neck Surgery
• /
• 제60권3호
• /
• pp.107-111
• /
• 2017

Background and Objectives The bedside head impulse test (bHIT) in bare eyes often overlooks possible vestibular losses by missing the corrective saccade. This is why it is necessary to compare bHIT against video head impulse test (vHIT), which is more accurate in identifying vestibular losses than the bedside test. Subjects and Method A total of 51 vHIT positive ears underwent the study, and out of those, 47 were diagnosed with dizziness. bHIT and vHIT were performed for patients, and the occurrence rate of overt saccade (OS) was calculated. Results Among the 51 vHIT positive ears, 33 (64.7%) were bHIT positive ears and 18 ears (35.3%) were bHIT negative. Patterns of positive vHIT were classified as A: no corrective saccade, B: covert saccade (CS) only, C: OS only, and D: CS with OS (CS+OS), which were 45 out of 51 ears (88%). The occurrence rate of OS was higher in the bHIT positive group than in the bHIT negative group (p=0.05), and higher in the CS negative group (CS-) than in the CS positive group (CS+) (p<0.001). Conclusion Possible causes of false negative results of bHIT are seen as following: the absence of corrective (covert and overt) saccade, the occurrence of CS only, and missing the OS during the bHIT (probably due to low occurrence rate of OS). The occurrence of CS should be considered as an important factor in false negative bHIT when lowering the occurrence rate of OS.

• 대한영상의학회지
• /
• 제84권2호
• /
• pp.361-371
• /
• 2023

영상 유도하 유방 조직검사의 성공 여부는 조직검사를 시행하는 당시의 정확한 판단에 근거한 조직검사 유도방식, 기구 선택, 적절한 술기에 의하여 상당 부분 결정되지만, 불충분한 또는 부정확한 검체 채취에 의한 위음성 또는 조직학적 저평가의 한계가 있을 수 있다. 이러한 이유로 영상-병리 합당성 판정을 포함한 조직검사 이후의 적절한 처치와 대응이 매우 중요하다. 조직검사 시 정확한 검체 획득이 이루어지지 않아 암 병변임에도 불구하고, 비특이적인 양성 병변의 병리 결과가 나오는 경우, 영상과 병리 간의 결과 일치 및 불일치 여부를 확인함으로써, 암을 놓치는 일을 막을 수 있다. 이 종설의 목적은 영상 유도하 유방 조직검사 후 결과의 정확한 해석을 위하여 구체적으로 고려할 사항들을 알아보고, 어떻게 적절한 평가를 할 수 있는지 알아보고자 한다.

• Journal of Microbiology and Biotechnology
• /
• 제16권11호
• /
• pp.1773-1777
• /
• 2006

We evaluated the usefulness of DNA microarray as a comparative genomics tool, and tested the validity of the cutoff values for defining absent genes in test genomes. Three genome-sequenced E. coli strains (K-12, EDL933, and CFT073) were subjected to comparative genomic hybridization with DNA microarrays covering almost all ORFs of the reference strain K-12, and the microarray results were compared with the results obtained from in silico analyses of genome sequences. For defining the K-12 ORFs absent in test genomes (reference strain-specific ORFs), we applied and evaluated the cutoff level of -1. The average sequence similarity between ORFs, to which corresponding spots showed a log-ratio of>-1, was $96.9{\pm}4.8$. The numbers of spots showing a log-ratio of <-1 (P<0.05, t-test) were 90 (2.5%) and 417 (10.6%) for the EDL933 genome and the CFT073 genome, respectively. Frequency of false negatives (FN) was ca. 0.2, and the cutoff level of -1.3 was required to achieve the FN of 0.1. The average sequence similarity of the false negative ORFs was $77.8{\pm}14.8$, indicating that the majority of the false negatives were caused by highly divergent genes. We concluded that the microarray is useful for identifying missing or divergent ORFs in closely related prokaryotic genomes.

• 핵의학기술
• /
• 제18권1호
• /
• pp.26-32
• /
• 2014

수술 전 림프절 전이 여부를 진단하고 병리학적 소견 및 원발 주위조직 전이 평가법을 이용하여 두경부암 PET-MRI 검사의 임상적 유용성을 평가하였다. 두경부암 환자 100명을 대상으로 $^{18}F-FDG$ (5.18 MBq/kg)를 정맥주사하고 60분 안정을 취한 후, BiographTM mMR 3T를 사용하여 torso(body tim coil, Vibe-Dixon)와 dedication (head/neck tim coil, UTE, Dotarem injection) 검사를 시행하였다. 반복계산법을 적용하여 데이터를 재구성한 후 workstation으로 림프절 전이 여부를 판독하고, 본원 종합의료정보시스템으로 수술 전/후 병리학적 검사 소견을 조사하였다. 환자의 진단 정보를 $2{\times}2$ 판정행렬의 각 항목에 기입하여 진양성, 진음성, 위양성, 위음성으로 구분하고 이렇게 구분된 검사결과를 토대로 예민도, 특이도, 정확도, 위음성률, 위양성률을 산출하였다. 두경부암 환자의 PET-MRI 검사 결과에서 림프절 전이 양성 및 음성 판정을 받은 경우는 각 49건, 51건이었으며 수술 전-후 병리학적 결과를 통해 림프절 전이 양성 및 음성 판정을 받은 경우는 각 46건, 54건으로 나타났다. 이 중 두 검사 모두 림프절 전이 양성 판정을 받은 진양성은 45건, PET-MRI 검사에서는 림프절 전이 양성이지만 병리학적 검사에서 림프절 전이 음성 판정을 받은 위양성은 4건, PET-MRI 검사에서 림프절 전이 음성이지만 병리학적 검사에서 양성 판정을 받은 위음성은 1건, 두 검사 모두 림프절 전이 음성 판정을 받은 진음성은 50건으로 분석되었다. 따라서 두경부암 환자의 PET-MRI 검사의 예민도는 97.8%, 특이도는 92.5%, 정확도는 95%, 위음성률은 2.1%, 위양성률은 7.0%로 나타났다. 따라서 PET-MRI는 두경부암의 진단에 있어 수술 전 병기 결정이나 치료 후 재발 및 원격전이의 발견, 불분명한 원발 경부 림프절 전이 등의 평가에 유용할 것으로 판단된다.

• Journal of Korean Neurosurgical Society
• /
• 제66권1호
• /
• pp.53-62
• /
• 2023

Objective : Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability. Methods : A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm's diagnostic performance. Results : In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anterior-posterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor. Conclusion : The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.

• 대한기관식도과학회:학술대회논문집
• /
• 대한기관식도과학회 1993년도 제27차 학술대회 초록집
• /
• pp.104-104
• /
• 1993

갑상선결절에서는 양성질환과 악성질환의 감별이 치료방침의 결정에 매우 중요하다. 술전검사 방법으로 세침흡인세포검사는 비교적 간단하고 정확하여 널리 시행되고있다. 이에 저자들은 1989년 1월부터 1992년 12월까지 원자력병원 이비인후과에서 갑상선질환으로 수술을 받은 203명의 환자중 110명을 대상으로, 세침흡인세포검사를 술후 병리조직학적 진단과 비교하여 다음과 같은 결과를 얻었다. 병리조직학적으로 전체 110명중 악성종양이 79명으로 70.9%를 차지하였고 세침흡인세포 검사의 민감도는 86.5%, 특이도 90.4%, 위음성율 13.5%, 위양성율 9.6%, 양성예측도 97.5%, 음성예측도 60.1%, 진단적 정확도는 87.3%이었다.