• Korean Journal of Radiology
• /
• 제22권6호
• /
• pp.912-921
• /
• 2021

Objective: To compare the performance of the deep learning-based lesion detection algorithm (DLLD) in detecting liver metastasis with that of radiologists. Materials and Methods: This clinical retrospective study used 4386-slice computed tomography (CT) images and labels from a training cohort (502 patients with colorectal cancer [CRC] from November 2005 to December 2010) to train the DLLD for detecting liver metastasis, and used CT images of a validation cohort (40 patients with 99 liver metastatic lesions and 45 patients without liver metastasis from January 2011 to December 2011) for comparing the performance of the DLLD with that of readers (three abdominal radiologists and three radiology residents). For per-lesion binary classification, the sensitivity and false positives per patient were measured. Results: A total of 85 patients with CRC were included in the validation cohort. In the comparison based on per-lesion binary classification, the sensitivity of DLLD (81.82%, [81/99]) was comparable to that of abdominal radiologists (80.81%, p = 0.80) and radiology residents (79.46%, p = 0.57). However, the false positives per patient with DLLD (1.330) was higher than that of abdominal radiologists (0.357, p < 0.001) and radiology residents (0.667, p < 0.001). Conclusion: DLLD showed a sensitivity comparable to that of radiologists when detecting liver metastasis in patients initially diagnosed with CRC. However, the false positives of DLLD were higher than those of radiologists. Therefore, DLLD could serve as an assistant tool for detecting liver metastasis instead of a standalone diagnostic tool.

• 대한의용생체공학회:의공학회지
• /
• 제19권1호
• /
• pp.1-8
• /
• 1998

X-선 유방영상에서 군집성 미세석회화는 유방암의 조기 검출에 중요한 징후로 이용된다. 본 논문은 X-선 유방영상에서 군집성 미세석회를 검출하여 그것의 위치를 표시하는 컴퓨터 보조 검출 방법을 제안한다. 제안된 검출방법의 구성도는 ROI9region of interest)선택, 필름흠제거, srdm(surrounding region dependence method), 분류기, 그리고 위치 표시로 구성되어 있다. SRDM은 이미 저자들에 의해 제안되었으며, 이것은 현재의 픽셀을 둘러싸고 있는 두 개의 영역에서의 2차 히스토그램에 근거한 통계적인 텍스처(texture)분석 방법이며 X-선 유방영상에서 군집성 미세석회화의 검출을 위해 제안되었다. 또한, 본 논문에서 제안된 필름흠 제거 필터의 효과는 ROC (receiver operating-characteristics) 분석에 의한 분류 성능 측면에서 평가되어진다. 정상조직(normal tissue)과 군집성 미세석회화를 포함한 조직을 분류하기 위해 3계층 backpropagation 신경망이 분류기로 이용되었다. 검출된 군집성 미세석회화의 위치와 적절한 표시를 함으로써 진단방사선의사에게 더 많은 주의를 상기시킬 수 있다

• 한국의학물리학회지:의학물리
• /
• 제9권2호
• /
• pp.115-121
• /
• 1998

본 연구는 암을 조기진단을 위한 장치개발의 기초 연구로서, 질병(암)을 검출할수 있는 광 특성의 존재를 결정하기 위하여 12개 생체조직의 계층별 시료와 인체의 혈액에서 광 특성을 측정하였다. 실험은 동물의 지방 및 근육 조직과 인체 혈액 HCT의 27.3%, 35.4%, 45.6%과 59.1%을 대상으로, 광파장이 630nm, 660nm, 780nm, 880nm, 940nm 에서 흡수 계수, $\mu$$_{\alpha}$를 측정하였다. 측정된 흡수계수는 일정하고 특이한 변화를 보여 주었다. 본 연구의 결과에 의하면 생체조직의 계층별과 광파장의 특정 파장대에서 분명한 차이를 구분할 수 있었다. 차이를 구분할 수 있었다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권3호
• /
• pp.1007-1010
• /
• 2015

Background: The clinical significance of bilateral breast cancer is unclear and its influence on prognosis is controversial. Materials and Methods: Between 2005 and 2009 we identified 110 cases of bilateral breast cancer (BBC) ; 49 patients had synchronous (duration between the occurrence of carcinoma in both breasts was less than 12 months) and 61 had metachronous (duration was more than one year with no ipsilateral local recurrence). We compared the patient characteristics including age, menopausal status, clinical stage, tumor size, histological classification, lymph node status, and hormone receptor and Her-2 status. We also compared the treatment given and overall and disease free survival (DFS) of both groups. Results: Synchronous cases tend to present more aggressively than metachronous cases and age at first presentation adversely affects survival. The 5 year overall survival was 78.7% for metachronous and 60% for synchronous. Patients with positive hormonal status had better five year disease free survival in metachronous compared to synchronous cases, at 76% and 63%, respectively. Age at first presentation >45years had better DFS (65%) compared to those with age ${\leq}45$ years (52%) at 5 years follow up. Conclusions: Patients with synchronous breast cancer may have worse prognosis. Young age and hormone receptor negative were risk factors in our study. Close follow up and early detection of contralateral breast cancer is mandatory.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권9호
• /
• pp.4665-4667
• /
• 2012

Cervical cancer is the most common cancer in Laos women and a screening programme, even with the PAP smear test (PAP test), has yet to be established for routine use. The Pap test is accepted as the most appropriate for cervical cancer screening in some settings but it is not commonly available in Laos hospitals, because there are few cytopathologists and gynecologists have little experience. As a pilot program, seminars for the PAP test were given in 2007 and 2008, and then PAP tests were carried out using self-sampling instrument (Kato's device) with 200 healthy volunteers in Setthathirath hospital, Laos, in 2008. The actual examination number was 196, divided into class I 104 (53.1%), class II 85 (43.3%), class IIIa 4 (2.0%), class IIIb 1 (0.5%), and class V 1 (0.5%) by modified Papanicolau classification. Four cases had menstruation. There were 6 cases with epithelial cell abnormalities including malignancy. There were 7 cases with fungus and 2 cases with trichomonas in Class II. More than 70% volunteers felt comfortable with the Kato's device and wanted to use it next time, because of the avoidance of the embarrassment and a low cost as compared with pelvic examination by gynecologists. This first trial for PAP test for healthy Laos women related to a hospital found three percent to have abnormal cervical epithelial cells. Therefore, this appraoch using a self-sampling device suggests that it should be planned for cervical cancer prevention in Laos.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2008년도 춘계종합학술대회 A
• /
• pp.967-970
• /
• 2008

우리나라 암 발생빈도 중 간암은 위암에 이어 두 번째로 흔한 암으로, 초기에는 특이 증상이나 증후 없이 서서히 진행되는 경우가 많아 증상이 생긴 후 간암으로 진단될 경우, 대부분 마땅한 치료방법이 별로 없어 어떠한 치료를 해도 환자의 예후는 불량하나, 조기에 발견될 경우는 치료성적이 우수하여 조기 발견이 대단히 중요시된다. 본 시스템은 간암의 조기발견을 위한 시스템으로, 간암으로 확진된 환자와 간암이외의 대조군의 혈액을 바이오침에 반응시켜 바이오칩 프로파일을 기계학습을 통해 분류하는 시스템이다. 본 논문에서는 총 50샘플로 구성된 간암환자 와 100샘플로 구성된 간암 이외의 대조군의 혈액시료를 1149의 서로 다른 올리고로 구성된 바이오칩에 반응시켜 획득한 데이터를 인공신경 망을 통해 분석한 결과 $92{\sim}96%$의 분류 성능을 보였다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권7호
• /
• pp.3489-3494
• /
• 2016

Background: A major problem with cervical cancer screening in countries which have no organized national screening program for cervical cancer is sub-optimal participation. Implementation of self-sampling method may increase the coverage. Objective: We determined the agreement of cytological diagnoses made on samples collected by women themselves (self-sampling) versus samples collected by physicians (Physician sampling). Materials and Methods: We invited women volunteers to undergo two procedures; cervical self-sampling using the Evalyn brush and physician sampling using a Cervex brush. The women were shown a video presentation on how to take their own cervical samples before the procedure. The samples taken by physicians were taken as per routine testing (Gold Standard). All samples were subjected to Thin Prep monolayer smears. The diagnoses made were according to the Bethesda classification. The results from these two sampling methods were analysed and compared. Results: A total of 367 women were recruited into the study, ranging from 22 to 65 years age. There was a significant good agreement of the cytological diagnoses made on the samples from the two sampling methods with the Kappa value of 0.568 (p=0.040). Using the cytological smears taken by physicians as the gold standard, the sensitivity of self-sampling was 71.9% (95% CI:70.9-72.8), the specificity was 86.6% (95% CI:85.7-87.5), the positive predictive value was 74.2% (95% CI:73.3-75.1) and the negative predictive value was 85.1% (95% CI: 84.2-86.0). Self-sampling smears (22.9%) allowed detection of micro-organisms better than physicians samples (18.5%). Conclusions: This study shows that samples taken by women themselves (self-sampling) and physicians have good diagnostic agreement. Self-sampling could be the method of choice in countries in which the coverage of women attending clinics for screening for cervical cancer is poor.

• 대한비뇨기종양학회지
• /
• 제16권3호
• /
• pp.110-118
• /
• 2018

Purpose: The aim of this study is to confirm the detection rate of transperineal biopsy after multiparametric magnetic resonance imaging (mpMRI) and compared it to that of transrectal biopsy. We also examined the role of mpMRI and the rate of complications for each method. Materials and Methods: In a retrospective study, we analyzed 147 patients who underwent mpMRI before prostate biopsy because of elevated serum prostate-specific antigen and/or abnormal digital rectal examination findings at Korea University Hospital, Seoul, Korea from March 2017 to April 2018. Regions on the mpMRI that were suggestive of prostate cancer were categorized according to the Prostate Imaging-Reporting and Data System (PI-RADS v2). For transperineal biopsy, a 20-core saturation biopsy was performed by MRI-TRUS cognitive or fusion techniques and a 12-core biopsy was performed in transrectal biopsy. Results: Sixty-three and 84 patients were enrolled in transperineal group and transrectal group, respectively. The overall detection rate of prostate cancer in transperineal group was 27% higher than that in transrectal group. Classification according to PI-RADS score revealed a significant increase in detection rate in all patients, as the PI-RADS score increased. Frequency of complications using the Clavien-Dindo classifications revealed no significant differences in the total complications rate, but two patients in transrectal group received intensive care unit care due to urosepsis. Conclusions: Our results confirmed that transperineal biopsy is superior to transrectal biopsy for the detection of prostate cancer. From the complication point of view, this study confirmed that there were fewer severe complications in transperineal biopsy.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권18호
• /
• pp.8487-8490
• /
• 2016

Background: Helicobacter pylori infection and premalignant gastric mucosa can be reliably identified using conventional narrow band imaging (C-NBI) gastroscopy. The aim of our study was to compare standard biopsy with site specific biopsy for diagnosis of H. pylori infection and premalignant gastric mucosa in daily clinical practice. Materials and Methods: Of a total of 500 patients who underwent gastroscopy for investigation of dyspeptic symptoms, 250 patients underwent site specific biopsy using C-NBI (Group 1) and 250 standard biopsy (Group 2). Sensitivity, specificity, and positive and negative predictive values were assessed. The efficacy of detecting H. pylori associated gastritis and premalignant gastric mucosa according to the updated Sydney classification was also compared. Results: In group 1 the sensitivity, specificity, positive and negative predictive values for predicting H. pylori positivity were 95.4%, 97.3%, 98.8% and 90.0% respectively, compared to 92.9%, 88.6%, 83.2% and 76.1% in group 2. Site specific biopsy was more effective than standard biopsy in terms of both H. pylori infection status and premalignant gastric mucosa detection (P<0.01). Conclusions: Site specific biopsy using C-NBI can improve detection of H. pylori infection and premalignant gastric mucosa in daily clinical practice.

• 대한의용생체공학회:의공학회지
• /
• 제30권2호
• /
• pp.153-161
• /
• 2009

Mammogram is one of the important techniques for mass detection, which is the early diagnosis stage of a breast cancer. Especially, the CAD(Computer Aided Diagnosis) using mammogram improves the working performance of radiologists as it offers an effective mass detection. There are two types of CAD systems using mammogram; automatic and semi-automatic CAD systems. However, the automatic segmentation is limited in performance due to the difficulty of obtaining an accurate segmentation since mass occurs in the dense areas of the breast tissue and has smoother boundaries. Semi-automatic CAD systems overcome these limitations, however, they also have problems including high FP (False Positive) rate and a large amount of training data required for training a classifier. The proposed system which overcomes the aforementioned problems to detect mass is composed of the suspected area selection, the level set segmentation and SVM (Support Vector Machine) classification. To assess the efficacy of the system, 60 test images from the FFDM (Full-Field Digital Mammography) are analyzed and compared with the previous semi-automatic system, which uses the ANN classifier. The experimental results of the proposed system indicate higher accuracy of detecting mass in comparison to the previous systems.