ABSTRACT
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.
ABSTRACT
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.
ABSTRACT
Purpose@#The purpose of this study was to evaluate the predictive performance of ultrasonography (US)-based radiomics for axillary lymph node metastasis and to compare it with that of a clinicopathologic model. @*Methods@#A total of 496 patients (mean age, 52.5±10.9 years) who underwent breast cancer surgery between January 2014 and December 2014 were included in this study. Among them, 306 patients who underwent surgery between January 2014 and August 2014 were enrolled as a training cohort, and 190 patients who underwent surgery between September 2014 and December 2014 were enrolled as a validation cohort. To predict axillary lymph node metastasis in breast cancer, we developed a preoperative clinicopathologic model using multivariable logistic regression and constructed a radiomics model using 23 radiomic features selected via least absolute shrinkage and selection operator regression. @*Results@#In the training cohort, the areas under the curve (AUC) were 0.760, 0.812, and 0.858 for the clinicopathologic, radiomics, and combined models, respectively. In the validation cohort, the AUCs were 0.708, 0.831, and 0.810, respectively. The combined model showed significantly better diagnostic performance than the clinicopathologic model. @*Conclusion@#A radiomics model based on the US features of primary breast cancers showed additional value when combined with a clinicopathologic model to predict axillary lymph node metastasis.
ABSTRACT
Background/Objectives@#Extracapsular dissection has the advantage of reducing complications by minimizing tissue loss of the parotid without intentionally exposing the facial nerve in patients with benign parotid tumor. However, there has been controversy over the surgical results. Thus, the surgical outcomes of extracapsular dissection for benign parotid tumor was compared to those of superficial parotidectomy.Materials & Methods: A retrospective chart review was conducted with 132 patients who received surgery for benign parotid tumor in our center from January 2014 to December 2018 retrospectively. @*Results@#A total of 132 people were enrolled, with 62 people receiving extracapsular dissection, 38 people receiving partial superficial parotidectomy and 32 people receiving superficial parotidectomy. No significant difference was found between the three groups regarding complications such as facial nerve palsy, Frey's syndrome, or first bite syndrome. Operation time and hospital stay was significantly short in extracapsular dissection group. @*Conclusion@#For well-selected cases, extracapsular dissection can be considered as an option for surgery of benign parotid tumor.
ABSTRACT
Purpose@#Recently, there has been a rise in the interest to understand the composition of indoor dust due to its association with lung diseases such as asthma, chronic obstructive pulmonary disease (COPD) and lung cancer. Furthermore, it has been found that bacterial extracellular vesicles (EVs) within indoor dust particles can induce pulmonary inflammation, suggesting that these might play a role in lung disease. @*Methods@#We performed microbiome analysis of indoor dust EVs isolated from mattresses in apartments and hospitals. We developed diagnostic models based on the bacterial EVs antibodies detected in serum samples via enzyme-linked immunosorbent assay (ELISA) in this analysis. @*Results@#Proteobacteria was the most abundant bacterial EV taxa observed at the phylum level while Pseudomonas, Enterobacteriaceae (f) and Acinetobacter were the most prominent organisms at the genus level, followed by Staphylococcus. Based on the microbiome analysis, serum anti-bacterial EV immunoglobulin G (IgG), IgG1 and IgG4 were analyzed using ELISA with EV antibodies that targeted Staphylococcus aureus, Acinetobacter baumannii, Enterobacter cloacae and Pseudomonas aeruginosa. The levels of anti-bacterial EV antibodies were found to be significantly higher in patients with asthma, COPD and lung cancer compared to the healthy control group. We then developed a diagnostic model through logistic regression of antibodies that showed significant differences between groups with smoking history as a covariate. Four different variable selection methods were compared to construct an optimal diagnostic model with area under the curves ranging from 0.72 to 0.81. @*Conclusions@#The results of this study suggest that ELISA-based analysis of anti-bacterial EV antibodies titers can be used as a diagnostic tool for lung disease. The present findings provide insights into the pathogenesis of lung disease as well as a foundation for developing a novel diagnostic methodology that synergizes microbial EV metagenomics and immune assays.
ABSTRACT
Purpose@#Recently, there has been a rise in the interest to understand the composition of indoor dust due to its association with lung diseases such as asthma, chronic obstructive pulmonary disease (COPD) and lung cancer. Furthermore, it has been found that bacterial extracellular vesicles (EVs) within indoor dust particles can induce pulmonary inflammation, suggesting that these might play a role in lung disease. @*Methods@#We performed microbiome analysis of indoor dust EVs isolated from mattresses in apartments and hospitals. We developed diagnostic models based on the bacterial EVs antibodies detected in serum samples via enzyme-linked immunosorbent assay (ELISA) in this analysis. @*Results@#Proteobacteria was the most abundant bacterial EV taxa observed at the phylum level while Pseudomonas, Enterobacteriaceae (f) and Acinetobacter were the most prominent organisms at the genus level, followed by Staphylococcus. Based on the microbiome analysis, serum anti-bacterial EV immunoglobulin G (IgG), IgG1 and IgG4 were analyzed using ELISA with EV antibodies that targeted Staphylococcus aureus, Acinetobacter baumannii, Enterobacter cloacae and Pseudomonas aeruginosa. The levels of anti-bacterial EV antibodies were found to be significantly higher in patients with asthma, COPD and lung cancer compared to the healthy control group. We then developed a diagnostic model through logistic regression of antibodies that showed significant differences between groups with smoking history as a covariate. Four different variable selection methods were compared to construct an optimal diagnostic model with area under the curves ranging from 0.72 to 0.81. @*Conclusions@#The results of this study suggest that ELISA-based analysis of anti-bacterial EV antibodies titers can be used as a diagnostic tool for lung disease. The present findings provide insights into the pathogenesis of lung disease as well as a foundation for developing a novel diagnostic methodology that synergizes microbial EV metagenomics and immune assays.
ABSTRACT
The emergence of new technologies, especially digital transformation, influences the entire society, including the medical aspects. Therefore, the concept of digital hospital has been emerging. Here we present the Yongin Severance Hospital, which has developed various novel solutions to serve as foundations for the establishment of a digitally innovative hospital. Further strategies have also been provided to implement consistent and long-term planning.
ABSTRACT
Artificial intelligence (AI) is expected to affect various fields of medicine substantially and has the potential to improve many aspects of healthcare. However, AI has been creating much hype, too. In applying AI technology to patients, medical professionals should be able to resolve any anxiety, confusion, and questions that patients and the public may have. Also, they are responsible for ensuring that AI becomes a technology beneficial for patient care. These make the acquisition of sound knowledge and experience about AI a task of high importance for medical students. Preparing for AI does not merely mean learning information technology such as computer programming. One should acquire sufficient knowledge of basic and clinical medicines, data science, biostatistics, and evidence-based medicine. As a medical student, one should not passively accept stories related to AI in medicine in the media and on the Internet. Medical students should try to develop abilities to distinguish correct information from hype and spin and even capabilities to create thoroughly validated, trustworthy information for patients and the public.
ABSTRACT
OBJECTIVE: To identify an imaging predictor for the assessment of early treatment response to yttrium-90 transarterial radioembolization (TARE) in patients with hepatocellular carcinoma (HCC), using a quantitative assessment of dynamic computed tomography (CT) images. MATERIALS AND METHODS: Dynamic contrast-enhanced CT was obtained pre- and 4 weeks post-TARE in 44 patients (34 men, 10 women; mean age, 60 years) with HCC. Computer software was developed for measuring the percentage increase in the combined delayed-enhancing area and necrotic area (pD + N) and the percentage increase in the necrotic area (pNI) in the tumor-containing segments pre- and post-TARE. Local progression-free survival (PFS) was compared between patient groups using Cox regression and Kaplan-Meier analyses. RESULTS: Post-TARE HCC with pD + N ≥ 35.5% showed significantly longer PFS than those with pD + N < 35.5% (p = 0.001). The local tumor progression hazard ratio was 17.3 (p = 0.009) for pD + N < 35.5% versus pD + N ≥ 35.5% groups. HCCs with a high pNI tended to have longer PFS, although this difference did not reach statistical significance. CONCLUSION: HCCs with a larger pD + N are less likely to develop local progression after TARE.
Subject(s)
Female , Humans , Male , Carcinoma, Hepatocellular , Disease-Free Survival , Tomography, X-Ray Computed , Treatment Outcome , Yttrium RadioisotopesABSTRACT
INTRODUCTION: Bronchial carcinoid tumors seldom occur in children, sometimes mistaken for a minor disease and diagnosed slowly. MATERIALS AND METHODS: We report on a patient who diagnose tumors slowly because confused with asthma. RESULTS: This case describes a 14-year-old boy, presenting with asthma-like symptoms throughout 3 years. He was treated as asthma but wax and wane. Chest x-ray showed an hyperlucent left lung, so we rechecked high resolution computed tomography (HRCT) for unilateral hyperinflation diseases diagnosis. It was found 1×1cm nodule in left main bronchus. We did bronchoscopy and discovered a round mass in the left bronchus, 2∼3cm away from carina. In the biopsy, it was bronchial carcinoid tumor, so we resected tumor. DISCUSSION: Because symptoms of bronchial carcinoid tumors are various, it can often be misdiagnosed firstly. It is confused with asthma, pneumonia and foreign body. An additional examination were necessary when respiratory symptoms persist.
Subject(s)
Adolescent , Child , Humans , Male , Asthma , Biopsy , Bronchi , Bronchoscopy , Carcinoid Tumor , Diagnosis , Foreign Bodies , Lung , Pneumonia , ThoraxABSTRACT
Lack of awareness, the stigma of carrying a genetic mutation, and economic factors are barriers to acceptance of BRCA genetic testing or appropriate risk management. We aimed to investigate the influence of Angelina Jolie's announcement of her medical experience and also health insurance reimbursement for BRCA gene testing on practice patterns for hereditary breast and ovarian cancer (HBOC). A survey regarding changes in practice patterns for HBOC before and after the announcement was conducted online. The rate of BRCA gene testing was obtained from the National Health Insurance Review and Assessment Service database. From May to August 2016, 70 physicians responded to the survey. Genetic testing recommendations and prophylactic management were increased after the announcement. Risk-reducing salpingo-oophorectomy and contralateral prophylactic mastectomy was significantly increased in BRCA carriers with breast cancer. The BRCA testing rate increased annually. Health insurance and a celebrity announcement were associated with increased genetic testing.
Subject(s)
Breast Neoplasms , Breast , Genetic Testing , Insurance Coverage , Insurance , Insurance, Health , Insurance, Health, Reimbursement , Mastectomy , National Health Programs , Ovarian Neoplasms , Risk ManagementABSTRACT
Intracranial lesions may show contrast enhancement through various mechanisms that are closely associated with the disease process. The preferred magnetic resonance sequence in contrast imaging is T1-weighted imaging (T1WI) at most institutions. However, lesion enhancement is occasionally inconspicuous on T1WI. Although fluid-attenuated inversion recovery (FLAIR) sequences are commonly considered as T2-weighted imaging with dark cerebrospinal fluid, they also show mild T1-weighted contrast, which is responsible for the contrast enhancement. For several years, FLAIR imaging has been successfully incorporated as a routine sequence at our institution for contrast-enhanced (CE) brain imaging in detecting various intracranial diseases. In this pictorial essay, we describe and illustrate the diagnostic importance of CE-FLAIR imaging in various intracranial pathologic conditions.
Subject(s)
Humans , Arachnoid Cysts/diagnosis , Brain/pathology , Brain Neoplasms/diagnosis , Contrast Media , Magnetic Resonance Imaging/methodsABSTRACT
PURPOSE: We examined the respiratory morbidities in late-preterm infants compared to those of the early-preterm infants and term infants throughout the first year of life. METHODS: Data were retrospectively collected for 87 late-preterm, 72 early-preterm, and 608 term infants who were admitted to NICU and the nursery of Busan St. Mary's Medical Center from Jan 2007 to Oct 2009. RESULTS: There were significant differences in the proportions of the out-born infants, twin pregnancy, small for gestational age, and Caesarean section in the three groups (P<0.05). Late-preterm and early-preterm infants had longer duration of hospitalization, larger proportions of respiratory distress syndrome, mechanical ventilation at birth, oxygen therapy after 48 hours of birth, oxygen dependency at 28 days, and continuous positive airway pressure support at 28 days compared to term infants during the neonatal period (P=0.000). Late-preterm infants and early-preterm infants were re-admitted more often than term infants during the first year of life (P=0.000). Also Late-preterm and early-preterm infants had increased chance of respiratory tract illness than term infants (P=0.001). CONCLUSION: In this study, we demonstrated that there are higher chances of respiratory morbidities in the late-preterm infants than the term infants either during the neonatal period or throughout the first year of life, although early-preterm infants showed greatest respiratory morbidities.