Deep Learning Techniques for Ear Diseases Based on Segmentation of the Normal Tympanic Membrane

Objectives@#. Otitis media is a common infection worldwide. Owing to the limited number of ear specialists and rapid development of telemedicine, several trials have been conducted to develop novel diagnostic strategies to improve the diagnostic accuracy and screening of patients with otologic diseases based on abnormal otoscopic findings. Although these strategies have demonstrated high diagnostic accuracy for the tympanic membrane (TM), the insufficient explainability of these techniques limits their deployment in clinical practice. @*Methods@#. We used a deep convolutional neural network (CNN) model based on the segmentation of a normal TM into five substructures (malleus, umbo, cone of light, pars flaccida, and annulus) to identify abnormalities in otoscopic ear images. The mask R-CNN algorithm learned the labeled images. Subsequently, we evaluated the diagnostic performance of combinations of the five substructures using a three-layer fully connected neural network to determine whether ear disease was present. @*Results@#. We obtained the receiver operating characteristic (ROC) curve of the optimal conditions for the presence or absence of eardrum diseases according to each substructure separately or combinations of substructures. The highest area under the curve (0.911) was found for a combination of the malleus, cone of light, and umbo, compared with the corresponding areas under the curve of 0.737–0.873 for each substructure. Thus, an algorithm using these five important normal anatomical structures could prove to be explainable and effective in screening abnormal TMs. @*Conclusion@#. This automated algorithm can improve diagnostic accuracy by discriminating between normal and abnormal TMs and can facilitate appropriate and timely referral consultations to improve patients’ quality of life in the context of primary care.

2019 Tabletop Exercise for Laboratory Diagnosis and Analyses of Unknown Disease Outbreaks by the Korea Centers for Disease Control and Prevention

Objectives@#The Korea Centers for Disease Control and Prevention has published “A Guideline for Unknown Disease Outbreaks (UDO).” The aim of this report was to introduce tabletop exercises (TTX) to prepare for UDO in the future. @*Methods@#The UDO Laboratory Analyses Task Force in Korea Centers for Disease Control and Prevention in April 2018, assigned unknown diseases into 5 syndromes, designed an algorithm for diagnosis, and made a panel list for diagnosis by exclusion. Using the guidelines and laboratory analyses for UDO, TTX were introduced. @*Results@#Since September 9th , 2018, the UDO Laboratory Analyses Task Force has been preparing TTX based on a scenario of an outbreak caused by a novel coronavirus. In December 2019, through TTX, individual missions, epidemiological investigations, sample treatments, diagnosis by exclusions, and next generation sequencing analysis were discussed, and a novel coronavirus was identified as the causal pathogen. @*Conclusion@#Guideline and laboratory analyses for UDO successfully applied in TTX. Conclusions drawn from TTX could be applied effectively in the analyses for the initial response to COVID-19, an ongoing epidemic of 2019 - 2020. Therefore, TTX should continuously be conducted for the response and preparation against UDO.

Newly Diagnosed Diabetes Mellitus With Pancreatic Cancer Manifested as Hyperglycemic Hyperosmolar State

Here, we report a case of newly diagnosed diabetes, with concurrent pancreatic cancer manifested as hyperglycemic crisis, and aggravated by urinary tract infection. We summarize the initial clinical manifestations and pertinent laboratory, radiologic, and clinical findings in an elderly patient with hyperglycemic emergency. A review of the documents involving pancreatic tumors and hyperglycemic hyperosmolar state, which is an acute complication of diabetes mellitus, is presented. In the absence of other identifiable conditions, it is reasonable to speculate that some factor (or factors) produced by the tumor had a role in the metabolic decompensation. In addition, this discussion should be more carefully considered in the aged people group.

A Case of Successful Colonoscopic Treatment of Colonic Obstruction Caused by Phytobezoar

A phytobezoar is the most common type of bezoar, which is a gastrointestinal mass composed of vegetable. A persimmon is a common cause of a phytobezoar. The majority of bezoars are found in the stomach, with the small intestine being the next most commonly involved site. The colon is a rare site for a bezoar. Recently, we experienced a colonic bezoar that caused colonic obstruction in a 66-year-old female patient who took persimmons regularly. The patient came to the hospital because of abdominal pain and distension. To differentiate a tumor or other problems that can cause intestinal obstruction, we performed an abdominal computed tomography scan and found an ovoid intraluminal mass with a mottled gas pattern in the distal descending colon. A large impacted bezoar was seen in the sigmoid colon, which was completely obstructed, and it was successfully removed by using colonoscopy.