Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Schizophyllum commune is a mold in phylum Basidiomycota and is an uncommon human pathogen. Sinusitis and allergic bronchopulmonary mycosis are the two major diseases caused by S. commune. Although there have been several reports of invasive fungal diseases, most of them were invasive sinusitis. We present a case of invasive fungal pneumonia due to S. commune, developed in a patient with acute myeloid leukemia presenting neutropenic fever. The diagnosis was made by characteristic macroscopic and microscopic findings of fungal isolate and was confirmed via sequencing of internal transcribed spacer region. The patient was improved after 8 weeks of antifungal therapy based on the susceptibility result.We propose that S. commune should be considered as an emerging pathogen of invasive fungal pneumonia when a patient is under immunocompromised state. We also reviewed global literatures focused on the invasive fungal diseases caused by S. commune

Anti-myelin oligodendrocyte glycoprotein (anti-MOG) syndrome is an immunemediated inflammatory condition of the central nervous system, which usually involves spinal cord and optic nerves. Herein, we studied the case of a 57-yearold female patient who presented with acute/subacute symptoms of sphincter dysfunction, paraparesis, and ocular pain. The patient was diagnosed with anti-MOG syndrome with findings resembling snake-eye appearance (SEA), characterized by nearly symmetrical round high signal intensity lesions located at anterior horns (gray matter) on T2-weighted image.

Purpose: To evaluate the MRI findings and clinical factors that are characteristic of patients who ultimately undergo surgery for medial epicondylitis. Materials and Methods: Fifty-two consecutive patients who were diagnosed with medial epicondylitis and underwent an elbow MRI between March 2010 and December 2018 were included in this retrospective study. The patients’ demographic information, clinical data, and MRI findings were evaluated. All variables were compared between the conservative treatment and surgical treatment groups. Logistic regression analyses were conducted to identify which factors were associated with surgical treatment. Results: Common flexor tear (CFT) tear size showed a statistically significant difference in both the transverse and longitudinal planes (p < 0.001, p = 0.013). The CFT abnormality grade significantly differed in both the transverse and longitudinal planes (p = 0.022, p = 0.003). A significant difference was also found in the medial collateral ligament abnormality (p = 0.025). Logistic regression analyses showed that only the transverse diameter of the CFT tear size (odds ratio:1.864; 95% confidence interval: 1.264–2.750) was correlated with surgical treatment. Conclusion Of patients diagnosed with medial epicondylitis, patients with a larger transverse CFT tear size tend to undergo surgical treatment ultimately.

Anti-myelin oligodendrocyte glycoprotein (anti-MOG) syndrome is an immunemediated inflammatory condition of the central nervous system, which usually involves spinal cord and optic nerves. Herein, we studied the case of a 57-yearold female patient who presented with acute/subacute symptoms of sphincter dysfunction, paraparesis, and ocular pain. The patient was diagnosed with anti-MOG syndrome with findings resembling snake-eye appearance (SEA), characterized by nearly symmetrical round high signal intensity lesions located at anterior horns (gray matter) on T2-weighted image.

Purpose: To evaluate the MRI findings and clinical factors that are characteristic of patients who ultimately undergo surgery for medial epicondylitis. Materials and Methods: Fifty-two consecutive patients who were diagnosed with medial epicondylitis and underwent an elbow MRI between March 2010 and December 2018 were included in this retrospective study. The patients’ demographic information, clinical data, and MRI findings were evaluated. All variables were compared between the conservative treatment and surgical treatment groups. Logistic regression analyses were conducted to identify which factors were associated with surgical treatment. Results: Common flexor tear (CFT) tear size showed a statistically significant difference in both the transverse and longitudinal planes (p < 0.001, p = 0.013). The CFT abnormality grade significantly differed in both the transverse and longitudinal planes (p = 0.022, p = 0.003). A significant difference was also found in the medial collateral ligament abnormality (p = 0.025). Logistic regression analyses showed that only the transverse diameter of the CFT tear size (odds ratio:1.864; 95% confidence interval: 1.264–2.750) was correlated with surgical treatment. Conclusion Of patients diagnosed with medial epicondylitis, patients with a larger transverse CFT tear size tend to undergo surgical treatment ultimately.