Background: s/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot’s triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score:0.7761). Conclusions Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Background: s/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot’s triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score:0.7761). Conclusions Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Background: s/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot’s triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score:0.7761). Conclusions Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Esophageal perforation can lead to serious complications, and rapid diagnosis and treatment significantly affect the prognosis. Endoscopic vacuum-assisted closure (EndoVAC) therapy is widely accepted as a safe, well-tolerated, effective, versatile and practical procedure for the management of esophageal perforation in selected patients. We report the successful use of EndoVAC therapy for management of an esophageal perforation secondary to foreign body removal. A 56-year-old man presented to the emergency department for evaluation of chest pain after swallowing the plastic shell of a pill. Emergency endoscopy revealed an esophageal wall laceration (approximately 3 cm) and microperforation. The esophageal laceration and microperforation were limited to the mid-esophagus. The patient underwent EndoVAC therapy, which was repeated every 3–4 days for a total of six sessions over a period of 21 days. We observed improvement in the esophageal injury with granulation tissue formation during the fifth session. Subsequent follow-up evaluation, including esophagography and chest computed tomography confirmed complete healing of the esophageal injury. Following resumption of diet, the patienton a was discharged without any complications.

Morules, or morule-like features, can be identified in benign and malignant lesions in various organs. Morular features are unusual in pulmonary adenocarcinoma cases with only 26 cases reported to date. Here, we describe two cases of pulmonary adenocarcinoma with morule-like features in Korean women. One patient had a non-mucinous-type adenocarcinoma in situ and the other had an acinarpredominant adenocarcinoma with a micropapillary component. Both patients showed multiple intra-alveolar, nodular, whorled proliferative foci composed of atypical spindle cells with eosinophilic cytoplasm. Targeted next-generation sequencing was performed on DNA extracted from formalin-fixed paraffin-embedded samples of the tumors. Results showed unusual epidermal growth factor receptor (EGFR) mutations, which are associated with drug resistance to EGFR tyrosine kinase inhibitors, revealing the importance of identifying morule-like features in pulmonary adenocarcinoma and the need for additional study, since there are few reported cases.

No abstract available.
Adenocarcinoma ; Thymoma

No abstract available.
Humans ; Recurrence

BACKGROUND: Colorectal cancer (CRC) is one of the most common malignancies worldwide. Approximately 10%–15% of the CRC cases have defective DNA mismatch repair (MMR) genes. Although the high level of microsatellite instability status is a predictor of favorable outcome in primary CRC, little is known about its frequency and importance in secondary CRC. Immunohistochemical staining (IHC) for MMR proteins (e.g., MLH1, MSH2, MSH6, and PMS2) has emerged as a useful technique to complement polymerase chain reaction (PCR) analyses. METHODS: In this study, comparison between the MMR system of primary CRCs and paired liver and lung metastatic lesions was done using IHC and the correlation with clinical outcomes was also examined. RESULTS: Based on IHC, 7/61 primary tumors (11.4%) showed deficient MMR systems, while 13/61 secondary tumors (21.3%) showed deficiencies. In total, 44 cases showed proficient expression in both the primary and metastatic lesions. Three cases showed deficiencies in both the primary and paired metastatic lesions. In 10 cases, proficient expression was found only in the primary lesions, and not in the corresponding metastatic lesions. In four cases, proficient expression was detected in the secondary tumor, but not in the primary tumor. CONCLUSIONS: Although each IHC result and the likely defective genes were not exactly matched between the primary and the metastatic tumors, identical results for primary and metastatic lesions were obtained in 77% of the cases (47/61). These data are in agreement with the previous microsatellite detection studies that used PCR and IHC.

BACKGROUND: Extensive evidence has accumulated regarding the role of mesenchymal stromal cells (MSCs) in tumor progression, but the exact effects and mechanisms underlying this role remain unclear. We investigated the effects of MSC-associated tumor progression in MSC-sarcoma models and a gastric cancer metastatic model. METHODS: We conducted an in vitro growth kinetics assay and an in vivo tumor progression assay for sarcoma cells and gastric cancer cells in the presence or absence of MSCs. RESULTS: MSC-cocultured human fibrosarcoma cells (HT1080) showed accelerated growth compared with HT1080 alone (79- vs 37-fold change, p<.050). For HT1080, human MSC-coinjected tumors showed significantly greater and highly infiltrative growth compared to those of HT1080 alone (p=.035). For mouse fibrosarcoma cells (WEHI164), mouse MSC-coinjected tumors had greater volume than those of WEHI164 alone (p=.141). For rat sarcoma cells (RR1022), rat MSC-coinjected tumors exhibited greater volume and infiltrative growth than those of RR1022 alone (p=.050). For human gastric cancer cells (5FU), tumors of 5FU alone were compact, nodular in shape, and expansile with good demarcation and no definite lung metastatic nodules, whereas tumors grown in the presence of human MSCs showed highly desmoplastic and infiltrative growth and multiple lung metastasis. CONCLUSIONS: We observed morphological evidence for MSC-associated tumor progression of fibrosarcomas and gastric cancer cells.
Animals ; Fibrosarcoma* ; Fluorouracil ; Humans ; Kinetics ; Lung ; Mesenchymal Stromal Cells* ; Mice ; Neoplasm Metastasis ; Rats ; Sarcoma ; Stomach Neoplasms*

Eosinophilic pleural effusion (EPE) is defined as a pleural effusion that contains at least 10% eosinophils. EPE occurs due to a variety of causes such as blood or air in the pleural space, infection, malignancy, or an autoimmune disease. Undifferentiated connective tissue disease (UCTD) associated with eosinophilic pleural effusion is a rare condition generally characterized by the presence of the signs and symptoms but not fulfilling the existing classification criteria. We report a case involving a 67-year-old man with UCTD and EPE, who has been successfully treated with a single intrapleural corticosteroid injection.
Aged ; Autoimmune Diseases ; Connective Tissue Diseases* ; Connective Tissue* ; Eosinophilia ; Eosinophils* ; Humans ; Pleural Effusion*