Background Immune checkpoint inhibitors (ICIs) are emerging agents used for the treatment of various malignant tumors. As ICIs are generally used for unresectable malignant tumors, there have been only a few reports of patients who underwent surgery after receiving these drugs. Therefore, it remains unclear how immune-related adverse events (irAEs) affect the postoperative course. Here, we report a patient with advanced gastric cancer who underwent laparoscopic hepatectomy for liver metastases after an objective response with lenvatinib plus pembrolizumab and developed hypothyroidism and hypopituitarism as irAEs in the immediate postoperative period. Case presentation A 73-year-old man had undergone total gastrectomy for pT4aN2M0 gastric cancer followed by adjuvant chemotherapy with S-1 and docetaxel, and developed liver metastases in segments 6 and 7. He was enrolled in phase 2 clinical trial of lenvatinib plus pembrolizumab. He continuously achieved a partial response with the study treatment, and the liver metastases were decreased in size on imaging. The tumors were judged to be resectable and the patient underwent laparoscopic partial hepatectomy for segments 6 and 7. From the 1st postoperative day, the patient continuously presented with fever and general fatigue, and his fasting blood glucose level remained slightly lower than that before the surgery. On the 4th postoperative day, laboratory examination revealed hypothyroidism and hypopituitarism, which were suspected to be irAE caused by lenvatinib plus pembrolizumab after surgery. He received hydrocortisone first, followed by levothyroxine after adrenal insufficiency was recovered. Subsequently, his fever, general fatigue, and any abnormality regarding fasting blood glucose level resolved, and he was discharged on the 12th postoperative day. After discharge, his laboratory data for thyroid and pituitary function remained stable while receiving hydrocortisone and levothyroxine without recurrence of gastric cancer. Conclusion We present a case of laparoscopic hepatectomy after receiving lenvatinib plus pembrolizumab and developed hypothyroidism and hypopituitarism after surgery. Regarding surgery after ICI therapy, it is important to recognize that irAEs might occur in the postoperative period.

Objective: To develop a machine learning model that automatically quantifies the spread of blood in the surgical field using intraoperative videos of laparoscopic colorectal surgery and evaluate whether the index measured with the developed model can be used to assess tissue handling skill. Background: Although skill evaluation is crucial in laparoscopic surgery, existing evaluation systems suffer from evaluator subjectivity and are labor-intensive. Therefore, automatic evaluation using machine learning is potentially useful. Materials and Methods: In this retrospective experimental study, we used training data with annotated labels of blood or non-blood pixels on intraoperative images to develop a machine learning model to classify pixel RGB values into blood and non-blood. The blood pixel count per frame (the total number of blood pixels throughout a surgery divided by the number of frames) was compared among groups of surgeons with different tissue handling skills. Results: The overall accuracy of the machine learning model for the blood classification task was 85.7%. The high tissue handling skill group had the lowest blood pixel count per frame, and the novice surgeon group had the highest count (mean [SD]: high tissue handling skill group 20972.23 [19287.05] vs. low tissue handling skill group 34473.42 [28144.29] vs. novice surgeon group 50630.04 [42427.76], P<0.01). The difference between any 2 groups was significant. Conclusions: We developed a machine learning model to measure blood pixels in laparoscopic colorectal surgery images using RGB information. The blood pixel count per frame measured with this model significantly correlated with surgeons’ tissue handling skills.

Background: To perform accurate laparoscopic hepatectomy (LH) without injury, novel intraoperative systems of computer-assisted surgery (CAS) for LH are expected. Automated surgical workflow identification is a key component for developing CAS systems. This study aimed to develop a deep-learning model for automated surgical step identification in LH. Materials and methods: We constructed a dataset comprising 40 cases of pure LH videos; 30 and 10 cases were used for the training and testing datasets, respectively. Each video was divided into 30 frames per second as static images. LH was divided into nine surgical steps (Steps 0-8), and each frame was annotated as being within one of these steps in the training set. After extracorporeal actions (Step 0) were excluded from the video, two deeplearning models of automated surgical step identification for 8-step and 6-step models were developed using a convolutional neural network (Models 1 & 2). Each frame in the testing dataset was classified using the constructed model performed in real-time.Results: Above 8 million frames were annotated for surgical step identification from the pure LH videos. The overall accuracy of Model 1 was 0.891, which was increased to 0.947 in Model 2. Median and average accuracy for each case in Model 2 was 0.927 (range, 0.884-0.997) and 0.937 ± 0.04 (standardized difference), respectively. Real-time automated surgical step identification was performed at 21 frames per second. Conclusions: We developed a highly accurate deep-learning model for surgical step identification in pure LH. Our model could be applied to intraoperative systems of CAS.