Phase-separated structures of tunable thermoresponsive and matrix polymers for large-scale temperature monitoring coatings.

Temperature monitoring is significant and fundamental in the fields of healthcare and medicine. In surgery, ultrasonic cutting devices are used for cutting, coagulation, and hemostasis. However, surgeons are concerned about the collateral thermal damages. For example, due to the limited space during endoscopic surgery, thermal damage is caused by touching the surrounding tissues of the targeted organ with the heated shaft of the ultrasonic cutting device. The present work exhibits thermoresponsive and reversible color-change coatings for temperature-distribution imaging. The phase-separated structures of the layered conjugated and matrix polymers enable both the tuned thermoresponsivity and large-scale coating. Layered polydiacetylene (PDA) with intercalated guests exhibits reversible and thermoresponsive gradual color changes from blue to red. A matrix polymer facilitates formation of the phase-separated layered PDA and large-scale coating. Spraying the precursor solution containing the diacetylene monomer, guest molecule, and matrix polymer provides the self-organized large-scale coatings on substrates. The temperature distribution on the shaft of an ultrasonic cutting device is monitored using the coatings. The phase-separated structure of thermoresponsive and matrix polymers can be applied to tunable temperature monitoring in a variety of fields.

Prognostic Impact of Thoracic Duct Resection in Patients Who Underwent Transthoracic Esophagectomy Following Neoadjuvant Therapy for Esophageal Squamous Cell Carcinoma: Exploratory Analysis of JCOG1109.

BACKGROUND: Although several studies have investigated whether thoracic duct (TD) resection improves prognosis, the conclusion remains controversial. JCOG1109 is a three-arm randomized phase III trial to confirm the survival advantage of docetaxel, cisplatin, 5-fluorouracil (DCF), and cisplatin plus 5-fluorouracil (CF) combined with radiotherapy (CF-RT) over CF as neoadjuvant treatment. The study aimed to evaluate the survival impact of TD resection and its association with neoadjuvant treatment and pathological response in patients enrolled in JCOG1109. PATIENTS AND METHODS: Clinicopathological factors, surgical results, and prognosis were compared between TD preserved and resected groups. The survival impact of TD resection was also evaluated in the subgroups on the basis of combinations of preoperative therapy and pathological response. RESULTS: Between December 2012 and July 2018, 601 patients were randomized (CF/DCF/CF-RT; 199/202/200) in JCOG1109. Of them, 541 patients underwent esophagectomy (183/181/177), and TD was resected in 265 patients (93/91/81). For the entire cohort, TD resection was not a significant prognostic factor for overall survival in the multivariable analysis (HR 1.20, 95% CI 0.91-1.57). In the subgroup analyses by combinations of neoadjuvant treatment and pathological response, TD resected group had a significantly better overall survival compared with TD preserved group in patients who received DCF and achieved pathological response (HR 0.20, 95% CI 0.07-0.61). CONCLUSIONS: The survival benefit of TD resection was not demonstrated in patients with surgically resectable esophageal squamous cell carcinoma enrolled in JCOG1109. The residual tumor burden after neoadjuvant treatment might be linked to the survival impact of TD resection.

Safety and Efficacy of Conversion Therapy After Systemic Chemotherapy in Advanced Esophageal Cancer with Distant Metastases: A Multicenter Retrospective Observational Study.

BACKGROUND: Patients with esophageal squamous cell carcinoma (ESCC) with distant metastasis were treated with systemic chemotherapy. Recent advances in multimodal treatments have made conversion therapy a viable option for patients with incurable ESCC. OBJECTIVE: We aimed to assess the safety and efficacy of conversion therapy for ESCC with distant metastases. METHODS: Conversion therapy was defined as surgery or chemoradiotherapy (CRT) used to cure tumors that were previously considered incurable because of distant metastasis. We conducted a retrospective review of patients who underwent ESCC conversion therapy and assessed the treatment outcomes, including adverse events and survival rates. RESULTS: A total of 147 patients from 22 institutions were included. Systemic chemotherapy was initially administered to all patients. The most common M1 factor was the para-aortic lymph node, accounting for 55% of cases. Following the initial treatment, 116 patients underwent surgery, with 31 receiving CRT as conversion therapy. Postoperative complications in surgery patients included pneumonia (16%), anastomotic leakage (7%), and recurrent laryngeal nerve palsy (6%). During CRT, 18% of patients developed grade 3 or higher non-hematological toxicities. The 5-year overall survival (OS) rate was 31.7%. Pathological responders had significantly longer OS than non-responders (hazard ratio 0.493, p = 0.012). The distribution of distant metastasis, regimen type, clinical response, and conversion therapy modality did not have a significant impact on OS. CONCLUSIONS: Conversion therapy can be safely performed for ESCC with distant metastasis and has a favorable prognosis.

Usefulness of an Artificial Intelligence Model in Recognizing Recurrent Laryngeal Nerves During Robot-Assisted Minimally Invasive Esophagectomy.

BACKGROUND: Recurrent laryngeal nerve (RLN) palsy is a common complication in esophagectomy and its main risk factor is reportedly intraoperative procedure associated with surgeons' experience. We aimed to improve surgeons' recognition of the RLN during robot-assisted minimally invasive esophagectomy (RAMIE) by developing an artificial intelligence (AI) model. METHODS: We used 120 RAMIE videos from four institutions to develop an AI model and eight other surgical videos from another institution for AI model evaluation. AI performance was measured using the Intersection over Union (IoU). Furthermore, to verify the AI's clinical validity, we conducted the two experiments on the early identification of RLN and recognition of its location by eight trainee surgeons with or without AI. RESULTS: The IoUs for AI recognition of the right and left RLNs were 0.40 ± 0.26 and 0.34 ± 0.27, respectively. The recognition of the right RLN presence in the beginning of right RLN lymph node dissection (LND) by surgeons with AI (81.3%) was significantly more accurate (p = 0.004) than that by surgeons without AI (46.9%). The IoU of right RLN during right RLN LND recognized by surgeons with AI (0.59 ± 0.18) was significantly higher (p = 0.010) than that by surgeons without AI (0.40 ± 0.29). CONCLUSIONS: Surgeons' recognition of anatomical structures in RAMIE was improved by our AI system with high accuracy. Especially in right RLN LND, surgeons could recognize the RLN more quickly and accurately by using the AI model.

Outcomes of laparoscopic and endoscopic cooperative surgery for gastric submucosal tumors: A retrospective multicenter study at 21 Japanese institutions.

Aim: We conducted a multicenter study on classical laparoscopic and endoscopic cooperative surgery (LECS) and LECS-related procedures to retrospectively clarify the safety, problems, and mid-term outcomes of these methods after their coverage by the national health insurance. Methods: A total of 201 patients who underwent classical LECS/LECS-related procedures for gastric submucosal tumors (G-SMTs) in 21 institutions affiliated with the Laparoscopy Endoscopy Cooperative Surgery Study Group from April 2014 to March 2016 were included. Data was retrospectively obtained from the patients' charts. Results: The most common surgical procedure was classical LECS (155 patients, 77.1%), non-exposed endoscopic wall inversion surgery (22 patients, 11.4%), a combination of laparoscopic and endoscopic approaches to neoplasia with non-exposure technique (16 patients, 8%), and closed LECS (two patients, 1%). Only six (3%) patients underwent LECS with gastrostomy. The mean operative time and blood loss were 188.4 (70-462) minutes and 23.3 (0-793) g, respectively. Ten (5%) patients developed postoperative complications (Clavien-Dindo classification grade II or higher). Two patients needed reoperation due to postoperative bleeding or anastomotic leakage. All tumors were resected with negative margins. A total of 127 (63.2%) patients underwent follow-up observations for over 36 months, one of whom had a recurrence of peritoneal dissemination and one had poor oral intake. Conclusion: Classical LECS and LECS-related procedures for G-SMTs have favorable short/mid-term outcomes.

Endoscopic ultrasound classification for prediction of endoscopic submucosal dissection resectability: PREDICT classification.

Background and study aims The safety of endoscopic submucosal dissection (ESD) has been reported, and the risk of lymph node metastasis is low for colorectal cancer if depth of invasion is the only non-curative factor on histological evaluation. ESD is increasingly performed even if submucosal (SM) invasion is suspected. However, reports about endoscopic findings for the criteria to predict ESD resectability remain limited. Endoscopic ultrasound (EUS) can directly visualize the tomographic image of the gastrointestinal wall and may help predict ESD resectability. Therefore, we investigated the possibility of predicting ESD resectability using EUS. Patients and methods We compared the association between EUS findings and pathological results for gastric or colorectal lesions with suspected SM invasion using white light endoscopy between June 2020 and January 2023. EUS findings were grouped based on the status of the underlying the tumor, as follows: Type I, submucosal layer was observed with reproducibility; Type II, submucosal layer not fully visible; and Type III, submucosal layer disrupted and muscularis propria (MP) layer thickened. Results Forty-one gastric cancer and 22 colorectal cancer cases were analyzed. The proportions of pathological VM0 (no tumor exposed on any vertical margin) for ESD-resected specimens were 89% and 33% for Type I and II, respectively, ( P ≤ 0.01). The proportions of cancer involving MP or deeper were significantly higher for Type II/III than for Type I (41% vs 0%, P ≤ 0.01). Conclusions EUS may have an important role in predicting ESD resectability of gastric and colorectal cancers suspected of having SM invasion.

Simple severity scale for perforated peptic ulcer with generalized peritonitis: A derivation and internal validation study.

BACKGROUND: Perforated peptic ulcer (PPU) causes peritonitis and requires surgery based on disease severity. This study aimed to develop and validate a severity scale for PPU with generalized peritonitis. MATERIALS AND METHODS: This retrospective cohort study used a nationwide multi-center surgical database (2013-2020). Patients aged >15 years who underwent surgery for PPU with generalized peritonitis were included and categorized into the derivation (2013-2018) and two validation (2019 and 2020) cohorts. Possible severity predictors were selected via a literature review, and Lasso models were developed to predict severe postoperative adverse events with 2000 bootstrapping. Final variables for the scoring system were determined based on inclusion frequency (≥90%) in the Lasso models. Discrimination and accuracy were evaluated using c-statistics and calibration plots. Cutoff values for minimal postoperative adverse events were examined using negative predictive values. RESULTS: Among 12,513 patients included (1,202 underwent laparoscopic surgery), 533 (5.9%), 138 (7.6%), and 117 (6.9%) in the derivation and two validation cohorts experienced postoperative adverse events. Age, dyspnea at rest, preoperative sepsis, III/IV/V of American Society of Anesthesiologists physical status, and albumin and creatinine were selected for the final model. A 0-11 scoring system was developed with c-statistics of 0.812-0.819. Cutoff value was determined as 5, which predicted <3% probability of postoperative adverse events regardless of type of surgery. CONCLUSIONS: A score of <5 predicts minimal risks for postoperative adverse events and therefore would be clinically useful to determine type of surgery. Further studies are needed to validate the score.

Targeting SNCA in the treatment of malignant ascites in gastrointestinal cancer.

Peritoneal tumor dissemination and subsequent malignant tumor ascites (MTA) occur unexpectedly and repeatedly in patients with gastrointestinal (GI) cancers, and worsen quality of life and prognosis of the patients. Various treatments have been clinically developed for these patients, while most of the MTA cases are refractory to the treatments. Thus, effective treatments are urgently needed to improve the clinical outcomes. In this study, we identified α-synuclein (SNCA) as an immunological determinant of MTA progression in GI cancer through translational research using mouse tumor models and clinical specimens collected from gastric cancer patients. We found that the SNCA+ subsets were significantly increased in CD3+ T cells, CD56+ NK cells, and CD11b+ myeloid cells within MTA and peripheral blood cells (PBCs) of MTA cases, albeit almost absent in PBCs of healthy donors, and spleen of naive mice. Of note, the SNCA+ T-cell subset was rarely seen in patients that intraperitoneal lavage fluid without tumor cells was collected before surgery as a tumor-free control, suggesting a possible cancer-induced product, especially within the peritoneal cavity. In vivo treatment with anti-SNCA blocking mAb significantly induced anti-tumor effects in mouse MTA models, and synergistically improved anti-PD1 therapeutic efficacy, providing a significantly better prognosis. These suggest that SNCA is involved in severe immunosuppression in the MTA cases, and that blocking SNCA is effective in dramatically improving the immune status in the hosts. Targeting SNCA will be a promising strategy to improve clinical outcomes in the treatment of GI cancer patients, especially with MTA.

Evaluating surgical expertise with AI-based automated instrument recognition for robotic distal gastrectomy.

Introduction: Complexities of robotic distal gastrectomy (RDG) give reason to assess physician's surgical skill. Varying levels in surgical skill affect patient outcomes. We aim to investigate how a novel artificial intelligence (AI) model can be used to evaluate surgical skill in RDG by recognizing surgical instruments. Methods: Fifty-five consecutive robotic surgical videos of RDG for gastric cancer were analyzed. We used Deeplab, a multi-stage temporal convolutional network, and it trained on 1234 manually annotated images. The model was then tested on 149 annotated images for accuracy. Deep learning metrics such as Intersection over Union (IoU) and accuracy were assessed, and the comparison between experienced and non-experienced surgeons based on usage of instruments during infrapyloric lymph node dissection was performed. Results: We annotated 540 Cadiere forceps, 898 Fenestrated bipolars, 359 Suction tubes, 307 Maryland bipolars, 688 Harmonic scalpels, 400 Staplers, and 59 Large clips. The average IoU and accuracy were 0.82 ± 0.12 and 87.2 ± 11.9% respectively. Moreover, the percentage of each instrument's usage to overall infrapyloric lymphadenectomy duration predicted by AI were compared. The use of Stapler and Large clip were significantly shorter in the experienced group compared to the non-experienced group. Conclusions: This study is the first to report that surgical skill can be successfully and accurately determined by an AI model for RDG. Our AI gives us a way to recognize and automatically generate instance segmentation of the surgical instruments present in this procedure. Use of this technology allows unbiased, more accessible RDG surgical skill.

MUC1-C Dependence for the Progression of Pancreatic Neuroendocrine Tumors Identifies a Druggable Target for the Treatment of This Rare Cancer.

Patients with pancreatic neuroendocrine tumors (pNETs) have limited access to effective targeted agents and invariably succumb to progressive disease. MUC1-C is a druggable oncogenic protein linked to driving pan-cancers. There is no known involvement of MUC1-C in pNET progression. The present work was performed to determine if MUC1-C represents a potential target for advancing pNET treatment. We demonstrate that the MUC1 gene is upregulated in primary pNETs that progress with metastatic disease. In pNET cells, MUC1-C drives E2F- and MYC-signaling pathways necessary for survival. Targeting MUC1-C genetically and pharmacologically also inhibits self-renewal capacity and tumorigenicity. Studies of primary pNET tissues further demonstrate that MUC1-C expression is associated with (i) an advanced NET grade and pathological stage, (ii) metastatic disease, and (iii) decreased disease-free survival. These findings demonstrate that MUC1-C is necessary for pNET progression and is a novel target for treating these rare cancers with anti-MUC1-C agents under clinical development.

Doublet chemotherapy, triplet chemotherapy, or doublet chemotherapy combined with radiotherapy as neoadjuvant treatment for locally advanced oesophageal cancer (JCOG1109 NExT): a randomised, controlled, open-label, phase 3 trial.

BACKGROUND: Neoadjuvant therapy is the standard treatment for patients with locally advanced oesophageal squamous cell carcinoma (OSCC). However, the prognosis remains poor and more intensive neoadjuvant treatment might be needed to improve patient outcomes. We therefore aimed to compare the efficacy and safety of neoadjuvant doublet chemotherapy, triplet chemotherapy, and doublet chemotherapy plus radiotherapy in patients with previously untreated locally advanced OSCC. METHODS: In this randomised, open-label, phase 3 trial, patients aged 20-75 years with previously untreated locally advanced OSCC and an Eastern Cooperative Oncology Group performance status of 0 or 1 were recruited from 44 centres across Japan. Patients were randomly assigned (1:1:1) centrally via a web-based system to receive neoadjuvant doublet chemotherapy (two courses of fluorouracil [800 mg/m2 per day intravenously on days 1-5] and cisplatin [80 mg/m2 per day on day 1] separated by an interval of 3 weeks [NeoCF]), triplet chemotherapy (three courses of fluorouracil [750 mg/m2 per day on days 1-5], cisplatin [70 mg/m2 per day on day 1], and docetaxel [70 mg/m2 per day on day 1] repeated every 3 weeks [NeoCF+D]), or doublet chemotherapy (two courses of fluorouracil [1000 mg/m2 per day on days 1-4] and cisplatin [75 mg/m2 per day on day 1] separated by an interval of 4 weeks) plus 41·4 Gy radiotherapy [NeoCF+RT]) followed by oesophagectomy with regional lymph node dissection. Randomisation was stratified by T stage and institution. Participants, investigators, and those assessing outcomes were not masked to group assignment. The primary endpoint was overall survival, analysed by intention to treat. Analysis of safety included all patients who received at least one course of chemotherapy, and analysis of surgical complications included those who also underwent surgery. This study is registered with the Japan Registry of Clinical Trials, jRCTs031180202, and the trial is complete. FINDINGS: A total of 601 patients (529 male individuals and 72 female individuals) were randomly assigned between Dec 5, 2012, and July 20, 2018, with 199 patients in the NeoCF group, 202 patients in the NeoCF+D group, and 200 patients in the NeoCF+RT group. Compared with the NeoCF group, during a median follow-up period of 50·7 months (IQR 23·8-70·7), the 3-year overall survival rate was significantly higher in the NeoCF+D group (72·1% [95% CI 65·4-77·8] vs 62·6% [55·5-68·9]; hazard ratio [HR] 0·68, 95% CI 0·50-0·92; p=0·006) but not in the NeoCF+RT group (68·3% [61·3-74·3]; HR 0·84, 0·63-1·12; p=0·12). Grade 3 or higher febrile neutropenia occurred in two (1%) of 193 patients in the NeoCF group, 32 (16%) of 196 patients in the NeoCF+D group, and nine (5%) of 191 patients in the NeoCF+RT group. Treatment-related adverse events leading to termination of neoadjuvant therapy were more common in the NeoCF+D group (18 [9%] of 202 participants) than in the NeoCF+RT group (12 [6%] of 200) and NeoCF group (eight [4%] of 199). There were three (2%) treatment-related deaths during neoadjuvant therapy in the NeoCF group, four (2%) deaths in the NeoCF+D group, and two (1%) deaths in the NeoCF+RT group. Grade 2 or higher postoperative pneumonia, anastomotic leak, and recurrent laryngeal nerve paralysis were reported in 19 (10%), 19 (10%), and 28 (15%) of 185 patients, respectively, in the NeoCF group; 18 (10%), 16 (9%), and 19 (10%) of 183 patients, respectively, in the NeoCF+D group; and 23 (13%), 23 (13%), and 17 (10%) of 178 patients, respectively, in the NeoCF+RT group. The in-hospital deaths following surgery included three deaths in the NeoCF group, two deaths in the NeoCF+D group, and one in the NeoCF+RT group. INTERPRETATION: Neoadjuvant triplet chemotherapy followed by oesophagectomy resulted in a statistically significant overall survival benefit compared with doublet chemotherapy and might be the new standard of care for locally advanced OSCC who are in good condition in Japan. Neoadjuvant doublet chemotherapy plus radiotherapy did not show significant improvement of survival compared with doublet chemotherapy. FUNDING: Japan Agency for Medical Research and Development and National Cancer Center Research and Development Fund.

Identifying the Trends of Urinary microRNAs within Extracellular Vesicles for Esophageal Cancer.

Background: The advancement of multidisciplinary treatment has increased the need to develop tests to monitor tumor burden during treatment. We herein analyzed urinary microRNAs within extracellular vesicles from patients with esophageal squamous cell carcinoma (ESCC) and normal individuals using a microarray. Methods: Patients with advanced ESCC who underwent esophagectomy (A), endoscopic submucosal resection (ESD) (B), and healthy donors (C) were included. Based on microRNA expression among the groups (Analysis 1), microRNAs with significant differences between groups A and C were selected (Analysis 2). Of these candidates, microRNAs in which the change between A and C was consistent with the change between B and C were selected for downstream analysis (Analysis 3). Finally, microRNA expression was validated in patients with recurrence from A (exploratory analysis). Results: For analysis 1, 205 microRNAs were selected. For Analyses 2 and 3, the changes in 18 microRNAs were consistent with changes in tumor burden as determined by clinical imaging and pathological findings. The AUC for the detection of ESCC using 18 microRNAs was 0.72. In exploratory analysis, three of eighteen microRNAs exhibited a concordant trend with recurrence. Conclusions: The current study identified the urinary microRNAs which were significantly expressed in ESCC patients. Validation study is warranted to evaluate whether these microRNAs could reflect tumor burden during multidisciplinary treatment for ESCC.

Comparison of the survival outcomes between retrocolic and antecolic Roux-en-Y reconstruction after gastrectomy for gastric cancer.

Background: There are two methods of Roux-en-Y (RY) reconstruction after gastrectomy: the antecolic route (ACR) and retrocolic route (RCR). There is no evidence to support that the ACR achieves comparable long-term survival. Methods: This was a multi-center historical cohort study. Patients diagnosed with clinical T3/4a and any N stage who underwent open gastrectomy and R0 resection for gastric adenocarcinoma between January 2006 and December 2012 were enrolled. The primary outcome was the hazard ratio of ACR for overall survival, with adjustment for confounding factors by propensity score matching, and a Cox proportional hazards model. Results: A total of 1758 eligible patients were identified from the database. After matching, 410 patients in the ACR and RCR groups were included in the final analysis. The adjusted hazard ratio (95% CI) for ACR was 1.148 (0.870-1.492). The five-year survival rates in the ACR and RCR groups were 74.3% (69.5-78.4) and 77.3% (72.3-81.2), respectively. The short-term surgical outcomes of the two groups did not differ to a statistically significant extent. Conclusion: The route used to lift the jejunum in RY reconstruction did not affect the incidence of long-term survival or postoperative complications. The ACR and RCR are both acceptable options for RY reconstruction during gastric cancer surgery.

Recurrence-free survival as a surrogate endpoint for overall survival after neoadjuvant chemotherapy and surgery for oesophageal squamous cell carcinoma.

BACKGROUND: Overall survival is considered as one of the most important endpoints of treatment efficacy but often requires long follow-up. This study aimed to determine the validity of recurrence-free survival as a surrogate endpoint for overall survival in patients with surgically resectable advanced oesophageal squamous cell carcinoma (OSCC). METHODS: Patients with OSCC who received neoadjuvant cisplatin and 5-fluorouracil, or docetaxel, cisplatin and 5-fluorouracil, at 58 Japanese oesophageal centres certified by the Japan Esophageal Society were reviewed retrospectively. The correlation between recurrence-free and overall survival was assessed using Kendall's τ. RESULTS: The study included 3154 patients. The 5-year overall and recurrence-free survival rates were 56.6 and 47.7% respectively. The primary analysis revealed a strong correlation between recurrence-free and overall survival (Kendall's τ 0.797, 95% c.i. 0.782 to 0.812) at the individual level. Subgroup analysis showed a positive relationship between a more favourable pathological response to neoadjuvant chemotherapy and a higher τ value. In the meta-regression model, the adjusted R2 value at the institutional level was 100 (95% c.i. 40.2 to 100)%. The surrogate threshold effect was 0.703. CONCLUSION: There was a strong correlation between recurrence-free and overall survival in patients with surgically resectable OSCC who underwent neoadjuvant chemotherapy, and this was more pronounced in patients with a better response to neoadjuvant chemotherapy.

Remarkable response as a new indicator for endoscopic evaluation of local efficacy of non-surgical treatments for esophageal cancer.

In Japan, standard of care of the patients with resectable esophageal cancer is neoadjuvant chemotherapy (NAC) followed by esophagectomy. Patients unfitted for surgery or with unresectable locally advanced esophageal cancer are generally indicated with definitive chemoradiotherapy (CRT). Local disease control is undoubtful important for the management of patients with esophageal cancer, therefore endoscopic evaluation of local efficacy after non-surgical treatments must be essential. The significant shrink of primary site after NAC has been reported as a good indicator of pathological good response as well as favorable survival outcome after esophagectomy. And patients who could achieve remarkable shrink to T1 level after CRT had favorable outcomes with salvage surgery and could be good candidates for salvage endoscopic treatments. Based on these data, "Japanese Classification of Esophageal Cancer, 12th edition" defined the new endoscopic criteria "remarkable response (RR)", that means significant volume reduction after treatment, with the subjective endoscopic evaluation are proposed. In addition, the finding of local recurrence (LR) at primary site after achieving a CR was also proposed in the latest edition of Japanese Classification of Esophageal Cancer. The findings of LR are also important for detecting candidates for salvage endoscopic treatments at an early timing during surveillance after CRT. The endoscopic evaluation would encourage us to make concrete decisions for further treatment indications, therefore physicians treating patients with esophageal cancer should be well-acquainted with each finding.

Automated artificial intelligence-based phase-recognition system for esophageal endoscopic submucosal dissection (with video).

BACKGROUND AND AIMS: Endoscopic submucosal dissection (ESD) for superficial esophageal cancer is a multistep treatment involving several endoscopic processes. Although analyzing each phase separately is worthwhile, it is not realistic in practice owing to the need for considerable manpower. To solve this problem, we aimed to establish a state-of-the-art artificial intelligence (AI)-based system, specifically, an automated phase-recognition system that can automatically identify each endoscopic phase based on video images. METHODS: Ninety-four videos of ESD procedures for superficial esophageal cancer were evaluated in this single-center study. A deep neural network-based phase-recognition system was developed in an automated manner to recognize each of the endoscopic phases. The system was trained with the use of videos that were annotated and verified by 2 GI endoscopists. RESULTS: The overall accuracy of the AI model for automated phase recognition was 90%, and the average precision, recall, and F value rates were 91%, 90%, and 90%, respectively. Two representative ESD videos predicted by the model indicated the usability of AI in clinical practice. CONCLUSIONS: We demonstrated that an AI-based automated phase-recognition system for esophageal ESD can be established with high accuracy. To the best of our knowledge, this is the first report on automated recognition of ESD treatment phases. Because this system enabled a detailed analysis of phases, collecting large volumes of data in the future may help to identify quality indicators for treatment techniques and uncover unmet medical needs that necessitate the creation of new treatment methods and devices.

Identifying intense inflammatory subtype of esophageal squamous cell carcinoma using clustering approach.

OBJECTIVE: To establish a risk-stratification system for predicting the postoperative recurrence of esophageal squamous cell carcinoma, this study aimed to evaluate the prognostic value of clusters based on blood inflammation and coagulation markers and investigate their correlation with serum cytokines and genetic alteration. METHOD: This single-center, retrospective cohort study enrolled 491 patients with esophageal cancer who underwent subtotal esophagectomy between 2004 and 2012. For cluster exploration, nonhierarchical cluster analysis and k-means were applied using serum C-reactive protein, albumin, fibrinogen, and platelet-lymphocyte ratio as variables. Then, multivariate survival analysis was conducted to investigate the association of clusters with recurrence-free survival. To characterize the clusters, serum interleukin-6, interleukin-8, and genetic alteration in primary tumors, the PleSSision-Rapid panel, which can evaluate 160 representative driver genes, was used. RESULTS: Patients were classified into clusters 1, 2, and 3, which included 24 (5%), 161 (33%), and 306 (62%) patients, respectively. Compared with cluster 3, cluster 1 or 2 had significantly worse recurrence-free survival. Based on the multivariable analysis using cluster, pStage, and age as covariates, cluster was an independent prognostic factor for recurrence-free survival (hazard ratio, 1.55; 95% confidence interval, 1.08-2.21; P = 0.02). The percentage of serum interleukin-6 and interleukin-8 levels was the highest in cluster 1, followed by clusters 2 and 3. In 23 patients with available genomic profiles, no significant difference in representative genomic alterations was observed. CONCLUSIONS: Non-biased clustering using inflammation and coagulation markers identified the intense inflammatory subtype, which had an independent prognostic effect on recurrence-free survival.