Efficacy of double-scope endoscopic submucosal dissection and long-term outcomes of endoscopic resection for superficial pharyngeal cancer

Effectiveness and outcomes of endoscopic resection for superficial pharyngeal squamous cell carcinomas

BACKGROUND

With the development of endoscopic imaging, superficial pharyngeal squamous cell carcinoma can now be detected during routine endoscopy. Recently, the effectiveness of endoscopic resection for superficial pharyngeal squamous cell carcinoma have been reported.

METHODS

This study had a retrospective single-center design that included patients with superficial pharyngeal squamous cell carcinoma who underwent endoscopic resection. A total 47 patients with 53 lesions were analyzed.

RESULTS

En bloc and R0 resection rates were 83.0% and 56.6%. Local recurrence and cervical lymph node metastasis (CLNM) were detected in 1 and 3 patients during follow-up. The macroscopic type 0-I was an independent factor for CLNM. The 3-year cumulative incidence of metachronous pharyngeal squamous cell carcinoma following endoscopic resection was 33.0%, and the 5-year overall survival rate was 89.2%.

CONCLUSIONS

Endoscopic resection is an effective treatment for superficial pharyngeal squamous cell carcinomas, and the macroscopic type 0-I is a useful predictor of CLNM.

Efficacy and safety of the water pressure method for endoscopic submucosal dissection in superficial pharyngeal cancer

Background and study aims Superficial pharyngeal cancers can be cured with transoral surgery (TOS), which preserves organ function and quality of life. Pharyngeal endoscopic submucosal dissection (ESD) is challenging to perform because of limited maneuverability and complex anatomical features. The water pressure method (WPM) is useful for natural traction techniques during ESD and is potentially useful for pharyngeal ESD. This study aimed to investigate the short-term outcomes of WPM-ESD for pharyngeal lesions. Patients and methods Therapeutic outcomes of patients who underwent WPM-ESD for pharyngeal lesions at Keio University between May 2019 and February 2022 were retrospectively analyzed. Results Twenty-one pharyngeal lesions treated with WPM-ESD were analyzed. Three lesions were located in the oropharynx and 18 in the hypopharynx. All ESD procedures were performed under general anesthesia. The endoscopic en bloc resection rate was 100%. The median procedure time was 15 minutes (range 4-45 minutes). All patients were successfully extubated on the day of ESD. No serious adverse events (AEs) related to WPM-ESDs were observed. None of the patients required nasogastric intubation, percutaneous endoscopic gastrostomy, or tracheotomy. The median fasting time and hospital stay were 2 days (range 2-5 days) and 6 days (range 6-10 days), respectively. All the histological results indicated squamous cell carcinoma. The complete histologic resection rate was 76.2%. Conclusions WPM-ESD achieved a high en bloc resection rate and short procedure time without serious AEs. Thus, it may be a useful treatment for pharyngeal lesions.

Long-term outcome of cervical lymph node metastasis in superficial pharyngeal squamous cell carcinoma after endoscopic submucosal dissection

BACKGROUND AND AIMS

Superficial pharyngeal squamous cell carcinoma (PSCC) has received increasing attention as a therapeutic target in the GI field with recent innovations in endoscopic submucosal dissection (ESD). However, there are currently no defined criteria for the application of ESD to superficial PSCC. One of the problems encountered during follow-up after ESD is cervical lymph node metastasis (LNM). Identifying the clinicopathologic predictors of cervical LNM can help to provide a basis for the refinement of therapeutic strategies for superficial PSCC.

METHODS

The risk of cervical LNM was evaluated in 331 patients with superficial PSCC who underwent initial ESD between 2008 and 2021. Since tumor size, rather than depth, is the dominant factor in the current TNM classification for PSCC, the correlation between tumor size and thickness was investigated.

RESULTS

The median follow-up period was 4.8 years. The cumulative 5-year cervical LNM rate was 6.1%. Multivariate Cox proportional hazards regression analysis identified tumor thickness ≥1000 μm and lymphatic invasion as significant independent predictors. Among 204 cases with subepithelial invasion, both factors were also revealed to be significant independent predictors, suggesting that tumor thickness was superior to tumor size in predicting cervical LNM. Despite the positive correlation between tumor thickness and size, there was noticeable variability in the values (R = .20), and the current staging was inadequate to identify groups at high risk for cervical LNM.

CONCLUSIONS

Tumor thickness and lymphatic invasion are validated as significant independent predictors for cervical LNM and can be useful indicators to optimize the therapeutic strategies for superficial PSCC.

Prediction of depth of invasion and lymph node metastasis in superficial pharyngeal cancer by magnifying endoscopy using the Japan Esophageal Society classification

Backgrounds

The pharynx has no muscularis mucosae, so it is unclear whether diagnostic techniques used for the esophagus can be applied to the pharynx. This study investigated the usefulness of magnifying endoscopy with narrowband imaging using the Japan Esophageal Society (JES) classification for predicting the depth of invasion and lymph node metastasis (LNM) in pharyngeal cancer.

Methods

A total of 123 superficial pharyngeal carcinoma lesions that had been observed preoperatively with magnifying endoscopy with narrowband imaging between January 2014 and June 2021 were analyzed. Predictors of subepithelial invasion (SEP) and LNM were sought based on endoscopic findings, including microvascular morphology, using the JES classification.

Results

The lesions were divided into carcinoma in situ (n = 41) and SEP (n = 82). Multivariate analysis identified B2–B3 vessels (odds ratio [OR] 6.54, 95% confidence interval [CI] 1.74–24.61, p = 0.005) and a middle/large avascular area (OR 4.15, 95% CI 1.18–14.62, p = 0.027) as independent predictors of SEP. Significant predictors of LNM were protruding type, B2–B3 vessels, middle/large avascular area, SEP, venous invasion, lymphatic invasion, and tumor thickness > 1000 μm. Median tumor thickness increased significantly in the order of B1 < B2 < B3 vessels (B1, 305 μm; B2, 1045 μm; B3, 4043 μm; p < 0.001). The LNM rates for B1, B2, and B3 vessels were 1.6% (1/63), 4.8% (2/42), and 55.6% (10/18), respectively (p < 0.001).

Conclusions

Magnifying endoscopy with narrowband imaging using the JES classification could predict the depth of invasion in superficial pharyngeal carcinoma. The JES classification may contribute to the prediction of LNM, suggesting that it could serve as an alternative to tumor thickness.

Efficacy of a new traction method using ring-shaped thread for endoscopic submucosal dissection in the pharynx

BACKGROUND

Endoscopic submucosal dissection (ESD) is a minimally invasive treatment for pharyngeal cancers. However, pharyngeal ESD is sometimes technically challenging because of the narrow and complex space in which to work. Traction is important to complete the procedure efficiently. Here, we report the technical details and efficacy of a new traction method for pharyngeal ESD using ring-shaped thread and grasping forceps.

METHODS

We analyzed pharyngeal ESD performed between January 2016 and March 2021 at our Institute. We designated cases resected using ring-shaped threads "Group R" and those resected without ring-shaped threads as conventional "Group C", and compared the technical outcomes between them. Multivariate analysis and the inverse probability treatment weighting (IPTW) method using propensity scores were adjusted by confounding variables.

RESULTS

We analyzed 89 lesions from 68 patients, of which 46 were in Group R and 43 in Group C. Median procedure time and median dissection speed were significantly shorter in Group R than C (37 min vs. 55 min, and 16.0 mm²/min vs. 7.0 mm²/min, respectively, both P < 0.05). These results were confirmed by both multivariate analysis and after IPTW adjustment. All lesions were resected en bloc, and the complete resection rate was not significantly different between Group R and C (91.3% vs. 79.1%, P = 0.14). There were no treatment-related adverse events in either group.

CONCLUSIONS

The traction method using ring-shaped thread increases the efficiency of pharyngeal ESD. This simple new traction method should be a useful option for pharyngeal ESD.

Risk factors for incomplete resection with pharyngeal endoscopic submucosal dissection and long-term prognosis after resection

BACKGROUND

Advances in endoscopic imaging technology have led to an increase in detection of superficial pharyngeal squamous carcinoma. Endoscopic submucosal dissection (ESD) has been reported to be effective for the treatment of these lesions, however there is still insufficient evidence on the long-term results of pharyngeal ESD.

METHODS

This is a single-center retrospective study of all cases of superficial pharyngeal cancer that underwent ESD as primary treatment between January 2010 and May 2022. A total of 83 lesions in 63 patients were analyzed.

RESULTS

The en bloc resection rate was 100%, and R0 resection rate was 59.0%, with an adverse event rate of 6.0%. During a mean observation period of 1134 days, there were 0 cases of disease-specific metastasis or death. However, the 5-year cumulative incidence of metachronous head and neck cancer after resection was 27.1% and the 5-year overall survival and 10-year overall survival after pharyngeal ESD were 87.0% and 69.6%, respectively. Of the 34 cases with non-R0 resection, local recurrence occurred in 8.8%. Location of lesion (p = 0.011), disparity between demarcation of the lesion with NBI and iodine staining (p = 0.026), and non-effective laryngeal elevation (p = 0.080) were risk factors for non-R0 resection.

CONCLUSION

Pharyngeal ESD is effective and safe. Further studies are needed to improve and standardize indications and strategies for pharyngeal ESD.

Endoscopic submucosal dissection using an ultrathin endoscope for superficial pharyngeal cancer: a prospective feasibility study (with video)

Background and study aims  Endoscopic submucosal dissection (ESD) of pharyngeal cancers with conventional endoscopes often is difficult, not only because of the narrow working space, but also because endoscope maneuverability in the pharynx is poor due to interference from the endotracheal tube and/or hyoid bone. However, we hypothesized that those problems could possibly be resolved by use of an ultrathin endoscope for ESD of superficial pharyngeal cancer. The aim of this prospective interventional study was to investigate the feasibility of ESD for superficial pharyngeal cancer using an ultrathin endoscope. Patients and methods  This feasibility study was conducted at NTT Medical Center Tokyo between June 2020 and September 2021, and data from a total of 20 consecutively superficial pharyngeal cancers were analyzed. The primary outcome measure was the R0 resection rate. The ESD completion rate, en bloc resection rate, procedure time, and frequency of intraoperative and postoperative adverse events (AEs) were also evaluated as secondary outcome measures. Results  Data from 16 patients with 20 lesions were included in the analysis. All of the lesions were successfully resected by ultrathin endoscope ESD, and the en bloc and R0 resection rates were 100 % and 85.0 % (17/20), respectively; the procedure time was 37.8 ± 28.2 minutes. No intraoperative or postoperative AEs were encountered in any cases. Conclusions  ESD using an ultrathin endoscope is feasible for superficial pharyngeal cancers and has potential to be a safe and effective treatment option for these cancers.

Emergent endoscopic submucosal dissection for a polypoid fibroadipose tumor accidentally disgorged from the mouth: an organ-preserving minimally invasive treatment

Video 1The yellow protruded lesion at the larynx is different from the main lesion.

Novel Colorectal Endoscopic Submucosal Dissection With Double-Endoscope and Snare-Based Traction

BACKGROUND

Colorectal endoscopic submucosal dissection is technically demanding, and the traction offered by gravity, cap, or clip-with-line during conventional endoscopic submucosal dissection remains unsatisfactory. Robotic systems are still under development and are expensive. We proposed double-scope endoscopic submucosal dissection with strong and adjustable traction offered by snaring the lesion with additional scope.

OBJECTIVE

This study aimed to test the novel double-scope endoscopic submucosal dissection with snare-based traction.

DESIGN

This was a retrospective study that reviewed double-scope endoscopic submucosal dissection compared with matched conventional endoscopic submucosal dissection, and size, location, morphology, and pathology between groups were compared.

SETTINGS

This study was conducted in a referral endoscopy center in a local hospital.

PATIENTS

This study included patients with colorectal lesions receiving double-scope endoscopic submucosal dissection and matched conventional endoscopic submucosal dissection.

MAIN OUTCOME MEASURES

The pathological completeness, procedure time, and complications were analyzed.

RESULTS

Fifteen double-scope endoscopic submucosal dissection procedures, with 11 lesions located in the proximal colon with a median size of 40 mm, were performed. The median procedure time of double-scope endoscopic submucosal dissection was 32.45 (interquartile range, 16.03-38.20) minutes. The time required for second scope insertion was 2.57 (interquartile range, 0.95-6.75) minutes; for snaring, 3.03 (interquartile range, 2.12-6.62) minutes; and for actual endoscopic submucosal dissection, 28.23 (interquartile range, 7.90-37.00) minutes. All lesions were resected completely. No major complication was encountered. The procedure time was significantly shorter than that of 14 matched conventional endoscopic submucosal dissections (54.61 [interquartile range, 33.11-97.25] min; p = 0.021).

LIMITATIONS

This was a single-center, single-operator, retrospective case-controlled study with limited cases.

CONCLUSIONS

This study confirmed the feasibility of double-scope endoscopic submucosal dissection with snare-based traction to shorten procedure time and to simplify endoscopic submucosal dissection. Additional trials are required.

Comprehensive risk evaluation for metachronous carcinogenesis after endoscopic submucosal dissection of superficial pharyngeal squamous cell carcinoma

BACKGROUND

Pharyngeal squamous cell carcinoma (PSCC) is associated with a high likelihood of metachronous carcinogenesis, which is known to have a poor prognosis. This study aimed to identify comprehensive risk evaluation indicators for metachronous carcinogenesis after endoscopic submucosal dissection (ESD) of superficial PSCC.

METHODS

The risk of metachronous carcinogenesis was evaluated in 144 patients with superficial PSCC (with no history of PSCC or esophageal squamous cell carcinoma) who underwent initial ESD from 2008 to 2020. Multiple lugol-voiding lesions (LVLs) in the background pharyngeal and esophageal epithelium were evaluated as endoscopic indicators. The hemoglobin, albumin, lymphocyte, and platelet (HALP) score was analyzed as a serum marker.

RESULTS

The median follow-up period was 4.3 years. The coincidence rate for pharyngeal and esophageal LVL grade was 55%. The cumulative 3-year metachronous PSCC rate was 18.9%. The cumulative 3-year second metachronous PSCC rate was 43.9%. Forward stepwise multivariate Cox proportional hazards regression analysis identified pharyngeal LVL grade and a lower HALP score as significant independent predictors. Pharyngeal LVL grade was superior to esophageal LVL grade as a predictor of metachronous PSCC. A lower HALP score was significantly associated with younger age in forward stepwise multivariate logistic regression analysis.

CONCLUSIONS

Patients with a history of superficial PSCC remain at risk for metachronous carcinogenesis over time, and long-term follow-up is imperative. Comprehensive evaluation of endoscopic features with a novel serum marker, namely, the HALP score, can help predict metachronous carcinogenesis.

Long-term outcomes of esophageal squamous cell carcinoma with invasion depth of pathological T1a-muscularis mucosae and T1b-submucosa by endoscopic resection followed by appropriate additional treatment

OBJECTIVES

Endoscopic resection (ER) is indicated for a wide range of superficial esophageal squamous cell carcinomas (ESCCs). We examined the long-term outcomes in patients with pathological (p) invasion of ESCC into the T1a-muscularis mucosae (MM) and T1b-submucosa (SM) after ER, for which data on prognosis are limited.

METHODS

Of the 1217 patients with superficial ESCC who underwent ER, 225 patients with a pathological diagnosis of ESCC invasion into the MM, minute submucosal invasion ≤200 µm (SM1), or massive submucosal invasion (SM2) were included. In patients with lymphovascular invasion, droplet infiltration, or SM2 invasion, additional treatments, including chemoradiation (CRT) or esophagectomy with two- to three-field lymph node dissection, were recommended. The median observation period was 66 months (interquartile range 48-91 months).

RESULTS

In total, there were 151, 28, and 46 pT1a-MM, pT1b-SM1, and pT1b-SM2 cases, respectively. Metastatic recurrence was observed in 1.3%, 10.7%, and 6.5% patients with pT1a-MM, pT1b-SM1, and pT1b-SM2 ESCCs, respectively. Of the eight patients with metastatic recurrence, six were successfully treated, and two died of ESCC. The 5-year overall survival rates were 84.1%, 71.4%, and 67.4%, the 5-year relapse-free survival rates were 82.8%, 64.3%, and 65.2%, and the 5-year disease-specific survival rates were 100%, 96.4%, and 99.1% in patients with pT1a-MM, pT1b-SM1, and pT1b-SM2 ESCCs, respectively. Multivariate analysis showed that additional CRT and esophagectomy, and T1b-SM2 were positively and negatively associated with overall survival, respectively.

CONCLUSIONS

Endoscopic resection preceding appropriate additional treatments resulted in favorable outcomes. Many cases of metastatic recurrence in this cohort could be successfully treated.

Advances in traction methods for endoscopic submucosal dissection: What is the best traction method and traction direction?

Endoscopic submucosal dissection (ESD) has been developed as a treatment for superficial gastrointestinal neoplasms, which can achieve en bloc resection regardless of the lesion size. However, ESD is technically difficult because endoscopists cannot bring their hand into the gastrointestinal tract, unlike surgeons in regular surgery. It is difficult to obtain sufficient tension in the dissection plane and a good field of vision. Therefore, ESD is associated with a long procedure time and a high risk of adverse events in comparison with endoscopic mucosal resection. Traction methods have been developed to provide sufficient tension for the dissection plane and a good field of vision during the ESD procedure. However, traction direction is limited in most traction methods, resulting in insufficient effect in some cases. Although traction direction is considered important, there have been few investigations of its effect. In the first half of this review, important traction methods are discussed, including traction direction. In second half, appropriate traction methods for each organ are considered. Other important considerations for traction method, such as ability to adjust traction strength, interference between traction device and endoscope, and the need for specialized devices are also discussed.

Advances in traction methods for endoscopic submucosal dissection: What is the best traction method and traction direction?

Endoscopic submucosal dissection (ESD) has been developed as a treatment for superficial gastrointestinal neoplasms, which can achieve en bloc resection regardless of the lesion size. However, ESD is technically difficult because endoscopists cannot bring their hand into the gastrointestinal tract, unlike surgeons in regular surgery. It is difficult to obtain sufficient tension in the dissection plane and a good field of vision. Therefore, ESD is associated with a long procedure time and a high risk of adverse events in comparison with endoscopic mucosal resection. Traction methods have been developed to provide sufficient tension for the dissection plane and a good field of vision during the ESD procedure. However, traction direction is limited in most traction methods, resulting in insufficient effect in some cases. Although traction direction is considered important, there have been few investigations of its effect. In the first half of this review, important traction methods are discussed, including traction direction. In second half, appropriate traction methods for each organ are considered. Other important considerations for traction method, such as ability to adjust traction strength, interference between traction device and endoscope, and the need for specialized devices are also discussed.

Efficacy of endoscopic ultrasonography in evaluating tumor thickness in patients with superficial pharyngeal carcinoma: A pilot study

OBJECTIVES

A histopathological tumor thickness of ≥1000 μm has been reported as one of many risk factors for recurrent lymph node metastasis in superficial pharyngeal cancer (SPC). However, methods for assessing this risk factor preoperatively have not yet been established. Hence, the current study aimed to evaluate the efficacy of endoscopic ultrasonography (EUS) in measuring tumor thickness preoperatively in patients with SPC.

METHODS

This single-center retrospective study included 44 consecutive patients with 47 lesions who underwent endoscopic submucosal dissection (ESD). Prior to surgery, EUS examination was performed while under general anesthesia. Further, microvascular irregularity in the target lesion was evaluated using the Japan Esophageal Society (JES) magnification endoscopic classification system.

RESULTS

A significant correlation was noted between histopathological and EUS tumor thickness (Spearman's correlation r == 0.879, p < 0.001). In tumors ≥1000 µm thick on histopathology, the cutoff value for EUS tumor thickness was 2.6 mm, and the following values were obtained: sensitivity, 100%; specificity, 81.8%; positive predictive value (PPV), 70%; negative predictive value (NPV), 100%; and accuracy, 87.2%. In B2 lesions ≥1000-μm thick, the following values were obtained: sensitivity, 85.7%; specificity, 90.9%; PPV, 80%; NPV, 93.8%; and accuracy, 89.4%. The diagnostic accuracy rate of combined EUS and the JES magnifying endoscopic classification system was 95.7%.

CONCLUSIONS

Tumor thickness assessed using EUS was effective in diagnosing histopathological tumor thickness of ≥1000 μm. The combined use of EUS and the JES magnifying endoscopic classification system may be useful for assessing preoperative risk factors for lymph node metastasis in SPC.

Transoral surgery for superficial head and neck cancer: National Multi-Center Survey in Japan

Head and neck cancers, especially in hypopharynx and oropharynx, are often detected at advanced stage with poor prognosis. Narrow band imaging enables detection of superficial cancers and transoral surgery is performed with curative intent. However, pathological evaluation and real‐world safety and clinical outcomes have not been clearly understood. The aim of this nationwide multicenter study was to investigate the safety and efficacy of transoral surgery for superficial head and neck cancer. We collected the patients with superficial head and neck squamous cell carcinoma who were treated by transoral surgery from 27 hospitals in Japan. Central pathology review was undertaken on all of the resected specimens. The primary objective was effectiveness of transoral surgery, and the secondary objective was safety including incidence and severity of adverse events. Among the 568 patients, a total of 662 lesions were primarily treated by 575 sessions of transoral surgery. The median tumor diameter was 12 mm (range 1–75) endoscopically. Among the lesions, 57.4% were diagnosed as squamous cell carcinoma in situ. The median procedure time was 48 minutes (range 2–357). Adverse events occurred in 12.7%. Life‐threatening complications occurred in 0.5%, but there were no treatment‐related deaths. During a median follow‐up period of 46.1 months (range 1–113), the 3‐year overall survival rate, relapse‐free survival rate, cause‐specific survival rate, and larynx‐preservation survival rate were 88.1%, 84.4%, 99.6%, and 87.5%, respectively. Transoral surgery for superficial head and neck cancer offers effective minimally invasive treatment.

Clinical trials registry number: UMIN000008276.

Clinical relevance of endoscopic treatment for superficial pharyngeal cancer: feasibility of techniques corresponding to each location and long-term outcomes

BACKGROUND AND AIMS

Superficial pharyngeal cancers are being detected and treated using endoscopy in many medical facilities with increasing frequency. However, the reports focus on the hypopharynx. We identified reliable treatments by adapting the method for each region of the pharynx. Here, we introduce our methods for treating various pharyngeal regions and show their long-term results.

METHODS

Of 308 consecutive patients who underwent pharyngeal endoscopic submucosal dissection between February 2007 and December 2018 at our institution, we selected 293 patients who were diagnosed histologically with squamous cell carcinoma. The patients were divided into 4 groups based on the specific location of superficial pharyngeal lesions and the short- and long-term outcomes, such as technical success, adverse events, overall survival, and case-specific survival, were evaluated.

RESULTS

The procedure time was 51 minutes at location A where cancer develops most commonly. The rate of en bloc resection was 99.4%, and the R0 resection rate was 82.6%. With regard to adverse events, there were 2 cases of postoperative hemorrhage, both treated with endoscopic hemostasis. The average observation period was 61.2 months overall, with 14 cases of recurrent lymph node metastasis. The 5-year survival rate was 84.1%, and cause-specific survival was 100%.

CONCLUSIONS

Adaptation of the treatment method according to the location of the lesion led to good results. Endoscopic treatment of superficial pharyngeal cancer is both feasible and beneficial.

Relationship between the microvascular patterns observed by magnifying endoscopy with narrow-band imaging and the depth of invasion in superficial pharyngeal squamous cell carcinoma

BACKGROUND

Prediction of the invasive depth is the objective of endoscopic observation for digestive cancer. In superficial esophageal cancer, a close relationship between microvascular patterns observed by magnifying endoscopy with narrow-band imaging (M-NBI) and pathological depth of invasion is well known. The ability of M-NBI to predict the invasion depth in superficial pharyngeal squamous cell carcinoma (SPSCC) has been seldom evaluated. This study aimed to clarify the relationship between the microvasculature patterns and pathological depth in SPSCC.

METHODS

SPSCC lesions evaluated with M-NBI followed by endoscopic resection were analyzed between April 2010 and March 2017. Endoscopic images were classified as microvasculature tumor types B1, B2, and B3 according to the Japan Esophageal Society classification. The pathological depth of invasion was described as either squamous cell carcinoma in situ (Tis) or invasive subepithelial cancer, and the tumor thickness of all lesions was examined. Data were analyzed using the unpaired t, χ², or Mann-Whitney U test.

RESULTS

Type B1 and type B2/B3 (35/3) microvessels were found in 180 lesions (82%) and 39 (18%), respectively. Of the flat lesions, 115 (83%) were classified as Tis and 23 (17%) as subepithelial cancer. Positive and negative predictive values of the B1 vessels were 77% and 82%, respectively. Additional analysis showed that the positive predictive value of the B1 vessels for the flat-type lesions was 87%; the negative predictive value for the elevated lesions was 93%.

CONCLUSIONS

Microvascular patterns observed by M-NBI are an important factor in predicting the pathological depth of invasion.

Artificial intelligence for cancer detection of the upper gastrointestinal tract

In recent years, artificial intelligence (AI) has been found to be useful to physicians in the field of image recognition due to three elements: deep learning (that is, CNN, convolutional neural network), a high-performance computer, and a large amount of digitized data. In the field of gastrointestinal endoscopy, Japanese endoscopists have produced the world's first achievements of CNN-based AI system for detecting gastric and esophageal cancers. This study reviews papers on CNN-based AI for gastrointestinal cancers, and discusses the future of this technology in clinical practice. Employing AI-based endoscopes would enable early cancer detection. The better diagnostic abilities of AI technology may be beneficial in early gastrointestinal cancers in which endoscopists have variable diagnostic abilities and accuracy. AI coupled with the expertise of endoscopists would increase the accuracy of endoscopic diagnosis.

Artificial intelligence-based detection of pharyngeal cancer using convolutional neural networks

OBJECTIVES

The prognosis for pharyngeal cancer is relatively poor. It is usually diagnosed in an advanced stage. Although the recent development of narrow-band imaging (NBI) and increased awareness among endoscopists have enabled detection of superficial pharyngeal cancer, these techniques are still not prevalent worldwide. Nevertheless, artificial intelligence (AI)-based deep learning has led to significant advancements in various medical fields. Here, we demonstrate the diagnostic ability of AI-based detection of pharyngeal cancer from endoscopic images in esophagogastroduodenoscopy.

METHODS

We retrospectively collected 5403 training images of pharyngeal cancer from 202 superficial cancers and 45 advanced cancers from the Cancer Institute Hospital, Tokyo, Japan. Using these images, we developed an AI-based diagnostic system with convolutional neural networks. We prepared 1912 validation images from 35 patients with 40 pharyngeal cancers and 40 patients without pharyngeal cancer to evaluate our system.

RESULTS

Our AI-based diagnostic system correctly detected all pharyngeal cancer lesions (40/40) in the patients with cancer, including three small lesions smaller than 10 mm. For each image, the AI-based system correctly detected pharyngeal cancers in images obtained via NBI with a sensitivity of 85.6%, much higher sensitivity than that for images obtained via white light imaging (70.1%). The novel diagnostic system took only 28 s to analyze 1912 validation images.

CONCLUSIONS

The novel AI-based diagnostic system detected pharyngeal cancer with high sensitivity. It could facilitate early detection, thereby leading to better prognosis and quality of life for patients with pharyngeal cancers in the near future.

Utilizing artificial intelligence in endoscopy: a clinician's guide

INTRODUCTION

Artificial intelligence (AI) that surpasses human ability in image recognition is expected to be applied in the field of gastrointestinal endoscopes. Accordingly, its research and development (R &D) is being actively conducted. With the development of endoscopic diagnosis, there is a shortage of specialists who can perform high-precision endoscopy. We will examine whether AI with excellent image recognition ability can overcome this problem.

AREAS COVERED

Since 2016, papers on artificial intelligence using convolutional neural network (CNN in other word Deep Learning) have been published. CNN is generally capable of more accurate detection and classification than conventional machine learning. This is a review of papers using CNN in the gastrointestinal endoscopy area, along with the reasons why AI is required in clinical practice. We divided this review into four parts: stomach, esophagus, large intestine, and capsule endoscope (small intestine).

EXPERT OPINION

Potential applications for the AI include colorectal polyp detection and differentiation, gastric and esophageal cancer detection, and lesion detection in capsule endoscopy. The accuracy of endoscopic diagnosis will increase if the AI and endoscopist perform the endoscopy together.

Synchronous triple primary cancers of the pharynx and esophagus

A 72-year-old male with nausea and heartburn was found to have early pharyngeal squamous cell carcinoma, superficial and advanced esophageal squamous cell carcinoma and early esophageal adenocarcinoma by esophagogastroduodenoscopy. Computerized tomography demonstrated left cardiac lymph node swellings. We prioritized the treatment for esophageal squamous cell carcinoma, as this was the most advanced cancer among the triple primaries. The patient underwent neoadjuvant chemotherapy for esophageal squamous cell carcinoma followed by esophagectomy. Four months after esophagectomy, endoscopic submucosal dissection for pharyngeal squamous cell carcinoma was performed. This is a first report of pharyngeal squamous cell carcinoma, esophageal squamous cell carcinoma and esophageal adenocarcinoma occurring as triple primary cancers in a single patient. Smoking-induced tumor formation through DNA methylation is a common risk factor for patients with triple primary malignancies, being an example of epigenetic field cancerization induced by exposure to carcinogenic factors.