Estimation of invasion depth of early colorectal cancer using EUS and NBI-ME: a meta-analysis

Chao, Guanqun; Ye, F; Li, T; Gong, Weihua; Zhang, S

doi:10.1007/s10151-019-02076-w

Cited by 13 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a randomized controlled trial, endoscopic identification of invasive cancer was limited to around 70 % sensitivity and 70 % specificity, even with the aid of advanced endoscopic imaging modalities such as magnifying endoscopy or ultrasonography [2]. The low specificity in identifying deeply invasive submucosal cancer was also demonstrated in the recently published meta-analysis; the pooled sensitivity and specificity were 98 % and 65 %, respectively when magnifying narrow-band imaging was used for lesion assessment [3]. The relatively lower specificity for cancer recognition may contribute to the observed increase in unnecessary surgeries of large colorectal adenomas.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-assisted colonic endocytoscopy for cancer recognition: a multicenter study

et al. 2021

View full text Add to dashboard Cite

Background and study aims Large adenomas are sometimes misidentified as cancers during colonoscopy and are surgically removed. To address this overtreatment, we developed an artificial intelligence (AI) tool that identified cancerous pathology in vivo with high specificity. We evaluated our AI tool under the supervision of a government agency to obtain regulatory approval. Patients and methods The AI tool outputted three pathological class predictions (cancer, adenoma, or non-neoplastic) for endocytoscopic images obtained at 520-fold magnification and previously trained on 68,082 images from six academic centers. A validation test was developed, employing 500 endocytoscopic images taken from various parts of randomly selected 50 large (≥ 20 mm) colorectal lesions (10 images per lesion). An expert board labelled each of the 500 images with a histopathological diagnosis, which was made using endoscopic and histopathological images. The validation test was performed using the AI tool under a controlled environment. The primary outcome measure was the specificity in identifying cancer. Results The validation test consisted of 30 cancers, 15 adenomas, and five non-neoplastic lesions. The AI tool could analyze 83.6 % of the images (418/500): 231 cancers, 152 adenomas, and 35 non-neoplastic lesions. Among the analyzable images, the AI tool identified the three pathological classes with an overall accuracy of 91.9 % (384/418, 95 % confidence interval [CI]: 88.8 %–94.3 %). Its sensitivity and specificity for differentiating cancer was 91.8 % (212/231, 95 % CI: 87.5 %–95.0 %) and 97.3 % (182/187, 95 % CI: 93.9 %–99.1 %), respectively. Conclusions The newly developed AI system designed for endocytoscopy showed excellent specificity in identifying colorectal cancer.

show abstract

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-assisted colonic endocytoscopy for cancer recognition: a multicenter study

et al. 2021

View full text Add to dashboard Cite

show abstract

“…24 Regarding the diagnostic ability of EUS to distinguish between T1a and T1b CRC, a previous meta-analysis reported a significantly higher specificity than that of NBI-magnifying endoscopy. 25 Another meta-analysis confined to rectal carcinoma reported high sensitivity and specificity of EUS in T1 carcinoma staging. 26 The present study focused on the distance between the tumor invasive front and the muscle layer on EUS, and we termed it EUS-TFD.…”

Section: Discussionmentioning

confidence: 99%

“…EUS provides cross‐sectional images of the tumor, enabling objective diagnosis of the tumor invasion depth through visualization and detection of colon wall structures 24 . Regarding the diagnostic ability of EUS to distinguish between T1a and T1b CRC, a previous meta‐analysis reported a significantly higher specificity than that of NBI‐magnifying endoscopy 25 . Another meta‐analysis confined to rectal carcinoma reported high sensitivity and specificity of EUS in T1 carcinoma staging 26 .…”

Section: Discussionmentioning

confidence: 99%

Novel endoscopic ultrasonography classification for assured vertical resection margin (≥500 μm) in colorectal endoscopic submucosal dissection

Kamigaichi

Oka

Tanino

et al. 2022

J of Gastro and Hepatol

View full text Add to dashboard Cite

Background and Aim The risk of local recurrence might be low in pT1 colorectal carcinoma with a tumor vertical margin (VM) ≥500 μm. We investigated the relationship between endoscopic ultrasonography (EUS) findings and VM in cases with colorectal endoscopic submucosal dissection (ESD) categorized as Type 2B according to the Japan NBI Expert Team (JNET) classification. Methods We analyzed 179 JNET Type 2B colorectal tumors resected by ESD at Hiroshima University Hospital from January 2010 to May 2021. The distance from the tumor invasive front to the muscle layer on EUS was defined as the tumor‐free distance (EUS‐TFD) and classified as Type I (EUS‐TFD ≥1 mm) and II (<1 mm). We investigated the relationship between EUS‐TFD and VM and analyzed the predictive factors for VM ≥500 μm. Results EUS‐TFD Type I was diagnosed in 133 (74.3%) lesions: VM ≥500 μm (114, 85.7%); VM <500 μm (19, 14.3%); and VM positive (VM1) (0, 0%). Type II was diagnosed in 46 (25.7%) lesions: VM ≥500 μm (14, 30.5%); VM <500 μm (22, 47.8%); and VM1 (10, 21.7%). In the EUS‐TFD Type I cases, 84.5% and 87.8% were protruded and superficial types; whereas for Type II cases, these were 38.9% and 25%, respectively. EUS‐TFD classification (Type I), scope operability (good), submucosal invasion depth (<2000 μm), histology at the deepest invasive portion (favorable), and degree of fibrosis (F0/F1) were significant predictors of VM ≥500 μm. Conclusions In JNET Type 2B lesions, EUS‐TFD classification is a novel diagnostic indicator to predict VM ≥500 μm in ESD preoperatively.

show abstract

“…Before endoscopic treatment, using magnifying IEE and EUS simultaneously to assess the depth of invasion of early CRC is recommended. 135 Statement After endoscopic resection of the lesion, tissue specimen should be stretched, marked, and fixed immediately and sent to the pathology department. Forceps can be used to stretch the specimens.…”

Section: Grade Of Recommendation: Cmentioning

confidence: 99%

Chinese consensus on prevention of colorectal neoplasia (2021, Shanghai)

Fang¹

2022

J of Digest Diseases

View full text Add to dashboard Cite

Most patients with colorectal cancer (CRC) were diagnosed in advanced stage and the prognosis is poor. Therefore, early detection and prevention of CRC are very important. As with other cancers, there is also the tertiary prevention for CRC. The primary prevention is etiological prevention, which is mainly the treatment of adenoma or inflammation for preventing the development into cancer. The secondary prevention is the early diagnosis and early treatment for avoiding progressing to advanced cancer. The tertiary prevention belongs to the broad category of prevention, mainly for advanced CRC, through surgical treatment and postoperative adjuvant chemotherapy, radiotherapy, targeted therapy, immunotherapy for preventing tumor recurrence or metastasis. This consensus is based on the recent domestic and international consensus guidelines and the latest progress of international researches

show abstract

Estimation of invasion depth of early colorectal cancer using EUS and NBI-ME: a meta-analysis

Cited by 13 publications

References 36 publications

Artificial intelligence-assisted colonic endocytoscopy for cancer recognition: a multicenter study

Artificial intelligence-assisted colonic endocytoscopy for cancer recognition: a multicenter study

Novel endoscopic ultrasonography classification for assured vertical resection margin (≥500 μm) in colorectal endoscopic submucosal dissection

Chinese consensus on prevention of colorectal neoplasia (2021, Shanghai)

Contact Info

Product

Resources

About