Introduction

Positron emission tomography (PET) scan involves injecting a radioactive isotope (18-fluoro-2-deoxyglucose) to locate areas where the radiotracer accumulates. The established indications of PET scanning mainly concern oncology, where it is used for staging, treatment monitoring, and long-term surveillance. It is also useful in cases of secondary lesions for identifying the primary lesion. Outside of oncology, PET scan has other clinical applications such as diagnosing and monitoring inflammatory diseases, and searching for infectious foci. The incidental discovery of metabolic hyperfixation in the digestive system on PET scan is becoming increasingly common, raising questions about the clinical significance of this hypermetabolism and the need for endoscopic exploration. The aim of our study is to report the endoscopic findings from examinations performed in our department where the indication was the incidental discovery of digestive hypermetabolism on PET scan.

Aims & Methods

This is a descriptive and analytical retrospective monocentric study including all patients referred for endoscopy due to the incidental discovery of digestive metabolic hyperfixation on PET scan, not corresponding to a previously known lesion, between January 2017 and September 2023. Only hypermetabolic fixations located in the stomach, colon, and rectum were included.

Results

28 hypermetabolic fixations were included in the study, of which 46.4% were located in the colon, 42.9% in the rectum, and 10.7% in the stomach. The mean age was 54.9 years with a standard deviation [32,78]. The male-to-female sex ratio was 0.6. PET scan indications were mainly dominated by surveillance of treated cancers or during treatment (57.1%). In 21.4% of cases, PET scan was requested for staging a newly diagnosed tumor, and in 17.9% of patients, it was used to search for a primary tumor with hepatic, pulmonary, or bone metastases. Other indications were rarer, representing 3.6% of cases. Hypermetabolism on PET scan corresponded to a neoplastic lesion in 17.9% of cases, an adenoma in 14.3% of cases, and a benign lesion (non-specific ulceration, inflammatory lesion, or stenosis) in 32.2% of cases. In 35.7% of patients, endoscopic examination did not reveal detectable abnormalities. Hypermetabolism was most often focal (67.9%). According to this study, the presence of focal metabolic hyperfixation was significantly associated with the presence of a neoplastic lesion on digestive endoscopy (P <0.01).

Conclusion

All metabolic hyperfixations on PET scan referred to our endoscopy center underwent endoscopic exploration to rule out a neoplastic lesion. However, additional studies, ideally prospective and multicentric with a larger sample size, are essential to establish the criteria for endoscopic exploration in the case of incidental discovery of digestive hypermetabolism on PET Scan

References

1.Kousgaard SJ, Thorlacius-Ussing O. Incidental colorectal FDG uptake on PET/CT scan and lesions observed during subsequent colonoscopy: a systematic review. Tech Coloproctol. juill 2017;21(7):521-9.
2.van Hoeij FB, Keijsers RGM, Loffeld BC a. J, Dun G, Stadhouders PHGM, Weusten BL a. M. Incidental colonic focal FDG uptake on PET/CT: can the maximum standardized uptake value (SUVmax) guide us in the timing of colonoscopy? Eur J Nucl Med Mol Imaging. janv 2015;42(1):66-71.

Introduction

The prescription of colonoscopies is constantly increasing for the screening and diagnosis of colorectal cancer, precancerous lesions, polyps, and adenomas. Sometimes, indications become excessive due to the availability of this examination on one hand and the fear of missing a neoplastic lesion on the other. The EPAGE II criteria (European Panel on the Appropriateness of Gastrointestinal Endoscopy) was developped to assess the relevance of colonoscopy indications and to rationalize its prescription. The aim of our study was to evaluate the relevance of colonoscopy indications performed in our department according to EPAGE II criteria and to investigate a possible correlation between the appropriateness of the examination and the endoscopic result.

Aims & Methods

A retrospective study was conducted at a hepatogastroenterology department including all colonoscopies performed during the period from January 2022 to June 2023. The relevance of colonoscopy indications according to EPAGE II criteria was classified as appropriate, uncertain, or inappropriate.

Results

The relevance of the indication was evaluated in 406 colonoscopies. The sex ratio (Male / Female) was 1.15. The median age was 51 with an IQ [15.93]. Rectal bleeding represented the most frequently found indications (30%), followed by Crohn's disease (12.8%), then chronic diarrhea (11.1%). 49% of colonoscopies had satisfactory preparation (Boston ≥7). Colonoscopy was complete in 86% of patients, with catheterization of the terminal ileum in 36.2% of cases. A significant endoscopic lesion was found in 63% of colonoscopies, represented mainly by inflammatory lesions of inflammatory bowel disease (20.7%) followed by neoplastic lesions (15.3%) of colorectal cancer, then polyps (10%), benign strictures (6.4%), and diverticulosis (5.7%). Overall, colonoscopy indication was appropriate in 83.5% of cases, uncertain in 10.8%, and inappropriate in 5.7%. A significant endoscopic lesion was found in 63% of patients with an appropriate indication.

Conclusion

The indication for colonoscopies performed in our department was considered appropriate in more than 80% of cases, with rectal bleeding being the main indication. Significant endoscopic lesions were mostly found in cases of appropriate indication, leading us to encourage the use of this software to regulate colonoscopy indications

References

Clinical Case Summary

Introduction: ​​​​Blue rubber bleb nevus syndrome or bean’s syndrome, is a rare congenital disorder characterized by the presence of vascular malformations in the skin and other internal organs with a predilection of the gastro intestinal tract. The most common clinical manifestations are gastrointestinal bleeding causing severe iron deficiency anemia, and bluish-purple soft compressible nodules on skin or mucous membranes usually present at birth or during early childhood. We presented a clinical case of upper gastrointestinal bleeding revealing a blue rubber bleb nevus syndrome treated symptomatically with good evolution.
Case Report: A 73 years old woman, who has a history of a gastric and hepatic hemangiomatosis, was hospitalized for 3 months’ history of melena complicated by multiple episodes of hematemesis, with fatigue, pallor and severe anemia. Physical examination revealed small bluish nodules on the trunk, the lower limb and the nose. The abdomen was soft and no tender. Complete blood count revealed a hypochromic microcytic severe anemia with a hemoglobin level of 5.7g/dl. Oesogastroduodenoscopy revealed a large vascular mass in the lower third of the esophagus, with other vascular malformations in the fundus with active bleeding. CT scan of the body revealed the presence of an esophageal large mass extended to the lesser curvature of the stomach with multiple micro calcifications. Cerebral MRI showed no remarkable lesion. The diagnosis of blue rubber bleb nevus syndrome was established based on medical history, cutaneous lesions and the pathognomonic endoscopic lesion. Proton pump inhibitor and blood transfusion, with a regular follow up, treated the patient. The patient presents no other episodes of GI bleeding during the hospital stay and was discharged with a hemoglobin level of 10g/dl.

References

[1] Moodley M, Ramdial P. Blue rubber bleb nevus syndrome: case report and review of the literature. Pediatrics 1993; 92: 160–162.
[2] Cho YM, Steen C, James J. Blue rubber bleb nevus syndrome: a rare cause of abdominal pain. ANZ J Surg 2020; 90: 619–621.
[3] Xia H, Wu J, Huang Y. Blue rubber bleb nevus syndrome: a single-center case series in 12 years. Transl Pediatr 2021; 10: 2960–2971.
[4] Rodrigues D, Bourroul ML, Ferrer AP, et al. Blue rubber bleb nevus syndrome. Rev Hosp Clin Fac Med Sao Paulo 2000; 55: 29–34.
[5] Soblet J, Kangas J, Nätynki M, et al. Blue Rubber Bleb Nevus (BRBN) Syndrome Is Caused by Somatic TEK (TIE2) Mutations. Journal of Investigative Dermatology 2017; 137: 207–216.
[6] Tang X, Gao J, Yang X, et al. A 10-year delayed diagnosis of blue rubber bleb nevus syndrome characterized by refractory iron-deficiency anemia. Medicine (Baltimore) 2018; 97: e10873.
[7] Shin SH, Chae HS, Ji JS, et al. A case of blue rubber bleb nevus syndrome. Korean J Intern Med 2008
[8] Tyrrel RT, Baumgartner BR, Montemayor KA. Blue rubber bleb nevus syndrome: CT diagnosis of intussusception. AJR Am J Roentgenol 1990

​

Introduction

Capsule endoscopy (CE) is a minimally invasive exam suitable of panendoscopic evaluation of the gastrointestinal tract. Nevertheless, CE is time-consuming, with suboptimal diagnostic yield in the upper GI tract. Convolutional neural networks (CNN) are human brain architecture-based models suitable for image analysis. However, there is no study about their role in capsule panendoscopy.

Aims & Methods

Our aim was to develop an artificial intelligence (AI) model for panendoscopic automatic detection of pleomorphic lesions (namely vascular lesions, protuberant lesions, hematic residues, ulcers, and erosions). 355110 images (6977 esophageal, 12918 gastric, 258443 small bowel, 76772 colonic) from eight different CE and colon CE (CCE) devices were divided into a training and validation dataset in a patient split design. The model classification was compared to three CE experts’ classifications. The model’s performance was evaluated by its sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and area under the precision-recall curve.

Results

The binary esophagus CNN had a diagnostic accuracy for pleomorphic lesions of 83.6%. The binary gastric CNN identified pleomorphic lesions with a 96.6% accuracy. The undenary small bowel CNN distinguished pleomorphic lesions with different hemorrhagic potential with 97.6% accuracy. The trinary colonic CNN (detection and differentiation of normal mucosa, pleomorphic lesions, and hematic residues) had 94.9% global accuracy.

Conclusion

Our group developed the first AI model for panendoscopic automatic detection of pleomorphic lesions in both CE and colon CE from multiple brands, solving a critical interoperability technological challenge. Deep learning-based tools may change the landscape of minimally invasive capsule panendoscopy.

References

1. Pennazio M, Rondonotti E, Despott EJ, Dray X, Keuchel M, Moreels T, et al. Small-bowel capsule endoscopy and device-assisted enteroscopy for diagnosis and treatment of small-bowel disorders: European Society of Gastrointestinal Endoscopy (ESGE) Guideline - Update 2022. Endoscopy. 2023 Jan;55(1):58-95. PubMed PMID: 36423618. Epub 20221124.
2. Le Berre C, Trang-Poisson C, Bourreille A. Small bowel capsule endoscopy and treat-to-target in Crohn's disease: A systematic review. World J Gastroenterol. 2019 Aug 21;25(31):4534-54. PubMed PMID: 31496630. PMCID: PMC6710184.
3. Iddan G, Meron G, Glukhovsky A, Swain P. Wireless capsule endoscopy. Nature. 2000 May 25;405(6785):417. PubMed PMID: 10839527.
4. Rondonotti E, Pennazio M. Colon capsule for panendoscopy: a narrow window of opportunity. Endosc Int Open. 2021 Dec;9(12):E1860-E2. PubMed PMID: 34917450. PMCID: PMC8670997. Epub 20211214.
5. Vuik FER, Moen S, Spaander MCW. Colon capsule endoscopy as panendoscopy: Using current knowledge to enhance possibilities. Endosc Int Open. 2022 May;10(5):E584. PubMed PMID: 35571484. PMCID: PMC9106432. Epub 20220513.

Introduction

Capsule endoscopy (CE) is commonly used as the initial exam in situations of suspected mid-gastrointestinal bleeding, after normal upper and lower endoscopy. Although the assessment of the small bowel is the primary focus of CE, detection of upstream or downstream vascular lesions may also be clinically significant. This study aimed to develop and test a Convolutional Neural Network (CNN)-based model for panendoscopic automatic detection of vascular lesions during CE.

Aims & Methods

A multicentric retrospective study was conducted, based on 1022 CE exams. We used a total of 35655 frames, from seven types of CE devices (PillCam Colon 1, PillCam Crohn's, PillCam SB1, PillCam SB3, OMOM HD, Olympus, Mirocam), of which 11091 were considered to have vascular lesions (angiectasia or varices) after triple validation. We divided data into a training and a validation set, the latter being used to evaluate the model’s performance. At time of division, all frames from a given patient were assigned to the same dataset. Our primary outcome measures were sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV) and an area under the precision-recall curve (AUC-PR).

Results

A total of 35655 frames were used, with 11091 including vascular lesions. The validation data set contained 2433 frames with normal mucosa and 933 vascular lesions.
Sensitivity and specificity were 86.4% and 98.3%, respectively. PPV was 95.2%, while the NPV was 95.0%. Overall accuracy was 95.0%. The AUC-PR value was 0.96. The CNN processed 115 frames per second.

Conclusion

The study presents promising results for the application of AI deep learning models in panendoscopic automatic detection of vascular lesions in various gastrointestinal topographies. The methodological details, including the patient-split design and the use of frames from different types of CE devices, suggest that the model could be effectively used in routine clinical practice independently of the device brand. This study highlights the potential of panendoscopic evaluation of all gastrointestinal tract and the need for further research in this area. Overall, the high diagnostic performance of this CNN in multibrand devices addresses an important issue of technological interoperability, allowing it to be replicated in multiple technological settings. However, the study has some limitations, including a small number of frames and a retrospective design, which may introduce selection bias, therefore prospective and multicentric studies are needed before introducing this deep learning model into clinical practice. This is the first proof-of concept AI deep learning model developed for panendoscopic automatic detection of vascular lesions during CE.

References

Triester, S.L., et al., A meta-analysis of the yield of capsule endoscopy compared to other diagnostic modalities in patients with obscure gastrointestinal bleeding. Am J Gastroenterol, 2005. 100(11): p. 2407-18.
Liao, Z., et al., Indications and detection, completion, and retention rates of small-bowel capsule endoscopy: a systematic review. Gastrointest Endosc, 2010. 71(2): p. 280-6.
Rondonotti, E., et al., Small-bowel capsule endoscopy and device-assisted enteroscopy for diagnosis and treatment of small-bowel disorders: European Society of Gastrointestinal Endoscopy (ESGE) Technical Review. Endoscopy, 2018. 50(4): p. 423-446.
Ribeiro, T.F.-U.I.C.H., Colon capsule endoscopy and artificial intelligence: a perfect match por panendoscopy, in Artificial Intelligence in Capsule Endoscopy, C.H. Mascarenhas M, Macedo G, Editor. 2023, Academic Press.
Tsuboi, A., et al., Artificial intelligence using a convolutional neural network for automatic detection of small-bowel angioectasia in capsule endoscopy images. Dig Endosc, 2020. 32(3): p. 382-390.
Saurin, J.C., et al., Diagnostic value of endoscopic capsule in patients with obscure digestive bleeding: blinded comparison with video push-enteroscopy. Endoscopy, 2003. 35(7): p. 576-84.
Mascarenhas, M., et al., Deep learning and colon capsule endoscopy: automatic detection of blood and colonic mucosal lesions using a convolutional neural network. Endosc Int Open, 2022. 10(2): p. E171-e177