1
|
Baumer S, Streicher K, Alqahtani SA, Brookman-Amissah D, Brunner M, Federle C, Muehlenberg K, Pfeifer L, Salzberger A, Schorr W, Zustin J, Pech O. Accuracy of polyp characterization by artificial intelligence and endoscopists: a prospective, non-randomized study in a tertiary endoscopy center. Endosc Int Open 2023; 11:E818-E828. [PMID: 37727511 PMCID: PMC10506867 DOI: 10.1055/a-2096-2960] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/17/2023] [Accepted: 05/08/2023] [Indexed: 09/21/2023] Open
Abstract
Background and study aims Artificial intelligence (AI) in gastrointestinal endoscopy is developing very fast. Computer-aided detection of polyps and computer-aided diagnosis (CADx) for polyp characterization are available now. This study was performed to evaluate the diagnostic performance of a new commercially available CADx system in clinical practice. Patients and methods This prospective, non-randomized study was performed at a tertiary academic endoscopy center from March to August 2022. We included patients receiving a colonoscopy. Polypectomy had to be performed in all polyps. Every patient was examined concurrently by an endoscopist and AI using two opposing screens. The AI system, overseen by a second observer, was not visible to the endoscopist. The primary outcome was accuracy of the AI classifying the polyps into "neoplastic" and "non-neoplastic." The secondary outcome was accuracy of the classification by the endoscopists. Sessile serrated lesions were classified as neoplastic. Results We included 156 patients (mean age 65; 57 women) with 262 polyps ≤10 mm. Eighty-four were hyperplastic polyps (32.1%), 158 adenomas (60.3%), seven sessile serrated lesions (2.7%) and 13 other entities (normal/inflammatory colonmucosa, lymphoidic polyp) (4.9%) on histological diagnosis. Sensitivity, specificity and accuracy of AI were 89.70% (95% confidence interval [CI]: 84.02%-93.88%), 75.26% (95% CI: 65.46%-83.46%) and 84.35% (95% CI:79.38%-88.53%), respectively. Sensitivity, specificity and accuracy for less experienced endoscopists (2-5 years of endoscopy) were 95.56% (95% CI: 84.85%-99.46%), 61.54% (95% CI: 40.57%-79.77%) and 83.10% (95% CI: 72.34%-90.95%) and for experienced endoscopists 90.83% (95% CI: 84.19%-95.33%), 71.83% (95% CI: 59.90%-81.87%) and 83.77% (95% CI: 77.76%-88.70%), respectively. Conclusion Accuracy for polyp characterization by a new commercially available AI system is high, but does not fulfill the criteria for a "resect-and-discard" strategy.
Collapse
Affiliation(s)
- Sebastian Baumer
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| | - Kilian Streicher
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| | - Saleh A. Alqahtani
- Department of Gastroenterology and Hepatology, Johns Hopkins Hospital, Baltimore, United States
- Liver Transplant Center, King Faisal Specialist Hospital and Research Center, Riyadh, Saudi Arabia
| | - Dominic Brookman-Amissah
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| | - Monika Brunner
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| | - Christoph Federle
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| | - Klaus Muehlenberg
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| | - Lukas Pfeifer
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| | - Andrea Salzberger
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| | - Wolfgang Schorr
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| | - Jozef Zustin
- Private Practice, Histopathology Service Private Practice, Regensburg, Germany
- Gerhard-Domagk-Institute of Pathology, Universitätsklinikum Münster, Munster, Germany
| | - Oliver Pech
- Department of Gastroenterology and Interventional Endoscopy, Krankenhaus Barmherzige Brüder Regensburg, Regensburg, Germany
| |
Collapse
|
2
|
Amin A, Yasmeen S, Jeyachandran D, Khoury T, Desouki MM. Diagnostic Utility and Significance of Performing Multistep Level Sections in Breast and Gynecologic Biopsy Specimens. Am J Clin Pathol 2021; 156:620-624. [PMID: 33769440 DOI: 10.1093/ajcp/aqaa277] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
Abstract
OBJECTIVES The significance of performing multistep level sections, including preparation of unstained sections in breast and gynecologic biopsy specimens, has been studied. METHODS Consecutive H&E-stained level sections of 785 atypical and malignant biopsy specimens were included. The diagnostic material was categorized into present, absent, increased in size, or depleted. If the multistep level sections helped in establishing the diagnosis after a nondiagnostic material or the tissue significantly increased in size, this was considered a positive impact. RESULTS No effect and positive impact of performing multistep level sections were obtained in 84.8% and 15.2% by preparing a second level and 97.2% and 2.8% by preparing a third level, respectively. Eighteen (2.3%) of the diagnoses could have been missed without performing a second level, while 8 (1%) could have been missed without performing a third level. The intervening unstained sections were used in 27 of 785 (3.4%) of the cases. CONCLUSIONS Staining two level sections with H&E significantly affected the diagnosis. However, preparing a third level did not improve the diagnosis. A universal protocol should be considered to standardize the handling of biopsy specimens among laboratories.
Collapse
Affiliation(s)
- Al Amin
- Department of Pathology and Anatomical Sciences, State University of New York, Buffalo, NY, USA
| | - Sayeeda Yasmeen
- Department of Pathology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA
| | - Devi Jeyachandran
- Department of Pathology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA
| | - Thaer Khoury
- Department of Pathology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA
- Jacobs School of Medicine and Biomedical Sciences, State University of New York, Buffalo, NY, USA
| | - Mohamed Mokhtar Desouki
- Department of Pathology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA
- Jacobs School of Medicine and Biomedical Sciences, State University of New York, Buffalo, NY, USA
- Department of Pathology, Microbiology and Immunology, University of South Carolina, Columbia, SC, USA
| |
Collapse
|
3
|
Lama G, Upadhyaya P, Karki S, Pradhan A. Deeper Sections: Its Frequency and Diagnostic Utility in Histopathology of Noncutaneous Small Biopsy Specimen in a Tertiary Hospital in Nepal. Adv Med 2021; 2021:5926047. [PMID: 34497860 PMCID: PMC8419504 DOI: 10.1155/2021/5926047] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/21/2020] [Accepted: 08/21/2021] [Indexed: 11/17/2022] Open
Abstract
BACKGROUND Biopsy is an important tool for accurate diagnosis of disease in histopathology which can be examined at multiple levels during microscopic examination. The initial sections may not be representative of the entire biopsy, which leads to frequent request for deeper sections. This study assessed the frequency and diagnostic utility of deeper sections in noncutaneous small biopsy specimens at a tertiary hospital. Material and Methods. All the formalin fixed noncutaneous small biopsy specimens received were processed for grossing followed by tissue processing and embedding. The paraffin-embedded blocks were cut into 3-5 µm sections, fixed in a glass slide, deparaffinised, and then stained with hematoxylin and eosin (H&E) stain as per the standard protocol. Deeper sections were instructed based on microscopic findings of initial slides. The overall frequency of deeper section, its levels of cutting, tissue survival, and outcome were assessed and interpreted for the final diagnosis. RESULTS A total of 125 cases (26.9%) from 464 samples received were requested for deeper sections. The most frequent deeper sections were from cervix (72 cases) followed by stomach (18 cases) and endometrium (17 cases). The deeper sections were performed most frequently at 4 levels (17.8%) followed by 5 levels (14.8%) and 6 levels (13.3%). Deeper sections revealed nondiagnostic additional features in 28.2%, while 2.2% showed additional diagnostic features. Likewise, 2.2% had tissue segment loss. The overall mean level showing additional features was 6 levels. Tissue survival increased in 13% cases and 1.5% had decreased survival. The most common reason for requesting deeper section was to enhance sensitivity and diagnostic accuracy of disease. CONCLUSIONS Deeper sections often contribute to final diagnosis. Therefore, deeper sections on biopsies that cannot readily be diagnosed on routine levels are recommended regardless of size of the lesion and there should be uniformity in the practice of deeper sections across the globe.
Collapse
Affiliation(s)
- Gopal Lama
- Department of Pathology, B.P. Koirala Institute of Health Sciences, Dharan, Nepal
- Department of Pathology, Rapti Academy of Health Sciences, Ghorahi, Nepal
| | - Paricha Upadhyaya
- Department of Pathology, B.P. Koirala Institute of Health Sciences, Dharan, Nepal
| | - Smriti Karki
- Department of Pathology, B.P. Koirala Institute of Health Sciences, Dharan, Nepal
| | - Anju Pradhan
- Department of Pathology, B.P. Koirala Institute of Health Sciences, Dharan, Nepal
| |
Collapse
|
4
|
Hyperplastic polyp or sessile serrated lesion? The contribution of serial sections to reclassification. Diagn Pathol 2020; 15:140. [PMID: 33298116 PMCID: PMC7726909 DOI: 10.1186/s13000-020-01057-0] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2020] [Accepted: 11/29/2020] [Indexed: 01/16/2023] Open
Abstract
BACKGROUND The histological discrimination of hyperplastic polyps from sessile serrated lesions can be difficult. Sessile serrated lesions and hyperplastic polyps are types of serrated polyps which confer different malignancy risks, and surveillance intervals, and are sometimes difficult to discriminate. Our aim was to reclassify previously diagnosed hyperplastic polyps as sessile serrated lesions or confirmed hyperplastic polyps, using additional serial sections. METHODS Clinicopathological data for all colorectal hyperplastic polyps diagnosed in 2016 and 2017 was collected. The slides were reviewed and classified as hyperplastic polyps, sessile serrated lesion, or other, using current World Health Organization criteria. Eight additional serial sections were performed for the confirmed hyperplastic polyp group and reviewed. RESULTS Of an initial 147 hyperplastic polyps from 93 patients, 9 (6.1%) were classified as sessile serrated lesions, 103 as hyperplastic polyps, and 35 as other. Of the 103 confirmed hyperplastic polyps, 7 (6.8%) were proximal, and 8 (7.8%) had a largest fragment size of ≥5 mm and < 10 mm. After 8 additional serial sections, 11 (10.7%) were reclassified as sessile serrated lesions. They were all less than 5 mm and represented 14.3% of proximal polyps and 10.4% of distal polyps. An average of 3.6 serial sections were required for a change in diagnosis. CONCLUSION Histopathological distinction between hyperplastic polyps and sessile serrated lesions remains a challenge. This study has uncovered a potential role for the use of additional serial sections in the morphological reappraisal of small hyperplastic polyps, especially when proximally located.
Collapse
|
5
|
Khararjian A, Mannan R, Byrnes K, Barker N, Voltaggio L. Are Upfront Levels for Colon "Polyps" Necessary? A Pragmatic Review. Int J Surg Pathol 2018; 27:15-18. [PMID: 29944023 DOI: 10.1177/1066896918783264] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
INTRODUCTION Colon biopsies are among the most frequently examined specimens by pathologists. Many pathology practices, ours included, review upfront levels on all gastrointestinal biopsies. In our experience, when a lesion is present on specimens labeled "colon polyp," it is readily identified on the first level. To test our hypothesis, we re-reviewed 500 cases in which a lesion was identified histologically and determined if the diagnosis could be made on the first level. Furthermore, we examined 50 additional cases of high-grade dysplasia/carcinoma to determine if the higher-grade component was also present on the first level. MATERIALS AND METHODS Cases were retrieved for lesions that could account for a colon polyp clinically, and the first level was examined to determine if lesional tissue was present on the first level. Fifty additional cases of higher-grade lesions were included to ensure higher-grade lesions were present on the first level. RESULTS Overall, 497/500 (99.4%) of the non-high-grade lesions were present on the first level, whereas 3/500 (0.6%) required the additional level for diagnosis. All 50 high-grade lesions were present on the first level examined. DISCUSSION Many pathology practices routinely order upfront levels on all gastrointestinal biopsies, often generating 2 or 3 slides. Additional slides increase costs, increase the likelihood of laboratory-generated errors, and can waste limited tissue on small biopsies for which ancillary studies may be necessary. Our study showed that a single level is sufficient in the overwhelming majority of cases in which a lesion is identified histologically.
Collapse
|
6
|
Schick BA, McLean CA, Driman DK. Negative colorectal polyp biopsies: the utility of cutting deeper levels. Virchows Arch 2015; 467:10.1007/s00428-015-1866-9. [PMID: 26475150 DOI: 10.1007/s00428-015-1866-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2015] [Revised: 09/22/2015] [Accepted: 10/05/2015] [Indexed: 10/22/2022]
Abstract
The objectives of this study were to determine the frequency with which deeper levels reveal a lesion in polyp biopsies where no polyp was found on initial sections and to identify features that predict such occult (histologically unapparent) lesions. All initially negative biopsy specimens were accumulated over an 18-month period. Following standard sections, three to ten levels were cut, 50 μm apart. The presence of any lesion, the level at which it was found, the location, number and size of fragments, number of levels obtained, presence of any lymphoid aggregate, endoscopic size and appearance, and bowel preparation quality were recorded. There were 214 specimens, mean patient age 61.4 years (range 27-86 years). Deeper levels revealed a lesion in 52/214 (24.3 %) cases; 76.9 % were tubular adenomas (TA), 21.2 % were hyperplastic polyps, and one was a leiomyoma. All TAs were negative for high-grade dysplasia and malignancy. The mean level at which TAs were found was 1.85 (range 1-9). Male sex (p = 0.021) and right-sided location (p = 0.0075) were statistically significant predictors of an occult TA. As the presence of an adenoma affects screening, pathologists should consider "pursuing" polyps when initial sections reveal no lesion, after ascertaining the incidence of occult lesions in their own practice.
Collapse
Affiliation(s)
- Brian A Schick
- London Health Sciences Centre and Western University, London, ON, Canada
| | - Carolyn A McLean
- London Health Sciences Centre and Western University, London, ON, Canada
| | - David K Driman
- London Health Sciences Centre and Western University, London, ON, Canada.
- Department of Pathology and Laboratory Medicine, London Health Sciences Centre, 339 Windermere Road N6A 5A5, London, ON, Canada.
| |
Collapse
|
7
|
Application of three-dimensional imaging to the intestinal crypt organoids and biopsied intestinal tissues. ScientificWorldJournal 2013; 2013:624342. [PMID: 24348177 PMCID: PMC3848346 DOI: 10.1155/2013/624342] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2013] [Accepted: 09/11/2013] [Indexed: 12/16/2022] Open
Abstract
Two-dimensional (2D) histopathology is the standard analytical method for intestinal biopsied tissues; however, the role of 3-dimensional (3D) imaging system in the analysis of the intestinal tissues is unclear. The 3D structure of the crypt organoids from the intestinal stem cell culture and intestinal tissues from the donors and recipients after intestinal transplantation was observed using a 3D imaging system and compared with 2D histopathology and immunohistochemistry. The crypt organoids and intestinal tissues showed well-defined 3D structures. The 3D images of the intestinal tissues with acute rejection revealed absence of villi and few crypts, which were consistent with the histopathological features. In the intestinal transplant for megacystis microcolon intestinal hypoperistalsis syndrome, the donor's intestinal tissues had well-developed nerve networks and interstitial cells of Cajal (ICCs) in the muscle layer, while the recipient's intestinal tissues had distorted nerve network and the ICCs were few and sparsely distributed, relative to those of the donor. The 3D images showed a clear spatial relationship between the microstructures of the small bowel and the features of graft rejection. In conclusion, integration of the 3D imaging and 2D histopathology provided a global view of the intestinal tissues from the transplant patients.
Collapse
|
8
|
Nielsen JA, Lager DJ, Lewin M, Weber JJ, Roberts CA. Incidence of diagnostic change in colorectal polyp specimens after deeper sectioning at 2 different laboratories staffed by the same pathologists. Am J Clin Pathol 2013; 140:231-7. [PMID: 23897260 DOI: 10.1309/ajcppxu66qzaznyn] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2023] Open
Abstract
OBJECTIVES To calculate the incidence of nondiagnostic (ND) colorectal (CR) polyp cases in which deeper tissue sectioning rendered new diagnostic information--particularly adenomas--in 2 laboratories staffed by the same pathologists. METHODS After initial diagnosis, 100 ND CR polyps from each laboratory were reexamined with 3 deeper levels to establish rates of diagnostic conversion based on biopsy specimen location and original observation(s). RESULTS Deeper sectioning rendered new diagnostic information in 43 (21.5%) of 200 biopsy specimens and specifically adenomas in 16 (8.0%) of 200 biopsy specimens. CONCLUSIONS These results support routine ordering of deeper levels on ND CR polyps to improve adenoma detection rates, especially those cases without any histologic abnormality. If another biopsy in the same case already is adenomatous, examination of deeper levels may not be necessary, as it may not have any significant effect on the clinical management of the patient.
Collapse
|
9
|
Liu YA, Chen Y, Chiang AS, Peng SJ, Pasricha PJ, Tang SC. Optical clearing improves the imaging depth and signal-to-noise ratio for digital analysis and three-dimensional projection of the human enteric nervous system. Neurogastroenterol Motil 2011; 23:e446-57. [PMID: 21895876 DOI: 10.1111/j.1365-2982.2011.01773.x] [Citation(s) in RCA: 25] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/08/2023]
Abstract
BACKGROUND Due to the dispersed nature of neurites and fibers, the microtome-based 2-dimensional histology provides only a limited perspective of the enteric nervous system. To visualize the enteric plexus, we applied optical clearing to avoid scattering in the human ileum to facilitate photon penetration for 3-dimensional (3-D) microscopy of the neural tissue. METHODS Human ileal specimens were derived by trimming the donor bowel due to its excess length during the clinical trial of small intestinal transplantation. The pan-neuronal marker PGP9.5 was used as the immunostaining target to reveal the enteric plexuses. The labeled tissues were immersed in the optical-clearing solution prior to deep-tissue confocal microscopy. The serial sections were digitally analyzed and processed by reconstruction algorithms for 3-D visualization. KEY RESULTS Optical clearing of the ileal specimen led to less fluorescence signal decay along the focal path in the tissue and a higher signal-to-noise ratio of the confocal micrographs in comparison with the untreated saline control. Taking advantage of the high signal-to-noise ratio images, we applied software-based signal analysis to identify the presence of the nerve fibers and quantify the signal peaks. The image stacks derived from the serial anatomic micrographs created panoramic views of the gut wall innervations with their associated microstructures. CONCLUSIONS & INFERENCES We provide an optical approach to improve the imaging depth in 3-D neurohistology of the human ileum. This methodology has significant promise in facilitating our understanding of the enteric nervous system in health and disease.
Collapse
Affiliation(s)
- Y-A Liu
- Department of Chemical Engineering, National Tsing Hua University, Hsinchu, Taiwan
| | | | | | | | | | | |
Collapse
|
10
|
Abstract
Modern evaluation of specimens from biopsies of colorectal polyps has become increasingly complex because of tremendous progress in the understanding of colorectal neoplasia. Although pathologists are generally familiar with the basic handling of carcinoma in the setting of polypectomies or resections, the comprehensive evaluation of specimens from biopsies of colorectal polyps obtained with forceps is far from intuitive and has yet to be reviewed. Comprehensive evaluation requires always addressing several key issues, even when dealing with seemingly routine cases. These issues include taking further action when initial sections lack polyps, accurately quantitating polyps, accurately classifying polyps, determining whether thresholds are met for considering conditions at high risk for carcinoma, detecting incidental findings other than polyps, and determining which incidental findings are clinically significant. In particular, polyposis with attenuated phenotype or Lynch syndrome may be clinically occult, and the possibility of these entities should always be kept in mind, regardless of age or history. Ancillary studies performed immediately on carcinoma that is detected at biopsy guides surgery, guides medical therapy, prognosticates, provides evidence for hereditary neoplasia, and guides surveillant colonoscopy for the family.
Collapse
|