EP772 - Deep Learning and Endoanal Ultrasound: a Multilesion Model for Differentiating Anorectal Benign Lesions

Monday, May 11, 2026

8:16 AM - 8:21 AM ET

ePoster Presenter(s)

PD

Pedro Diaz Donoso, MD (he/him/his)

Colorectal surgeon
Centro Privado de Cirugia y Coloprctologia
Buenos Aires, Ciudad Autonoma de Buenos Aires, Argentina

Disclosure information not submitted.

View ePoster

Senior Author(s)

MM

Miguel Mascarehnas, n/a

Department of Gastroenterology, São João University Hospital
.
., Porto, Portugal

Disclosure information not submitted.

Author(s)

MJ

Maria João Almeida, n/a

Department of Gastroenterology, São João University Hospital
.
., Porto, Portugal

Disclosure information not submitted.
MM

Miguel Martins, n/a

Engineer
Faculty of Engineering of the University of Porto
Porto, Porto, Portugal

Disclosure information not submitted.
FM

Francisco Mendes, .

Department of Gastroenterology, São João University Hospital
.
., Porto, Portugal

Disclosure information not submitted.
JM

Joana Mota, n/a

Dr
Hospital São João, Porto.
Porto, Porto, Portugal

Disclosure information not submitted.
TR

Tiago Ribeiro, n/a

Department of Surgery, Instituto de Infectologia Emílio Ribas
.
., Porto, Portugal

Disclosure information not submitted.
PC

Pedro Cardoso, MD

Dr
Centro Hospitalar Universitário de São João, Gastroenterology, Porto, Portugal
Porto, Porto, Portugal

Disclosure information not submitted.
PA

Patricia Andrade, .

Department of Gastroenterology, São João University Hospital
.
., Porto, Portugal

Disclosure information not submitted.
AP

Antonio Pinto da Costa, .

Department of Gastroenterology, Puerta del Hierro University Hospital
.
., Porto, Portugal

Disclosure information not submitted.
PF

Pablo Farina, .

Colorectal surgeon, Centro Privado de Cirgugia y Coloproctologia
.
Buenos Aires, Ciudad Autonoma de Buenos Aires, Argentina

Disclosure information not submitted.
JA

Jorge Arias, .

Colorectal surgeon, Centro Privado de Cirgugia y Coloproctologia
.
Buenos Aires, Ciudad Autonoma de Buenos Aires, Argentina

Disclosure information not submitted.
Matias La Francesca, MD

Fellow
Centro privado de cirugia y coloproctologia
University of Buenos Aires
Buenos aires, Ciudad Autonoma de Buenos Aires, Argentina

All disclosed relationships have been reviewed and managed prior to the start of this activity. Any relevant relationships will be listed below. This individual has no financial relationships to disclose
MS

Mateo Santillan, MD

Fellow
Centro Privado de Cirugía y Coloproctología
Ciudad autónoma de Buenos Aires, Buenos Aires, Argentina

Disclosure information not submitted.
MM

Myrna Y. Martin, n/a

Colorectal Surgeon, Centro Privado de Cirugía y Coloproctologia
.
Caba, Ciudad Autonoma de Buenos Aires, Argentina

Disclosure information not submitted.
CL

Carlos Miguel Lumi, .

Colorectal Surgeon, Centro Privado de Cirugía y Coloproctologia
.
Buenos Argentina, Ciudad Autonoma de Buenos Aires, Argentina

Disclosure information not submitted.
JF

Joao Ferreira, .

Department of Gastroenterology, São João University Hospital
.
., Porto, Portugal

Disclosure information not submitted.
GM

Guilherme Macedo, .

Department of Gastroenterology, São João University Hospital
.
., Porto, Portugal

Disclosure information not submitted.
FP

Fernando Poças, .

Centro Hospitalar Universitário de Santo António, Gastroenterology
.
., Porto, Portugal

Disclosure information not submitted.
BM

Bruno Mendes, .

Faculty of Engineering of the University of Porto
.
., Porto, Portugal

Disclosure information not submitted.
PJ

Pamela Jacinto, .

Colorectal surgeon, Centro Privado de Cirugía y Coloproctologia
.
., Ciudad Autonoma de Buenos Aires, Argentina

Disclosure information not submitted.

Purpose/Background: Endoanal Ultrasound (EAUS) is a key diagnostic tool for anorectal diseases, valued for its simplicity and tolerability. However, its interpretation is challenged by significant interobserver variability, a steep learning curve, and limited accessibility. The application of artificial intelligence (AI) to enhance EAUS remains in its early stages. The aim of this study was to develop and validate an interoperable AI model capable of differentiating multiple benign anorectal lesions using EAUS.

Methods/Interventions: An EfficientNet-based AI model was developed using 4722 EAUS frames, from 105 procedures performed across two centers using two different ultrasound devices. Two experts independently classified frames into 5 categories: external anal sphincter (EAS) laceration, internal anal sphincter (IAS) laceration, anal fissure (AF), intersphincteric fistula (ISF), and transsphincteric fistula (TSF). Frames with concordant classifications established the ground truth. The dataset was split into training/validation (90%, with 3-fold cross-validation) and test (10%) sets. The model with the best F1-score was tested Performance metrics included accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score

Results/Outcomes: Training/validation mean (±SD) accuracies were: EAS 0.85 (±0.03), IAS 0.85 (±0.003), AF 0.98 (±0.02), ISF 0.99 (±0.01), TSF 0.99 (±0.01). On the test set, respective accuracies were: EAS 0.88, IAS 0.88, AF 0.99, ISF 1.00, TSF 0.99

Conclusion/Discussion: This pioneering AI model demonstrates high accuracy in differentiating five benign anorectal lesions using EAUS. As the first multilesion solution in this area, it represents a significant step toward standardizing EAUS interpretation and expanding access to expert-level diagnostic support. With further prospective validation, this technology has the potential to transform clinical workflows and improving decision-making in anorectal care.

Performance Metrics

Table 1. Performance Metrics (sensitivity, specificity, and accuracy) of the model for each ontology.
Multilesion Artificial Intelligence Model for Differentiating Anorectal Benign Lesions

Multilesion Artificial Intelligence Model for Differentiating Anorectal Benign Lesions