Convolutional neural network deep learning model accurately detects rectal cancer in endoanal ultrasounds

• Published in: Techniques in coloproctology Vol. 28; no. 1; p. 44
• Main Authors: Carter, D., Bykhovsky, D., Hasky, A., Mamistvalov, I., Zimmer, Y., Ram, E., Hoffer, O.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.12.2024; Springer Nature B.V
• Subjects: Abdominal Surgery; Accuracy; Clinical outcomes; Colorectal cancer; Colorectal Surgery; Deep Learning; Endosonography - methods; Gastroenterology; Humans; Medical diagnosis; Medicine; Medicine & Public Health; Neural networks; Neural Networks, Computer; Original; Original Article; Proctology; Rectal Neoplasms - diagnostic imaging; Surgery; Ultrasonic imaging; Ultrasonography - methods; Rectal cancer; Endoanal ultrasound,deep learning; Convolutional neural network
• ISSN: 1123-6337; 1128-045X
• DOI: 10.1007/s10151-024-02917-3

Background Imaging is vital for assessing rectal cancer, with endoanal ultrasound (EAUS) being highly accurate in large tertiary medical centers. However, EAUS accuracy drops outside such settings, possibly due to varied examiner experience and fewer examinations. This underscores the need for an AI-based system to enhance accuracy in non-specialized centers. This study aimed to develop and validate deep learning (DL) models to differentiate rectal cancer in standard EAUS images. Methods A transfer learning approach with fine-tuned DL architectures was employed, utilizing a dataset of 294 images. The performance of DL models was assessed through a tenfold cross-validation. Results The DL diagnostics model exhibited a sensitivity and accuracy of 0.78 each. In the identification phase, the automatic diagnostic platform achieved an area under the curve performance of 0.85 for diagnosing rectal cancer. Conclusions This research demonstrates the potential of DL models in enhancing rectal cancer detection during EAUS, especially in settings with lower examiner experience. The achieved sensitivity and accuracy suggest the viability of incorporating AI support for improved diagnostic outcomes in non-specialized medical centers.