Deep Learning in Classifying Bowel Obstruction Radiographs

Self-supervised Learning for Classifying Bowel Obstruction on Upright Abdominal Radiography

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT06321614

Enrollment

4500

Registered

2024-03-20

Start date

2022-12-31

Completion date

2024-12-31

Last updated

2024-03-20

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Bowel Disease, Digestive System Disease, Polyp of Colon

Keywords

Deep learning, Artificial intelligence, Machine learning

Brief summary

Background: Accurate labeling of obstruction site on upright abdominal radiograph is a challenging task. The lack of ground truth leads to poor performance on supervised learning models. To address this issue, self-supervised learning (SSL) is proposed to classify normal, small bowel obstruction (SBO), and large bowel obstruction (LBO) radiographs using a few confirmed samples. Methods: A few number of confirmed and a large number of unlabeled radiographs were categorized based on the ground truth. The SSL model was firstly trained on the unlabeled radiographs, and then fine-tuned on the confirmed radiographs. ResNet50 and VGG16 were used for the embedded base encoders, whose weights and parameters were adjusted during training process. Furthermore, it was tested on an independent dataset, compared with supervised learning models and human interpreters. Finally, the t-SNE and Grad-CAM were used to visualize the model's interpretation.

Interventions

None listed

Study design

Observational model

CASE_CONTROL

Time perspective

RETROSPECTIVE

Eligibility

Sex/Gender

ALL

Age

18 Years to 80 Years

Healthy volunteers

Inclusion criteria

1. The hospital imaging system looked for plain abdominal standing films diagnosed as intestinal obstruction or normal between 2022 and 2024 2. Aged 18 to 80 years 3. The main complaint was gastrointestinal symptoms

Exclusion criteria

1. Image interference, fuzzy performance, difficult to distinguish 2. Non-gastrointestinal symptoms were the main complaint 3. Supine, prone, or lateral decubitus radiography 4. Paralytic obstruction, closed loop obstruction, et al

Design outcomes

Primary

Measure	Time frame	Description
Diagnostic and classification performance	1 week	Accuracy, Recall, Precision, F1-score and confusion matrix

Secondary

Measure	Time frame	Description
Visualized interpretation of the self-supervised model	1 week	Grad-CAM and t-SNE to visualize the interpretation of the SSL model

Countries

China

Outcome results