Related Experiment Video
Updated: Jan 26, 2026
Multiple-mouse Neuroanatomical Magnetic Resonance Imaging
Published on: February 27, 2011
Full convolutional network based multiple side-output fusion architecture for the segmentation of rectal tumors in
Mengmeng Wang1,2, Peiyi Xie3, Zhao Ran1,2
1University of Science and Technology of China, Hefei, Anhui, 230026, China.
Purpose:
Accurate segmentation of rectal tumors is a basic and crucial task for diagnosis and treatment of rectal cancer. To avoid tedious manual delineation, an automatic rectal tumor segmentation model is proposed.
Methods:
A pretrained Resnet50 model was introduced for feature extraction. To reduce the complexity of the model, all layers after the 13th residual block of ResNet50 were removed, and three side-output modules were added to the hidden layer of ResNet50 to guide multiscale feature learning. The final boundaries of tumors were determined by fusion of the predictions from side-output modules. The proposed model was compared with two other models, and the effects of different region of interest (ROI) sizes, loss functions, and side-output fusion strategy were also evaluated.
Results:
The models were trained and evaluated on data from four clinical centers; T2-weighted magnetic resonance images (T2W-MRIs) from 461 patients in the first clinical center were used for training, while T2W-MRIs from 51 patients in the same clinical center and 56 patients in three other clinical centers were used for performance evaluation. The proposed model was superior to the two other models and achieved an average Dice similarity coefficient of 82.39%, sensitivity of 86.32%, specificity of 92.25%, and Hausdorff distance of 12.10 px. In addition, when the ROI contained rectal tumors, the smaller the ROI size, the higher the segmentation accuracy. For a certain ROI size, there were no considerable differences in segmentation results among the loss functions. Compared to the models with single side-output module, the proposed model performed better.
Conclusions:
The results show that the proposed model has potential clinical applications in rectal cancer treatment, particularly with regard to therapeutic response evaluation and preoperative planning.
Insights
An automated model using ResNet50 was developed for accurate rectal tumor segmentation, improving diagnosis and treatment planning for rectal cancer. This AI-driven approach offers superior performance compared to existing methods.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Accurate segmentation of rectal tumors is critical for effective rectal cancer diagnosis and treatment.
- Manual delineation is time-consuming and prone to variability.
- Automated segmentation models aim to improve efficiency and consistency.
Purpose of the Study:
- To propose an automatic rectal tumor segmentation model to overcome the limitations of manual delineation.
- To evaluate the performance of the proposed model against existing methods.
- To investigate the impact of region of interest (ROI) size, loss functions, and side-output fusion on segmentation accuracy.
Main Methods:
- A ResNet50 model was utilized for feature extraction, with layers after the 13th residual block removed.
- Three side-output modules were integrated into the hidden layer to guide multiscale feature learning.
- Tumor boundaries were determined by fusing predictions from these side-output modules.
- The model was trained and validated on T2-weighted MRI data from 461 patients across four clinical centers.
Main Results:
- The proposed model outperformed two other models, achieving a Dice similarity coefficient of 82.39%, sensitivity of 86.32%, and specificity of 92.25%.
- Smaller ROI sizes correlated with higher segmentation accuracy when tumors were included.
- The model with fused side-output modules demonstrated superior performance compared to single-module models.
Conclusions:
- The developed automatic rectal tumor segmentation model shows significant potential for clinical applications in rectal cancer.
- It can aid in therapeutic response evaluation and preoperative planning.
- The model offers a more efficient and accurate alternative to manual segmentation.
Related Concept Videos
01:27Imaging Studies IV: Magnetic Resonance Imaging
01:24Magnetic Resonance Imaging
02:45Nuclear Fusion
A helium nucleus has a mass that is 0.7% less than that of four hydrogen nuclei; this lost mass is converted into energy during the fusion. This reaction produces about...
01:17Convolution Properties II
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
02:26Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
01:05Atomic Nuclei: Magnetic Resonance