Deep Learning-Based Anatomical Level Classification of Craniofacial CT Slices: Comparison of CNN Architectures and Ensemble Methods
Nishimoto, S.; Nakajima, K.; Yoshiike, H.; Ishise, H.; Saito, T.; Kawai, K.
Show abstract
Computed tomography (CT) interpretation requires recognition of the anatomical level of each slice. Classification may facilitate preprocessing and AI-assisted fracture diagnosis. We developed deep learning models to classify craniofacial CT slices into six anatomical categories. A total of 11,769 images were collected from a multicenter database involving 10 Japanese university hospitals and the public Head-Neck-Radiomics-HN1 dataset. Patients were divided into training (70%) and evaluation (30%) sets. Five CNN architectures were trained from scratch, and hard- and soft-voting ensembles were evaluated. Individual-model accuracy ranged from 94.72% to 96.09%; the hard-voting ensemble achieved 96.46% accuracy (Cohen's k = 0.954). Although performance differed among individual models (Cochran's Q = 99.29, p < 0.001), the ensemble did not significantly outperform EfficientNetV2B1 (McNemar's p = 0.163). Errors occurred mainly between adjacent anatomical regions. Deep learning can classify craniofacial CT slices accurately and may support automated dataset organization and AI-assisted fracture diagnosis. External validation is needed.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Fully automatic segmentation of craniomaxillofacial CT scans for computer-assisted orthognathic surgery planning using the nnU-Net framework 95%
- From Community Acquired Pneumonia to COVID-19: A Deep Learning Based Method for Quantitative Analysis of COVID-19 on thick-section CT Scans 93%
- Assessing GPT-4 Multimodal Performance in Radiological Image Analysis 92%
Similar papers in this journal
- Functional Aspects of the Eustachian Tube by Means of 3D-Modeling 93%
- Enhancing Semantic Segmentation in Chest X-Ray Images through Image Preprocessing: ps-KDE for Pixel-wise Substitution by Kernel Density Estimation 93%
- Investigating the relationship between internal spinal alignment and back shape in patients with scoliosis using PCdare: a comparative, reliability and validation study 93%
Similar papers in this journal
- Tracking And Predicting COVID-19 Radiological Trajectory Using Deep Learning On Chest X-Rays: Initial Accuracy Testing 93%
- Multi-center Clinical Study Using Optical Coherence Tomography for Evaluation of Cervical Lesions In-vivo 93%
- Development and Validation of Collaborative Robot-assisted Cutting Method for Iliac Crest Flap Raising: Randomized Crossover Trial 92%
Similar papers in this journal
- Comparing performance of deep convolutional neural network with orthopaedic surgeons on identification of total hip prosthesis design from plain radiographs 95%
- Fully Automated Explainable Abdominal CT Contrast Media Phase Classification Using Organ Segmentation and Machine Learning 92%
- Phase Recognition in Contrast-Enhanced CT Scans based on Deep Learning and Random Sampling 91%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.