CoMoTo: Unpaired Cross-Modal Lesion Distillation Improves Breast Lesion Detection in Tomosynthesis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909267271876608 |
|---|---|
| author | Alberb, Muhammad Elbatel, Marawan Elgebaly, Aya Montoya-del-Angel, Ricardo Li, Xiaomeng Martí, Robert |
| author_facet | Alberb, Muhammad Elbatel, Marawan Elgebaly, Aya Montoya-del-Angel, Ricardo Li, Xiaomeng Martí, Robert |
| contents | Digital Breast Tomosynthesis (DBT) is an advanced breast imaging modality that offers superior lesion detection accuracy compared to conventional mammography, albeit at the trade-off of longer reading time. Accelerating lesion detection from DBT using deep learning is hindered by limited data availability and huge annotation costs. A possible solution to this issue could be to leverage the information provided by a more widely available modality, such as mammography, to enhance DBT lesion detection. In this paper, we present a novel framework, CoMoTo, for improving lesion detection in DBT. Our framework leverages unpaired mammography data to enhance the training of a DBT model, improving practicality by eliminating the need for mammography during inference. Specifically, we propose two novel components, Lesion-specific Knowledge Distillation (LsKD) and Intra-modal Point Alignment (ImPA). LsKD selectively distills lesion features from a mammography teacher model to a DBT student model, disregarding background features. ImPA further enriches LsKD by ensuring the alignment of lesion features within the teacher before distilling knowledge to the student. Our comprehensive evaluation shows that CoMoTo is superior to traditional pretraining and image-level KD, improving performance by 7% Mean Sensitivity under low-data setting. Our code is available at https://github.com/Muhammad-Al-Barbary/CoMoTo . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_17620 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CoMoTo: Unpaired Cross-Modal Lesion Distillation Improves Breast Lesion Detection in Tomosynthesis Alberb, Muhammad Elbatel, Marawan Elgebaly, Aya Montoya-del-Angel, Ricardo Li, Xiaomeng Martí, Robert Computer Vision and Pattern Recognition Artificial Intelligence Digital Breast Tomosynthesis (DBT) is an advanced breast imaging modality that offers superior lesion detection accuracy compared to conventional mammography, albeit at the trade-off of longer reading time. Accelerating lesion detection from DBT using deep learning is hindered by limited data availability and huge annotation costs. A possible solution to this issue could be to leverage the information provided by a more widely available modality, such as mammography, to enhance DBT lesion detection. In this paper, we present a novel framework, CoMoTo, for improving lesion detection in DBT. Our framework leverages unpaired mammography data to enhance the training of a DBT model, improving practicality by eliminating the need for mammography during inference. Specifically, we propose two novel components, Lesion-specific Knowledge Distillation (LsKD) and Intra-modal Point Alignment (ImPA). LsKD selectively distills lesion features from a mammography teacher model to a DBT student model, disregarding background features. ImPA further enriches LsKD by ensuring the alignment of lesion features within the teacher before distilling knowledge to the student. Our comprehensive evaluation shows that CoMoTo is superior to traditional pretraining and image-level KD, improving performance by 7% Mean Sensitivity under low-data setting. Our code is available at https://github.com/Muhammad-Al-Barbary/CoMoTo . |
| title | CoMoTo: Unpaired Cross-Modal Lesion Distillation Improves Breast Lesion Detection in Tomosynthesis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.17620 |