TY - GEN
T1 - DetectDiffuse
T2 - 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
AU - Li, Xinyu
AU - Ai, Danni
AU - Fan, Jingfan
AU - Fu, Tianyu
AU - Song, Hong
AU - Xiao, Deqiang
AU - Yang, Jian
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - Automated Universal Lesion Detection (ULD) based on computed tomography (CT) images provides physicians with rapid and objective information regarding lesion locations and shapes. However, it is difficult to detect universal lesions in various regions because of the disparity in lesion sizes and the grayscale variation present in CT images. In this paper, we propose DetectDiffuse, a multi-scale diffusion model driven by feature aggregation and 3D attention. First, we utilize the diffusion model to generate noisy detection boxes, incorporating a scale factor to simulate lesions at different scales and mitigate detection errors. Second, we develop a Neighborhood Aggregation (NA) module to enhance the model’s capability to distinguish between lesioned and normal tissues. This module aggregates features within and around detection boxes, reducing false detections caused by significant grayscale differences in lesions. Third, we propose a 3D Stripe Attention (SA) module leveraging dimensional disambiguation. This module uses an attention mechanism to extract information across different dimensions of CT images more effectively. We performed comparison experiments on five datasets, the results show that the proposed method outperforms the 12 compared state-of-the-art methods, and improves the performance by 5.82% compared with the best method.
AB - Automated Universal Lesion Detection (ULD) based on computed tomography (CT) images provides physicians with rapid and objective information regarding lesion locations and shapes. However, it is difficult to detect universal lesions in various regions because of the disparity in lesion sizes and the grayscale variation present in CT images. In this paper, we propose DetectDiffuse, a multi-scale diffusion model driven by feature aggregation and 3D attention. First, we utilize the diffusion model to generate noisy detection boxes, incorporating a scale factor to simulate lesions at different scales and mitigate detection errors. Second, we develop a Neighborhood Aggregation (NA) module to enhance the model’s capability to distinguish between lesioned and normal tissues. This module aggregates features within and around detection boxes, reducing false detections caused by significant grayscale differences in lesions. Third, we propose a 3D Stripe Attention (SA) module leveraging dimensional disambiguation. This module uses an attention mechanism to extract information across different dimensions of CT images more effectively. We performed comparison experiments on five datasets, the results show that the proposed method outperforms the 12 compared state-of-the-art methods, and improves the performance by 5.82% compared with the best method.
KW - 3D Stripe Aggregation
KW - Neighbor boxes Aggregation
KW - Universal Lesion Detection
UR - https://www.scopus.com/pages/publications/105017862648
U2 - 10.1007/978-3-032-04971-1_15
DO - 10.1007/978-3-032-04971-1_15
M3 - Conference contribution
AN - SCOPUS:105017862648
SN - 9783032049704
T3 - Lecture Notes in Computer Science
SP - 154
EP - 164
BT - Medical Image Computing and Computer Assisted Intervention, MICCAI 2025 - 28th International Conference, 2025, Proceedings
A2 - Gee, James C.
A2 - Hong, Jaesung
A2 - Sudre, Carole H.
A2 - Golland, Polina
A2 - Alexander, Daniel C.
A2 - Iglesias, Juan Eugenio
A2 - Venkataraman, Archana
A2 - Kim, Jong Hyo
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 23 September 2025 through 27 September 2025
ER -