Real Time Multi Organ Classification on Computed Tomography Images

📅 2024-04-29
🏛️ DEMI@MICCAI
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the need for real-time multi-organ localization in CT imaging, this paper proposes a sparse spatial classification method that bypasses full-image segmentation. The method employs large-receptive-field modeling and a gridded sliding-query mechanism to directly predict organ class labels at arbitrary 3D coordinates, while optionally generating quasi-segmentation maps. Its core innovation lies in the first application of a lightweight deep convolutional classifier for high-accuracy organ localization—achieving millisecond-level per-point inference speed (substantially faster than state-of-the-art segmentation models) while retaining scalable segmentation capability. By eliminating the computational redundancy inherent in conventional segmentation pipelines, the approach maintains clinically acceptable accuracy (Dice > 0.85) and enables real-time, interactive diagnostic applications. This work establishes an efficient new paradigm for automated medical image analysis.

Technology Category

Application Category

📝 Abstract
Organ segmentation is a fundamental task in medical imaging since it is useful for many clinical automation pipelines. However, some tasks do not require full segmentation. Instead, a classifier can identify the selected organ without segmenting the entire volume. In this study, we demonstrate a classifier based method to obtain organ labels in real time by using a large context size with a sparse data sampling strategy. Although our method operates as an independent classifier at query locations, it can generate full segmentations by querying grid locations at any resolution, offering faster performance than segmentation algorithms. We compared our method with existing segmentation techniques, demonstrating its superior runtime potential for practical applications in medical imaging.
Problem

Research questions and friction points this paper is trying to address.

Multiple Organ Segmentation
Real-time Processing
Medical Image Analysis
Innovation

Methods, ideas, or system contributions that make the work stand out.

Sparse Data Sampling
Organ Identification and Localization
Efficient Segmentation
🔎 Similar Papers
No similar papers found.
H
H. Yerebakan
Siemens Medical Solutions Malvern, USA
Y
Y. Shinagawa
Siemens Medical Solutions Malvern, USA
G
Gerardo Hermosillo
Siemens Medical Solutions Malvern, USA