Radiopharmaceutical distribution image generation system and method using deep learning
The present invention relates to a radiopharmaceutical distribution image generation system and method using deep learning and, more specifically, to a radiopharmaceutical distribution image generation system and method using deep learning, wherein dynamic medical images collected from multiple patients and a time-radiation dose distribution curve for each organ can be learnt through a deep learning network and a spatial distribution image of a radiopharmaceutical can be generated from a static medical image acquired from a specific patient. According to the present invention, even when a medical image is acquired only for a specific time after a radiopharmaceutical is injected into a patient, a spatial distribution image of the radiopharmaceutical can be acquired across the entire time by using the deep learning network, and quantitative analysis of the radiopharmaceutical can be performed by calculating a time-radiation dose distribution curve on the basis thereof.
1. A radiopharmaceutical distribution image generation system using deep learning, the system comprising:
a dynamic medical image acquisition unit configured to acquire dynamic medical images by continuously collecting medical images of a patient concurrently with injection of radiopharmaceuticals;
a distribution curve acquisition unit configured to acquire a time-radiation dose distribution curve, which represents a radiation dose for each organ of a human body over time, from the dynamic medical images;
a static medical image acquisition unit configured to acquire static medical images for a specific period of time after the injection of the radiopharmaceuticals;
a deep-learning image generation network configured to predict and generate medical images corresponding to times before and after the static medical images by collecting and learning the dynamic medical images of multiple patients and the corresponding time-radiation dose distribution curve; and
a spatial distribution image acquisition unit configured to acquire a spatial distribution image of the radiopharmaceuticals from the static medical images and the generated medical images,
wherein the deep learning network comprises:
a deep learning unit configured to collect and learn the dynamic medical images of the multiple patients and the corresponding time-radiation dose distribution curve; and
an image generation unit configured to predict and generate the medical images corresponding to times before and after the static medical images are taken.
2. The system of claim 1 , wherein the deep learning network uses a generative adversarial network (GAN) to generate the medical images according to the dynamic medical images and the corresponding time-radiation dose distribution curve.
3. The system of claim 1 , further comprising a distribution curve predictor configured to acquire the time-radiation dose distribution curve by acquiring a radiation dose and a position of each region over time from the spatial distribution image.
4. A method performed by a radiopharmaceutical distribution image generation system using deep learning, the method comprising:
acquiring dynamic medical images by continuously collecting medical images of a patient concurrently with injection of radiopharmaceuticals;
acquiring a time-radiation dose distribution curve, which represents a radiation dose for each organ of a human body over time, from the dynamic medical images;
collecting the dynamic medical images of multiple patients and the corresponding time-radiation dose distribution curve and learning through a deep learning network;
acquiring static medical images for a specific period of time after the injection of the radiopharmaceuticals;
predicting and generating medical images corresponding to times before and after the static medical images through the deep learning network; and
acquiring a spatial distribution image of the radiopharmaceuticals from the static medical images and the generated medical images,
wherein the deep learning network comprises:
a deep learning unit configured to collect and learn the dynamic medical images of the multiple patients and the corresponding time-radiation dose distribution curve, and
an image generation unit configured to predict and generate the medical images corresponding to times before and after the static medical images are taken.
5. The method of claim 4 , wherein the deep learning network uses a generative adversarial network (GAN) to generate the medical images according to the dynamic medical images and the corresponding time-radiation dose distribution curve.
6. The method of claim 4 , further comprising acquiring the time-radiation dose distribution curve by acquiring a radiation dose and a position of each region over time from the spatial distribution image.