Abstract
Compared with static optical imaging, dynamic optical imaging technology can obtain quantitative pharmacokinetics information, such as the probe metabolism curve, removal rate, and binding potential of the receptor. Accurate segmentation of the region of interest (ROI) is an important step in dynamic optical imaging. Generally, the ROI is manually labeled by researchers based on experience. This will lead to two unavoidable problems. First, manual segmentation of the ROI is very time consuming, especially when there are many sequential dynamic optical images. Second, manual segmentation cannot ensure accuracy when the optical signal gradually decays to a point at which it is difficult to distinguish by using the naked eyes. These problems will inevitably lead to inaccuracy of quantitative results of dynamic optical imaging. Here, we presented a machine learning-based automatic segmentation method to avoid these time-consuming and inaccuracy problems caused by manual segmentation. The K-means clustering algorithm and fuzzy c-means clustering algorithm were implemented to separate the ROI from the background of sequential dynamic optical images. Automatic selection of clustering results was completed by mathematical methods. The accuracy and feasibility of machine learning-based methods were verified by comparing their results with the manual segmentation results. The preliminary results demonstrated that the machine learning-based automatic segmentation has coherent performance with the manual one.
Highlights
In recent years, the prevalence of cancer is increasing with lifestyle changes,1 so the treatment of cancer has become an urgent problem to be solved.2 To solve this problem, on the one hand, we need to improve the ability to detect the cancer early, and on the other hand, it is necessary to develop new anticancer drugs and treatment methods.3 Molecular imaging and targeted therapy of tumor vessels provide a new way for early accurate diagnosis and research of new cancer treatment techniques
We segmented the region of interest (ROI) from sequential dynamic optical images by using the clustering algorithms, including the k-means clustering algorithm and fuzzy c-means clustering algorithm
We find that the segmentation results obtained by both the k-means and fuzzy c-means clustering algorithms are highly consistent and of high similarity with manual segmentation results
Summary
The prevalence of cancer is increasing with lifestyle changes, so the treatment of cancer has become an urgent problem to be solved. To solve this problem, on the one hand, we need to improve the ability to detect the cancer early, and on the other hand, it is necessary to develop new anticancer drugs and treatment methods. Molecular imaging and targeted therapy of tumor vessels provide a new way for early accurate diagnosis and research of new cancer treatment techniques. Molecular imaging and targeted therapy of tumor vessels provide a new way for early accurate diagnosis and research of new cancer treatment techniques. Both techniques rely on a specific marker that reflects the specific molecular or vascular characteristics of tumors. Dynamic OI can real-time access physiological or biochemical parameters of the tissue microenvironment, such as blood perfusion and clearance rate, peak drug metabolism time, volume of distribution, and binding potential of the receptor.. Dynamic OI can real-time access physiological or biochemical parameters of the tissue microenvironment, such as blood perfusion and clearance rate, peak drug metabolism time, volume of distribution, and binding potential of the receptor.16–18 These parameters are very useful for early detection and treatment scitation.org/journal/adv evaluation of tumors.. Qualitative and quantitative analyses of tumor markers are of great significance for precise diagnosis, personalized diagnosis, and development and evaluation of anti-tumor drugs. The most commonly used quantitative technique in this field is dynamic positron emission computed tomography (dPET); the characteristics of high safety risk, lower sampling rate, and high cost severely restricted the application of dPET. Optical imaging (OI) enables quantitative imaging of biomedical processes of tumor markers at cellular and molecular levels non-invasively, well compensating for these shortcomings of dPET. OI technology has many advantages such as high time resolution, high throughput imaging capability, high safety, and low cost so that it has been widely used in preclinical and clinical research. Traditional static OI takes a single frame image when the probe reaches a stable distribution in the circulating metabolism in the body, which will inevitably lose the kinetic information of internal circulations. Dynamic OI can real-time access physiological or biochemical parameters of the tissue microenvironment, such as blood perfusion and clearance rate, peak drug metabolism time, volume of distribution, and binding potential of the receptor. These parameters are very useful for early detection and treatment scitation.org/journal/adv evaluation of tumors. Combined with pharmacokinetics modeling, dynamic OI has gradually become a powerful tool for quantitative analysis of tumor markers.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
