At present, as Artificial Intelligence (AI) is rapidly being popularized, and it has presented a strong capability in medicine, even outperforming humans. Its potential application is growing by the day. As we know, AI has been widely applied in ophthalmology, radiologic diagnoses, tumors, and other more fields. AI has achieved superior results for many tasks by utilizing the massive information available in the big data era.
As the medical data form is being changed by Magnetic Resonance Imaging (MRI), Ultrasound, and Positron Emission Tomography (PET), X-Ray, Mammograms, and histological images, massive medical image data related to tumors is being generated. It is very difficult to handle the massive image data by adopting traditional techniques. Tumor image data processing involves more and more information techniques such as data storage, recognition, classification, segmentation, reconstruction and analysis. The urgent concern is how we can use this massive tumor image data to build an automated system with better and faster diagnosis for tumor patients. Machine learning (ML) approaches as one of branches of AI techniques are widely used to build automated systems for tumor diagnosis and better decision making.
However, with increasing data volume in tumor images, ML approaches are taking a back seat for another powerful AI technique named deep learning (DL) approaches. DL approaches can solve more complicated problems, unsolvable by ML approaches and produce high accurate diagnosis for tumors. The tumor diagnosis is one of the biggest medical industries which implements DL approaches. DL approaches can discover some hidden features and patterns in tumor images, helping doctors to predict the treatment. Incorporating DL approaches into tumors can provide radical innovations in tumor image processing, disease diagnosing, data analysis and pathbreaking medical applications. Therefore, with the help of DL approaches, collecting and extracting available information from massive tumor image data, looking for internal connections and rules will bring unprecedented opportunities for tumor research and diagnosis.
This special issue aims to focus mainly on the design, architecture, and application of DL approaches in image-guided diagnosis for tumors. This special issue welcomes original research and review articles discussing the challenges associated with this topic. Potential topics include but are not limited to the following:
? DL approaches for feature extraction in tumor images
? DL approaches for tumor image classification
? DL-based image-guided therapy for tumors
? DL approaches for tumor image retrieval
? DL approaches for tumor image segmentation
? DL approaches for big image data analysis in tumors
? Visualization of deep learning features for tumor images
? DL approaches for features selection in tumor images
? DL approaches for tumor images information fusion
? DL approaches for semantic segmentation in tumor image analysis
? DL approaches for tumor image reconstruction
? DL approaches for measuring the size of tumors
? DL approaches for predicting tumor grade
? Any novel DL approaches in image-guided diagnosis for tumors
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) are out of scope for this section and will not be accepted as part of this Research Topic.
At present, as Artificial Intelligence (AI) is rapidly being popularized, and it has presented a strong capability in medicine, even outperforming humans. Its potential application is growing by the day. As we know, AI has been widely applied in ophthalmology, radiologic diagnoses, tumors, and other more fields. AI has achieved superior results for many tasks by utilizing the massive information available in the big data era.
As the medical data form is being changed by Magnetic Resonance Imaging (MRI), Ultrasound, and Positron Emission Tomography (PET), X-Ray, Mammograms, and histological images, massive medical image data related to tumors is being generated. It is very difficult to handle the massive image data by adopting traditional techniques. Tumor image data processing involves more and more information techniques such as data storage, recognition, classification, segmentation, reconstruction and analysis. The urgent concern is how we can use this massive tumor image data to build an automated system with better and faster diagnosis for tumor patients. Machine learning (ML) approaches as one of branches of AI techniques are widely used to build automated systems for tumor diagnosis and better decision making.
However, with increasing data volume in tumor images, ML approaches are taking a back seat for another powerful AI technique named deep learning (DL) approaches. DL approaches can solve more complicated problems, unsolvable by ML approaches and produce high accurate diagnosis for tumors. The tumor diagnosis is one of the biggest medical industries which implements DL approaches. DL approaches can discover some hidden features and patterns in tumor images, helping doctors to predict the treatment. Incorporating DL approaches into tumors can provide radical innovations in tumor image processing, disease diagnosing, data analysis and pathbreaking medical applications. Therefore, with the help of DL approaches, collecting and extracting available information from massive tumor image data, looking for internal connections and rules will bring unprecedented opportunities for tumor research and diagnosis.
This special issue aims to focus mainly on the design, architecture, and application of DL approaches in image-guided diagnosis for tumors. This special issue welcomes original research and review articles discussing the challenges associated with this topic. Potential topics include but are not limited to the following:
? DL approaches for feature extraction in tumor images
? DL approaches for tumor image classification
? DL-based image-guided therapy for tumors
? DL approaches for tumor image retrieval
? DL approaches for tumor image segmentation
? DL approaches for big image data analysis in tumors
? Visualization of deep learning features for tumor images
? DL approaches for features selection in tumor images
? DL approaches for tumor images information fusion
? DL approaches for semantic segmentation in tumor image analysis
? DL approaches for tumor image reconstruction
? DL approaches for measuring the size of tumors
? DL approaches for predicting tumor grade
? Any novel DL approaches in image-guided diagnosis for tumors
Please note: manuscripts consisting solely of bioinformatics or computational analysis of public genomic or transcriptomic databases which are not accompanied by validation (independent cohort or biological validation in vitro or in vivo) are out of scope for this section and will not be accepted as part of this Research Topic.