About this Research Topic
Colorectal cancer (CRC) is one of the leading death causes in developed countries: one in ten people will suffer from it in their lifetime and it estimated to cause 700,000 deaths annually.
Early detection, through screening programmes, is the main strategy to reduce the incidence of CRC, as the survival rate increases if the cancer is detected at an early stage, from 18 % 5- years survival rate to 88.5 %. Colonoscopy is the diagnostic technique most commonly used for the detection and treatment of colorectal polyps, precursor lesions of CRC.
In recent years, artificial intelligence (AI) has been applied with great success in several computer vision-related tasks involving huge data volumes: classification, segmentation or annotation of natural images, object identification or information retrieval. Similarly, deep learning (DL) has also started to be applied in the medical field, where it has achieved results comparable to those obtained by clinical experts. However, it presents a general challenge that lies in the limited amount of information available, since the generation of the dataset requires expert clinical knowledge by practitioners who usually have little time available.
Therefore, the goal of this research topic is to gather knowledge on the current state of the artof applications of AI/DL for early diagnosis of CRC. For the last years, AI/DL methods and systems have been applied in the field of CRC for early detection as well as diagnosis of lesions. There is still wide room for improvement and
development to increase the detection rates with the new technical development of IA/DL models that support early diagnosis of CRC.
This Research Topic aims to collect articles dedicated to the early detection of CRC. Colonoscopy images (either from colonoscopes or wireless capsules) are preferred, but CT, MRI or other medical imaging modalities will also be considered. CRC staging and lesion classification will also be considered. Manuscripts containing methods not based on AI/DL are out of scope for this section and will not be accepted as part of this Research Topic.
We welcome submissions covering but not limited to the following sub-topics:
- AI/DL methods for polyp detection, localization and segmentation including all types of
networks: CNNs, transformers, LSTM, GANs, etc.
- Performance comparison of AI/DL methods vs traditional ones.
- Presentation of datasets of colorectal images.
- Data augmentation methods.
- Validation of early detection systems.
- Clinical trials, preferably RCT, of the use of IA systems for CRC diagnosis.
The following types of articles are welcome: original articles, clinical trials, systematic
literatures searches and meta-analyses.
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 the scope for this section and will not be accepted as part of this Research Topic.
Early detection, through screening programmes, is the main strategy to reduce the incidence of CRC, as the survival rate increases if the cancer is detected at an early stage, from 18 % 5- years survival rate to 88.5 %. Colonoscopy is the diagnostic technique most commonly used for the detection and treatment of colorectal polyps, precursor lesions of CRC.
In recent years, artificial intelligence (AI) has been applied with great success in several computer vision-related tasks involving huge data volumes: classification, segmentation or annotation of natural images, object identification or information retrieval. Similarly, deep learning (DL) has also started to be applied in the medical field, where it has achieved results comparable to those obtained by clinical experts. However, it presents a general challenge that lies in the limited amount of information available, since the generation of the dataset requires expert clinical knowledge by practitioners who usually have little time available.
Therefore, the goal of this research topic is to gather knowledge on the current state of the artof applications of AI/DL for early diagnosis of CRC. For the last years, AI/DL methods and systems have been applied in the field of CRC for early detection as well as diagnosis of lesions. There is still wide room for improvement and
development to increase the detection rates with the new technical development of IA/DL models that support early diagnosis of CRC.
This Research Topic aims to collect articles dedicated to the early detection of CRC. Colonoscopy images (either from colonoscopes or wireless capsules) are preferred, but CT, MRI or other medical imaging modalities will also be considered. CRC staging and lesion classification will also be considered. Manuscripts containing methods not based on AI/DL are out of scope for this section and will not be accepted as part of this Research Topic.
We welcome submissions covering but not limited to the following sub-topics:
- AI/DL methods for polyp detection, localization and segmentation including all types of
networks: CNNs, transformers, LSTM, GANs, etc.
- Performance comparison of AI/DL methods vs traditional ones.
- Presentation of datasets of colorectal images.
- Data augmentation methods.
- Validation of early detection systems.
- Clinical trials, preferably RCT, of the use of IA systems for CRC diagnosis.
The following types of articles are welcome: original articles, clinical trials, systematic
literatures searches and meta-analyses.
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 the scope for this section and will not be accepted as part of this Research Topic.
Keywords: colorectal cancer, artificial intelligence, early diagnosis, medical imaging, polyp detection
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
