Artificial intelligence use in diagnosis, grading, and segmentation of neuro-oncology: a narrative review
Abstract Background Artificial intelligence (AI) is a broad term that encompasses Machine Learning (ML) and Deep Learning (DL). Advancements in AI and its methodologies allow its application in multiple stages of neuro-oncology management. This article aims to provide a comprehensive review of curre...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-06-01
|
| Series: | The Egyptian Journal of Neurology, Psychiatry and Neurosurgery |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41983-025-00980-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849335612397584384 |
|---|---|
| author | Adham Al-Rahbi Tariq Al-Habsi Abir Al-Suli Tariq Al-Saadi |
| author_facet | Adham Al-Rahbi Tariq Al-Habsi Abir Al-Suli Tariq Al-Saadi |
| author_sort | Adham Al-Rahbi |
| collection | DOAJ |
| description | Abstract Background Artificial intelligence (AI) is a broad term that encompasses Machine Learning (ML) and Deep Learning (DL). Advancements in AI and its methodologies allow its application in multiple stages of neuro-oncology management. This article aims to provide a comprehensive review of current applications of AI in neuro-oncology diagnosis, segmentation, and grading. In addition, it expresses the challenges faced in those fields. This is the only study that includes those three fields of AI use in neuro-oncology. The search in four databases (Scopus, PubMed, Wiley, and Google Scholar) gave a total of 28 articles using AI in neuro-oncology diagnosis, segmentation, and grading. Articles were collected and reviewed, and data were summarized and presented in tables. Results The majority of the articles are about diagnosis 13, with the radiological diagnosis as the most used method by AI, followed by Segmentation in 10 articles, and then grading 5. Chattopadhyay's study, which diagnoses using MRI and CNN-based deep learning methods, has the highest sample size, 2473, among all included articles. It also has the highest accuracy among others, reaching 99.74%. Conclusions AI in neuro-oncology is promising and rapidly growing despite the challenges. We still need more research applying AI in brain tumors to aid in developing new therapeutic targets and a better understanding of brain tumors. |
| format | Article |
| id | doaj-art-66224986fe8d43f1b83ff100fbdbe67e |
| institution | Kabale University |
| issn | 1687-8329 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | The Egyptian Journal of Neurology, Psychiatry and Neurosurgery |
| spelling | doaj-art-66224986fe8d43f1b83ff100fbdbe67e2025-08-20T03:45:12ZengSpringerOpenThe Egyptian Journal of Neurology, Psychiatry and Neurosurgery1687-83292025-06-0161112510.1186/s41983-025-00980-7Artificial intelligence use in diagnosis, grading, and segmentation of neuro-oncology: a narrative reviewAdham Al-Rahbi0Tariq Al-Habsi1Abir Al-Suli2Tariq Al-Saadi3Sultan Qaboos UniversitySultan Qaboos UniversityOman Medical Specialty BoardCedars-Sinai Medical CenterAbstract Background Artificial intelligence (AI) is a broad term that encompasses Machine Learning (ML) and Deep Learning (DL). Advancements in AI and its methodologies allow its application in multiple stages of neuro-oncology management. This article aims to provide a comprehensive review of current applications of AI in neuro-oncology diagnosis, segmentation, and grading. In addition, it expresses the challenges faced in those fields. This is the only study that includes those three fields of AI use in neuro-oncology. The search in four databases (Scopus, PubMed, Wiley, and Google Scholar) gave a total of 28 articles using AI in neuro-oncology diagnosis, segmentation, and grading. Articles were collected and reviewed, and data were summarized and presented in tables. Results The majority of the articles are about diagnosis 13, with the radiological diagnosis as the most used method by AI, followed by Segmentation in 10 articles, and then grading 5. Chattopadhyay's study, which diagnoses using MRI and CNN-based deep learning methods, has the highest sample size, 2473, among all included articles. It also has the highest accuracy among others, reaching 99.74%. Conclusions AI in neuro-oncology is promising and rapidly growing despite the challenges. We still need more research applying AI in brain tumors to aid in developing new therapeutic targets and a better understanding of brain tumors.https://doi.org/10.1186/s41983-025-00980-7Artificial intelligence (AI)Machine learning (ML)Deep learning (DL)Neuro-oncologyDiagnosisGrading |
| spellingShingle | Adham Al-Rahbi Tariq Al-Habsi Abir Al-Suli Tariq Al-Saadi Artificial intelligence use in diagnosis, grading, and segmentation of neuro-oncology: a narrative review The Egyptian Journal of Neurology, Psychiatry and Neurosurgery Artificial intelligence (AI) Machine learning (ML) Deep learning (DL) Neuro-oncology Diagnosis Grading |
| title | Artificial intelligence use in diagnosis, grading, and segmentation of neuro-oncology: a narrative review |
| title_full | Artificial intelligence use in diagnosis, grading, and segmentation of neuro-oncology: a narrative review |
| title_fullStr | Artificial intelligence use in diagnosis, grading, and segmentation of neuro-oncology: a narrative review |
| title_full_unstemmed | Artificial intelligence use in diagnosis, grading, and segmentation of neuro-oncology: a narrative review |
| title_short | Artificial intelligence use in diagnosis, grading, and segmentation of neuro-oncology: a narrative review |
| title_sort | artificial intelligence use in diagnosis grading and segmentation of neuro oncology a narrative review |
| topic | Artificial intelligence (AI) Machine learning (ML) Deep learning (DL) Neuro-oncology Diagnosis Grading |
| url | https://doi.org/10.1186/s41983-025-00980-7 |
| work_keys_str_mv | AT adhamalrahbi artificialintelligenceuseindiagnosisgradingandsegmentationofneurooncologyanarrativereview AT tariqalhabsi artificialintelligenceuseindiagnosisgradingandsegmentationofneurooncologyanarrativereview AT abiralsuli artificialintelligenceuseindiagnosisgradingandsegmentationofneurooncologyanarrativereview AT tariqalsaadi artificialintelligenceuseindiagnosisgradingandsegmentationofneurooncologyanarrativereview |