Models for the marrow: A comprehensive review of AI‐based cell classification methods and malignancy detection in bone marrow aspirate smears
Abstract Given the high prevalence of artificial intelligence (AI) research in medicine, the development of deep learning (DL) algorithms based on image recognition, such as the analysis of bone marrow aspirate (BMA) smears, is rapidly increasing in the field of hematology and oncology. The models a...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | HemaSphere |
| Online Access: | https://doi.org/10.1002/hem3.70048 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556235922440192 |
|---|---|
| author | Tabita Ghete Farina Kock Martina Pontones David Pfrang Max Westphal Henning Höfener Markus Metzler |
| author_facet | Tabita Ghete Farina Kock Martina Pontones David Pfrang Max Westphal Henning Höfener Markus Metzler |
| author_sort | Tabita Ghete |
| collection | DOAJ |
| description | Abstract Given the high prevalence of artificial intelligence (AI) research in medicine, the development of deep learning (DL) algorithms based on image recognition, such as the analysis of bone marrow aspirate (BMA) smears, is rapidly increasing in the field of hematology and oncology. The models are trained to identify the optimal regions of the BMA smear for differential cell count and subsequently detect and classify a number of cell types, which can ultimately be utilized for diagnostic purposes. Moreover, AI is capable of identifying genetic mutations phenotypically. This pipeline has the potential to offer an accurate and rapid preliminary analysis of the bone marrow in the clinical routine. However, the intrinsic complexity of hematological diseases presents several challenges for the automatic morphological assessment. To ensure general applicability across multiple medical centers and to deliver high accuracy on prospective clinical data, AI models would require highly heterogeneous training datasets. This review presents a systematic analysis of models for cell classification and detection of hematological malignancies published in the last 5 years (2019–2024). It provides insight into the challenges and opportunities of these DL‐assisted tasks. |
| format | Article |
| id | doaj-art-93799c7e1ce94f9db15e8610bce4996b |
| institution | Kabale University |
| issn | 2572-9241 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | HemaSphere |
| spelling | doaj-art-93799c7e1ce94f9db15e8610bce4996b2025-01-07T12:35:28ZengWileyHemaSphere2572-92412024-12-01812n/an/a10.1002/hem3.70048Models for the marrow: A comprehensive review of AI‐based cell classification methods and malignancy detection in bone marrow aspirate smearsTabita Ghete0Farina Kock1Martina Pontones2David Pfrang3Max Westphal4Henning Höfener5Markus Metzler6Department of Pediatrics and Adolescent Medicine University Hospital Erlangen Erlangen GermanyComputational Pathology Fraunhofer Institute for Digital Medicine (MEVIS) Bremen GermanyDepartment of Pediatrics and Adolescent Medicine University Hospital Erlangen Erlangen GermanyComputational Pathology Fraunhofer Institute for Digital Medicine (MEVIS) Bremen GermanyComputational Pathology Fraunhofer Institute for Digital Medicine (MEVIS) Bremen GermanyComputational Pathology Fraunhofer Institute for Digital Medicine (MEVIS) Bremen GermanyDepartment of Pediatrics and Adolescent Medicine University Hospital Erlangen Erlangen GermanyAbstract Given the high prevalence of artificial intelligence (AI) research in medicine, the development of deep learning (DL) algorithms based on image recognition, such as the analysis of bone marrow aspirate (BMA) smears, is rapidly increasing in the field of hematology and oncology. The models are trained to identify the optimal regions of the BMA smear for differential cell count and subsequently detect and classify a number of cell types, which can ultimately be utilized for diagnostic purposes. Moreover, AI is capable of identifying genetic mutations phenotypically. This pipeline has the potential to offer an accurate and rapid preliminary analysis of the bone marrow in the clinical routine. However, the intrinsic complexity of hematological diseases presents several challenges for the automatic morphological assessment. To ensure general applicability across multiple medical centers and to deliver high accuracy on prospective clinical data, AI models would require highly heterogeneous training datasets. This review presents a systematic analysis of models for cell classification and detection of hematological malignancies published in the last 5 years (2019–2024). It provides insight into the challenges and opportunities of these DL‐assisted tasks.https://doi.org/10.1002/hem3.70048 |
| spellingShingle | Tabita Ghete Farina Kock Martina Pontones David Pfrang Max Westphal Henning Höfener Markus Metzler Models for the marrow: A comprehensive review of AI‐based cell classification methods and malignancy detection in bone marrow aspirate smears HemaSphere |
| title | Models for the marrow: A comprehensive review of AI‐based cell classification methods and malignancy detection in bone marrow aspirate smears |
| title_full | Models for the marrow: A comprehensive review of AI‐based cell classification methods and malignancy detection in bone marrow aspirate smears |
| title_fullStr | Models for the marrow: A comprehensive review of AI‐based cell classification methods and malignancy detection in bone marrow aspirate smears |
| title_full_unstemmed | Models for the marrow: A comprehensive review of AI‐based cell classification methods and malignancy detection in bone marrow aspirate smears |
| title_short | Models for the marrow: A comprehensive review of AI‐based cell classification methods and malignancy detection in bone marrow aspirate smears |
| title_sort | models for the marrow a comprehensive review of ai based cell classification methods and malignancy detection in bone marrow aspirate smears |
| url | https://doi.org/10.1002/hem3.70048 |
| work_keys_str_mv | AT tabitaghete modelsforthemarrowacomprehensivereviewofaibasedcellclassificationmethodsandmalignancydetectioninbonemarrowaspiratesmears AT farinakock modelsforthemarrowacomprehensivereviewofaibasedcellclassificationmethodsandmalignancydetectioninbonemarrowaspiratesmears AT martinapontones modelsforthemarrowacomprehensivereviewofaibasedcellclassificationmethodsandmalignancydetectioninbonemarrowaspiratesmears AT davidpfrang modelsforthemarrowacomprehensivereviewofaibasedcellclassificationmethodsandmalignancydetectioninbonemarrowaspiratesmears AT maxwestphal modelsforthemarrowacomprehensivereviewofaibasedcellclassificationmethodsandmalignancydetectioninbonemarrowaspiratesmears AT henninghofener modelsforthemarrowacomprehensivereviewofaibasedcellclassificationmethodsandmalignancydetectioninbonemarrowaspiratesmears AT markusmetzler modelsforthemarrowacomprehensivereviewofaibasedcellclassificationmethodsandmalignancydetectioninbonemarrowaspiratesmears |