Skip to content
DraconiticResearch
Search Sources API
201,818 studies31 sourcesUpdated 27 min ago
Peer-reviewedCC BY 4.0International Journal of Laboratory Hematology

AI‐Enabled Automated Schistocyte Classification in Peripheral Blood for TMA Auxiliary Diagnosis

  • Lei Shang1
  • Chao Fang2
  • Dongshuo Li1
  • Xuesong Wang3
  • Jiani Yu4
  • Yunchu Cui4
  • Jingliang Chen1
  • Xuekai Liu1
4 affiliations
  1. 1Department of Clinical Laboratory Aerospace Center Hospital Beijing China
  2. 2Faculty of Engineering and Design University of Auckland Auckland New Zealand
  3. 3School of Science, Beijing Jiaotong University Beijing China
  4. 4School of Public Health, Xiamen University Xiamen China
Read full textDOICite

Abstract

Background: Schistocytes are critical morphological markers for thrombotic microangiopathy (TMA) diagnosis. Manual identification is hampered by inconsistent standards and high interobserver variability, compromising accuracy. Although AI has advanced in hematology, AI‐enabled schistocyte classification remains under‐studied, creating a clinical gap.

Methods: We constructed a two‐stage AI system for segmentation and classification. Three segmentation models (U‐Net, ENet, and R2U‐Net) were assessed on 25 067 RBCs from 183 patients. ResNet‐50 and Xception were trained on 28 586 RBCs, including 13 125 ICSH‐classified schistocytes, using grayscale and RGB images. Clinical validation was performed on 156 784 RBCs from 219 patients. Performance was evaluated using recall, specificity, precision, and F 1 score.

Results: R2U‐Net achieved the best segmentation (recall = 0.868, F 1 = 0.881, mIoU = 0.807). The Xception‐RGB model performed best in classification (weighted F 1 = 0.957), with high precision and recall for schistocyte subtypes. Clinical validation showed excellent reliability with all weighted metrics at 0.998.

Conclusions: This two‐stage framework enables accurate schistocyte analysis with better feature representation using RGB images and Xception. It improves diagnostic accuracy and reproducibility, supporting TMA auxiliary diagnosis and clinical decision‐making.

Related

  1. Construction of an auxiliary diagnostic model for Alzheimer’s disease based on routine peripheral blood parameters
    Weifeng Jin, Shuzi Chen, Dan Li +5
    BMC PsychiatryPeer-reviewedCC BY-NC-ND 4.0Full textPsychiatry & mental healthPMC
  2. A modified cryobiopsy specimen retrieval method using a thin bronchoscope and small guide sheath for the diagnosis of peripheral pulmonary lesions
    Translational Lung Cancer ResearchPeer-reviewedCC BY-NC-NDFull textOncologyEurope PMC
  3. Digital pathological classification of peripheral neuroblastic tumors across multi-continent cohorts
    Yuanning Zheng, Yuichi Shibui, Balint Laszlo Forgo +11
    bioRxivPreprintAll rights reservedFull textGeneral medicinebioRxivPMC
  4. Evaluation of BCR::ABL1 Positivity in Peripheral Blood Neutrophils Enables the Diagnosis of De Novo Blast Phase Chronic Myeloid Leukemia with Additional Structural Abnormalities of the Philadelphia Chromosome
    Hirotaka Sakai, Ikuo Miura, Ayako Arai
    Internal MedicinePeer-reviewedCC BY-NC-NDFull textGeneral medicineJ-STAGE
  5. Curriculum-Based Deep Learning for Automated Segmental Left Ventricular Hypertrophy Classification Using Short-Axis Echocardiography
    Rajeswari Periyasamy, Srinivasan Selvaraj, Francis Antony Selvi Pitchaimuthu +1
    Diagnostics (Basel, Switzerland)Peer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{shang2026aienabled,
  title = {{AI‐Enabled Automated Schistocyte Classification in Peripheral Blood for TMA Auxiliary Diagnosis}},
  author = {Lei Shang and Chao Fang and Dongshuo Li and Xuesong Wang and Jiani Yu and Yunchu Cui and Jingliang Chen and Xuekai Liu},
  journal = {International Journal of Laboratory Hematology},
  year = {2026},
  month = aug,
  doi = {10.1111/ijlh.70209},
  url = {https://doi.org/10.1111/ijlh.70209},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - AI‐Enabled Automated Schistocyte Classification in Peripheral Blood for TMA Auxiliary Diagnosis
AU  - Lei Shang
AU  - Chao Fang
AU  - Dongshuo Li
AU  - Xuesong Wang
AU  - Jiani Yu
AU  - Yunchu Cui
AU  - Jingliang Chen
AU  - Xuekai Liu
PY  - 2026
DA  - 2026/08/05
JO  - International Journal of Laboratory Hematology
DO  - 10.1111/ijlh.70209
UR  - https://doi.org/10.1111/ijlh.70209
AB  - Background: Schistocytes are critical morphological markers for thrombotic microangiopathy (TMA) diagnosis. Manual identification is hampered by inconsistent standards and high interobserver variability, compromising accuracy. Although AI has advanced in hematology, AI‐enabled schistocyte classification remains under‐studied, creating a clinical gap.  Methods: We constructed a two‐stage AI system for segmentation and classification. Three segmentation models (U‐Net, ENet, and R2U‐Net) were assessed on 25 067 RBCs from 183 patients. ResNet‐50 and Xception were trained on 28 586 RBCs, including 13 125 ICSH‐classified schistocytes, using grayscale and RGB images. Clinical validation was performed on 156 784 RBCs from 219 patients. Performance was evaluated using recall, specificity, precision, and F 1 score.  Results: R2U‐Net achieved the best segmentation (recall = 0.868, F 1 = 0.881, mIoU = 0.807). The Xception‐RGB model performed best in classification (weighted F 1 = 0.957), with high precision and recall for schistocyte subtypes. Clinical validation showed excellent reliability with all weighted metrics at 0.998.  Conclusions: This two‐stage framework enables accurate schistocyte analysis with better feature representation using RGB images and Xception. It improves diagnostic accuracy and reproducibility, supporting TMA auxiliary diagnosis and clinical decision‐making.
SN  - 1751-5521
SN  - 1751-553X
ER  -