Expert-Level Immunofixation Electrophoresis Image Recognition based on Explainable and Generalizable Deep Learning.
BACKGROUND: Immunofixation electrophoresis (IFE) is important for diagnosis of plasma cell disorders (PCDs). Manual analysis of IFE images is time-consuming and potentially subjective. An artificial intelligence (AI) system for automatic and accurate IFE image recognition is desirable. METHODS: In t...
| Publicado en: | Clinical Chemistry Vol. 69; no. 2; pp. 130 - 140 |
|---|---|
| Autores principales: | , , , , , , , , |
| Formato: | Journal Article |
| Publicado: |
Oxford University Press / USA
Feb2023
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=161929894&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 161929894 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 00099147 10CS jtl: Clinical Chemistry issn: 00099147 maglogo: N pubinfo: dt: Feb2023 vid: 69 iid: 2 pid: 622 pub: Oxford University Press / USA artinfo: ui: 161929894 10.1093/clinchem/hvac190 161929894 ppf: 130 ppct: 10 formats: fmt: @attributes: type: P tig: atl: Expert-Level Immunofixation Electrophoresis Image Recognition based on Explainable and Generalizable Deep Learning. aug: au: Honghua Hu Wei Xu Ting Jiang Yuheng Cheng Xiaoyan Tao Wenna Liu Meiling Jian Kang Li Guotai Wang affil: Department of Laboratory Medicine and Sichuan Provincial Key Laboratory for Human Disease Gene Study, Sichuan Provincial People's Hospital, University of Electronic Science and Technology of China, Chengdu 610072, China sug: ab: BACKGROUND: Immunofixation electrophoresis (IFE) is important for diagnosis of plasma cell disorders (PCDs). Manual analysis of IFE images is time-consuming and potentially subjective. An artificial intelligence (AI) system for automatic and accurate IFE image recognition is desirable. METHODS: In total, 12 703 expert-annotated IFE images (9182 from a new IFE imaging system and 3521 from an old one) were used to develop and test an AI system that was an ensemble of 3 deep neural networks. The model takes an IFE image as input and predicts the presence of 8 basic patterns (IgA-κ, IgA-λ, IgG-κ, IgG-λ, IgM-κ, IgM-λ, and their combinations. Score-based class activation maps (Score-CAMs) were used for visual explanation of the model's prediction. RESULTS: The AI model achieved an average accuracy, sensitivity, and specificity of 99.82%, 93.17%, and 99.93%, respectively, for detection of the 8 basic patterns, which outperformed 4 junior experts with <1 year's experience and was comparable to a senior expert with 5 years' experience. The Score-CAMs gave a reasonable visual explanation of the prediction by highlighting the target aligned regions in the bands and indicating potentially unreliable predictions. When trained with only the new system images, the model's performance was still higher than junior experts on both the new and old IFE systems, with average accuracy of 99.91% and 99.81%, respectively. CONCLUSIONS: Our AI system achieved human-level performance in automatic recognition of IFE images, with high explainability and generalizability. It has the potential to improve the efficiency and reliability of diagnosis of PCDs. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|