Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes.
BACKGROUND: Morphologic profiling of the erythrocyte population is a widely used and clinically valuable diagnostic modality, but one that relies on a slow manual process associated with significant labor cost and limited reproducibility. Automated profiling of erythrocytes from digital images by ca...
| Publicado en: | Clinical Chemistry Vol. 63; no. 12; pp. 1847 - 1856 |
|---|---|
| Autores principales: | , , , |
| Formato: | Journal Article |
| Publicado: |
Oxford University Press / USA
2017
|
| 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=128019953&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 128019953 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 00099147 10CS jtl: Clinical Chemistry issn: 00099147 maglogo: N pubinfo: dt: 2017 vid: 63 iid: 12 pid: 622 pub: Oxford University Press / USA artinfo: ui: 128019953 10.1373/clinchem.2017.276345 128019953 ppf: 1847 ppct: 9 formats: fmt: @attributes: type: P tig: atl: Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes. aug: au: Durant, Thomas J.S. Olson, Eben M. Schulz, Wade L. Torres, Richard affil: Department of Laboratory Medicine, Yale University School of Medicine, New Haven, CT sug: ab: BACKGROUND: Morphologic profiling of the erythrocyte population is a widely used and clinically valuable diagnostic modality, but one that relies on a slow manual process associated with significant labor cost and limited reproducibility. Automated profiling of erythrocytes from digital images by capable machine learning approaches would augment the throughput and value of morphologic analysis. To this end, we sought to evaluate the performance of leading implementation strategies for convolutional neural networks (CNNs) when applied to classification of erythrocytes based on morphology. METHODS: Erythrocytes were manually classified into 1 of 10 classes using a custom-developed Web application. Using recent literature to guide architectural considerations for neural network design, we implemented a "very deep" CNN, consisting of >150 layers, with dense shortcut connections. RESULTS: The final database comprised 3737 labeled cells. Ensemble model predictions on unseen data demonstrated a harmonic mean of recall and precision metrics of 92.70% and 89.39%, respectively. Of the 748 cells in the test set, 23 misclassification errors were made, with a correct classification frequency of 90.60%, represented as a harmonic mean across the 10 morphologic classes. CONCLUSIONS: These findings indicate that erythrocyte morphology profiles could be measured with a high degree of accuracy with "very deep" CNNs. Further, these data support future efforts to expand classes and optimize practical performance in a clinical environment as a prelude to full implementation as a clinical tool. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|