Show simple item record

dc.contributor.authorVigil, Nicolle
dc.contributor.authorBarry, Madeline
dc.contributor.authorAmini, Arya
dc.contributor.authorAkhloufi, Moulay
dc.contributor.authorMaldague, Xavier P V
dc.contributor.authorMa, Lan
dc.contributor.authorRen, Lei
dc.contributor.authorYousefi, Bardia
dc.date.accessioned2022-06-14T15:20:40Z
dc.date.available2022-06-14T15:20:40Z
dc.date.issued2022-05-27
dc.identifier.urihttp://hdl.handle.net/10713/19162
dc.description.abstractAutomated medical data analysis demonstrated a significant role in modern medicine, and cancer diagnosis/prognosis to achieve highly reliable and generalizable systems. In this study, an automated breast cancer screening method in ultrasound imaging is proposed. A convolutional deep autoencoder model is presented for simultaneous segmentation and radiomic extraction. The model segments the breast lesions while concurrently extracting radiomic features. With our deep model, we perform breast lesion segmentation, which is linked to low-dimensional deep-radiomic extraction (four features). Similarly, we used high dimensional conventional imaging throughputs and applied spectral embedding techniques to reduce its size from 354 to 12 radiomics. A total of 780 ultrasound images-437 benign, 210, malignant, and 133 normal-were used to train and validate the models in this study. To diagnose malignant lesions, we have performed training, hyperparameter tuning, cross-validation, and testing with a random forest model. This resulted in a binary classification accuracy of 78.5% (65.1-84.1%) for the maximal (full multivariate) cross-validated model for a combination of radiomic groups.en_US
dc.description.urihttps://doi.org/10.3390/cancers14112663en_US
dc.language.isoenen_US
dc.publisherMDPI AGen_US
dc.relation.ispartofCancersen_US
dc.subjectbreast canceren_US
dc.subjectdeep learningen_US
dc.subjectdimensionality reductionen_US
dc.subjectmedical image analysisen_US
dc.subjectradiomicsen_US
dc.subjectultrasound imagingen_US
dc.titleDual-Intended Deep Learning Model for Breast Cancer Diagnosis in Ultrasound Imaging.en_US
dc.typeArticleen_US
dc.identifier.doi10.3390/cancers14112663
dc.identifier.pmid35681643
dc.source.journaltitleCancers
dc.source.volume14
dc.source.issue11
dc.source.countrySwitzerland


This item appears in the following Collection(s)

Show simple item record