Application of transfer learning and ensemble learning in image-level classification for breast histopathology

Background Breast cancer has the highest prevalence among all cancers in women globally.The classification of histopathological images in the diagnosis of breast cancers is an area of clinical concern.In computer-aided diagnosis,most traditional classification models use a single network to extract features,although this approach has significant limitations.Moreover,many networks are trained and optimized on patient-level datasets,ignoring lower-level data labels.Methods This paper proposed a deep ensemble model based on image-level labels for the binary classification of breast histopathological images of benign and malignant lesions.First,the BreaKHis dataset was randomly divided into training,validation,and test sets.Then,data augmentation techniques were used to balance the numbers of benign and malignant samples.Third,based on their transfer learning performance and the complementarity between networks,VGG16,Xception,ResNet50,and DenseNet201 were selected as base classifiers.Results In a ensemble network model with accuracy as the weight,the image-level binary classification achieved an accuracy of 98.90%.To verify the capabilities of our method,it was experimentally compared with the latest transformer and multilayer perception(MLP)models on the same dataset.Our ensemble model showed a 5%-20%advantage,emphasizing its far-reaching abilities in classification tasks.Conclusions This research focuses on improving the performance of a classification model with an ensemble algorithm.Transfer learning has an essential role in classification of small datasets,improving training speed and accuracy.Our model may outperform many existing approaches with respect to accuracy and has applications in the field of auxiliary medical diagnosis.

Necklace-like Si@C nano?bers as robust anode materials for high performance lithium ion batteries

Silicon is believed to be a promising anode material for lithium ion batteries because of its highest theoretical capacity and low discharge potential. However, severe pulverization and capacity fading caused by huge volume change during cycling limits its practical application. In this work, necklace-like N-doped carbon wrapped mesoporous Si nanofibers(NL-Si@C) network has been synthesized via electrospinning method followed by magnesiothermic reduction reaction process to suppress these issues. The mesoporous Si nanospheres are wrapped with N-doped carbon shells network to form yolk-shell structure.Interestingly, the distance of adjacent Si@C nanospheres can be controllably adjusted by different addition amounts of SiO_2 nanospheres. When used as an anode material for lithium ion batteries, the NL-Si@C-0.5 exhibits best cycling stability and rate capability. The excellent electrochemical performances can be ascribed to the necklace-like network structure and N-doped carbon layers, which can ensure fast ions and electrons transportation, facilitate the electrolyte penetration and provide finite voids to allow large volume expansion of inner Si nanoparticles. Moreover, the protective carbon layers are also beneficial to the formation of stable solid electrolyte interface film.