Investigating the detection of breast cancer with deep transfer learning using ResNet18 and ResNet34.

A lot of underdeveloped nations particularly in Africa struggle with cancer-related, deadly diseases. Particularly in women, the incidence of breast cancer is rising daily because of ignorance and delayed diagnosis. Only by correctly identifying and diagnosing cancer in its very early stages of development can be effectively treated. The classification of cancer can be accelerated and automated with the aid of computer-aided diagnosis and medical image analysis techniques. This research provides the use of transfer learning from a Residual Network 18 (ResNet18) and Residual Network 34 (ResNet34) architectures to detect breast cancer. The study examined how breast cancer can be identified in breast mammography pictures using transfer learning from ResNet18 and ResNet34, and developed a demo app for radiologists using the trained models with the best validation accuracy. 1, 200 datasets of breast x-ray mammography images from the National Radiological Society's (NRS) archives were employed in the study. The dataset was categorised as implant cancer negative, implant cancer positive, cancer negative and cancer positive in order to increase the consistency of x-ray mammography images classification and produce better features. For the multi-class classification of the images, the study gave an average accuracy for binary classification of benign or malignant cancer cases of 86.7% validation accuracy for ResNet34 and 92% validation accuracy for ResNet18. A prototype web application showcasing ResNet18 performance has been created. The acquired results show how transfer learning can improve the accuracy of breast cancer detection, providing invaluable assistance to medical professionals, particularly in an African scenario.

Synthesis of Nano-Oxide Precipitates by Implantation of Ti, Y and O Ions in Fe-10%Cr: Towards an Understanding of Precipitation in Oxide Dispersion-Strengthened (ODS) Steels.

The properties of oxide dispersion-strengthened steels are highly dependent on the nature and size distribution of their constituting nano-oxide precipitates. A fine control of the processes of synthesis would enable the optimization of pertinent properties for use in various energy systems. This control, however, requires knowledge of the precise mechanisms of nucleation and growth of the nanoprecipitates, which are still a matter of debate. In the present study, nano-oxide precipitates were produced via the implantation of Y, Ti, and O ions in two different sequential orders in an Fe-10%Cr matrix that was subsequently thermally annealed. The results show that the oxides that precipitate are not necessarily favoured thermodynamically, but rather result from complex kinetics aspects related to the interaction between the implanted elements and induced defects. When Y is implanted first, the formation of nanoprecipitates with characteristics similar to those in conventionally produced ODS steels, especially with a core/shell structure, is evidenced. In contrast, when implantation starts with Ti, the precipitation of yttria during subsequent high-temperature annealing is totally suppressed, and corundum Cr2O3 precipitates instead. Moreover, the systematic involvement of {110} matrix planes in orientation relationships with the precipitates, independently of the precipitate nature, suggests matrix restriction effects on the early stages of precipitation.