Resource-Limited Automated Ki67 Index Estimation in Breast Cancer
This work addresses resource limitations in IoT-based healthcare applications for breast cancer prognosis, representing an incremental improvement in efficiency.
The paper tackled the high computational resource demands of deep neural networks for Ki67 index estimation in breast cancer by proposing a resource consumption-aware DNN, which reduced memory usage by up to 75%, disk space by up to 89%, and energy consumption by up to 1.5x while maintaining or improving accuracy compared to a state-of-the-art benchmark.
The prediction of tumor progression and chemotherapy response has been recently tackled exploiting Tumor Infiltrating Lymphocytes (TILs) and the nuclear protein Ki67 as prognostic factors. Recently, deep neural networks (DNNs) have been shown to achieve top results in estimating Ki67 expression and simultaneous determination of intratumoral TILs score in breast cancer cells. However, in the last ten years the extraordinary progress induced by deep models proliferated at least as much as their resource demand. The exorbitant computational costs required to query (and in some cases also to store) a deep model represent a strong limitation in resource-limited contexts, like that of IoT-based applications to support healthcare personnel. To this end, we propose a resource consumption-aware DNN for the effective estimate of the percentage of Ki67-positive cells in breast cancer screenings. Our approach reduced up to 75% and 89% the usage of memory and disk space respectively, up to 1.5x the energy consumption, and preserved or improved the overall accuracy of a benchmark state-of-the-art solution. Encouraged by such positive results, we developed and structured the adopted framework so as to allow its general purpose usage, along with a public software repository to support its usage.