2 May 2023 in APL Machine Learning
Cancer diagnostics is an important field of cancer recovery and survival with many expensive procedures needed to administer the correct treatment. Machine Learning (ML) approaches can help with the diagnostic prediction from circulating tumor cells in liquid biopsy or from a primary tumor in solid biopsy. After predicting the metastatic potential from a deep learning model, doctors in a clinical setting can administer a safe and correct treatment for a specific patient. This paper investigates the use of deep convolutional neural networks for predicting a specific cancer cell line as a tool for label free identification. Specifically, deep learning strategies for weight initialization and performance metrics are described, with transfer learning and the accuracy metric utilized in this work. The equipment used for prediction involves brightfield microscopy without the use of chemical labels, advanced instruments, or time-consuming biological techniques, giving an advantage over current diagnostic methods. In the procedure, three different binary datasets of well-known cancer cell lines were collected, each having a difference in metastatic potential. Two different classification models were adopted (EfficientNetV2 and ResNet-50) with the analysis given for each stage in the ML architecture. The training results for each model and dataset are provided and systematically compared. We found that the test set accuracy showed favorable performance for both ML models with EfficientNetV2 accuracy reaching up to 99%. These test results allowed EfficientNetV2 to outperform ResNet-50 at an average percent increase of 3.5% for each dataset. The high accuracy obtained from the predictions demonstrates that the system can be retrained on a large-scale clinical dataset.
8 January 2025 in Lab on a Chip
Heterogeneities among tumor cells significantly contribute towards cancer progression and therapeutic inefficiency. Herein, we discuss recent microfluidic platforms for sorting and profiling of tumor cells for prognostics and personalized therapies.
9 September 2025 in Biomaterials Science
Biomaterials and machine learning enable isolation, profiling, and clinical translation of circulating tumor cells and extracellular vesicles to address tumor heterogeneity and therapy resistance.
5 October 2026 in Journal of Polymer Science
NFNur Hendri Wahyu Firdaus
Peanut allergy can lead to severe and life‐threatening reactions, yet management still relies primarily on strict peanut avoidance. Because IgE antibodies play a critical role in driving allergic responses, several therapeutic strategies target the IgE pathway. However, these approaches often require biologics and can be limited by cost, dosing constraints, or systemic side effects. Here, we present a microfluidic immunoadsorption platform functionalized with a layer‐by‐layer (LbL) assembly of poly(diallyldimethylammonium chloride) (PDDA) and peanut allergens nanofilms to selectively capture peanut‐specific antibodies directly from the whole blood of peanut allergy mouse. The LbL coating formed a uniform surface in microfluidic channels as confirmed by fluorescence microscopy, SEM, and QCM‐D assessments. Using serum from peanut‐sensitized mice, the peanut protein extract (PE) coated device demonstrated efficient depletion of anti‐PE IgG. When operated with unprocessed whole blood, the device achieved measurable removal of PE‐specific antibodies in continuous flow conditions without significant hemolysis, altering red blood cell count, mast cell activation, or oxidative stress. These results demonstrate that PE functionalized LbL microfluidic immunoadsorption enables selective antibody depletion using minimal blood volumes and without preprocessing, offering a low shear and biocompatible alternative to conventional extracorporeal systems.