China 
Africa 
Explore chapters and articles related to this topic
Cancer Diagnosis from Histopathology Images Using Deep Learning: A Review
Published in Ranjeet Kumar Rout, Saiyed Umer, Sabha Sheikh, Amrit Lal Sangal, Artificial Intelligence Technologies for Computational Biology, 2023
Vijaya Gajanan Buddhavarapu, J. Angel Arul Jothi
Song at al. proposed a parallel network called a synchronized asymmetric hybrid deep autoencoder network (Syn-AHDA) that simultaneously detected and classified erythroid and myeloid cells from bone marrow trephine histology images [84]. This model was novel as it combined both detection and classification of cells using a single DL network thereby reducing the training time. The architecture was based on the fact that both the detection and the classification networks rely on the same high level features. The Syn-AHDA network was built using a stacked autoencoder (AE) neural network. The network consisted of the following four subnetworks: an input network, a connection network, a classification network and a detection network. The input network extracted high level features from the input image (I). These features were then fed to the classification and the detection network via the connection network. The F1 scores of the proposed model for the detection and the classification tasks were 0.9466 and 0.8795, respectively. The model was accurate when compared with other DL architectures for detection and classification tasks and also exhibited reduced training time. Moreover, the model performed better in identifying irregularly shaped cells.
The Human Immune System Seen from a Biomedical Engineering Viewpoint
Published in Robert B. Northrop, Endogenous and Exogenous Regulation and Control of Physiological Systems, 2020
Immune system autacoids (also known as immunocytokines), including the interleukins, interferons, tumor necrosis factors, prostaglandins, and chemokines, are secreted by immune system cells and diverse somatic cells. These signaling substances must bind to receptor proteins on their target cells. After binding, specific internal biochemical processes are initiated, leading to events such as cell growth, differentiation, clonal expansion, and production of receptor proteins and other immunocytokines. Autacoid receptors and other immune system cell surface molecules are generally classified as cluster of differentiation (CD) antigens. Over 182 CD molecules have been described.169 For example, CD127 found on bone marrow lymphoid precursor cells, pro-B-cells, mature T-cells, and monocytes is the IL7 receptor; CD25 found on activated T-cells, B-cells, and monocytes is the receptor for IL2; and CD37 found on mature B- and T-cells and myeloid cells has unknown function.
Plasmonic Nanoparticles for Cancer Bioimaging, Diagnostics and Therapy
Published in Klaus D. Sattler, st Century Nanoscience – A Handbook, 2020
Bridget Crawford, Tuan Vo-Dinh
Our group has demonstrated a novel cancer therapy, synergistic immune photo nanotherapy (SYMPHONY) on bladder cancer with mice animal model [195]. The SYMPHONY therapy combines GNS-mediated PTT and immune checkpoint inhibitor [196]. In recent years, immunotherapy with specific immune checkpoint inhibitor has provided a promising way to break tumor immunosuppressive environment. PD-L1, a protein overexpressed on cancer cell membrane, contributes to the suppression of the immune system. To modulate T cell function, PDL1 binds to its receptor, PD-1, found on activated T cells, B cells and myeloid cells. The therapeutic anti-PD-L1 antibody is designed to block the PD-L1/PD-1 interaction and reverse tumor-mediated immunosuppression. Blocking the PD-L1/PD-1 axis has been shown to be highly beneficial in many human tumors [197]. However, only modest clinical response to single-agent activity of PD-L1 and PD-1 antibodies is achieved in patients [198].
An Efficient Hybrid Model for Acute Myeloid Leukaemia detection using Convolutional Bi-LSTM based Recurrent Neural Network
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2023
Myeloid cells are described from myeloblasts that consist of eosinophils, monocytes, erythrocytes, basophils, neutrophils and megakaryocytes. In 1976, the French American British (FAB) Co-operative group established the classification system, which classifies the AML that depends on the bone marrow, blood and cytochemical staining (Petiti et al. 2020). The AML FAB classification depends upon the morphologic, where the AML is classified into eight categories as M1, M2, M3, M4, M4 E0, M5, M6 and M7. Specifically, in AML the M2 feature is myeloblastic leukaemia, it contains Auer rod, oval or round shape nucleus and cytoplasm, whereas the AML M3 is the acute promyelocytic leukaemia, it contains an extra Auer rod, lobulated and round nucleus and soft cytoplasm (Mashima et al. 2018).