• 2019-10
  • 2019-11
  • 2020-03
  • 2020-07
  • 2020-08
  • 2021-03
  • br arrest with altered cell membrane and nuclear


    arrest with altered cell membrane and nuclear integrity in MDA-MB-231 cancer cells. A schematic model illustrating the possible mechanism of WSPF induced apoptosis is shown in Fig. 10. The present results do suggest future characterization of WSPF for the effective therapeutically active protein(s) responsible for the anti-cancerous activity. Studies in this direction are underway in our lab.
    TAD gratefully acknowledges the financial assistance provided by Department of Biotechnology (DBT), Govt. of India, New Delhi, India as a research grant with Ref. No. BT/PR6307/GBD/27/399/2012. PAD is thankful to DBT and Council of Scientific and Industrial Research (CSIR), Govt. of India, New Delhi for fellowship. Authors are thankful to the pro-teomics facility of Molecular Biophysics Unit, IISc, Bangalore for mass spectrometric measurement and Dr. Rebecca J. Boohaker, Oncology De-partment, Drug Discovery Division, Southern Research, USA, for critical reading of the manuscript.
    Declaration of Competing Interests
    The authors declare no conflict of interest.
    [9] R. Thangam, D. Senthilkumar, V. Suresh, M. Sathuvan, S. Sivasubramanian, K. Pazhanichamy, P.K. Gorlagunta, S. Kannan, P. Gunasekaran, R. Rengasamy, Induction of ROS-dependent mitochondria-mediated intrinsic apoptosis in MDA-MB-231 SB 203580 by glycoprotein from Codium decorticatum, J. Agric. Food Chem. 62 (15) (2014) 3410–3421.
    [16] T. Mosmann, Rapid colorimetric assay for cellular growth and survival: application to proliferation and cytotoxicity assays, J. Immunol. Methods 65 (1–2) (1983) 55–63.
    [23] S. Khazraei-Moradian, M. Ganjalikhani-Hakemi, A. Andalib, R. Yazdani, J. Arasteh, G.A. Kardar, The effect of licorice protein fractions on proliferation and apoptosis of gastrointestinal cancer cell lines, Nutr. Cancer 69 (2) (2017) 330–339.
    [50] R. Mandelkow, D. Guembel, H. Ahrend, A. Kaul, U. Zimmermann, M. Burchardt, M.B. Stope, Detection and quantification of nuclear morphology changes in apoptotic cells by fluorescence microscopy and subsequent analysis of visualized fluorescent signals, Anticancer Res. 37 (5) (2017) 2239–2244. [51] O.P. Mgbonyebi, J. Russo, I.H. Russo, Roscovitine induces cell death and morpholog-ical changes indicative of apoptosis in MDA-MB-231 breast cancer cells, Cancer Res. 59 (8) (1999) 1903–1910.
    Contents lists available at ScienceDirect
    Future Generation Computer Systems
    journal homepage:
    An e-Health care services framework for the detection and classification of breast cancer in breast cytology images as an IoMT application
    Sana Ullah Khan a, Naveed Islam a, Zahoor Jan a, Ikram Ud Din b,∗, Atif Khan a, Yasir Faheem c a Department of Computer Science, Islamia College University Peshawar, Pakistan
    b Department of Information Technology, The University of Haripur, Pakistan c COMSATS Institute of Information Technology, Islamabad, Pakistan
    • ML and computational intelligence based approach to detect and classify malignant cells in breast cancer.
    • Malignant cells are detected by extracting various shape and textured based features.
    • Three classifiers are applied for the classification of malignant cells, i.e., SVM, NB, and RF, are applied.
    • Optimal features are selected for the use of Genetic Algorithm.
    Article history:
    Breast cancer
    Internet of Medical Things (IoMT)
    Support Vector Machine (SVM)
    Naïve Bayesian (NB)
    Random Forest (RF)
    Genetic Algorithm (GA)
    Chain-like Agent Genetic Algorithm (CAGA) 
    One of the primary causes of mortality among women aged 20–59 worldwide is breast cancer. Early detection and getting proper treatment can reduce the rate of morbidity of breast cancer. In this paper, we proposed a framework which combines machine learning and computational intelligence-based approaches in e-Health care service as an application of the Internet of Medical Things (IoMT) technology, for the early detection and classification of malignant cells in breast cancer. In the proposed approach, the detection of malignant cells is achieved by extracting various shapes and textured based features, whereas the classification is performed using three well-known classification algorithms. The most innovative part of the proposed approach is the use of Evolutionary Algorithms (EA) for the selection of optimal features, which reduces the computational complexity and accelerates the classification process in cloud-based e-Health care service. Similarly, an ensemble based classifier is used to select the best classifier by adopting the majority voting technique. The performance of the proposed approach is validated through experiments on real data sets which provide an accuracy of 98.0% in the detection and classification of malignant cells in breast cytology images.