Hyperparameter Tuning in Deep Learning Approach for Classification of Classical Myeloproliferative Neoplasm


  • Umi Kalsom Mohamad Yusof Department of Computer and Communication Systems Engineering, Faculty of Engineering, Universiti Putra Malaysia, Selangor, Malaysia https://orcid.org/0000-0002-0529-4672
  • Syamsiah Mashohor Department of Computer and Communication Systems Engineering, Faculty of Engineering, Universiti Putra Malaysia, Selangor, Malaysia https://orcid.org/0000-0003-0851-6127
  • Marsyita Hanafi Department of Computer and Communication Systems Engineering, Faculty of Engineering, Universiti Putra Malaysia, Selangor, Malaysia
  • Sabariah Md Noor Department of Pathology, Faculty of Medicine and Health Sciences, Universiti Putra Malaysia, Selangor, Malaysia https://orcid.org/0000-0002-2292-5149
  • Norsafina Zainal Pathology Department, Hospital Serdang, Selangor, Malaysia




Deep learning, Artificial intelligence, Histopathology images, Classical MPN


Histopathology images are an essential resource for defining biological compositions or examining the composition of cells and tissues. The analysis of histopathology images is also crucial in supporting different class of disease including for rare disease like Myeloproliferative Neoplasms (MPN). Despite technological advancement in diagnostic tools to boost procedure in classification of MPN, morphological assessment from histopathology images acquired by bone marrow trephine (BMT) is remained critical to confirm MPN subtypes. However, the outcome of assessment at a present is profoundly challenging due to subjective, poorly reproducible criteria and highly dependent on pathologist where it caused interobserver variability in the interpretation. To address, this study developed a classification of classical MPN namely polycythemia vera (PV), essential thrombocythemia (ET) and primary myelofibrosis (MF) using deep learning approach. Data collection was undergoing several image augmentations processes to increase features variability and expand the dataset. The augmented images were then fed into CNN classifier followed by implementation of cross validation method. Finally, the best classification model was performed 95.3% of accuracy by using Adamax optimizer. High accuracy and best output given by proposed model shows significant potential in the deployment of the classification of MPN and hence facilitates the interpretation and monitoring of samples beyond conventional approaches.


A. A. and K. T. Michael Keng, “Cleveland Clinic Myeloproliferative Neoplasms - Virtual Medical School,” Cleveland Clinic Myeloproliferative Neoplasms, Dec. 2013. https://teachmemedicine.org/cleveland-clinic-myeloproliferative-neoplasms/ (accessed May 17, 2021).

W. J. Wong and O. Pozdnyakova, “Myeloproliferative neoplasms: Diagnostic workup of the cythemic patient,” Int. J. Lab. Hematol., vol. 41, no. S1, pp. 142–150, 2019, doi: 10.1111/ijlh.13005.

H. Fujiwara, “Histological evaluation of myeloproliferative neoplasms,” J. Clin. Exp. Hematop., vol. 58, no. 2, pp. 45–50, 2018, doi: 10.3960/jslrt.18006.

Swerdlow SH et al., “WHO Classification of Tumours of Haematopoietic and Lymphoid Tissues 2017 - Revised 4th Ed, Volume 2 (IARC WHO Classification of Tumours) | Lymphoma | Leukemia,” IARC Publications, 2017. https://www.scribd.com/document/376677186/WHO-Classification-of-Tumours-of-Haematopoietic-and-Lymphoid-Tissues-2017-Revised-4th-Ed-Volume-2-IARC-WHO-Classification-of-Tumours (accessed May 18, 2021).

“Histology images of Bone marrow by PathPedia.com: Pathology e-Atlas.” https://www.pathpedia.com/education/eatlas/histology/bone_marrow/Images.aspx?1 (accessed Sep. 12, 2021).

Aaron T. Gerds, “Myeloproliferative Neoplasms,” 2016. https://www.clevelandclinicmeded.com/medicalpubs/diseasemanagement/hematology-oncology/chronic-myeloproliferative-disorders/ (accessed May 17, 2021).

“Latest Medical News, Clinical Trials, Guidelines - Today on Medscape.” https://www.medscape.com/ (accessed Oct. 02, 2021).

M. Kantardzic, B. Djulbegovic, and H. Hamdan, “A data-mining approach to improving Polycythemia Vera diagnosis,” Comput. Ind. Eng., vol. 43, no. 4, pp. 765–773, 2002, doi: 10.1016/S0360-8352(02)00138-9.

V. C. Korfiatis, P. A. Asvestas, K. K. Delibasis, and G. K. Matsopoulos, “A classification system based on a new wrapper feature selection algorithm for the diagnosis of primary and secondary polycythemia,” Comput. Biol. Med., vol. 43, no. 12, pp. 2118–2126, 2013, doi: 10.1016/j.compbiomed.2013.09.016.

T. H. Song, V. Sanchez, H. Eidaly, and N. M. Rajpoot, “Dual-Channel Active Contour Model for Megakaryocytic Cell Segmentation in Bone Marrow Trephine Histology Images,” IEEE Trans. Biomed. Eng., vol. 64, no. 12, pp. 2913–2923, 2017, doi: 10.1109/TBME.2017.2690863.

K. Sirinukunwattana et al., “Artificial intelligence-based morphological fingerprinting of megakaryocytes: A new tool for assessing disease in MPN patients,” Blood Adv., vol. 4, no. 14, pp. 3284–3294, 2020, doi: 10.1182/BLOODADVANCES.2020002230.

Z. E. Fitri and A. M. N. Imron, “Classification of White Blood Cell Abnormalities for Early Detection of Myeloproliferative Neoplasms Syndrome Using Backpropagation,” 2021, doi: 10.1007/978-981-33-6926-9_43.

L. Alzubaidi et al., Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, vol. 8, no. 53. Springer International Publishing, 2021.

J. Wang, H. Zhu, S. H. Wang, and Y. D. Zhang, “A Review of Deep Learning on Medical Image Analysis,” Mob. Networks Appl., 2021, doi: 10.1007/s11036-020-01672-7.

M. Puttagunta and S. Ravi, “Medical image analysis based on deep learning approach,” Multimed. Tools Appl., 2021, doi: 10.1007/s11042-021-10707-4.

J. Xu, C. Zhou, B. Lang, and Q. Liu, Deep learning for histopathological image analysis: Towards computerized diagnosis on cancers, no. 9783319429. 2017.

W. Jiao et al., “A deep learning system accurately classifies primary and metastatic cancers using passenger mutation patterns,” Nat. Commun., vol. 11, no. 1, pp. 1–12, 2020, doi: 10.1038/s41467-019-13825-8.

C. Roaldsnes, R. Holst, H. Frederiksen, and W. Ghanima, “Myeloproliferative neoplasms: trends in incidence, prevalence and survival in Norway,” Eur. J. Haematol., vol. 98, no. 1, pp. 85–93, 2017, doi: 10.1111/ejh.12788.




How to Cite

U. K. Mohamad Yusof, Syamsiah Mashohor, Marsyita Hanafi, Sabariah Md Noor, and Norsafina Zainal, “Hyperparameter Tuning in Deep Learning Approach for Classification of Classical Myeloproliferative Neoplasm”, Malaysian J. Sci. Adv. Tech., vol. 2, no. 3, pp. 96–101, Aug. 2022.