Hybrid Models Based on Fusion Features of a CNN and Handcrafted Features for Accurate Histopathological Image Analysis for Diagnosing Malignant Lymphomas

Malignant lymphoma is one of the most severe types of disease that leads to death as a result of exposure of lymphocytes to malignant tumors. The transformation of cells from indolent B-cell lymphoma to B-cell lymphoma (DBCL) is life-threatening. Biopsies taken from the patient are the gold standard for lymphoma analysis. Glass slides under a microscope are converted into whole slide images (WSI) to be analyzed by AI techniques through biomedical image processing. Because of the multiplicity of types of malignant lymphomas, manual diagnosis by pathologists is difficult, tedious, and subject to disagreement among physicians. The importance of artificial intelligence (AI) in the early diagnosis of malignant lymphoma is significant and has revolutionized the field of oncology. The use of AI in the early diagnosis of malignant lymphoma offers numerous benefits, including improved accuracy, faster diagnosis, and risk stratification. This study developed several strategies based on hybrid systems to analyze histopathological images of malignant lymphomas. For all proposed models, the images and extraction of malignant lymphocytes were optimized by the gradient vector flow (GVF) algorithm. The first strategy for diagnosing malignant lymphoma images relied on a hybrid system between three types of deep learning (DL) networks, XGBoost algorithms, and decision tree (DT) algorithms based on the GVF algorithm. The second strategy for diagnosing malignant lymphoma images was based on fusing the features of the MobileNet-VGG16, VGG16-AlexNet, and MobileNet-AlexNet models and classifying them by XGBoost and DT algorithms based on the ant colony optimization (ACO) algorithm. The color, shape, and texture features, which are called handcrafted features, were extracted by four traditional feature extraction algorithms. Because of the similarity in the biological characteristics of early-stage malignant lymphomas, the features of the fused MobileNet-VGG16, VGG16-AlexNet, and MobileNet-AlexNet models were combined with the handcrafted features and classified by the XGBoost and DT algorithms based on the ACO algorithm. We concluded that the performance of the two networks XGBoost and DT, with fused features between DL networks and handcrafted, achieved the best performance. The XGBoost network based on the fused features of MobileNet-VGG16 and handcrafted features resulted in an AUC of 99.43%, accuracy of 99.8%, precision of 99.77%, sensitivity of 99.7%, and specificity of 99.8%. This highlights the significant role of AI in the early diagnosis of malignant lymphoma, offering improved accuracy, expedited diagnosis, and enhanced risk stratification. This study highlights leveraging AI techniques and biomedical image processing; the analysis of whole slide images (WSI) converted from biopsies allows for improved accuracy, faster diagnosis, and risk stratification. The developed strategies based on hybrid systems, combining deep learning networks, XGBoost and decision tree algorithms, demonstrated promising results in diagnosing malignant lymphoma images. Furthermore, the fusion of handcrafted features with features extracted from DL networks enhanced the performance of the classification models.

[1]  L. Pantanowitz,et al.  Value of Artificial Intelligence in Evaluating Lymph Node Metastases , 2023, Cancers.

[2]  Ibrahim A. Ahmed,et al.  AI Techniques of Dermoscopy Image Analysis for the Early Detection of Skin Lesions Based on Combined CNN Features , 2023, Diagnostics.

[3]  Ibrahim A. Ahmed,et al.  Multi-Models of Analyzing Dermoscopy Images for Early Detection of Multi-Class Skin Lesions Based on Fused Features , 2023, Processes.

[4]  A. Navin,et al.  Acute Leukemia Diagnosis Based on Images of Lymphocytes and Monocytes Using Type-II Fuzzy Deep Network , 2023, Electronics.

[5]  C. Zwaan,et al.  Machine Learning Logistic Regression Model for Early Decision Making in Referral of Children with Cervical Lymphadenopathy Suspected of Lymphoma , 2023, Cancers.

[6]  Ibrahim A. Ahmed,et al.  Multi-Techniques for Analyzing X-ray Images for Early Detection and Differentiation of Pneumonia and Tuberculosis Based on Hybrid Features , 2023, Diagnostics.

[7]  Abdulaziz M. Alayba,et al.  Hybrid Techniques of Analyzing MRI Images for Early Diagnosis of Brain Tumours Based on Hybrid Features , 2023, Processes.

[8]  Amin Babazadeh Sangar,et al.  A Customized Efficient Deep Learning Model for the Diagnosis of Acute Leukemia Cells Based on Lymphocyte and Monocyte Images , 2023, Electronics.

[9]  P. Jain,et al.  Is There Still a Role for Transplant for Patients with Mantle Cell Lymphoma (MCL) in the Era of CAR-T Cell Therapy? , 2022, Current Treatment Options in Oncology.

[10]  Zeyad Ghaleb Al-Mekhlafi,et al.  Diagnosis of Histopathological Images to Distinguish Types of Malignant Lymphomas Using Hybrid Techniques Based on Fusion Features , 2022, Electronics.

[11]  Zeyad Ghaleb Al-Mekhlafi,et al.  Hybrid Techniques for Diagnosis with WSIs for Early Detection of Cervical Cancer Based on Fusion Features , 2022, Applied Sciences.

[12]  Ching-Wei Wang,et al.  Deep Learning Using Endobronchial-Ultrasound-Guided Transbronchial Needle Aspiration Image to Improve the Overall Diagnostic Yield of Sampling Mediastinal Lymphadenopathy , 2022, Diagnostics.

[13]  J. Beatty,et al.  Nasal Lymphoma with Low Mitotic Index in Three Cats Treated with Chlorambucil and Prednisolone , 2022, Veterinary sciences.

[14]  A. Winnicka,et al.  Canine B Cell Lymphoma- and Leukemia-Derived Extracellular Vesicles Moderate Differentiation and Cytokine Production of T and B Cells In Vitro , 2022, International journal of molecular sciences.

[15]  Xuelei Ma,et al.  Computer-aided diagnostic models to classify lymph node metastasis and lymphoma involvement in enlarged cervical lymph nodes using PET/CT. , 2022, Medical physics.

[16]  Suliman Mohamed Fati,et al.  Early Diagnosis of Oral Squamous Cell Carcinoma Based on Histopathological Images Using Deep and Hybrid Learning Approaches , 2022, Diagnostics.

[17]  Gyanendra Prasad Joshi,et al.  Chaotic Sparrow Search Algorithm with Deep Transfer Learning Enabled Breast Cancer Classification on Histopathological Images , 2022, Cancers.

[18]  S. Stilgenbauer,et al.  Deep Neural Networks and Machine Learning Radiomics Modelling for Prediction of Relapse in Mantle Cell Lymphoma , 2022, Cancers.

[19]  P. M. Ameer,et al.  A content-based image retrieval system for the diagnosis of lymphoma using blood micrographs: An incorporation of deep learning with a traditional learning approach , 2022, Comput. Biol. Medicine.

[20]  Shugang Li,et al.  A New Fast Ant Colony Optimization Algorithm: The Saltatory Evolution Ant Colony Optimization Algorithm , 2022, Mathematics.

[21]  Monagi H. Alkinani,et al.  HSDDD: A Hybrid Scheme for the Detection of Distracted Driving through Fusion of Deep Learning and Handcrafted Features , 2022, Sensors.

[22]  Ibrahim A. Ahmed,et al.  Eye Tracking-Based Diagnosis and Early Detection of Autism Spectrum Disorder Using Machine Learning and Deep Learning Techniques , 2022, Electronics.

[23]  P. Kurtin,et al.  Chronic lymphocytic leukemia (CLL) with Reed–Sternberg-like cells vs Classic Hodgkin lymphoma transformation of CLL: does this distinction matter? , 2022, Blood cancer journal.

[24]  Sitara Afzal,et al.  Human Activity Recognition via Hybrid Deep Learning Based Model , 2022, Sensors.

[25]  Feiyang Zhang,et al.  Lymphoma recognition based on CNN models , 2021, Other Conferences.

[26]  Felipe Lumbreras,et al.  Hybrid MSRM-Based Deep Learning and Multitemporal Sentinel 2-Based Machine Learning Algorithm Detects Near 10k Archaeological Tumuli in North-Western Iberia , 2021, Remote. Sens..

[27]  G. Kanas,et al.  Epidemiology of diffuse large B-cell lymphoma (DLBCL) and follicular lymphoma (FL) in the United States and Western Europe: population-level projections for 2020–2025 , 2021, Leukemia & lymphoma.

[28]  Long Zhao,et al.  Decision Tree Application to Classification Problems with Boosting Algorithm , 2021, Electronics.

[29]  I. Takeuchi,et al.  Case-based similar image retrieval for weakly annotated large histopathological images of malignant lymphoma using deep metric learning , 2021, Medical Image Anal..

[30]  Xianjun Gao,et al.  Object-Oriented Building Contour Optimization Methodology for Image Classification Results via Generalized Gradient Vector Flow Snake Model , 2021, Remote. Sens..

[31]  Y. Kluger,et al.  Histopathologic and Machine Deep Learning Criteria to Predict Lymphoma Transformation in Bone Marrow Biopsies. , 2021, Archives of Pathology & Laboratory Medicine.

[32]  Dominik Grochala,et al.  Artificial Breath Classification Using XGBoost Algorithm for Diabetes Detection , 2021, Sensors.

[33]  D. Ennishi,et al.  Transformation to diffuse large B-cell lymphoma with germinal center B-cell like subtype and discordant light chain expression in a patient with Waldenström macroglobulinemia/lymphoplasmacytic lymphoma , 2021, International Journal of Hematology.

[34]  W. Xia,et al.  Deep Learning for Automatic Differential Diagnosis of Primary Central Nervous System Lymphoma and Glioblastoma: Multi‐Parametric Magnetic Resonance Imaging Based Convolutional Neural Network Model , 2021, Journal of magnetic resonance imaging : JMRI.

[35]  Kuixing Zhang,et al.  Research on the classification of lymphoma pathological images based on deep residual neural network , 2021, Technology and health care : official journal of the European Society for Engineering and Medicine.

[36]  Yiguo Hu,et al.  A deep learning diagnostic platform for diffuse large B-cell lymphoma with high accuracy across multiple hospitals , 2020, Nature Communications.

[37]  G. Saglio,et al.  A Clinically Applicable Approach to the Classification of B-Cell Non-Hodgkin Lymphomas with Flow Cytometry and Machine Learning , 2020, Cancers.

[38]  T. Furuta,et al.  Deep learning shows the capability of high-level computer-aided diagnosis in malignant lymphoma , 2020, Laboratory Investigation.

[39]  P. Brousset,et al.  Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning , 2020, npj Digital Medicine.

[40]  M. Podhorecka,et al.  The Neutrophil to Lymphocyte and Lymphocyte to Monocyte Ratios as New Prognostic Factors in Hematological Malignancies – A Narrative Review , 2020, Cancer management and research.

[41]  Geert J. S. Litjens,et al.  Predicting MYC translocation in HE specimens of diffuse large B-cell lymphoma through deep learning , 2020, Medical Imaging: Digital Pathology.

[42]  Mei Zhou,et al.  A blood cell dataset for lymphoma classification using faster R-CNN , 2020 .

[43]  Valerio Pascucci,et al.  Improving Augmented Human Intelligence to Distinguish Burkitt Lymphoma From Diffuse Large B-Cell Lymphoma Cases. , 2019, American journal of clinical pathology.

[44]  R. Cardell-Oliver,et al.  Dataset , 2019, Proceedings of the 2nd Workshop on Data Acquisition To Analysis - DATA'19.

[45]  William C. Regli,et al.  What are Feature Interactions , 1996 .