Hairy Cell Leukemia in a Filipino Male during the COVID-19 Pandemic - Report of a Rare Case

Hairy cell leukemia (HCL) is a rare, chronic, mature B-cell lymphoproliferative disorder accounting for 2% of all leukemias. In this paper, we would like to present our experience in the management of HCL in a financially limited setting where other diagnostic tests and chemotherapy are unavailable. The case report aims to emphasize the recognition of the distinctive morphology of hairy cells in the peripheral blood in the consideration of the initial diagnosis. A 60-year-old Filipino male was incidentally found to have anemia, thrombocytopenia and an absolute neutrophilic count below 1,000 in a pre-operative clearance for elective herniorrhaphy. Blood smear revealed atypical lymphocytes with hair like cytoplasmic projections. CT-scan of the abdomen showed splenomegaly and prominent paraaortic nodes. Flow cytometry of the bone marrow aspirate was consistent with an involvement of a Mature B cell neoplasm markers CD19, CD20, CD22 and surface immunoglobulin lambda and hairy cell leukemia markers CD11c, CD103 and CD25. He responded to six-weekly sessions of Cladribine with remission of the bone marrow and hematologic parameters. HCL is a rare type of a mature B cell neoplasm characterized by pancytopenia, splenomegaly, bone marrow fibrosis and the presence of atypical lymphoid cells with hairy projections in blood, bone marrow and spleen. Immunophenotyping express CD11c, CD103, CD123, and CD25. BRAF V600E mutation is the disease defining genetic event. Cladribine and Pentostatin are the first line of treatment. Cases of leukemia can be easily overlooked because of the mild derangement in the complete blood count. A meticulous differential review of the atypical lymphocyte, is the first step in the diagnosis of this rare disease.Copyright © 2022, Philippine College of Physicians. All rights reserved.

LungNet22: A Fine-Tuned Model for Multiclass Classification and Prediction of Lung Disease Using X-ray Images.

In recent years, lung disease has increased manyfold, causing millions of casualties annually. To combat the crisis, an efficient, reliable, and affordable lung disease diagnosis technique has become indispensable. In this study, a multiclass classification of lung disease from frontal chest X-ray imaging using a fine-tuned CNN model is proposed. The classification is conducted on 10 disease classes of the lungs, namely COVID-19, Effusion, Tuberculosis, Pneumonia, Lung Opacity, Mass, Nodule, Pneumothorax, and Pulmonary Fibrosis, along with the Normal class. The dataset is a collective dataset gathered from multiple sources. After pre-processing and balancing the dataset with eight augmentation techniques, a total of 80,000 X-ray images were fed to the model for classification purposes. Initially, eight pre-trained CNN models, AlexNet, GoogLeNet, InceptionV3, MobileNetV2, VGG16, ResNet 50, DenseNet121, and EfficientNetB7, were employed on the dataset. Among these, the VGG16 achieved the highest accuracy at 92.95%. To further improve the classification accuracy, LungNet22 was constructed upon the primary structure of the VGG16 model. An ablation study was used in the work to determine the different hyper-parameters. Using the Adam Optimizer, the proposed model achieved a commendable accuracy of 98.89%. To verify the performance of the model, several performance matrices, including the ROC curve and the AUC values, were computed as well.