Morphological diagnosis of hematologic malignancy using feature fusion-based deep convolutional neural network.

Leukemia is a cancer of white blood cells characterized by immature lymphocytes. Due to blood cancer, many people die every year. Hence, the early detection of these blast cells is necessary for avoiding blood cancer. A novel deep convolutional neural network (CNN) 3SNet that has depth-wise convolution blocks to reduce the computation costs has been developed to aid the diagnosis of leukemia cells. The proposed method includes three inputs to the deep CNN model. These inputs are grayscale and their corresponding histogram of gradient (HOG) and local binary pattern (LBP) images. The HOG image finds the local shape, and the LBP image describes the leukaemia cell's texture pattern. The suggested model was trained and tested with images from the AML-Cytomorphology_LMU dataset. The mean average precision (MAP) for the cell with less than 100 images in the dataset was 84%, whereas for cells with more than 100 images in the dataset was 93.83%. In addition, the ROC curve area for these cells is more than 98%. This confirmed proposed model could be an adjunct tool to provide a second opinion to a doctor.

Spatial attention-based residual network for human burn identification and classification.

Diagnosing burns in humans has become critical, as early identification can save lives. The manual process of burn diagnosis is time-consuming and complex, even for experienced doctors. Machine learning (ML) and deep convolutional neural network (CNN) models have emerged as the standard for medical image diagnosis. The ML-based approach typically requires handcrafted features for training, which may result in suboptimal performance. Conversely, DL-based methods automatically extract features, but designing a robust model is challenging. Additionally, shallow DL methods lack long-range feature dependency, decreasing efficiency in various applications. We implemented several deep CNN models, ResNeXt, VGG16, and AlexNet, for human burn diagnosis. The results obtained from these models were found to be less reliable since shallow deep CNN models need improved attention modules to preserve the feature dependencies. Therefore, in the proposed study, the feature map is divided into several categories, and the channel dependencies between any two channel mappings within a given class are highlighted. A spatial attention map is built by considering the links between features and their locations. Our attention-based model BuRnGANeXt50 kernel and convolutional layers are also optimized for human burn diagnosis. The earlier study classified the burn based on depth of graft and non-graft. We first classified the burn based on the degree. Subsequently, it is classified into graft and non-graft. Furthermore, the proposed model performance is evaluated on Burns_BIP_US_database. The sensitivity of the BuRnGANeXt50 is 97.22% and 99.14%, respectively, for classifying burns based on degree and depth. This model may be used for quick screening of burn patients and can be executed in the cloud or on a local machine. The code of the proposed method can be accessed at https://github.com/dhirujis02/Journal.git for the sake of reproducibility.

Feature Extraction Based Machine Learning for Human Burn Diagnosis From Burn Images.

Burn is one of the serious public health problems. Usually, burn diagnoses are based on expert medical and clinical experience and it is necessary to have a medical or clinical expert to conduct an examination in restorative clinics or at emergency rooms in hospitals. But sometimes a patient may have a burn where there is no specialized facility available, and in such a case a computerized automatic burn assessment tool may aid diagnosis. Burn area, depth, and location are the critical factors in determining the severity of burns. In this paper, a classification model to diagnose burns is presented using automated machine learning. The objective of the research is to develop the feature extraction model to classify the burn. The proposed method based on support vector machine (SVM) is evaluated on a standard data set of burns-BIP_US database. Training is performed by classifying images into two classes, i.e., those that need grafts and those that are non-graft. The 74 images of test data set are tested with the proposed SVM based method and according to the ground truth, the accuracy of 82.43% was achieved for the SVM based model, which was higher than the 79.73% achieved in past work using the multidimensional scaling analysis (MDS) approach.

Evaluation of tumor response to intra-arterial chemoembolization of hepatocellular carcinoma: Comparison of contrast-enhanced ultrasound with multiphase computed tomography.

PURPOSE: To compare the diagnostic accuracy of contrast-enhanced ultrasound (CEUS) with that of multiphase computed tomography (CT) in the evaluation of tumor response to transarterial chemoembolization (TACE) of hepatocellular carcinoma (HCC). MATERIAL AND METHODS: Fifty patients (41 men, 9 women; mean age, 53 years±12.5 [SD]) with a total of 70 HCCs (mean size, 5cm±3 [SD]) were evaluated. Post-TACE therapeutic assessment of HCC was done at 4 weeks. Patients with TACE done earlier and reporting with suspicion for recurrence were also included. Patients with hepatic masses seen on ultrasound were enrolled and subjected to CEUS, multiphase CT and magnetic resonance imaging (MRI). Hyperenhancing area at the tumor site on arterial phase of CEUS/multiphase CT/MRI was termed as residual disease (RD), the patterns of which were described on CEUS. Diagnostic accuracies of CEUS and MPCT were compared to that of MRI that was used as the reference standard. RESULTS: CEUS detected RD in 43/70 HCCs (61%). RD had a heterogeneous pattern in 22/43 HCCs (51%). Sensitivities of CEUS and multiphase CT were 94% (34/36; 95% CI: 81-99%) and 50% (18/36; 95% CI: 33-67%) respectively. Significant difference in sensitivity was found between CEUS and multiphase CT (P=0.0001). CEUS and multiphase CT had 100% specificity (95% CI: 83-100%). CONCLUSION: CEUS is a useful technique for detecting RD in HCC after TACE. For long term surveillance, CEUS should be complemented with multiphase CT/MRI for a comprehensive evaluation.

Prevalence and pattern of antiphospholipid antibody syndrome in a hospital based longitudinal study of 193 patients of systemic lupus erythematosus.

BACKGROUND: Antiphospholipid antibody syndrome (APS) is a systemic autoimmune disease characterised by thrombophilic state and obstetrical complications. Prevalence of APS varies in different parts of the world. So this study was conducted to find out the prevalence and pattern of APS in systemic lupus erythematosus (SLE) in this region. MATERIAL AND METHODS: In this hospital based longitudinal study from 2004 to 2011, we studied 193 patients of systemic lupus erythematosus (SLE) for prevalence of APS and its different characteristics. The diagnosis of SLE was made according to American College of Rheumatology (ACR) criteria and diagnosis of APS was made according to Sapporo criteria. RESULTS: Prevalence of APS in SLE was 25.38%. Mean age at study entry was 25.5 +/- 6.9 years and majority of APS patients were in the age group 21-30 yrs (44.89%). The most common clinical manifestation in both SLE with APS and SLE without APS was musuloskeletal involvement (79.59% and 84.72% respectively). Among 49 patients of SLE having APS, multisystem involvement was present in 16 patients and life threatening complications were present in 12 patients. Late foetal loss was the most common obstetrical manifestation of APS (26.53%) and deep vein thrombosis was most common thrombotic manifestation (16.32%). Anticardiolipin antibodies(IgG aCL) were the most common antibody (85.71%) detected. Lupus anticoagulant was present in 71.42% cases of SLE having APS. ANA and anti-dsDNA antibodies were present in 97.95% and 77.55% cases of SLE having APS. CONCLUSION: APS is a major cause of morbidity and mortality in patients of SLE. The incidence of secondary APS in SLE varies in different geographical regions and it was 25.38% in our study. Pregnancy morbidity and deep vein thrombosis were the most common complications of APS. IgG aCL was the most common antibody in APS patients. Screening for the presence of aPL antibodies in SLE patients and timely initiation of prophylactic treatment can prevent many of the complications.