Benign and Malignant Skin Lesion Detection from Melanoma Skin Cancer Images

Skin cancer is the most dangerous and lethal cancer that affects millions of people each year. The accurate identification of skin cancers can not be accomplished without expert dermatologists. However, specific research studies of WHO in Canada, US and Australia, show that in the year 1960s to 1980s, the cases of skin cancer has noted more than two times increased in comparison with the previous years. The identification of skin cancer in its early stage is an expensive and difficult task because it doesn't cause too much bad in the initial phase. Whereas, the growth of skin cancer requires biopsy and many other treatments each time which is quite costly as per the statistics of India. This challenge makes it a necessary step to identify the existence of skin cancer in the early stages to increase immortality. With the evolution and progression in technology, there are various methods which have participated in and solved medical issues including covid19, pneumonia and many others. Similarly, machine learning(ML) and deep learning(DL) models are applicable to diagnosing skin cancer in its early stages. In this work, the support vector machine (SVM), naive bayes (NB), K-nearest neighbour (KNN) and neural networks(NN) have been used for classifying benign and malignant lesions. Furthermore, for the feature extraction from the dataset, a pre-trained SqueezeNet model has been used. The classification results of KNN, SVM, NB and NN have been shown in the accuracy, recall, F1-Measure, precision, AUC and ROC. The comparison of the models has resulted that the NN model outperforms all other models when applied with the SqueezeNet feature extractor with the highest accuracy, F1-Measure, recall, precision and AUC as 88.2%, 0.882, 0.882, 0.882 and 0.957, respectively. Lastly, the performance metrics analogies results of each model have been illustrated for the classification of benign and malignant lesions. © 2023 IEEE.

SNELM: SqueezeNet-Guided ELM for COVID-19 Recognition.

(Aim) The COVID-19 has caused 6.26 million deaths and 522.06 million confirmed cases till 17/May/2022. Chest computed tomography is a precise way to help clinicians diagnose COVID-19 patients. (Method) Two datasets are chosen for this study. The multiple-way data augmentation, including speckle noise, random translation, scaling, salt-and-pepper noise, vertical shear, Gamma correction, rotation, Gaussian noise, and horizontal shear, is harnessed to increase the size of the training set. Then, the SqueezeNet (SN) with complex bypass is used to generate SN features. Finally, the extreme learning machine (ELM) is used to serve as the classifier due to its simplicity of usage, quick learning speed, and great generalization performances. The number of hidden neurons in ELM is set to 2000. Ten runs of 10-fold cross-validation are implemented to generate impartial results. (Result) For the 296-image dataset, our SNELM model attains a sensitivity of 96.35 ± 1.50%, a specificity of 96.08 ± 1.05%, a precision of 96.10 ± 1.00%, and an accuracy of 96.22 ± 0.94%. For the 640-image dataset, the SNELM attains a sensitivity of 96.00 ± 1.25%, a specificity of 96.28 ± 1.16%, a precision of 96.28 ± 1.13%, and an accuracy of 96.14 ± 0.96%. (Conclusion) The proposed SNELM model is successful in diagnosing COVID-19. The performances of our model are higher than seven state-of-the-art COVID-19 recognition models.

A Deep Learning Approach for Detecting Face Mask Using an Improved Yolo-V2 With Squeezenet

Face mask detection has become a critical issue in security and Covid-19 prevention. In this regard, the YOLO V2 network has demonstrated outstanding performance. The YOLO V2 on the other hand, employed Darknet as a feature extractor. However, as compared to Darknet, SqueezeNet allows us to reduce model size while reaching or surpassing the highest accuracy score. SqueezeNet is designed to have lower parameters that can be more readily stored in computer memory and transferred across a computer network. As a result, in this study, we recommended enhancing the YOLO network by replacing Darknet with Squeezenet. Compared to other existing face mask recognition systems that use the standard YOLO V2 algorithm, this improves overall performance in terms of model size and accuracy. As a result, this study proposed a rapid face mask detection model by improving the existing YOLO V2 network architecture by employing logistic classifiers and SqueezeNet for multi-label classification using FMD and MMD face-masked dataset. The model was evaluated on MATLAB 2021 against state-of-the-art approaches. The proposed model outperforms previous algorithms by attaining a good accuracy value of 81% and a recall value of 99.99%. © 2022 IEEE.

Internet of Medical Things-Based COVID-19 Detection in CT Images Fused with Fuzzy Ensemble and Transfer Learning Models.

One of the most difficult research areas in today's healthcare industry to combat the coronavirus pandemic is accurate COVID-19 detection. Because of its low infection miss rate and high sensitivity, chest computed tomography (CT) imaging has been recommended as a viable technique for COVID-19 diagnosis in a number of recent clinical investigations. This article presents an Internet of Medical Things (IoMT)-based platform for improving and speeding up COVID-19 identification. Clinical devices are connected to network resources in the suggested IoMT platform using cloud computing. The method enables patients and healthcare experts to work together in real time to diagnose and treat COVID-19, potentially saving time and effort for both patients and physicians. In this paper, we introduce a technique for classifying chest CT scan images into COVID, pneumonia, and normal classes that use a Sugeno fuzzy integral ensemble across three transfer learning models, namely SqueezeNet, DenseNet-201, and MobileNetV2. The suggested fuzzy ensemble techniques outperform each individual transfer learning methodology as well as trainable ensemble strategies in terms of accuracy. The suggested MobileNetV2 fused with Sugeno fuzzy integral ensemble model has a 99.15% accuracy rate. In the present research, this framework was utilized to identify COVID-19, but it may also be implemented and used for medical imaging analyses of other disorders.

A Methodology for Training Homomorphic Encryption Friendly Neural Networks

Privacy-preserving deep neural network (DNN) inference is a necessity in different regulated industries such as healthcare, finance, and retail. Recently, homomorphic encryption (HE) has been used as a method to enable analytics while addressing privacy concerns. HE enables secure predictions over encrypted data. However, there are several challenges related to the use of HE, including DNN size limitations and the lack of support for some operation types. Most notably, the commonly used ReLU activation is not supported under some HE schemes. We propose a structured methodology to replace ReLU with a quadratic polynomial activation. To address the accuracy degradation issue, we use a pre-trained model that trains another HE-friendly model, using techniques such as 'trainable activation' functions and knowledge distillation. We demonstrate our methodology on the AlexNet architecture, using the chest X-Ray and CT datasets for COVID-19 detection. Experiments using our approach reduced the gap between the F-1 score and accuracy of the models trained with ReLU and the HE-friendly model to within a mere 0.32-5.3% degradation. We also demonstrate our methodology using the SqueezeNet architecture, for which we observed 7% accuracy and F-1 improvements over training similar networks with other HE-friendly training methods.

VLSI Implementation of Optimized CNN based COVID-19 Lung Infection Segmentation and Classification from CT Image

The outbreak of COVID-19 challenged the existence of human life on earth. The diagnosis and treatment of this disease is highly crucial in current scenario. Since there is low difference in the intensity of normal cells and affected cells, Computed Tomography (CT) is an efficient tool for the diagnosis of lung infections caused due to COVID-19. In order to train a deep neural network, there is a requirement for huge number of labelled images. There is a necessity to develop an efficient neural network that requires less number of training images. To overcome these problems a novel network is developed for lung CT segmentation (SqueezeNet). For the extraction of energy values from the segmented image, Discrete Wavelet Transform (DWT) with lifting scheme is incorporated in the framework. These energy values are used for training the classifier (ResNet). The entire framework is implemented on hardware using Virtex 2 Pro FPGA. The performance of the proposed system is evaluated using Mean Absolute Error (MAE) and Specificity. The MAE of the system is found to be 0.099, which is very low compared to existing classifiers. The specificity of the system is 0.978, which is higher than that of existing classifiers. © 2022 IEEE.

A Modern Replica for COVID-19 Pestilential Disease Identification

Detection of COVID-19 disease and its unmasking, demands a certain level of proficiency. The Work exhibited in the paper proposes a novel Deep Learning based approach to recognize COVID-19 contagious infection using CT scans and X- Rays of lungs in Humans. So that labour and risk intensive task for radiotherapists of taking samples from the patients can be minimized and risk of community spread can be avoided. Our model takes into the CT scan chest images of the patient having a certainty of infection and returns the most significant disease category related to that patient. In our study, we demonstrated a Deep Learning framework model that follows the methodology of up-skilled feature extraction techniques along with Logistic Regression [LR] and other usable classifiers. This is used on images to detect and report the presence of infection that is being prevailed in an organ with a considerably pinpoint accuracy of 97.8%. Also after trying the model on spatial information real- time dataset of our Family members, who were infected by the disease, this model was able to detect 8 out of 10 images correctly. © 2022 IEEE.

Development Of A Deep Learning Model To Classify X-Ray Of Covid-19, Normal And Pneumonia-Affected Patients

Pneumonia is commonly seen in several diseases, including Covid-19 that has put countries under lockdown today [1]. Other than antigen rapid test kit (RTK) and reverse transcription-polymerase chain reaction (RT-PCR), an alternative method to detect COVID-19 is through the examination of patients' chest radiography (CXR). However, the results of manual inspections may be false and the misdiagnosis could lead to fatal consequences such as delayed treatment and death. The manual inspection can be inconsistent, inaccurate and may differ from different individuals due to different perspectives. Often, Covid-19 Xrays are misinterpreted as bacterial pneumonia. With the advancement of technology, this issue can be overcome by developing a Convolutional Neural Network (CNN) model to categorize X-ray of normal, pneumonia-affected and COVID-19 patients via deep learning. In this work, various CNN models (ResNet-50, ResNet-101, Vgg-16, Vgg-19 and SqueezeNet) were trained with the public databases that contain a combination of 1345 viral pneumonia, 1200 COVID-19 in addition to 1341 regular CXR images. The transfer learning method was employed, aided by image augmentation for training and validation of ResNet-50, ResNet-101, Vgg-16 and Vgg-19 architectures. Meanwhile, SqueezeNet was trained from scratch to investigate the importance of transfer learning to the model. The highest training accuracy achieved in this study was 97.38% by the VGG-16 model using a learning rate of 0.01 whereas the highest weighted average accuracy achieved was 94% by the VGG-16 model using a learning rate of 0.01 and the VGG-19 model using a learning rate of 0.001. The reliability and high accuracy of the CNN model would open a new avenue for the diagnosis of Covid-19. © 2021 IEEE

Covid-19 Detection Based on the Fine-Tuned MobileNetv2 Through Lung X-rays

Covid-19 is has become an epidemic, which is affecting millions of people around the world. The common symptoms of Covid-19 are cough and fever, which are very similar to the normal Flu. Covid-19 spreads fast and is devastating for people of all ages especially elderly and people having weak immune system. The standard technique used for Covid-19 detection is real-time polymerase chain reaction (RT-PCR) test. However, RT-PCR is unreliable for Covid-19 detection as it takes long time to detect the disease and it produces considerable number of false positive cases. Therefore, we need to propose an automated and reliable method for Covid-19 detection. Radiographic images are widely used for the detection of various pulmonary diseases such as lung cancer, asthma, pneumonia, etc. We also used chest x-rays for the diagnosis of Covid-19. In this paper, we employed two deep learning models such as SqueezeNet and MobileNetv2 and fine-tuned to check the classification performance. Moreover, we performed data augmentation technique to increase the amount of data and avoid the overfitting of model. We evaluated the performance of the proposed system on standard dataset Covid-19 Radiography dataset that is publicly available. More specifically, we achieved remarkable accuracy of 97%, precision of 95.19%, recall of 100%, specificity of 95%, area under the curve of 98.93%, and F1-score of 97.06% on MobileNetv2. Experimental results and comparative analysis with other existing methods demonstrate that our method is reliable than PT-PCR and other existing state-of-the-art methods for Covid-19 detection. © 2021 IEEE.

Deep Transfer Learning Based Unified Framework for COVID19 Classification and Infection Detection from Chest X-Ray Images.

The presentation of the COVID19 has endangered several million lives worldwide causing thousands of deaths every day. Evolution of COVID19 as a pandemic calls for automated solutions for initial screening and treatment management. In addition to the thermal scanning mechanisms, findings from chest X-ray imaging examinations are reliable predictors in COVID19 detection, long-term monitoring and severity evaluation. This paper presents a novel deep transfer learning based framework for COVID19 detection and segmentation of infections from chest X-ray images. It is realized as a two-stage cascaded framework with classifier and segmentation subnetwork models. The classifier is modeled as a fine-tuned residual SqueezeNet network, and the segmentation network is implemented as a fine-tuned SegNet semantic segmentation network. The segmentation task is enhanced with a bioinspired Gaussian Mixture Model-based super pixel segmentation. This framework is trained and tested with two public datasets for binary and multiclass classifications and infection segmentation. It achieves accuracies of 99.69% and 99.48% for binary and three class classifications, and a mean accuracy of 83.437% for segmentation. Experimental results and comparative evaluations demonstrate the superiority of this unified model and signify potential extensions for biomarker definition and severity quantization.

Deep transfer learning for COVID-19 detection and infection localization with superpixel based segmentation.

The evolution the novel corona virus disease (COVID-19) as a pandemic has inflicted several thousand deaths per day endangering the lives of millions of people across the globe. In addition to thermal scanning mechanisms, chest imaging examinations provide valuable insights to the detection of this virus, diagnosis and prognosis of the infections. Though Chest CT and Chest X-ray imaging are common in the clinical protocols of COVID-19 management, the latter is highly preferred, attributed to its simple image acquisition procedure and mobility of the imaging mechanism. However, Chest X-ray images are found to be less sensitive compared to Chest CT images in detecting infections in the early stages. In this paper, we propose a deep learning based framework to enhance the diagnostic values of these images for improved clinical outcomes. It is realized as a variant of the conventional SqueezeNet classifier with segmentation capabilities, which is trained with deep features extracted from the Chest X-ray images of a standard dataset for binary and multi class classification. The binary classifier achieves an accuracy of 99.53% in the discrimination of COVID-19 and Non COVID-19 images. Similarly, the multi class classifier performs classification of COVID-19, Viral Pneumonia and Normal cases with an accuracy of 99.79%. This model called the COVID-19 Super pixel SqueezNet (COVID-SSNet) performs super pixel segmentation of the activation maps to extract the regions of interest which carry perceptual image features and constructs an overlay of the Chest X-ray images with these regions. The proposed classifier model adds significant value to the Chest X-rays for an integral examination of the image features and the image regions influencing the classifier decisions to expedite the COVID-19 treatment regimen.