ABSTRACT
Dermoscopic images ideally depict pigmentation attributes on the skin surface which is highly regarded in the medical community for detection of skin abnormality, disease or even cancer. The identification of such abnormality, however, requires trained eyes and accurate detection necessitates the process being time-intensive. As such, computerized detection schemes have become quite an essential, especially schemes which adopt deep learning tactics. In this paper, a convolutional deep neural network, S2C-DeLeNet, is proposed, which (i) Performs segmentation procedure of lesion based regions with respect to the unaffected skin tissue from dermoscopic images using a segmentation sub-network, (ii) Classifies each image based on its medical condition type utilizing transferred parameters from the inherent segmentation sub-network. The architecture of the segmentation sub-network contains EfficientNet-B4 backbone in place of the encoder and the classification sub-network bears a 'Classification Feature Extraction' system which pulls trained segmentation feature maps towards lesion prediction. Inside the classification architecture, there have been designed, (i) A 'Feature Coalescing Module' in order to trail and mix each dimensional feature from both encoder and decoder, (ii) A '3D-Layer Residuals' block to create a parallel pathway of low-dimensional features with high variance for better classification. After fine-tuning on a publicly accessible dataset, a mean dice-score of 0.9494 during segmentation is procured which beats existing segmentation strategies and a mean accuracy of 0.9103 is obtained for classification which outperforms conventional and noted classifiers. Additionally, the already fine-tuned network demonstrates highly satisfactory results on other skin cancer segmentation datasets while cross-inference. Extensive experimentation is done to prove the efficacy of the network for not only dermoscopic images but also different medical modalities; which can show its potential in being a systematic diagnostic solution in the field of dermatology and possibly more.
ABSTRACT
Determining the severity level of hypoxemia, the scarcity of saturated oxygen (SpO2) in the human body, is very important for the patients, a matter which has become even more significant during the outbreak of Covid-19 variants. Although the widespread usage of Pulse Oximeter has helped the doctors aware of the current level of SpO2 and thereby determine the hypoxemia severity of a particular patient, the high sensitivity of the device can lead to the desensitization of the care-givers, resulting in slower response to actual hypoxemia event. There has been research conducted for the detection of severity level using various parameters and bio-signals and feeding them in a machine learning algorithm. However, in this paper, we have proposed a new residual-squeeze-excitation-attention based convolutional network (Res-SE-ConvNet) using only Photoplethysmography (PPG) signal for the comfortability of the patient. Unlike the other methods, the proposed method has outperformed the standard state-of-art methods as the result shows 96.5% accuracy in determining 3 class severity problems with 0.79 Cohen Kappa score. This method has the potential to aid the patients in receiving the benefit of an automatic and faster clinical decision support system, thus handling the severity of hypoxemia.