Automated Prediction of Malignant Melanoma using Two-Stage Convolutional Neural Network.

PURPOSE: A skin lesion refers to an area of the skin that exhibits anomalous growth or distinctive visual characteristics compared to the surrounding skin. Benign skin lesions are noncancerous and generally pose no threat. These irregular skin growths can vary in appearance. On the other hand, malignant skin lesions correspond to skin cancer, which happens to be the most prevalent form of cancer in the United States. Skin cancer involves the unusual proliferation of skin cells anywhere on the body. The conventional method for detecting skin cancer is relatively more painful. METHODS: This work involves the automated prediction of skin cancer and its types using two stage Convolutional Neural Network (CNN). The first stage of CNN extracts low level features and second stage extracts high level features. Feature selection is done using these two CNN and ABCD (Asymmetry, Border irregularity, Colour variation, and Diameter) technique. The features extracted from the two CNNs are fused with ABCD features and fed into classifiers for the final prediction. The classifiers employed in this work include ensemble learning methods such as gradient boosting and XG boost, as well as machine learning classifiers like decision trees and logistic regression. This methodology is evaluated using the International Skin Imaging Collaboration (ISIC) 2018 and 2019 dataset. RESULTS: As a result, the first stage CNN which is used for creation of new dataset achieved an accuracy of 97.92%. Second stage CNN which is used for feature selection achieved an accuracy of 98.86%. Classification results are obtained for both with and without fusion of features. CONCLUSION: Therefore, two stage prediction model achieved better results with feature fusion.

Case Series - Pediatric Tracheostomy for Upper Airway Obstruction.

Certain congenital craniofacial malformations can cause upper airway obstruction. Due to neurological involvement, these craniofacial deformities with upper airway blockage frequently require tracheostomy. Children who need weeks or months of continuous ventilator assistance require tracheostomies, which improve pulmonary toilet and decrease laryngotracheal lesions such subglottic stenosis and tracheomalacia. In this case report we will be discussing about two patients who underwent Pediatric tracheostomy for Pierre Robin sequence and supraglottic stenosis in our institute. This paper emphasizes on some of the rare causes of pediatric upper airway obstruction - Pierre Robin sequence and supraglottic stenosis. Also the importance of tracheostomy procedure, which is the gold standard for management of upper airway obstruction in patients who are not responding to conservative management is emphasized. Supplementary Information: The online version contains supplementary material available at 10.1007/s12070-023-03892-1.

Pulmonary Vein Stenosis Mimicking Nonspecific Interstitial Pneumonia.

Pulmonary vein stenosis (PVS) is a known complication after catheter ablation of arrhythmias. Surprisingly, little information is available on its manifestations in the lung. We describe the case of a 39-year-old woman who presented from an outside hospital with worsening shortness of breath after catheter ablation of pulmonary veins for atrial fibrillation. After an initial diagnosis of pneumonia and its nonimprovement with antibiotics, a surgical lung biopsy was done and interpreted as nonspecific interstitial pneumonia (NSIP) with vascular changes consistent with pulmonary arterial hypertension. Later, she was admitted to our institution where a transthoracic echocardiogram (TTE) and subsequent computed tomography (CT) angiogram of the heart showed severe stenosis of all four pulmonary veins. The previous lung biopsy was rereviewed and reinterpreted as severe parenchymal congestion mimicking NSIP. Our case demonstrates that PVS is an underrecognized complication of catheter ablation, and increased awareness among both clinicians and pathologists is necessary to avoid misdiagnosis.