Search

Lifestyle and early diagnosis can bring a drastic change in Cervical cancer patient Infections when diagnosed early enough that makes it easy to prevent. By the time symptoms appear, cancer might have manifested itself and begun to spread. Due to poor access to preventive and treatment services, a vast number of unfortunate deaths occur needlessly. Enhancing the prevalent method of treatment and diagnosis, deep learning models have been proved to be more precise and accurate than mere Visual Inspection by specialists. AI-assisted colposcopy reduces time and effort it takes for a gynecologist to gain an expertise and thus spares more time to improve other skills, training and activities.Here, we use Supervised(unsupervised) algorithms in order to classify the colposcopy images. To attain our target, we collect a large number of image datasets requested to ABC hospital and are categorized by our system to different stages of cancer, results of which can be further analyzed by specialists to imply appropriate clinical procedures of cure. The successful deployment promotes low-cost mobile technology to facilitate millions of women across the country who earlier had limited access to life-saving cancer tests. As the morbidity and mortality rates of cervix cancer are pretty high, early detection and treatment of the abnormal tissues or pre-cancerous cells is the ultimate solution to it. This study is useful to diagnose an early metamorphosis of cancerous cells more accurately and hence helps to drop down the death rate even in any low-middle resources areas of the country. Keywords: Cervical Cancer, Deep learning, Colposcopy, Pap smear and HPV

Paper-based analytical devices (PADs) employing colorimetric detection and smartphone images have gained wider acceptance in a variety of measurement applications. The PADs are primarily meant to be used in field settings where assay and imaging conditions greatly vary resulting in less accurate results. Recently, machine learning (ML) assisted models have been used in image analysis. We evaluated a combinations of four ML models - logistic regression, support vector machine, random forest, and artificial neural network, and three image color spaces - RGB, HSV, and LAB for their ability to accurately predict analyte concentrations. We used images of PADs taken at varying lighting conditions, with different cameras, and users for food color and enzyme inhibition assays to create training and test datasets. Prediction accuracy was higher for food color than enzyme inhibition assays in most of the ML model and colorspace combinations. All models better predicted coarse level classification than fine grained concentration labels. ML models using sample color along with a reference color increased the models’ ability in predicting the result in which the reference color may have partially factored out the variation in ambient assay and imaging conditions. The best concentration label prediction accuracy obtained for food color was 0.966 when using ANN model and LAB colorspace. The accuracy for enzyme inhibition assay was 0.908 when using SVM model and LAB colorspace. Appropriate model and colorspace combinations can be useful to analyze large numbers of samples on PADs as a powerful low-cost quick field-testing tool.

Scoliosis is a common medical condition, which occurs most often during the growth spurt just before puberty. Untreated Scoliosis may cause long-term sequelae. Therefore, accurate automated quantitative estimation of spinal curvature is an important task for the clinical evaluation and treatment planning of Scoliosis. A couple of attempts have been made for automated Cobb angle estimation on single-view x-rays. It is very challenging to achieve a highly accurate automated estimation of Cobb angles because it is difficult to utilize x-rays efficiently. With the idea of developing methods for accurate automated spinal curvature estimation, AASCE2019 challenge provides spinal anterior-posterior x-ray images with manual labels for training and testing the participating methods. We review eight top-ranked methods from 12 teams. Experimental results show that overall the best performing method achieved a symmetric mean absolute percentage (SMAPE) of 21.71%. Limitations and possible future directions are also described in the paper. We hope the dataset in AASCE2019 and this paper could provide insights into quantitative measurement of the spine.