Systematic approach for content and construct validation: Case studies for arthroscopy and laparoscopy.

BACKGROUND: In minimally invasive surgery, there are several challenges for training novice surgeons, such as limited field-of-view and unintuitive hand-eye coordination due to performing the operation according to video feedback. Virtual reality (VR) surgical simulators are a novel, risk-free, and cost-effective way to train and assess surgeons. METHODS: We developed VR-based simulations to accurately assess and quantify performance of two VR simulations: gentleness simulation for laparoscopy and rotator cuff repair for arthroscopy. We performed content and construct validity studies for the simulators. In our analysis, we systematically rank surgeons using data mining classification techniques. RESULTS: Using classification algorithms such as K-Nearest Neighbors, Support Vector Machines, and Logistic Regression we have achieved near 100% accuracy rate in identifying novices, and up to an 83% accuracy rate identifying experts. Sensitivity and specificity were up to 1.0 and 0.9, respectively. CONCLUSION: Developed methodology to measure and differentiate the highly ranked surgeons and less-skilled surgeons.

Texture based skin lesion abruptness quantification to detect malignancy.

BACKGROUND: Abruptness of pigment patterns at the periphery of a skin lesion is one of the most important dermoscopic features for detection of malignancy. In current clinical setting, abrupt cutoff of a skin lesion determined by an examination of a dermatologist. This process is subjective, nonquantitative, and error-prone. We present an improved computational model to quantitatively measure abruptness of a skin lesion over our previous method. To achieve this, we quantitatively analyze the texture features of a region within the lesion boundary. This region is bounded by an interior border line of the lesion boundary which is determined using level set propagation (LSP) method. This method provides a fast border contraction without a need for extensive boolean operations. Then, we build feature vectors of homogeneity, standard deviation of pixel values, and mean of the pixel values of the region between the contracted border and the original border. These vectors are then classified using neural networks (NN) and SVM classifiers. RESULTS: As lower homogeneity indicates sharp cutoffs, suggesting melanoma, we carried out our experiments on two dermoscopy image datasets, which consist of 800 benign and 200 malignant melanoma cases. LSP method helped produce better results than Kaya et al., 2016 study. By using texture homogeneity at the periphery of a lesion border determined by LSP, as a classification results, we obtained 87% f1-score and 78% specificity; that we obtained better results than in the previous study. We also compared the performances of two different NN classifiers and support vector machine classifier. The best results obtained using combination of RGB color spaces with the fully-connected multi-hidden layer NN. CONCLUSIONS: Computational results also show that skin lesion abrupt cutoff is a reliable indicator of malignancy. Results show that computational model of texture homogeneity along the periphery of skin lesion borders based on LSP is an effective way of quantitatively measuring abrupt cutoff of a lesion.