Objectives. Fetal sex determination with ultrasound (US) examination is indicated in pregnancies at risk of X‐linked genetic disorders or ambiguous genitalia. However, misdiagnoses often arise due to operator inexperience and technical difficulties while acquiring diagnostic images. We aimed to develop an efficient automated US‐based fetal sex classification model that can facilitate efficient screening and reduce misclassification.Methods. We have developed a novel feature engineering model termed PFP‐LHCINCA that employs pyramidal fixed‐size patch generation with average pooling‐based image decomposition, handcrafted feature extraction based on local phase quantization (LPQ), and histogram of oriented gradients (HOG) to extract directional and textural features and used Chi‐square iterative neighborhood component analysis feature selection (CINCA), which iteratively selects the most informative feature vector for each image that minimizes calculated feature parameter‐derived k‐nearest neighbor‐based misclassification rates. The model was trained and tested on a sizeable expert‐labeled dataset comprising 339 males’ and 332 females’ fetal US images. One transverse fetal US image per subject zoomed to the genital area and standardized to 256 × 256 size was used for analysis. Fetal sex was annotated by experts on US images and confirmed postnatally.Results. Standard model performance metrics were compared using five shallow classifiers—k‐nearest neighbor (kNN), decision tree, naïve Bayes, linear discriminant, and support vector machine (SVM)—with the hyperparameters tuned using a Bayesian optimizer. The PFP‐LHCINCA model achieved a sex classification accuracy of ≥88% with all five classifiers and the best accuracy rates (>98%) with kNN and SVM classifiers.Conclusions. US‐based fetal sex classification is feasible and accurate using the presented PFP‐LHCINCA model. The salutary results support its clinical use for fetal US image screening for sex classification. The model architecture can be modified into deep learning models for training larger datasets.
Objectives: Breast cancer (BCA) is one of the world’s most prevalent cancer and the top cause of mortality. For many decades, mammography has been used routinely for screening of early breast cancer and diagnosing symptomatic patients. The main purpose of this work is to investigate the usefulness of machine learning techniques using mammography images. Methods: A total of 194 patients who underwent ultrasound examination after observing suspicious lesions on mammography images and were diagnosed with BCA by ultrasound-guided core needle biopsy were included in the study. A set of mammography images with complete cancer subtypes was used. A transfer learning-based computer vision method was adopted in this study. AlexNet was to extract the features and select the most significant features using a feature selection function. Our deep learning-based model attained more than 80% accuracy in classifying malignant and benign cancers. However, the employed deep learning model cannot classify subtypes accurately. Results: Per the results, the commonly used image classification model is highly accurate in distinguishing malignant and benign changes, however unable to classify cancer subtypes. Conclusions: In conclusion, machine learning can still not simulate conventional immunohistochemistry subtyping using tissue biopsy.