Purpose: A novel and unconventional approach to a machine learning challenge was designed to spread knowledge, identify robust methods and highlight potential pitfalls about machine learning within the Medical Physics community.
Methods: A public dataset comprising 41 radiomic features and 535 patients was employed to assess the potential of radiomics in distinguishing between primary lung tumors and metastases. Each participant developed two classification models using: (i) all features (base model); (ii) only robust features (robust model).
Background: To address the numerous unmeet clinical needs, in recent years several Machine Learning models applied to medical images and clinical data have been introduced and developed. Even when they achieve encouraging results, they lack evolutionary progression, thus perpetuating their status as autonomous entities. We postulated that different algorithms which have been proposed in the literature to address the same diagnostic task, can be aggregated to enhance classification performance.
View Article and Find Full Text PDFShoulder pain is a serious clinical disease frequently related to absence from work. It is characterized by pain and stiffness, probably connected to the presence of an inflammatory substrate involving gleno-humeral capsule and collagen tissues. A physiotherapy program has shown to be effective for the conservative treatment of this disorder.
View Article and Find Full Text PDFInguinal hernias containing the appendix are rare, but even more exceptional is the occurrence of complicated appendicitis within the hernial sac with a cutaneous fistula. We report the case of a man in his 50s presenting to the emergency department with a right-sided erythematous and painful inguinal swelling secreting seropurulent material. A perforated appendix within an inguinal hernia complicated by an appendico-cutaneous fistula was diagnosed.
View Article and Find Full Text PDF