Classification of Breast Cancer Histopathological Images Using DenseNet and Transfer Learning.

Breast cancer is one of the most common invading cancers in women. Analyzing breast cancer is nontrivial and may lead to disagreements among experts. Although deep learning methods achieved an excellent performance in classification tasks including breast cancer histopathological images, the existing state-of-the-art methods are computationally expensive and may overfit due to extracting features from in-distribution images. In this paper, our contribution is mainly twofold. First, we perform a short survey on deep-learning-based models for classifying histopathological images to investigate the most popular and optimized training-testing ratios. Our findings reveal that the most popular training-testing ratio for histopathological image classification is 70%: 30%, whereas the best performance (e.g., accuracy) is achieved by using the training-testing ratio of 80%: 20% on an identical dataset. Second, we propose a method named DenTnet to classify breast cancer histopathological images chiefly. DenTnet utilizes the principle of transfer learning to solve the problem of extracting features from the same distribution using DenseNet as a backbone model. The proposed DenTnet method is shown to be superior in comparison to a number of leading deep learning methods in terms of detection accuracy (up to 99.28% on BreaKHis dataset deeming training-testing ratio of 80%: 20%) with good generalization ability and computational speed. The limitation of existing methods including the requirement of high computation and utilization of the same feature distribution is mitigated by dint of the DenTnet.

Developing a mobile application to better inform patients and enable effective consultation in implant dentistry.

The field of dentistry lacks satisfactory tools to help visualize planned procedures and their potential results to patients. Dentists struggle to provide an effective image in their patient's mind of the end results of the planned treatment only through verbal explanations. Thus, verbal explanations alone often cannot adequately help the patients make a treatment decision. Inadequate attempts are frequently made by dentists to sketch the procedure for the patient in an effort to depict the treatment. These attempts however require an artistic ability not all dentists have. Real case photographs are sometimes of help in explaining and illustrating treatments. However, particularly in implant cases, real case photographs are often ineffective and inadequate. The purpose of this study is to develop a mobile application with an effective user interface design to support the dentist-patient interaction by providing the patient with illustrative descriptions of the procedures and the end result. Sketching, paper prototyping, and wire framing were carried out with the actual user's participation. Hard and soft dental tissues were modeled using three dimensional (3D) modeling programs and real cases. The application enhances the presentation to the patients of potential implants and implant supported prosthetic treatments with rich 3D illustrative content. The application was evaluated in terms of perceived ease of use and perceived usefulness through an online survey. The application helps improve the information sharing behavior of dentists to enhance the patients' right to make informed decisions. The paper clearly demonstrates the relevance of interactive communication technologies for dentist-patient communication.