Biomedical Sensing System Based on Image Analysis

Dear Colleagues,

Medical images are one of the most important sources of biomedical sensing data, including radiological images, pathological images and photographs of affected areas with special instruments. The sensor system developed based on medical images can not only integrate multi-modal medical data information to realize real-time monitoring of patients' conditions, but also predict patients' prognosis and even rehabilitation. In addition, biomedical sensing systems based on medical images offer the possibility of a standardized disease assessment that removes subjective judgments. In particular, some new techniques are introduced in this domain, such as Medical Image Processing Knowledge Editing for LLM Aircraft Detection and Recognition with Few-Shot Medical Image Segmentation based on domain adaption multi-omics information integration and Infrared Small Target Detection. Finally, we welcome the submission of manuscripts to our Special Issue on (but not limited to) the following topics:

1. Test and analysis of the application effect of medical image key point detection algorithms;
2. Test and analysis of the application effect of medical image segmentation algorithms;
3. Test and analysis of the application effect of medical image target classification algorithms;
4. The application of artificial intelligence in this digital measurement of human anatomy;
5. Application of artificial intelligence in the diagnosis of coronary heart disease;
6. Application of artificial intelligence in the diagnosis of pulmonary nodules;
7. Application of human intelligence in spinal measurement;
8. Calculation of the risk of disease or other unexpected events for healthy people or patients based on medical images;
9. Use of real-time medical images to detect disease in patients, so as to assist treatment or provide an early warning of changes in patients' conditions;
10. Perform diagnosis and differential diagnosis through medical images during the course of the disease, assist in the formulation of medical plans and predict the prognosis of patients;
11. Based on medical images, evaluate the information that is difficult to obtain manually on images, including molecular biological characteristics and metabolites;
12. Adopt new methods, semi-automatic or fully automatic medical information extraction, so as to improve efficiency.

Dr. Chen Li
Prof. Dr. Marcin Grzegorzek
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at mdpi.longhoe.net by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• medical image analysis
• image classification
• image segmentation
• object detection
• feature extraction

Title: DEIT based bone position and orientation estimation for roboticsupport in total knee atrhroplasty - a simulation study
Authors: Jakob Schrott; Sabrina Affortunati; Christian Stadler; Christoph Hintermüller
Affiliation: Institute for Biomedical Mechatronics, Johannes Kepler University, Linz
Abstract: Total knee arthroplasty (TKA) is a well-established and successful treatment option for patients with end stage osteoarthritis of the knee providing high patient satisfaction. Robotic systems have been widely adopted to perform TKA in orthopedic centers. The exact spatial position of the femur and tibia is usually determined through pinned trackers, providing the surgeon with an exact illustration of the axis of the lower limb. The drilling holes required for mounting the trackers creates weak spots, causing adverse events such as bone fracture. In this study time differential electrical impedance tomography is used to locate the femur positions. Thereby the difference in conductivity distribution between two distinct states s_0 and s_1 of the measured object is reconstructed. The overall approach was tested by simulating 5 different configurations of thigh shape and considered tissue conductivity distributions. For the cylinder based models the reconstructed position deviated by about ≈ 1 mm from the actual bone center and in case of models mimicking a realistic cross section of the femur position deviated between 7.9 mm 24.8 mm. For all models the bone axis was off by about φ = 1.50 ◦ from its actual position.

Title: The VLSI design of Biomedical Image Analysis for Skin Cancer
Authors: Shih-Lun Chen
Affiliation: Chung Yuan Christian University
Abstract: The skin constitutes the largest human organ. Neglecting abnormal skin changes or moles can lead to the development of skin diseases, with melanoma being the most lethal among them. This study aims to eliminate image noise in skin surface images through preprocessing and image compression to reduce data volume and expedite image processing operations. Furthermore, feature enhancement is conducted to segment lesion identification, utilizing image asymmetry, color, and texture features as identification bases. Ultimately, skin disease identification is achieved. Among existing architectures, a MATLAB implementation utilizing machine learning approaches achieves 99.2% accuracy. Through the proposed Very Large-Scale Integration (VLSI) design employing supervised machine learning, the model utilizes a predefined threshold for melanoma and nevus identification, resulting in remarkably high efficiency. This threshold is calculated using MATLAB. Consequently, it is recommended for future endeavors to utilize the current system architecture for VLSI design realization without compromising accuracy. Verification of VLSI results is performed on the FPGA version of Intel's HAN Pilot Platform.