Medical image reconstruction, processing, visualization, and analysis: the MIPG perspective. Medical Image Processing Group

Review of Breast Cancer Pathologigcal Image Processing

Breast cancer is one of the most common malignancies. Pathological image processing of breast has become an important means for early diagnosis of breast cancer. Using medical image processing to assist doctors to detect potential breast cancer as early as possible has always been a hot topic in the field of medical image diagnosis. In this paper, a breast cancer recognition method based on image processing is systematically expounded from four aspects: breast cancer detection, image segmentation, image registration, and image fusion. The achievements and application scope of supervised learning, unsupervised learning, deep learning, CNN, and so on in breast cancer examination are expounded. The prospect of unsupervised learning and transfer learning for breast cancer diagnosis is prospected. Finally, the privacy protection of breast cancer patients is put forward.

Analysis of the anatomy of the maxillary sinus septum using 3-dimensional computed tomography

PURPOSE

Maxillary posterior teeth exhibit a high incidence of periodontal bone and tooth loss. After tooth loss, the edentulous alveolar process of the posterior maxilla is often affected by resorption, which results in loss of vertical bone volume. Moreover, progressive sinus pneumatization leads to a decrease in the alveolar process from the cranial side. The sinus elevation and augmentation surgical technique opened a new way of anchoring endosseous implants despite discernible bone reduction. However, the surgical interventions require in-depth knowledge of maxillary sinus anatomy such as sinus septum and potential variations. The purpose of this study was to investigate the prevalence, location, height, morphology, and orientation of maxillary sinus septa by use of computed tomography (CT) and 3-dimensional imaging.

MATERIALS AND METHODS

Two hundred patients undergoing implant treatment at the Yonsei University College of Dentistry, Seoul, South Korea, were randomly selected for analysis of maxillary sinus septa. CT and DentaScan (GE Medical Systems, Milwaukee, WI)-reformatted data from 400 sinuses were analyzed with the Preview program (Infinitt, Seoul, South Korea). Three-dimensional images were rendered for measurement by use of the Accurex program (CyberMed, Seoul, South Korea).

RESULTS

We found 111 septa in 400 maxillary sinuses (27.7%). This corresponded to 37% of the patients. Among total septa, 25 sinus septa (22.5%) were located in the anterior, 51 (45.9%) in the middle, and 35 (31.5%) in the posterior regions. The directional orientation analyses showed that 106 septa were buccopalatal, 4 were sagittal, and 1 was transverse type. The mean septal heights were 7.78 ± 2.99 and 7.89 ± 3.09 mm in the right and left sinuses, respectively.

CONCLUSION

Three-dimensional CT image analyses may provide useful information that can avoid unnecessary complications during sinus augmentation procedures by facilitating adequate, timely identification of the anatomic structures inherent to the maxillary sinus.

Reliability of tumor volume estimation from MR images in patients with malignant glioma. Results from the American College of Radiology Imaging Network (ACRIN) 6662 Trial

Reliable assessment of tumor growth in malignant glioma poses a common problem both clinically and when studying novel therapeutic agents. We aimed to evaluate two software-systems in their ability to estimate volume change of tumor and/or edema on magnetic resonance (MR) images of malignant gliomas. Twenty patients with malignant glioma were included from different sites. Serial post-operative MR images were assessed with two software systems representative of the two fundamental segmentation methods, single-image fuzzy analysis (3DVIEWNIX-TV) and multi-spectral-image analysis (Eigentool), and with a manual method by 16 independent readers (eight MR-certified technologists, four neuroradiology fellows, four neuroradiologists). Enhancing tumor volume and tumor volume plus edema were assessed independently by each reader. Intraclass correlation coefficients (ICCs), variance components, and prediction intervals were estimated. There were no significant differences in the average tumor volume change over time between the software systems (p > 0.05). Both software systems were much more reliable and yielded smaller prediction intervals than manual measurements. No significant differences were observed between the volume changes determined by fellows/neuroradiologists or technologists.Semi-automated software systems are reliable tools to serve as outcome parameters in clinical studies and the basis for therapeutic decision-making for malignant gliomas, whereas manual measurements are less reliable and should not be the basis for clinical or research outcome studies.

Temporomandibular joint: a methodology of magnetic resonance imaging 3-D reconstruction

OBJECTIVE

The aim of this study was to develop a new method for the 3-dimensional reconstruction of the temporomandibular joint (TMJ) images by means of magnetic resonance imaging (MRI). In a preliminary study, this modality of 3-D representation was tested to evaluate the joint motion.

STUDY DESIGN

Sagittal MRI slices were obtained from a healthy subject. Acquisitions were realized by a spin-echo sequence, with a proton-density weighting and a 2-mm slice thickness. A 3-D reconstruction of the TMJ images was performed.

RESULTS

Three-dimensional representations of the temporomandibular joint were obtained. The depiction of the principal anatomical elements of this joint was realized. A study of TMJ dynamics was also carried out. In this case, movements of the right and left disks and condyles were measured.

CONCLUSION

This 3-D reconstruction methodology allowed a more understandable anatomical description than 2-D images of the TMJ and offered possibilities for joint functional analysis.