Application of MRI Image Based on Computer Semiautomatic Segmentation Algorithm in the Classification Prediction of Breast Cancer Histology

Objective. The study aimed to investigate the predictive classification accuracy of computer semiautomatic segmentation algorithm for the histological grade of breast tumors through the magnetic resonance imaging (MRI) examination. Methods. Five dynamic contrast-enhanced (DCE) MRI regions of interest (ROIs) were captured using computer semiautomatic segmentation method, referring to the entire tumor area, tumor border area, proximal gland area, middle gland area, and distal gland area. According to the mutual information maximum protocol, the corresponding five ROIs were extracted from diffusion weighted imaging (DWI) combined with DCE-MRI images. To use the features in the nonoverlapping area of DWI image and DCE-MRI image as elements, a single-variable logistic regression model was established corresponding to element characteristics. After multiple training, the model was evaluated using the receiver operating characteristic (ROC) curve and area under curve (AUC). Results. This DCE-MRI combined with DWI was superior to DCE-MRI and DW in the prediction of tumor area features. To use DCE-MRI or DWI alone was less effective than DCE-MRI combined with DWI. The DWI combined DCE-MRI demonstrated good regional segmentation effects in the tumour area, with luminal A value being 0.767 and the area under curve (AUC) value being 0.758. After optimization, the AUC value of the tumor area was 0.929, indicating that classification effects can be enhanced by combining the two imaging methods, which complemented each other. Conclusions. The DWI combined DCE-MRI imaging has improved the early diagnosis effects of breast cancer by predicting the occurrence of breast cancer through the labeling of biomarkers.

An Automatic Knee Osteoarthritis Diagnosis Method Based on Deep Learning: Data from the Osteoarthritis Initiative

Osteoarthritis (OA) is the most common form of arthritis. According to the evidence presented on both sides of the knee bones, radiologists assess the severity of OA based on the Kellgren–Lawrence (KL) grading system. Recently, computer-aided methods are proposed to improve the efficiency of OA diagnosis. However, the human interventions required by previous semiautomatic segmentation methods limit the application on large-scale datasets. Moreover, well-known CNN architectures applied to the OA severity assessment do not explore the relations between different local regions. In this work, by integrating the object detection model, YOLO, with the visual transformer into the diagnosis procedure, we reduce human intervention and provide an end-to-end approach to automatic osteoarthritis diagnosis. Our approach correctly segments 95.57% of data at the expense of training on 200 annotated images on a large dataset that contains more than 4500 samples. Furthermore, our classification result improves the accuracy by 2.5% compared to the traditional CNN architectures.

Hybrid Additive Fabrication of a Transparent Liver with Biosimilar Haptic Response for Preoperative Planning

Due to the complexity of liver surgery, the interest in 3D printing is constantly increasing among hepatobiliary surgeons. The aim of this study was to produce a patient-specific transparent life-sized liver model with tissue-like haptic properties by combining additive manufacturing and 3D moulding. A multistep pipeline was adopted to obtain accurate 3D printable models. Semiautomatic segmentation and registration of routine medical imaging using 3D Slicer software allowed to obtain digital objects representing the structures of interest (liver parenchyma, vasculo-biliary branching, and intrahepatic lesion). The virtual models were used as the source data for a hybrid fabrication process based on additive manufacturing using soft resins and casting of tissue-mimicking silicone-based blend into 3D moulds. The model of the haptic liver reproduced with high fidelity the vasculo-biliary branching and the relationship with the intrahepatic lesion embedded into the transparent parenchyma. It offered high-quality haptic perception and a remarkable degree of surgical and anatomical information. Our 3D transparent model with haptic properties can help surgeons understand the spatial changes of intrahepatic structures during surgical manoeuvres, optimising preoperative surgical planning.

A volumetric study of mandibular condyles in orthognathic patients by semiautomatic segmentation

Purpose This study was conducted to elucidate volumetric data of mandibular condyles of orthognathic patients by analyzing cone beam computed tomography images based upon semiautomatic segmentation. Methods Cone beam computed tomography images of 87 patients with malocclusions were analyzed in this retrospective study. Patients were between 17 and 53 years old and diagnosed with Angle class I, II, or III malocclusion. By using the validated open-source software “ITK-SNAP,” the volumetric measurements of 174 mandibular condyles were performed. Volumetric analysis was performed according to intra-subject side differences by paired Student t test. In accordance to inter-subject side, gender, age and type of malocclusion differences bivariate analysis and ANOVA were applied. Results The mean volume for the right condyle was 1.378 ± 0.447 cm3, with a maximum of 2.379 cm3 and a minimum of 0.121 cm3. The mean volume for the left side was 1.435 ± 0.474 cm3, with a maximum of 3.264 cm3 and a minimum of 0.109 cm3. Bivariate analysis indicated a highly significant inter-subject difference between the volume of the left and right mandibular condyles (p < 0.01). Females had a significantly smaller condyle volume than males (p < 0.05 left condyle; p < 0.01 right condyle). Conclusion The fact that shape and volume of mandibular condyles show a high susceptibility to pathological alterations and particularly malocclusions makes a precise knowledge about volumetric changes indispensable. Our results show that significant inter-subject differences in condyle volume could be found with respect to the side and gender. Larger volumes could be assessed for the left condyle and for male patients.

Manual versus semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging: evaluation of similarity and comparison of segmentation times

Objective: To evaluate the degree of similarity between manual and semiautomatic segmentation of soft-tissue sarcomas on magnetic resonance imaging (MRI). Materials and Methods: This was a retrospective study of 15 MRI examinations of patients with histopathologically confirmed soft-tissue sarcomas acquired before therapeutic intervention. Manual and semiautomatic segmentations were performed by three radiologists, working independently, using the software 3D Slicer. The Dice similarity coefficient (DSC) and the Hausdorff distance were calculated in order to evaluate the similarity between manual and semiautomatic segmentation. To compare the two modalities in terms of the tumor volumes obtained, we also calculated descriptive statistics and intraclass correlation coefficients (ICCs). Results: In the comparison between manual and semiautomatic segmentation, the DSC values ranged from 0.871 to 0.973. The comparison of the volumes segmented by the two modalities resulted in ICCs between 0.9927 and 0.9990. The DSC values ranged from 0.849 to 0.979 for intraobserver variability and from 0.741 to 0.972 for interobserver variability. There was no significant difference between the semiautomatic and manual modalities in terms of the segmentation times (p > 0.05). Conclusion: There appears to be a high degree of similarity between manual and semiautomatic segmentation, with no significant difference between the two modalities in terms of the time required for segmentation.

Esophagus-to-posterior Atrial wall relationship: pre- and Intra-procedural three-dimensional multimodality imaging for esophageal position

Funding Acknowledgements Type of funding sources: Private grant(s) and/or Sponsorship. Main funding source(s): Dr Teres was funded by the research fellowship grant of the Swiss Heart Rhythm Foundation. Dr Carreno-Lineros was funded by a Scholarship from Sociedad Española de Cardiología (SEC). Introduction pulmonary vein isolation (PVI) approach implies unavoidable ablation on the posterior atrial wall which is closely related to the esophagus. PVI may result in several complications. Objective the present study aims to analyze the stability of the esophageal position inside the mediastinum at the level of the posterior atrial wall from one procedure to another (Redo group) and during a single procedure (multi-image group). Methods the esophageal position was compared in two groups. First, pre-procedural multidetector computerized tomography (MDCTs) of the first PVI and the redo intervention (Redo group) were segmented with ADAS 3D™ software to compare the esophageal position and the atrio-esophageal distance prints (Figure A). Second, three imaging modalities were compared for the same procedure (multi-image group): i) preprocedural MDCT; ii) intraprocedural fluoroscopy obtained with the TEE probe in place in three projections with CARTOUNIVU™ (Biosense Webster); and iii) esophageal fast-anatomical map (FAM) obtained at the end of the procedure (Figure D). Ablation procedures were performed under general anesthesia. Exclusion criteria were unavailability or contraindication to obtain any of the techniques. The 3D correlation of the esophageal position acquired with different techniques, was computed in Matlab using semiautomatic segmentation analysis. Results 35 patients were analyzed for the Redo group. Mean age 61 ± 10 years, 17 (65%) male, mean LVEF 57 ± 7%, mean LA diameter 43 ± 5 mm, median time since previous ablation (and therefore between MDCT acquisitions) was 6 months (IQR 3-9). Mean atrio-esophageal distance for both MDCTs was 1.2 ± 0.6 mm . The esophageal trajectory as related to the atrial posterior wall was left for 20 (57%) patients, central for 6 (18%) patients, and right for 3 (9%) patients, left-central for 4 (11%) patients, and right-central for 2 (5%) patients. There was a 91 ± 5% correlation on the esophageal position between the first procedure and the redo procedure MDCT. In 3 cases the position was clearly different with a correlation of only 40 ± 22%. The multi-imaging group was composed of 100 patients, mean age 61 ± 10 years, 17 (65%) male, mean LVEF 56 ± 7%, mean LA diameter 39 ± 6 mm. The esophageal trajectory as related to the atrial posterior wall was left for 55 (55%) patients, central for 23 (23%) patients, and right for 9 (9%) patients, left-central for 8 (8%) patients, and right-central for 5 (5%) patients. The correlation between MDCT and CARTOUNIVU™ was 82 ± 10% (Figure B); between MDCT and ESOFAM 80 ± 12% (Figure B); and between ESOFAM and CARTOUNIVU™ 83 ± 15% (Figure C). Conclusions There is a high stability of the esophageal position between procedures and from the beginning to the end of procedure. This observation needs to be tested for its clinical utility by designing studies that take into account the esophagus distance print to modulate RF delivery Abstract Figure. Multimodal Esophageal imaging

Novel three-dimensional methods to analyze the morphology of the nasal cavity and pharyngeal airway

ABSTRACT Objectives To assess the intraexaminer and interexaminer reliabilities of novel semiautomatic methods to segment the nasal cavity (NC) and pharyngeal airway (PA) and to determine the minimal cross-sectional area (CS) and hydraulic diameter (HD) of the PA. Materials and Methods To test reproducibility, two examiners analyzed the NC and PA independently in 10 retrospectively selected cone beam computed tomography (CBCT) images using semiautomatic segmentation. The PA centerline was determined to assess the minimal CS and HD. The intraclass correlation coefficient (ICC) was used to calculate intraexaminer and interexaminer reliabilities. Measurement errors were assessed by Dahlberg's formula and paired t-tests. The level of agreement was assessed using the Bland-Altman method. Results Intraexaminer and interexaminer reliabilities were excellent (minimal ICC, 0.960). The error of the method was good except for interexaminer values for the oropharynx (P = .016). The minimal CS and HD measurements were reliable (minimal ICC, 0.993; narrow limits of agreement). Conclusions The novel methods for analysis of the NC and PA are reliable. The minimal CS and HD demonstrated excellent reliabilities, which are critical to detect the most constricted part of the PA. Separation of the oropharynx from the voids close to the retroglossal area is not trivial and should be considered with caution.