Patient-Specific Semi-Supervised Learning for Postoperative Brain Tumor Segmentation

In contrast to preoperative brain tumor segmentation, the problem of postoperative brain tumor segmentation has been rarely approached so far. We present a fully-automatic segmentation method using multimodal magnetic resonance image data and patient-specific semi-supervised learning. The idea behind our semi-supervised approach is to effectively fuse information from both pre- and postoperative image data of the same patient to improve segmentation of the postoperative image. We pose image segmentation as a classification problem and solve it by adopting a semi-supervised decision forest. The method is evaluated on a cohort of 10 high-grade glioma patients, with segmentation performance and computation time comparable or superior to a state-of-the-art brain tumor segmentation method. Moreover, our results confirm that the inclusion of preoperative MR images lead to a better performance regarding postoperative brain tumor segmentation.

Cone beam computed tomography in implant dentistry: a systematic review focusing on guidelines, indications, and radiation dose risks.

PURPOSE The aim of the paper is to identify, review, analyze, and summarize available evidence in three areas on the use of cross-sectional imaging, specifically maxillofacial cone beam computed tomography (CBCT) in pre- and postoperative dental implant therapy: (1) Available clinical use guidelines, (2) indications and contraindications for use, and (3) assessment of associated radiation dose risk. MATERIALS AND METHODS Three focused questions were developed to address the aims. A systematic literature review was performed using a PICO-based search strategy based on MeSH key words specific to each focused question of English-language publications indexed in the MEDLINE database retrospectively from October 31, 2012. These results were supplemented by a hand search and gray literature search. RESULTS Twelve publications were identified providing guidelines for the use of cross-sectional radiography, particularly CBCT imaging, for the pre- and/or postoperative assessment of potential dental implant sites. The publications discovered by the PICO strategy (43 articles), hand (12), and gray literature searches (1) for the second focus question regarding indications and contraindications for CBCT use in implant dentistry were either cohort or case-controlled studies. For the third question on the assessment of associated radiation dose risk, a total of 22 articles were included. Publication characteristics and themes were summarized in tabular format. CONCLUSIONS The reported indications for CBCT use in implant dentistry vary from preoperative analysis regarding specific anatomic considerations, site development using grafts, and computer-assisted treatment planning to postoperative evaluation focusing on complications due to damage of neurovascular structures. Effective doses for different CBCT devices exhibit a wide range with the lowest dose being almost 100 times less than the highest dose. Significant dose reduction can be achieved by adjusting operating parameters, including exposure factors and reducing the field of view (FOV) to the actual region of interest.

Technical complications and failures of zirconia-based prostheses supported by implants followed up to 7 years: a case series.

PURPOSE To evaluate technical complications and failures of zirconia-based fixed prostheses supported by implants. MATERIALS AND METHODS Consecutive patients received zirconia-based single crowns (SCs) and fixed dental prostheses (FDPs) on implants in a private clinical setting between 2005 and 2010. One dentist performed all surgical and prosthetic procedures, and one master technician performed and coordinated all laboratory procedures. One-piece computer-aided design/ computer-assisted manufacture technology was used to fabricate abutments and frameworks, which were directly connected at the implant level, where possible. All patients were involved in a recall maintenance program and were finally reviewed in 2012. Data on framework fractures, chipping of veneering ceramics, and other technical complications were recorded. The primary endpoint was failure of the prostheses, ie, the need for a complete remake. A life table analysis was calculated. RESULTS A total of 289 implants supported 193 zirconia-based prostheses (120 SCs and 73 FDPs) in 127 patients (51 men, 76 women; average age: 62.5 ± 13.4 years) who were reviewed in 2012. Twenty-five (13%) prostheses were cemented on 44 zirconia abutments and 168 (87%) prostheses were screw-retained directly at the implant level. Fracture of 3 frameworks (1 SC, 2 FDPs) was recorded, and significant chipping resulted in the remake of 3 prostheses (1 SC, 2 FDPs). The 7-year cumulative survival rate was 96.4% ± 1.99%. Minor complications comprised 5 loose screws (these were retightened), small chips associated with 3 prostheses (these were polished), and dislodgement of 3 prostheses (these were recemented). Overall, 176 prostheses remained free of technical problems. CONCLUSIONS Zirconia-based prostheses screwed directly to implants are clinically successful in the short and medium term.

A Longitudinal Study of Mental Health in Emerging Adults

Emerging adulthood is a time of instability. This longitudinal study investigated the relationship between mental health and need satisfaction among emerging adults over a period of five years and focused on gender-specific differences. Two possible causal models were examined: (1) the mental health model, which predicts that incongruence is due to the presence of impaired mental health at an earlier point in time; (2) the consistency model, which predicts that impaired mental health is due to a higher level of incongruence reported at an earlier point in time. Emerging adults (N = 1,017) aged 18–24 completed computer-assisted telephone interviews in 2003 (T1), 2005 (T2), and 2008 (T3). The results indicate that better mental health at T1 predicts a lower level of incongruence two years later (T2), when prior level of incongruence is controlled for. The same cross-lagged effect is shown for T3. However, the cross-lagged paths from incongruence to mental health are marginally associated when prior mental health is controlled for. No gender differences were found in the cross-lagged model. The results support the mental health model and show that incongruence does not have a long-lasting negative effect on mental health. The results highlight the importance of identifying emerging adults with poor mental health early to provide support regarding need satisfaction.

Comparison of gadoteric acid and gadobutrol for detection as well as morphologic and dynamic characterization of lesions on breast dynamic contrast-enhanced magnetic resonance imaging

OBJECTIVE In contrast to conventional breast imaging techniques, one major diagnostic benefit of breast magnetic resonance imaging (MRI) is the simultaneous acquisition of morphologic and dynamic enhancement characteristics, which are based on angiogenesis and therefore provide insights into tumor pathophysiology. The aim of this investigation was to intraindividually compare 2 macrocyclic MRI contrast agents, with low risk for nephrogenic systemic fibrosis, in the morphologic and dynamic characterization of histologically verified mass breast lesions, analyzed by blinded human evaluation and a fully automatic computer-assisted diagnosis (CAD) technique. MATERIALS AND METHODS Institutional review board approval and patient informed consent were obtained. In this prospective, single-center study, 45 women with 51 histopathologically verified (41 malignant, 10 benign) mass lesions underwent 2 identical examinations at 1.5 T (mean time interval, 2.1 days) with 0.1-mmol kg doses of gadoteric acid and gadobutrol. All magnetic resonance images were visually evaluated by 2 experienced, blinded breast radiologists in consensus and by an automatic CAD system, whereas the morphologic and dynamic characterization as well as the final human classification of lesions were performed based on the categories of the Breast imaging reporting and data system MRI atlas. Lesions were also classified by defining their probability of malignancy (morpho-dynamic index; 0%-100%) by the CAD system. Imaging results were correlated with histopathology as gold standard. RESULTS The CAD system coded 49 of 51 lesions with gadoteric acid and gadobutrol (detection rate, 96.1%); initial signal increase was significantly higher for gadobutrol than for gadoteric acid for all and the malignant coded lesions (P < 0.05). Gadoteric acid resulted in more postinitial washout curves and fewer continuous increases of all and the malignant lesions compared with gadobutrol (CAD hot spot regions, P < 0.05). Morphologically, the margins of the malignancies were different between the 2 agents, whereas gadobutrol demonstrated more spiculated and fewer smooth margins (P < 0.05). Lesion classifications by the human observers and by the morpho-dynamic index compared with the histopathologic results did not significantly differ between gadoteric acid and gadobutrol. CONCLUSIONS Macrocyclic contrast media can be reliably used for breast dynamic contrast-enhanced MRI. However, gadoteric acid and gadobutrol differed in some dynamic and morphologic characterization of histologically verified breast lesions in an intraindividual, comparison. Besides the standardization of technical parameters and imaging evaluation of breast MRI, the standardization of the applied contrast medium seems to be important to receive best comparable MRI interpretation.

Response to neoadjuvant treatment of invasive ductal breast carcinomas including outcome evaluation: MRI analysis by an automatic CAD system in comparison to visual evaluation

BACKGROUND The aim of this study was to evaluate imaging-based response to standardized neoadjuvant chemotherapy (NACT) regimen by dynamic contrast-enhanced magnetic resonance mammography (DCE-MRM), whereas MR images were analyzed by an automatic computer-assisted diagnosis (CAD) system in comparison to visual evaluation. MRI findings were correlated with histopathologic response to NACT and also with the occurrence of metastases in a follow-up analysis. PATIENTS AND METHODS Fifty-four patients with invasive ductal breast carcinomas received two identical MRI examinations (before and after NACT; 1.5T, contrast medium gadoteric acid). Pre-therapeutic images were compared with post-therapeutic examinations by CAD and two blinded human observers, considering morphologic and dynamic MRI parameters as well as tumor size measurements. Imaging-assessed response to NACT was compared with histopathologically verified response. All clinical, histopathologic, and DCE-MRM parameters were correlated with the occurrence of distant metastases. RESULTS Initial and post-initial dynamic parameters significantly changed between pre- and post-therapeutic DCE-MRM. Visually evaluated DCE-MRM revealed sensitivity of 85.7%, specificity of 91.7%, and diagnostic accuracy of 87.0% in evaluating the response to NACT compared to histopathology. CAD analysis led to more false-negative findings (37.0%) compared to visual evaluation (11.1%), resulting in sensitivity of 52.4%, specificity of 100.0%, and diagnostic accuracy of 63.0%. The following dynamic MRI parameters showed significant associations to occurring metastases: Post-initial curve type before NACT (entire lesions, calculated by CAD) and post-initial curve type of the most enhancing tumor parts after NACT (calculated by CAD and manually). CONCLUSIONS In the accurate evaluation of response to neoadjuvant treatment, CAD systems can provide useful additional information due to the high specificity; however, they cannot replace visual imaging evaluation. Besides traditional prognostic factors, contrast medium-induced dynamic MRI parameters reveal significant associations to patient outcome, i.e. occurrence of distant metastases.

Preliminary Study on Finite Element Simulation for Optimizing Acetabulum Reorientation after Periacetabular Osteotomy

Periacetabular osteotomy (PAO) is an effective approach for surgical treatment of hip dysplasia. The aim of PAO is to increase acetabular coverage of the femoral head and to reduce contact pressures by reorienting the acetabulum fragment after PAO. The success of PAO significantly depends on the surgeon’s experience. Previously, we have developed a computer-assisted planning and navigation system for PAO, which allows for not only quantifying the 3D hip morphology for a computer-assisted diagnosis of hip dysplasia but also a virtual PAO surgical planning and simulation. In this paper, based on this previously developed PAO planning and navigation system, we developed a 3D finite element (FE) model to investigate the optimal acetabulum reorientation after PAO. Our experimental results showed that an optimal position of the acetabulum can be achieved that maximizes contact area and at the same time minimizes peak contact pressure in pelvic and femoral cartilages. In conclusion, our computer-assisted planning and navigation system with FE modeling can be a promising tool to determine the optimal PAO planning strategy.

FACTS: Fully Automatic CT Segmentation of a Hip Joint

Extraction of surface models of a hip joint from CT data is a pre-requisite step for computer assisted diagnosis and planning (CADP) of periacetabular osteotomy (PAO). Most of existing CADP systems are based on manual segmentation, which is time-consuming and hard to achieve reproducible results. In this paper, we present a Fully Automatic CT Segmentation (FACTS) approach to simultaneously extract both pelvic and femoral models. Our approach works by combining fast random forest (RF) regression based landmark detection, multi-atlas based segmentation, with articulated statistical shape model (aSSM) based fitting. The two fundamental contributions of our approach are: (1) an improved fast Gaussian transform (IFGT) is used within the RF regression framework for a fast and accurate landmark detection, which then allows for a fully automatic initialization of the multi-atlas based segmentation; and (2) aSSM based fitting is used to preserve hip joint structure and to avoid penetration between the pelvic and femoral models. Taking manual segmentation as the ground truth, we evaluated the present approach on 30 hip CT images (60 hips) with a 6-fold cross validation. When the present approach was compared to manual segmentation, a mean segmentation accuracy of 0.40, 0.36, and 0.36 mm was found for the pelvis, the left proximal femur, and the right proximal femur, respectively. When the models derived from both segmentations were used to compute the PAO diagnosis parameters, a difference of 2.0 ± 1.5°, 2.1 ± 1.6°, and 3.5 ± 2.3% were found for anteversion, inclination, and acetabular coverage, respectively. The achieved accuracy is regarded as clinically accurate enough for our target applications.

Which Radiographic Hip Parameters Do Not Have to Be Corrected for Pelvic Rotation and Tilt?

Background Acetabular anatomy on AP pelvic radiographsdepends on pelvic orientation during radiograph acquisition. However, not all parameters may change to a clinically relevant degree with differences in pelvic orientation. This issue may influence the diagnosis of acetabular pathologies and planning of corrective acetabular surgery (reorientation or rim trimming). However, to this point, it has not been well characterized. Questions/purposes We asked (1) which radiographic parameters change in a clinical setting when normalized to neutral pelvic orientation; (2) which parameters do not change in an experimental setting when the pelvis is experimentally rotated/tilted; and (3) which of these changes are ‘‘ultimately’’ relevant based on a prespecified definition of relevance. Methods In a clinical setup, 11 hip parameters were evaluated in 101 patients (126 hips) by two observers and the interobserver difference was calculated. All parameters were normalized to an anatomically defined neutral pelvic orientation with the help of a lateral pelvic radiograph and specific software. Differences between nonnormalized and normalized values were calculated (effect of normalization). In an experimental setup involving 20 cadaver pelves (40 hips), the maximum range for each parameter was computed with the pelvis rotated (range, −12° to 12°) and tilted (range, −24° to 24°). ‘‘Ultimately’’ relevant changes existed if the effect of normalization exceeded the interobserver difference (eg, 37% versus 6% for prevalence of a positive crossover sign) and/or the maximum experimental range exceeded 1 SD of interobserver difference (eg, 27% versus 6% for anterior acetabular coverage). Results In the clinical setup, all parameters except the ACM angle and craniocaudal acetabular coverage changed when being normalized, eg, effect of normalization for lateral center-edge angle, acetabular index, and sharp angle ranged from −5° to 4° (p values < 0.029). In the experimental setup, five parameters showed no major changes, whereas six parameters did change (all p values < 0.001). Ultimately relevant changes were found for anteroposterior acetabular coverage, retroversion index, and prevalence of a positive crossover or posterior wall sign. Conclusions Lateral center-edge angle, ACM angle, Sharp angle, acetabular and extrusion index, and craniocaudal acetabular coverage showed no relevant changes with varying pelvic orientation and can therefore be acquired independent from individual pelvic tilt and rotation in clinical practice. In contrast, anteroposterior acetabular coverage, crossover and posterior wall sign, and retroversion index call for specific efforts that address individual pelvic orientation such as computer-assisted evaluation of radiographs. Level of Evidence Level III, diagnostic study. See the Guidelines for Authors for a complete description of levels of evidence.

A complete-pelvis segmentation framework for image-free total hip arthroplasty (THA): methodology and clinical study

Background Complete-pelvis segmentation in antero-posterior pelvic radiographs is required to create a patient-specific three-dimensional pelvis model for surgical planning and postoperative assessment in image-free navigation of total hip arthroplasty. Methods A fast and robust framework for accurately segmenting the complete pelvis is presented, consisting of two consecutive modules. In the first module, a three-stage method was developed to delineate the left hemipelvis based on statistical appearance and shape models. To handle complex pelvic structures, anatomy-specific information processing techniques were employed. As the input to the second module, the delineated left hemi-pelvis was then reflected about an estimated symmetry line of the radiograph to initialize the right hemi-pelvis segmentation. The right hemi-pelvis was segmented by the same three-stage method, Results Two experiments conducted on respectively 143 and 40 AP radiographs demonstrated a mean segmentation accuracy of 1.61±0.68 mm. A clinical study to investigate the postoperative assessment of acetabular cup orientations based on the proposed framework revealed an average accuracy of 1.2°±0.9° and 1.6°±1.4° for anteversion and inclination, respectively. Delineation of each radiograph costs less than one minute. Conclusions Despite further validation needed, the preliminary results implied the underlying clinical applicability of the proposed framework for image-free THA.