Axial Plane Images Research Articles

Feasibility of an artificial intelligence system for tumor response evaluation

PurposeThe objective of this study was to evaluate the feasibility of using Artificial Intelligence (AI) to measure the long-diameter of tumors for evaluating treatment response.MethodsOur study included 48 patients with lung-specific target lesions and conducted 277 measurements. The radiologists recorded the long-diameter in axial imaging plane of the target lesions for each measurement. Meanwhile, AI software was utilized to measure the long-diameter in both the axial imaging plane and in three dimensions (3D). Statistical analyses including the Bland-Altman plot, Spearman correlation analysis, and paired t-test to ascertain the accuracy and reliability of our findings.ResultsThe Bland-Altman plot showed that the AI measurements had a bias of -0.28 mm and had limits of agreement ranging from − 13.78 to 13.22 mm (P = 0.497), indicating agreement with the manual measurements. However, there was no agreement between the 3D measurements and the manual measurements, with P < 0.001. The paired t-test revealed no statistically significant difference between the manual measurements and AI measurements (P = 0.497), whereas a statistically significant difference was observed between the manual measurements and 3D measurements (P < 0.001).ConclusionsThe application of AI in measuring the long-diameter of tumors had significantly improved efficiency and reduced the incidence of subjective measurement errors. This advancement facilitated more convenient and accurate tumor response evaluation.

Significant systematic bias of alpha angles measured on MRI compared to various radiographic views in patients with femoroacetabular impingement syndrome.

The aim of this study was to assess the inter-rater reproducibility and inter-method comparability of hip alpha angle measurements on magnetic resonance imaging (MRI)/magnetic resonance arthrography (MRA) and plain radiographs in patients with femoroacetabular impingement syndrome (FAIS). A cross-sectional study of patients who were diagnosed with symptomatic FAIS underwent preoperative MRI/MRA with axial oblique and/or radial plane imagingand had preoperative radiographs with anterior-posterior (AP), 45° Dunnand 90° Dunn views. Alpha angle measurements were performed independently by two musculoskeletal radiologists. Inter-rater reproducibility and inter-method comparability between MRI/MRA images and radiographic views were assessed using the intraclass correlation coefficient (ICC) with 95% confidence interval (CI). Ninety-seven patients were included of whom 93 (95.8%) received axial oblique plane images and 54 (55.6%) had radial plane MRI/MRA images. Inter-rater reproducibility was excellent (ICC > 0.9) for all planes on MRI/MRA and radiographs. MRI/MRA axial oblique images had poor (ICC 0.39, 95% CI [0.09, 0.59]), moderate (ICC 0.57, 95% CI [0.18, 0.75])and moderate (ICC 0.64, 95% CI [0.20, 0.81]) comparability with AP, 45° Dunnand 90° Dunn, respectively. MRI/MRA radial plane images had equivocal (0 included in all CIs) comparability with AP (ICC 0.66), 45° Dunn (ICC 0.35)and 90° Dunn (ICC 0.14) radiographs. On average, alpha angle measurements were significantly higher with radial images and lower with axial oblique images, when compared to all radiographic views (p < 0.05), except axial oblique versus 45° Dunn views, where angles measured on axial oblique were significantly larger. Alpha angle measurements taken on axial oblique MRI/MRA images show moderate comparability to radiographic 45° Dunnand 90° Dunn views despite negative bias to measurements taken on radiographic AP and 45° Dunn view. Larger alpha angles were appreciated on MRI/MRA radial and axial oblique views compared to radiographic views supporting the inclusion of MRI/MRA alpha angle measurements to properly identify deformity. Level II.

Patellar articular overlap is better associated with patellar alignment during weight-bearing than traditional measures of patellar height

BackgroundA consequence of a high riding patella is reduced osseous stability and malalignment of the patella (i.e., lateral patellar tilt and displacement). Although quantification of patellar height is a routine part of the radiographic examination of the patellofemoral joint, it is not clear which measure of patellar height is best associated with patella alignment. Hypothesis/PurposeTo determine if patellar articular overlap (PAO) is better associated with lateral patellar tilt and lateral patellar displacement compared to traditional measures of patellar height. Study Design: Cross-sectional. MethodsMagnetic resonance images were obtained from 50 female participants (21 with patellofemoral pain and 29 healthy controls) under loaded conditions (25–35% bodyweight) at 15–20 degrees of knee flexion. Measurements of lateral patellar tilt and displacement as well as the PAO, Insall-Salvati ratio (ISV), Caton Deschamps-index (CD-index), or the Blacburn Peel-index (BP-index) were obtained from sagittal and axial plane images. ResultsThe PAO was found to significantly correlated with lateral patellar tilt (r = −0.77, p < 0.001). In contrast, the ISV, CD-index, or the BP-index were not found to be associated with lateral patellar tilt (r = 0.13, p = 0.34; r = −0.14, p = 0.33; r = −0.08, p = 0.56, respectively). Both the PAO and ISV were found to be significantly correlated with lateral patellar displacement (r = −0.52, p < 0.001; r = 0.43, p = 0.002, respectively). Conversely, the CD-index and BP-index were not found to be associated with lateral patellar displacement (r = 0.03 p = 0.83; r = 0.05 p = 0.74, respectively). ConclusionOf the measures of patellar height evaluated, the PAO was found to provide the greatest association with lateral patellar tilt and displacement.

Coronal Plane Assessment for Levator Trauma.

Levator avulsion is a major etiological factor of pelvic organ prolapse (POP) and is primarily diagnosed on tomographic axial plane imaging. Two-dimensional imagingcan also image the levator. The objective was to test reproducibility and validity of coronal plane assessment for diagnosis of levator trauma by assessing the coronal plane obtained on tomographic ultrasound imaging. A retrospective study of women who had undergone an interview, POPQ and four-dimensional translabial ultrasound at a tertiary urogynecological unit. Post-processing of archived volume data was performed for assessment; and levator muscle area and estimate of remnant muscle mass in the coronal plane. Interobserver reproducibility of the latter two measures and associations between various measures of levator trauma and POP were tested. Interobserver agreement was good for percentage estimates (ICC 0.743), but fair for area measurements (ICC 0.482). Six hundred and twenty four women were seen, 468 (75%) had significant clinical prolapse. Full levator avulsions were diagnosed in 137 (22%). Mean TTS was 2.7 (range 0-12). On coronal plane assessment average muscle area was 1.47 (SD 0.76) cm2 and 1.55 (SD 0.74) cm2 on the right and left, respectively (P = .005). It was 76% and 79% for average estimates of muscle mass (P = .021). Both measures were strongly associated with POP; however, they were not superior to TTS in predicting POP. Coronal plane assessment in volume data is reproducible and valid for evaluation of levator trauma. Muscle mass estimate may be a better measure than muscle area.

Patellar Tendon-Lateral Femoral Condyle Friction Syndrome: About 5 Cases

Objective: The objective is to illustrate the MR imaging findings occurring in the posterior inferolateral patellar tendon and the lateral femoral condyle in patients experiencing chronic anterior and/or lateral knee pain. Material and methods: A retrospective review of the MR images in (patients who presented with chronic anterior or lateral knee pain. In all patients, postcontrast images were available. Results: Sagittal and axial imaging planes best demonstrated the patellar tendon and its relationship with the lateral femoral condyle. In all the patients, there was obliteration of the fat planes and abnormal signal intensity in the lateral soft tissues of the inferior patellofemoral joint. Enhancement after administration of gadolinium was noted in all cases in which contrast was administered. One patient showed cystic changes in the soft tissues adjacent to the lateral femoral condyle in addition to fat plane obliteration. Abnormal patellar alignment was noted in one patient. Patellar tendon pathology was seen in one patient. Conclusion: When assessing anterior knee symptoms, MR imaging facilitates the identification of changes associated with patellar tendon-lateral femoral condyle friction syndrome, which should be differentiated from other causes of anterior or lateral knee pain.

Transfer Learning for Alzheimer's Disease Diagnosis using EfficientNet-B0 Convolutional Neural Network

Alzheimer's disease (AD) is an irreversible neurological disorder that causes the gradual decline of one's cognitive abilities, and thus, early detection is significant to slow down its deterioration. Magnetic resonance imaging (MRI) images have been commonly used to diagnose AD. Furthermore, deep learning techniques such as the Convolutional Neural Network (CNN) are utilized to assist the diagnosis due to the complexity of MRI's analysis. However, CNN models require large datasets for training and have a challenging nature for model optimization. Thus, Transfer Learning, an emerging method that can improve the performance of the deep learning model by eliminating the need for training from scratch, is introduced. This paper will propose a Transfer Learning-based EfficientNet-B0 model to classify MRI brain images for AD diagnosis. The MRI images are obtained from Alzheimer's Disease Neuroimaging Initiative (ADNI) database; only axial-plane images are used in this study. As a result, the multi-class classification of MRI images into AD, MCI, and NC classes using a Transfer Learning-based model resulted in a training accuracy of 98.93% and a validation accuracy of 87.17%. These results evidenced the significance of Transfer Learning in improving model performance.

Assessment of the relationship between smoking and meniscal injury.

To determine whether being a smoker and the years of smoking correlate with the presence and degree of meniscal injury. Individuals who underwent magnetic resonance imaging of the knee were divided into two groups: smokers and nonsmokers. For each smoker, the total smoking history was calculated by multiplying the daily consumption (packs/day) by the years of smoking, and the result is expressed as pack-years. In the evaluation of meniscal injury, the grade of injury was recorded. The thickness of the subcutaneous adipose tissue, as an indicator of obesity, was measured at the medial knee on axial plane images. The relationships that smoking and obesity had with meniscal injury were analyzed statistically. A total of 156 individuals were included in the study. The smoker group consisted of 48 individuals (30.8%), and the nonsmoker group consisted of 108 (69.2%). The meniscus was normal in one (2.1%) of the smokers and in 32 (29.6%) of the nonsmokers (p < 0.0001). The median subcutaneous adipose tissue thickness was 23 mm and 24 mm in the smokers and nonsmokers, respectively (p = 0.900). A moderate but statistically significant correlation was observed between packs/day and injury grade, as well as between pack-years and injury grade (r = 0.462, p = 0.001 and r = 0.523, p = 0.001, respectively). Smoking and age significantly increased the risk of meniscal injury, by 31.221 times (p = 0.001) and 1.076 times (p < 0.001), respectively. Our findings indicate that current smoking and smoking history correlate significantly with meniscal injury grade.

Development of a comprehensive cardiac atlas on a 1.5 Tesla Magnetic Resonance Linear Accelerator

Background and purposeThe 1.5 Tesla (T) Magnetic Resonance Linear Accelerator (MRL) provides an innovative modality for improved cardiac imaging when planning radiation treatment. No MRL based cardiac atlases currently exist, thus, we sought to comprehensively characterize cardiac substructures, including the conduction system, from cardiac images acquired using a 1.5 T MRL and provide contouring guidelines. Materials and methodsFive volunteers were enrolled in a prospective protocol (NCT03500081) and were imaged on the 1.5 T MRL with Half Fourier Single-Shot Turbo Spin-Echo (HASTE) and 3D Balanced Steady-State Free Precession (bSSFP) sequences in axial, short axis, and vertical long axis. Cardiac anatomy was contoured by (AS) and confirmed by a board certified cardiologist (JR) with expertise in cardiac MR imaging. ResultsA total of five volunteers had images acquired with the HASTE sequence, with 21 contours created on each image. One of these volunteers had additional images obtained with 3D bSSFP sequences in the axial plane and additional images obtained with HASTE sequences in the key cardiac planes. Contouring guidelines were created and outlined. 15–16 contours were made for the short axis and vertical long axis. The cardiac conduction system was demonstrated with eleven representative contours. There was reasonable variation of contour volume across volunteers, with structures more clearly delineated on the 3D bSSFP sequence. ConclusionsWe present a comprehensive cardiac atlas using novel images acquired prospectively on a 1.5 T MRL. This cardiac atlas provides a novel resource for radiation oncologists in delineating cardiac structures for treatment with radiotherapy, with special focus on the cardiac conduction system.

Orbital Fractures: A New CT-Based Protocol to Guide the Surgical Approach and Reconstruction Material Decision-Making.

Preoperative computer-assisted planning and intraoperative navigation are becoming popular for orbital fracture treatment. However, not all institutions currently have access to these computer-aided applications. The authors present a simple and intuitive operative algorithm to guide orbital fracture reconstructions. The operative algorithm was based on linear measurements of orbital defects on high-resolution Computer tomography (CT) scans using specific axial, coronal, and sagittal plane images. The fractures were then divided into 3 types based on site and defect-size area. For each type, the authors suggested a surgical approach and material reconstruction. Between February 2022 and January 2023, 57 patients were treated according to the described CT-based protocol. The quality of reconstruction was classified as ideal, satisfactory, acceptable, and poor based on postoperative CT. Diplopia, enophthalmos, and postoperative complications were assessed. Fifty-seven patients were included. Forty-four (77.2%) patients were included in the type 1 group, 4 (7.01%) in the type 2 group, and 9 (15.79%) in the type 3 group. The reconstruction was considered ideal in 54 (94.7%) cases, satisfactory in 2 (3.5%), and acceptable in 1 (1.8%). No revision surgery was required. In all cases, preoperative diplopia was settled out, and only 1 patient reported postoperative enophthalmos. No complications occurred, with good clinical results and orbital symmetry. The linear CT measurement-based protocol is a simple and reliable workflow to guide the surgeon's choice of reconstruction material and surgical approach for primary orbital reconstruction. It allows good management of orbital trauma and could help standardize treatment decisions with an imaging technique available in all institutions.

Newly Developed Resorbable Magnesium Biomaterials for Orbital Floor Reconstruction in Caprine and Ovine Animal Models-A Prototype Design and Proof-of-Principle Study.

orbital floor fractures have not been reconstructed using magnesium biomaterials. To test technical feasibility, ex vivo caprine and ovine heads (n = 5) were used. Head tissues were harvested from pubescent animals (n = 5; mean age: 3.2 years; mean mass: 26.3 kg) and stored below 11 degrees for 7-10 days. All procedures were performed in a university animal resource facility. Two experienced maxillofacial surgeons performed orbital floor procedures in both orbits of all animals in a step-by-step preplanned dissection. A transconjunctival approach was chosen to repair the orbital floor with three different implants (i.e., magnesium implants; titanium mesh; and polydioxanone or PDO sheets). The position of each implant was evaluated by Cone-beam computed tomography (CBCT). Axial, coronal, and sagittal plane images showed good positioning of the magnesium plates. The magnesium plates had a radiographic visibility similar to that of the PDO sheets but lower than that of the titanium mesh. The prototype design study showed a novel indication for magnesium biomaterials. Further testing of this new biomaterial may lead to the first resorbable biomaterial with good mechanical properties for extensive orbital wall defects.

Two-dimensional imaging under meridional propagation through a dispersive thick lens based on RGB distributions and defocused planes.

In this paper, we consider a 2D polychromatic transparency serving as an object in front of a dispersive thick lens. The RGB based constituent colors are treated in terms of a center wavelength with a spectral spread, thereby enabling the phasor interpretation and tracking along axial image planes. It turns out that any individual color of the input transparency has a unique focal length or image position in the (meridional) observation plane after propagation through the lens. Under dispersion, image characteristics such as foci, axial location, magnification, and amplitude are controlled by narrow sidebands around a monochromatic carrier. The analytical results (derived numerically) are compared with standard non-dispersive imaging. Particular attention is given to the nature of transverse paraxial images in fixed axial planes, whereby defocusing effects due to dispersion are demonstrated in the manner of spherical aberration. Such selective axial focusing of individual wavelengths may find applications in improving the conversion efficiency of solar cells and photodetectors exposed to white light illumination.

The role of esophageal area for dysphagia after anterior cervical corpectomy fusion: Change trends and risk factors.

The objective of this study is to assess the change trends of perioperative esophageal area for anterior cervical corpectomy fusion (ACCF) and to analyze the risk factors of the area for postoperative dysphagia. We retrospectively analyzed 309 patients who underwent ACCF due to degenerative cervical diseases between November 2015 and September 2019 at our hospital. Patients were divided into 2 groups named the dysphagia group and the normal swallowing function group, according to the swallowing function after ACCF. The esophageal area was measured at T1 level using computed tomography axial plane images before and after surgery (1 week, 1 month, 8 months, and 12 months), in order to assess the change trends of esophageal area perioperatively and analyze risk factors of the area for dysphagia after ACCF. The area was highest at 1 week after surgery and would be decreased over time in both groups, which was recovered to the preoperative levels in 12 months after surgery. The incidence of dysphagia after ACCF was 41.1%. In the dysphagia group, 127 patients (mean age 59.299 years) had dysphagia after ACCF. In the normal-swallowing function group, 182 patients (mean age 59.8352 years) had normal swallowing function after ACCF. The preoperative esophageal area was larger in the dysphagia group than in the normal-swallowing function group. Preoperative esophageal area was correlated with postoperative dysphagia (odds ratio: 1.3457, 95% confidence interval: 1.106-1.637). When the esophageal area at preoperation was above 3.388 cm2, the risk of postoperative dysphagia was higher. The esophageal area was the biggest at 1 week postoperatively, significantly decreased over time and would be recovered to the normal size at 12 months after surgery. Preoperative esophageal area should be considered when evaluating the risk factor for dysphagia after ACCF.

Reliability of Cervical Neural Foramen Stenosis Grading Based on Axial Three-Dimensional Magnetic Resonance Images

Objective: To assess the reliability of cervical neural foramen stenosis (CNFS) grading by using three-dimensional (3D) T1W, 3D T2W, and twodimensional (2D) T2W images in axial plane. Materials and Methods: The authors enrolled 32 patients between December 2019 and February 2020 who underwent cervical spine magnetic resonance imaging (MRI) with clinical manifestations of cervical spondylosis. Two blinded radiologists interpreted the axial 3D T1W TSE, 3D T2W TSE, and 2D T2W TSE images using a 4-point visual scale for CNFS grading in all cervical levels. Intra-observer agreement of CNFS grading on the three imaging pulse sequences for each observer and inter-observer agreement between both observers were analyzed using intra-class correlation coefficient (ICC). Results: Three hundred eighty-four neural foramina were evaluated. The overall mean intra-observer agreement of CNFS grading was strong on the axial 3D T1W TSE, 3D T2W TSE, and 2D T2W TSE images for each observer with ICC values of 0.79 and 0.82. The overall mean inter-observer agreement for CNFS grading was strong on 3D T1W TSE, 3D T2W TSE, and 2D T2W TSE images with ICC values of 0.79, 0.79, and 0.86, respectively. Conclusion: Axial 3D T1W TSE, 3D T2W TSE, and 2D T2W TSE images exhibited comparable strong reliability in the grading of cervical neural foramen stenosis without the significant benefit of 3D over 2D technique. Keywords: Cervical spine; Neural foramen stenosis; MRI; Grading

Opportunistic screening for low bone density using abdominopelvic computed tomography scans.

While low bone density is a major burden on US health system, current osteoporosis screening guidelines by the US Preventive Services Task Force are limited to women aged ≥65 and all postmenopausal women with certain risk factors. Even within recommended screening groups, actual screening rates are low (<26%) and vary across socioeconomic groups. The proposed model can opportunistically screen patients using abdominal CT studies for low bone density who may otherwise go undiagnosed. To develop an artificial intelligence (AI) model for opportunistic screening of low bone density using both contrast and non-contrast abdominopelvic computed tomography (CT) exams, for the purpose of referral to traditional bone health management, which typically begins with dual energy X-ray absorptiometry (DXA). We collected 6083 contrast-enhanced CT imaging exams paired with DXA exams within ±6 months documented between May 2015 and August 2021 in a single institution with four major healthcare practice regions. Our fusion AI pipeline receives the coronal and axial plane images of a contrast enhanced abdominopelvic CT exam and basic patient demographics (age, gender, body cross section lengths) to predict risk of low bone mass. The models were trained on lumbar spine T-scores from DXA exams and tested on multi-site imaging exams. The model was again tested in a prospective group (N=344) contrast-enhanced and non-contrast-enhanced studies. The models were evaluated on the same test set (1208 exams)-(1) Baseline model using demographic factors from electronic medical records (EMR) - 0.7 area under the curve of receiver operator characteristic (AUROC); Imaging based models: (2) axial view - 0.83 AUROC; (3) coronal view- 0.83 AUROC; (4) Fusion model-Imaging + demographic factors - 0.86 AUROC. The prospective test yielded one missed positive DXA case with a hip prosthesis among 23 positive contrast-enhanced CT exams and 0% false positive rate for non-contrast studies. Both positive cases among non-contrast enhanced CT exams were successfully detected. While only about 8% patients from prospective study received a DXA exam within 2 years, about 30% were detected with low bone mass by the fusion model, highlighting the need for opportunistic screening. The fusion model, which combines two planes of CT images and EMRs data, outperformed individual models and provided a high, robust diagnostic performance for opportunistic screening of low bone density using contrast and non-contrast CT exams. This model could potentially improve bone health risk assessment with no additional cost. The model's handling of metal implants is an ongoing effort.

Tunable image quality control of 3-D ultrasound using switchable CycleGAN.

In contrast to 2-D ultrasound (US) for uniaxial plane imaging, a 3-D US imaging system can visualize a volume along three axial planes. This allows for a full view of the anatomy, which is useful for gynecological (GYN) and obstetrical (OB) applications. Unfortunately, the 3-D US has an inherent limitation in resolution compared to the 2-D US. In the case of 3-D US with a 3-D mechanical probe, for example, the image quality is comparable along the beam direction, but significant deterioration in image quality is often observed in the other two axial image planes. To address this, here we propose a novel unsupervised deep learning approach to improve 3-D US image quality. In particular, using unmatched high-quality 2-D US images as a reference, we trained a recently proposed switchable CycleGAN architecture so that every mapping plane in 3-D US can learn the image quality of 2-D US images. Thanks to the switchable architecture, our network can also provide real-time control of image enhancement level based on user preference, which is ideal for a user-centric scanner setup. Extensive experiments with clinical evaluation confirm that our method offers significantly improved image quality as well user-friendly flexibility.

Effect of anterior maxillary wall shape on ease of prelacrimal recess approach among Asians and Westerners.

Endoscopic sinus surgery has been widely used in the treatment of most maxillary diseases, although the inability to access lesions in the anterior and inferior maxillary sinus walls is a major disadvantage. In few cases, the prelacrimal recess (PLR) approach can be used, which secures an overall view within the maxillary sinus. The distance between the anterior maxillary wall and lacrimal duct is related to the ease of the PLR approach. First we measured the distance between the anterior maxillary wall and lacrimal duct using anatomical image analysis to classify the types and then evaluated whether anatomical factors were related to the results. Both sides of the sinuses were evaluated in 272 participants (544 sides). After marking a tangent line (line 1 [L1]) through the posterior surface of the anterior maxillary sinus wall and a parallel line (line 2 [L2]) to the anterior surface of the lacrimal duct, the vertical distance between L1 and L2 was measured. Vertical distances of < 3mm, 3-7mm, and > 7mm were classified as PLR approach types I, II, and III, respectively. In the axial plane image, line 3 (L3) (a horizontal line starting from the inner anterior maxillary sinus wall) was drawn and the angle with L1 (L1-L3A) was measured. The proportions of types I, II, and III were 23.2% (126), 55.0% (299), and 21.8% (119), respectively. The mean L1-L3As for types I, II, and III were 12.87 ± 4.92°, 11.20 ± 5.08°, and 10.40 ± 4.47°, respectively, showing a significant difference in mean values (p < 0.001). The L1-L3A and vertical distance between L1 and L2 showed a significant negative correlation (r = - 0.201, p < 0.001). We observed a correlation between the distance from the anterior maxillary wall to the lacrimal duct and L1-L3A. The L1-L3A indicates the degree of curvature of the anterior maxillary wall; therefore, the smaller the L1-L3A, the easier it may be to access the PLR.

BgNet: Classification of benign and malignant tumors with MRI multi-plane attention learning.

To propose a deep learning-based classification framework, which can carry out patient-level benign and malignant tumors classification according to the patient's multi-plane images and clinical information. A total of 430 cases of spinal tumor, including axial and sagittal plane images by MRI, of which 297 cases for training (14072 images), and 133 cases for testing (6161 images) were included. Based on the bipartite graph and attention learning, this study proposed a multi-plane attention learning framework, BgNet, for benign and malignant tumor diagnosis. In a bipartite graph structure, the tumor area in each plane is used as the vertex of the graph, and the matching between different planes is used as the edge of the graph. The tumor areas from different plane images are spliced at the input layer. And based on the convolutional neural network ResNet and visual attention learning model Swin-Transformer, this study proposed a feature fusion model named ResNetST for combining both global and local information to extract the correlation features of multiple planes. The proposed BgNet consists of five modules including a multi-plane fusion module based on the bipartite graph, input layer fusion module, feature layer fusion module, decision layer fusion module, and output module. These modules are respectively used for multi-level fusion of patient multi-plane image data to realize the comprehensive diagnosis of benign and malignant tumors at the patient level. The accuracy (ACC: 79.7%) of the proposed BgNet with multi-plane was higher than that with a single plane, and higher than or equal to the four doctors' ACC (D1: 70.7%, p=0.219; D2: 54.1%, p<0.005; D3: 79.7%, p=0.006; D4: 72.9%, p=0.178). Moreover, the diagnostic accuracy and speed of doctors can be further improved with the aid of BgNet, the ACC of D1, D2, D3, and D4 improved by 4.5%, 21.8%, 0.8%, and 3.8%, respectively. The proposed deep learning framework BgNet can classify benign and malignant tumors effectively, and can help doctors improve their diagnostic efficiency and accuracy. The code is available at https://github.com/research-med/BgNet.

The midcortical-line is more reliable than the T-line in predicting stem anteversion in patients with developmental hip dysplasia after total hip arthroplasty.

BackgroundPrecise preoperative planning improves postoperative outcomes in total hip arthroplasty (THA), especially in developmental dysplasia of the hip (DDH) cases. Previous studies used the T-line and midcortical-line as preoperative landmarks to predict postoperative stem anteversion (PSA). However, the most reliable landmark in predicting PSA in DDH patients remains unclear. To find the most reliable measurement to predict the PSA in DDH patients, this study compared the midcortical-line and T-line at different femoral neck levels.MethodsPre- and postoperative Computed Tomography (CT) scans of 28 hips in 21 DDH patients who received THA were obtained for three-dimensional femoral models. The preoperative CT scan was used to measure the anteversion of the midcortical-line on the axial cross-sectional plane images (AM-CT), the anteversion of the midcortical-line from 3D models (AM-3D), and the T-line from 3D models (AT-3D) at simulated osteotomy planes at 5 and 10 mm heights proximal to the base of the lesser trochanter. The correlation between the preoperative femoral anteversion (AM-CT, AM-3D, AT-3D) and the PSA was assessed to evaluate the prediction accuracy.ResultsThe correlations between the AM-CT and the PSA were 0.86 (mean difference (MD) = 1.9°) and 0.92 (MD = −3.0°) at 5 and 10 mm heights, respectively. The correlation between the AM-3D and the PSA were 0.71 (MD = −11.6°) and 0.61 (MD = −12.9°) at 5 and 10 mm heights. The AT-3D was significantly greater (MD = 15.4°) than the PSA (p-value <0.01) at 5 mm cutting height, and the correlation between the AT-3D and the PSA was 0.57 (MD = 7.8°) at 10 mm cutting height.ConclusionsThe AM-CT at the 10 mm height had the strongest correlation with the PSA and was more reliable in predicting the PSA when compared with the AM-3D and the AT-3D in DDH patients.

Spontaneous Volumetric Tumor Regression During Wait-and-Scan Management of 952 Sporadic Vestibular Schwannomas.

Spontaneous tumor shrinkage during wait-and-scan management of sporadic vestibular schwannoma is generally considered an uncommon phenomenon. However, most data informing this understanding stem from single-slice linear tumor measurements taken in the axial imaging plane. The objective of the current work was to characterize the regression capacity of sporadic vestibular schwannomas using volumetric tumor measurements. Retrospective cohort study using slice-by-slice, three-dimensional volumetric tumor measurements. Three tertiary referral centers. Patients with sporadic vestibular schwannoma. Wait-and-scan. Regression-free survival rates with regression defined as a decrease of at least 20% of the tumor volume. Among 952 patients undergoing a total of 3,505 magnetic resonance imaging studies during observation, 123 experienced volumetric tumor regression after diagnosis at a median of 1.2 years (interquartile range, 0.6-2.9 yr). Volumetric regression-free survival rates (95% confidence interval; number still at risk) at 1, 3, and 5 years after diagnosis were 94% (92-95%; 662), 86% (83-89%; 275), and 78% (73-82%; 132), respectively. Among 405 patients who demonstrated an initial period of tumor growth but continued wait-and-scan management, 48 experienced volumetric regression at a median of 1.2 years (interquartile range, 0.8-2.6 yr) after initial growth. Volumetric regression-free survival rates at 1, 3, and 5 years after initial growth were 94% (92-97%; 260), 84% (79-89%; 99), and 75% (67-83%; 43), respectively. Ultimately, only 82 of the 952 patients studied showed exclusively volumetric tumor regression (i.e., without any periods of tumor growth) by the time of last follow-up. Spontaneous volumetric tumor shrinkage during wait-and-scan management occurs more frequently than suggested by previous studies using linear tumor measurements and can even occur after previous episodes of documented tumor growth. These data further highlight the dynamic nature of vestibular schwannoma growth. To this end, the application of natural history data to patient management requires a nuanced approach that parallels the complex tumor behavior of vestibular schwannoma.

Radiological evaluation of temporal bone surgical landmarks for a transcanal transpromontorial approach to the internal auditory canal using three-dimensional computed tomography.

This study aimed to analyse a three-dimensional transcanal transpromontorial approach to the internal auditory canal using three-dimensional computed tomography. This study was a retrospective investigation of 48 ears of 24 patients using three-dimensional reconstruction data from normal temporal bone computed tomography. The inner structures of the temporal bone were three-dimensionally reconstructed. Eight points were marked in the three-dimensional object with reference to the axial, coronal and sagittal plane images of the computed tomography scans. Distances and angles to each point were measured from the oval and round windows. The point of the facial nerve from the internal auditory canal to the labyrinthine segment could be traced between the cochlear apex and the geniculate ganglion based on the oval window. This technique helps with identifying the locations of important surgical landmarks using three-dimensional reconstructions of pre-operative computed tomography scans and to identify the facial nerve from the internal auditory canal during surgery.