User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability

A Spatial Interpolation Approach to Assign Magnetic Resonance Imaging-Derived Material Properties for Finite Element Models of Adeno-Associated Virus Infusion Into a Recurrent Brain Tumor

Adeno-associated virus (AAV) is a clinically useful gene delivery vehicle for treating neurological diseases. To deliver AAV to focal targets, direct infusion into brain tissue by convection-enhanced delivery (CED) is often needed due to AAV's limited penetration across the blood-brain-barrier and its low diffusivity in tissue. In this study, computational models that predict the spatial distribution of AAV in brain tissue during CED were developed to guide future placement of infusion catheters in recurrent brain tumors following primary tumor resection. The brain was modeled as a porous medium, and material property fields that account for magnetic resonance imaging (MRI)-derived anatomical regions were interpolated and directly assigned to an unstructured finite element mesh. By eliminating the need to mesh complex surfaces between fluid regions and tissue, mesh preparation was expedited, increasing the model's clinical feasibility. The infusion model predicted preferential fluid diversion into open fluid regions such as the ventricles and subarachnoid space (SAS). Additionally, a sensitivity analysis of AAV delivery demonstrated that improved AAV distribution in the tumor was achieved at higher tumor hydraulic conductivity or lower tumor porosity. Depending on the tumor infusion site, the AAV distribution covered 3.67-70.25% of the tumor volume (using a 10% AAV concentration threshold), demonstrating the model's potential to inform the selection of infusion sites for maximal tumor coverage.

Effects of prospective motion correction on perivascular spaces at 7T MRI evaluated using motion artifact simulation

PURPOSE

The effectiveness of prospective motion correction (PMC) is often evaluated by comparing artifacts in images acquired with and without PMC (NoPMC). However, such an approach is not applicable in clinical setting due to unavailability of NoPMC images. We aim to develop a simulation approach for demonstrating the ability of fat-navigator-based PMC in improving perivascular space (PVS) visibility in T2-weighted MRI.

METHODS

MRI datasets from two earlier studies were used for motion artifact simulation and evaluating PMC, including T2-weighted NoPMC and PMC images. To simulate motion artifacts, k-space data at motion-perturbed positions were calculated from artifact-free images using nonuniform Fourier transform and misplaced onto the Cartesian grid before inverse Fourier transform. The simulation's ability to reproduce motion-induced blurring, ringing, and ghosting artifacts was evaluated using sharpness at lateral ventricle/white matter boundary, ringing artifact magnitude in the Fourier spectrum, and background noise, respectively. PVS volume fraction in white matter was employed to reflect its visibility.

RESULTS

In simulation, sharpness, PVS volume fraction, and background noise exhibited significant negative correlations with motion score. Significant correlations were found in sharpness, ringing artifact magnitude, and PVS volume fraction between simulated and real NoPMC images (p ≤ 0.006). In contrast, such correlations were reduced and nonsignificant between simulated and real PMC images (p ≥ 0.48), suggesting reduction of motion effects with PMC.

CONCLUSIONS

The proposed simulation approach is an effective tool to study the effects of motion and PMC on PVS visibility. PMC may reduce the systematic bias of PVS volume fraction caused by motion artifacts.

MR elastography-based slip interface imaging (SII) for functional assessment of myofascial interfaces: A feasibility study

PURPOSE

Abnormal adherence at functional myofascial interfaces is hypothesized as an important phenomenon in myofascial pain syndrome. This study aimed to investigate the feasibility of MR elastography (MRE)-based slip interface imaging (SII) to visualize and assess myofascial mobility in healthy volunteers.

METHODS

SII was used to assess local shear strain at functional myofascial interfaces in the flexor digitorum profundus (FDP) and thighs. In the FDP, MRE was performed at 90 Hz vibration to each index, middle, ring, and little finger. Two thigh MRE scans were performed at 40 Hz with knees flexed and extended. The normalized octahedral shear strain (NOSS) maps were calculated to visualize myofascial slip interfaces. The entropy of the probability distribution of the gradient NOSS was computed for the two knee positions at the intermuscular interface between vastus lateralis and vastus intermedius, around rectus femoris, and between vastus intermedius and vastus medialis.

RESULTS

NOSS map depicted distinct functional slip interfaces in the FDP for each finger. Compared to knee flexion, clearer slip interfaces and larger gradient NOSS entropy at the vastus lateralis-vastus intermedius interface were observed during knee extension, where the quadriceps are not passively stretched. This suggests the optimal position for using SII to visualize myofascial slip interface in skeletal muscles is when muscles are not subjected to any additional force.

CONCLUSION

The study demonstrated that MRE-based SII can visualize and assess myofascial interface mobility in extremities. The results provide a foundation for investigating the hypothesis that myofascial pain syndrome is characterized by changes in the mobility of myofascial interfaces.

Automated segmentation of epilepsy surgical resection cavities: Comparison of four methods to manual segmentation

Accurate resection cavity segmentation on MRI is important for neuroimaging research involving epilepsy surgical outcomes. Manual segmentation, the gold standard, is highly labour intensive. Automated pipelines are an efficient potential solution; however, most have been developed for use following temporal epilepsy surgery. Our aim was to compare the accuracy of four automated segmentation pipelines following surgical resection in a mixed cohort of subjects following temporal or extra temporal epilepsy surgery. We identified 4 open-source automated segmentation pipelines. Epic-CHOP and ResectVol utilise SPM-12 within MATLAB, while Resseg and Deep Resection utilise 3D U-net convolutional neural networks. We manually segmented the resection cavity of 50 consecutive subjects who underwent epilepsy surgery (30 temporal, 20 extratemporal). We calculated Dice similarity coefficient (DSC) for each algorithm compared to the manual segmentation. No algorithm identified all resection cavities. ResectVol (n = 44, 88 %) and Epic-CHOP (n = 42, 84 %) were able to detect more resection cavities than Resseg (n = 22, 44 %, P < 0.001) and Deep Resection (n = 23, 46 %, P < 0.001). The SPM-based pipelines (Epic-CHOP and ResectVol) performed better than the deep learning-based pipelines in the overall and extratemporal surgery cohorts. In the temporal cohort, the SPM-based pipelines had higher detection rates, however there was no difference in the accuracy between methods. These pipelines could be applied to machine learning studies of outcome prediction to improve efficiency in pre-processing data, however human quality control is still required.

Anesthesia Blunts Carbon Dioxide Effects on Glymphatic Cerebrospinal Fluid Dynamics in Mechanically Ventilated Rats

BACKGROUND

Impaired glymphatic clearance of cerebral metabolic products and fluids contribute to traumatic and ischemic brain edema and neurodegeneration in preclinical models. Glymphatic perivascular cerebrospinal fluid flow varies between anesthetics possibly due to changes in vasomotor tone and thereby in the dynamics of the periarterial cerebrospinal fluid (CSF)-containing space. To better understand the influence of anesthetics and carbon dioxide levels on CSF dynamics, this study examined the effect of periarterial size modulation on CSF distribution by changing blood carbon dioxide levels and anesthetic regimens with opposing vasomotor influences: vasoconstrictive ketamine-dexmedetomidine (K/DEX) and vasodilatory isoflurane.

METHODS

End-tidal carbon dioxide (ETco2) was modulated with either supplemental inhaled carbon dioxide to reach hypercapnia (Etco2, 80 mmHg) or hyperventilation (Etco2, 20 mmHg) in tracheostomized and anesthetized female rats. Distribution of intracisternally infused radiolabeled CSF tracer 111In-diethylamine pentaacetate was assessed for 86 min in (1) normoventilated (Etco2, 40 mmHg) K/DEX; (2) normoventilated isoflurane; (3) hypercapnic K/DEX; and (4) hyperventilated isoflurane groups using dynamic whole-body single-photon emission tomography. CSF volume changes were assessed with magnetic resonance imaging.

RESULTS

Under normoventilation, cortical CSF tracer perfusion, perivascular space size around middle cerebral arteries, and intracranial CSF volume were higher under K/DEX compared with isoflurane (cortical maximum percentage of injected dose ratio, 2.33 [95% CI, 1.35 to 4.04]; perivascular size ratio 2.20 [95% CI, 1.09 to 4.45]; and intracranial CSF volume ratio, 1.90 [95% CI, 1.33 to 2.71]). Under isoflurane, tracer was directed to systemic circulation. Under K/DEX, the intracranial tracer distribution and CSF volume were uninfluenced by hypercapnia compared with normoventilation. Intracranial CSF tracer distribution was unaffected by hyperventilation under isoflurane despite a 28% increase in CSF volume around middle cerebral arteries.

CONCLUSIONS

K/DEX and isoflurane overrode carbon dioxide as a regulator of CSF flow. K/DEX could be used to preserve CSF space and dynamics in hypercapnia, whereas hyperventilation was insufficient to increase cerebral CSF perfusion under isoflurane.

EDITOR’S PERSPECTIVE

Computed tomography-based radiomics combined with machine learning allows differentiation between primary intestinal lymphoma and Crohn's disease

BACKGROUND

Due to similar clinical manifestations and imaging signs, differential diagnosis of primary intestinal lymphoma (PIL) and Crohn's disease (CD) is a challenge in clinical practice.

AIM

To investigate the ability of radiomics combined with machine learning methods to differentiate PIL from CD.

METHODS

We collected contrast-enhanced computed tomography (CECT) and clinical data from 120 patients form center 1. A total of 944 features were extracted single-phase images of CECT scans. Using the last absolute shrinkage and selection operator model, the best predictive radiographic features and clinical indications were screened. Data from 54 patients were collected at center 2 as an external validation set to verify the robustness of the model. The area under the receiver operating characteristic curve, accuracy, sensitivity and specificity were used for evaluation.

RESULTS

A total of five machine learning models were built to distinguish PIL from CD. Based on the results from the test group, most models performed well with a large area under the curve (AUC) (> 0.850) and high accuracy (> 0.900). The combined clinical and radiomics model (AUC = 1.000, accuracy = 1.000) was the best model among all models.

CONCLUSION

Based on machine learning, a model combining clinical data with radiologic features was constructed that can effectively differentiate PIL from CD.

Deep learning prediction of survival in patients with heart failure using chest radiographs

Heart failure (HF) is associated with high rates of morbidity and mortality. The value of deep learning survival prediction models using chest radiographs in patients with heart failure is currently unclear. The aim of our study is to develop and validate a deep learning survival prediction model using chest X-ray (DLSPCXR) in patients with HF. The study retrospectively enrolled a cohort of 353 patients with HF who underwent chest X-ray (CXR) at our institution between March 2012 and March 2017. The dataset was randomly divided into training (n = 247) and validation (n = 106) datasets. Univariate and multivariate Cox analysis were conducted on the training dataset to develop clinical and imaging survival prediction models. The DLSPCXR was trained and the selected clinical parameters were incorporated into DLSPCXR to establish a new model called DLSPinteg. Discrimination performance was evaluated using the time-dependent area under the receiver operating characteristic curves (TD AUC) at 1, 3, and 5-years survival. Delong's test was employed for the comparison of differences between two AUCs of different models. The risk-discrimination capability of the optimal model was evaluated by the Kaplan-Meier curve. In multivariable Cox analysis, older age, higher N-terminal pro-B-type natriuretic peptide (NT-ProBNP), systolic pulmonary artery pressure (sPAP) > 50 mmHg, New York Heart Association (NYHA) functional class III-IV and cardiothoracic ratio (CTR) ≥ 0.62 in CXR were independent predictors of poor prognosis in patients with HF. Based on the receiver operating characteristic (ROC) curve analysis, DLSPCXR had better performance at predicting 5-year survival than the imaging Cox model in the validation cohort (AUC: 0.757 vs. 0.561, P = 0.01). DLSPinteg as the optimal model outperforms the clinical Cox model (AUC: 0.826 vs. 0.633, P = 0.03), imaging Cox model (AUC: 0.826 vs. 0.555, P < 0.001), and DLSPCXR (AUC: 0.826 vs. 0.767, P = 0.06). Deep learning models using chest radiographs can predict survival in patients with heart failure with acceptable accuracy.

The impact of diffusion tensor imaging tractography settings on muscle fascicle architecture and diffusion parameter estimates: Tract length, completion, and curvature are most sensitive to tractography settings

Diffusion-tensor (DT)-MRI tractography provides information about properties relevant to muscle health and function, including estimates of architectural properties such as fascicle length, pennation angle, and curvature and diffusion properties such as mean diffusivity (MD) and fractional anisotropy (FA). Tractography settings, including integration algorithms, thresholds for early tract termination, and tract smoothing approaches, impact the accuracy of the muscle property estimates. However, muscle DT-MRI tractography is performed using a variety of these settings, complicating comparisons between different studies. The effects of different tractography settings on muscle architecture estimates have not been fully explored, and optimized settings for muscle tractography have not yet been determined. We examined the influence of integration algorithm and termination check settings combined with a range of step sizes, termination criteria, and smoothing polynomial orders on tract characteristics, completion/reason for termination, and goodness of fit between fiber tracts and smoothing polynomials using 3-T DT-MR images of the lower leg muscles of seven healthy adults. We found that tract length and completion were highly sensitive to strict FA and intersegment angle thresholds (25%-69% reduction in complete fiber tracts from lowest to highest minimum FA threshold and 11%-36% reduction from highest to lowest intersegment angle threshold). Higher order polynomials (third and fourth order vs. second order) better fit the muscle fiber trajectories, but curvature estimates were highly sensitive to smoothing polynomial order (3.9-6.6 m-1 increase for second- vs. fourth-order fitting polynomials). Step size impacted curvature estimates, albeit to a lesser degree. Integration algorithm had little impact, and mean pennation angle, and tract-based FA and MD, were relatively insensitive to all parameters. The results demonstrate which muscle diffusion measures and architectural estimates are most sensitive to varying tractography settings and support the need for consistent reporting of tractography details to aid interpretation and comparison of results between studies.

ArborSim: Articulated, branching, OpenSim routing for constructing models of multi-jointed appendages with complex muscle-tendon architecture

Computational models of musculoskeletal systems are essential tools for understanding how muscles, tendons, bones, and actuation signals generate motion. In particular, the OpenSim family of models has facilitated a wide range of studies on diverse human motions, clinical studies of gait, and even non-human locomotion. However, biological structures with many joints, such as fingers, necks, tails, and spines, have been a longstanding challenge to the OpenSim modeling community, especially because these structures comprise numerous bones and are frequently actuated by extrinsic muscles that span multiple joints-often more than three-and act through a complex network of branching tendons. Existing model building software, typically optimized for limb structures, makes it difficult to build OpenSim models that accurately reflect these intricacies. Here, we introduce ArborSim, customized software that efficiently creates musculoskeletal models of highly jointed structures and can build branched muscle-tendon architectures. We used ArborSim to construct toy models of articulated structures to determine which morphological features make a structure most sensitive to branching. By comparing the joint kinematics of models constructed with branched and parallel muscle-tendon units, we found that among various parameters-the number of tendon branches, the number of joints between branches, and the ratio of muscle fiber length to muscle tendon unit length-the number of tendon branches and the number of joints between branches are most sensitive to branching modeling method. Notably, the differences between these models showed no predictable pattern with increased complexity. As the proportion of muscle increased, the kinematic differences between branched and parallel models units also increased. Our findings suggest that stress and strain interactions between distal tendon branches and proximal tendon and muscle greatly affect the overall kinematics of a musculoskeletal system. By incorporating complex muscle-tendon branching into OpenSim models using ArborSim, we can gain deeper insight into the interactions between the axial and appendicular skeleton, model the evolution and function of diverse animal tails, and understand the mechanics of more complex motions and tasks.

Low-Field Portable MR Imaging to Evaluate Ventricular Volumes: A Single-Center Retrospective Study

This study assesses the efficacy of low-field portable MR imaging in measuring ventricular volumes in the pediatric population in the hospital setting. We compared portable and standard of care MR images from the same patient. The estimated ventricular volumes had excellent agreement with a mean bias of 2.06% by Bland-Altman analysis and a correlation of 0.99. From this initial data set, our results suggest that low-field, portable MR imaging is a promising technique for imaging and quantifying ventricular volumes.

Sodium MRI of the Lumbar Intervertebral Discs of the Human Spine: An Ex Vivo Study

BACKGROUND

Lower back pain affects 75%-85% of people at some point in their lives. The detection of biochemical changes with sodium (23Na) MRI has potential to enable an earlier and more accurate diagnosis.

PURPOSE

To measure 23Na relaxation times and apparent tissue sodium concentration (aTSC) in ex-vivo intervertebral discs (IVDs), and to investigate the relationship between aTSC and histological Thompson grade.

STUDY TYPE

Ex-vivo.

SPECIMEN

Thirty IVDs from the lumbar spines of 11 human body donors (4 female, 7 male, mean age 86 ± 8 years).

FIELD STRENGTH/SEQUENCE

3 T; density-adapted 3D radial sequence (DA-3D-RAD).

ASSESSMENT

IVD 23Na longitudinal (T1), short and long transverse (T2s* and T2l*) relaxation times and the proportion of the short transverse relaxation (ps) were calculated for one IVD per spine sample (11 IVDs). Furthermore, aTSCs were calculated for all IVDs. The degradation of the IVDs was assessed via histological Thompson grading.

STATISTICAL TESTS

A Kendall Tau correlation (τ) test was performed between the aTSCs and the Thompson grades. The significance level was set to P < 0.05.

RESULTS

Mean 23Na relaxation parameters of a subset of 11 IVDs were T1 = 9.8 ± 1.3 msec, T2s* = 0.7 ± 0.1 msec, T2l* = 7.3 ± 1.1 msec, and ps = 32.7 ± 4.0%. A total of 30 IVDs were examined, of which 3 had Thompson grade 1, 4 had grade 2, 5 had grade 3, 5 had grade 4, and 13 had grade 5. The aTSC decreased with increasing degradation, being 274.6 ± 18.9 mM for Thompson grade 1 and 190.5 ± 29.5 mM for Thompson grade 5. The correlation between whole IVD aTSC and Thompson grade was significant and strongly negative (τ = -0.56).

DATA CONCLUSION

This study showed a significant correlation between aTSC and degenerative IVD changes. Consequently, aTSC has potential to be useful as an indicator of degenerative spinal changes.

EVIDENCE LEVEL

2 TECHNICAL EFFICACY: Stage 1.

Multiple diffusion models for predicting pathologic response of esophageal squamous cell carcinoma to neoadjuvant chemotherapy

BACKGROUND

To assess the feasibility and diagnostic performance of the fractional order calculus (FROC), continuous-time random-walk (CTRW), diffusion kurtosis imaging (DKI), intravoxel incoherent motion (IVIM), mono-exponential (MEM) and stretched exponential models (SEM) for predicting response to neoadjuvant chemotherapy (NACT) in patients with esophageal squamous cell carcinoma (ESCC).

MATERIALS AND METHODS

This study prospectively included consecutive ESCC patients with baseline and follow up MR imaging and pathologically confirmed cT1-4aN + M0 or T3-4aN0M0 and underwent radical resection after neoadjuvant chemotherapy (NACT) between July 2019 and January 2023. Patients were divided into pCR (TRG 0) and non-pCR (TRG1 + 2 + 3) groups according to tumor regression grading (TRG). The Pre-, Post- and Delta-treatment models were built. 18 predictive models were generated according to different feature categories, based on six models by five-fold cross-validation. Areas under the curve (AUCs) of the models were compared by using DeLong method.

RESULTS

Overall, 90 patients (71 men, 19 women; mean age, 64 years ± 6 [SD]) received NACT and underwent baseline and Post-NACT esophageal MRI, with 29 patients in the pCR group and 61 patients in the non-pCR group. Among 18 predictive models, The Pre-, Post-, and Delta-CTRW model showed good predictive efficacy (AUC = 0.722, 0.833 and 0.790). Additionally, the Post-FROC model (AUC = 0.907) also exhibited good diagnostic performance.

CONCLUSIONS

Our study indicates that the CTRW model, along with the Post-FROC model, holds significant promise for the future of NACT efficacy prediction in ESCC patients.

Placental multimodal MRI prior to spontaneous preterm birth <32 weeks' gestation: An observational study

OBJECTIVE

To utilise combined diffusion-relaxation MRI techniques to interrogate antenatal changes in the placenta prior to extreme preterm birth among both women with PPROM and membranes intact, and compare this to a control group who subsequently delivered at term.

DESIGN

Observational study.

SETTING

Tertiary Obstetric Unit, London, UK.

POPULATION

Cases: pregnant women who subsequently spontaneously delivered a singleton pregnancy prior to 32 weeks' gestation without any other obstetric complications.

CONTROLS

pregnant women who delivered an uncomplicated pregnancy at term.

METHODS

All women consented to an MRI examination. A combined diffusion-relaxation MRI of the placenta was undertaken and analysed using fractional anisotropy, a combined T2*-apparent diffusion coefficient model and a combined T2*-intravoxel incoherent motion model, in order to provide a detailed placental phenotype associated with preterm birth. Subgroup analyses based on whether women in the case group had PPROM or intact membranes at time of scan, and on latency to delivery were performed.

MAIN OUTCOME MEASURES

Fractional anisotropy, apparent diffusion coefficients and T2* placental values, from two models including a combined T2*-IVIM model separating fast- and slow-flowing (perfusing and diffusing) compartments.

RESULTS

This study included 23 women who delivered preterm and 52 women who delivered at term. Placental T2* was lower in the T2*-apparent diffusion coefficient model (p < 0.001) and in the fast- and slow-flowing compartments (p = 0.001 and p < 0.001) of the T2*-IVIM model. This reached a higher level of significance in the preterm prelabour rupture of the membranes group than in the membranes intact group. There was a reduced perfusion fraction among the cases with impending delivery.

CONCLUSIONS

Placental diffusion-relaxation reveals significant changes in the placenta prior to preterm birth with greater effect noted in cases of preterm prelabour rupture of the membranes. Application of this technique may allow clinically valuable interrogation of histopathological changes before preterm birth. In turn, this could facilitate more accurate antenatal prediction of preterm chorioamnionitis and so aid decisions around the safest time of delivery. Furthermore, this technique provides a research tool to improve understanding of the pathological mechanisms associated with preterm birth in vivo.

Association of Mismatch Profiles and Clinical Outcome from Endovascular Therapy in Large Infarct: A Post-Hoc Analysis of the ANGEL-ASPECT Trial

OBJECTIVES

We investigated whether patients with large infarct and the presence or absence of perfusion mismatch are associated with endovascular treatment benefit.

METHODS

This is a post-hoc analysis of the Endovascular Therapy in Anterior Circulation Large Vessel Occlusion with a Large Infarct (ANGEL-ASPECT) randomized trial, which enrolled patients within 24 hours of onset with ASPECTS 3 to 5 or ASPECTS 0 to 2 with an infarct core 70 to 100 ml. Mismatch ratio was defined as time-to-maximum (Tmax) >6 s cerebral volume/ischemic core volume, and mismatch volume was defined as Tmax >6 s volume minus ischemic core volume. We divided patients into mismatch ratio ≥1.2 and mismatch volume ≥10 ml, and mismatch ratio ≥1.8 and mismatch volume ≥15 ml groups. The primary outcome was the 90-day modified Rankin Scale score ordinal distribution. Safety outcomes were symptomatic intracranial hemorrhage and 90-day mortality.

RESULTS

There were 425 patients included. In both the mismatch ratio ≥1.2 and mismatch volume ≥10 ml (mismatch+, n = 395; mismatch-, n = 31) and mismatch ratio ≥1.8 and mismatch volume ≥15 ml groups (mismatch+, n = 346; mismatch-, n = 80), better 90-day modified Rankin Scale outcomes were found in the endovascular treatment group compared with the MM group (4 [2-5] vs 4 [3-5], common odds ratio [cOR], 1.9, 95% confidence interval [CI] 1.3-2.7, p = 0.001; 4 [2-5] vs 4 [3-5], cOR, 1.9, 95% CI 1.3-2.8, p = 0.001, respectively), but not in patients without mismatch ratio ≥1.2 and mismatch volume ≥10 ml (5 [3-6] vs 5 [4-6], cOR, 1.2, 95% CI 0.3-4.1, p = 0.83), and mismatch ratio ≥1.8 and mismatch volume ≥15 ml (4 [3-6] vs 5 [3-6], cOR, 1.2, 95% CI 0.6-2.7, p = 0.60). However, no interaction effect was found in both subgroups (p interaction >0.10).

CONCLUSION

Endovascular treatment was more efficacious than MM in patients with mismatch profiles, but no treatment effect or interaction was noted in the no mismatch profile patients. However, the small sample size of patients with no mismatch may have underpowered our analysis. A pooled analysis of large core trials stratified by mismatch is warranted. ANN NEUROL 2024.

Multifrequency Magnetic Resonance Elastography Detects Small Abdominal Lymph Node Metastasis by High Stiffness

OBJECTIVES

Response Evaluation Criteria in Solid Tumors (RECIST) 1.1 is a clinical and research standard for evaluating malignant tumors and lymph node metastasis. However, quantitative analysis of nodal status is limited to measurement of short axis diameter (SAD), and metastatic lymph nodes below 10 mm in SAD are often not detected. The purpose of this study was to evaluate the value of multifrequency magnetic resonance elastography (MRE) when added to RECIST 1.1 for detection of lymph node metastasis.

MATERIALS AND METHODS

Twenty-five benign and 82 metastatic lymph nodes were prospectively examined by multifrequency MRE at 1.5 T using tomoelastography postprocessing at 30, 40, 50, and 60 Hz (total scan time of 4 minutes). Shear wave speed as a surrogate of soft tissue stiffness was provided in m/s. Positron emission tomography-computed tomography was used as reference standard for identification of abdominal lymph node metastasis from histologically confirmed primary tumors. The diagnostic performance of MRE was compared with that of SAD according to RECIST 1.1 and evaluated by receiver operating characteristic curve analysis using generalized linear mixed models and binary logistic mixed models. Sensitivity, specificity, and predictive values were calculated for different cutoffs.

RESULTS

Metastatic lymph nodes (1.90 ± 0.57 m/s) were stiffer than benign lymph nodes (0.98 ± 0.20 m/s, P < 0.001). An area under the curve of 0.95 for a cutoff of 1.32 m/s was calculated. Using a conservative approach with 1.0 specificity, we found sensitivity (SAD/MRE/MRE + SAD, 0.56/0.84/0.88), negative predictive values (0.41/0.66/0.71), and overall accuracy (0.66/0.88/0.91) to be improved using MRE and even higher for combined MRE and SAD.

CONCLUSIONS

Multifrequency MRE improves metastatic abdominal lymph node detection by 25% based on higher tissue stiffness-even for lymph nodes with an SAD ≤10 mm. Stiffness information is quick to obtain and would be a promising supplement to RECIST.

Brain (Yakovlevian) torque direction is associated with volume asymmetry of the intracranial transverse sinuses: evidence from situs inversus totalis

Previous research reported reversal of the prototypical brain torque in individuals with mirrored visceral topology (situs inversus totalis, SIT). Here, we investigate if typical asymmetry of the posterior intracranial venous system is also reversed in SIT and whether the direction and magnitude of this asymmetry is related to the direction and magnitude of the brain torque. Brain structural MRI images of 38 participants with SIT were compared with those of 38 matched control participants. Occipital and frontal petalia and bending were measured using a standardized procedure. In addition, representative sections of the left and right transverse sinuses were segmented, and their respective volumes determined. Participants with SIT showed general reversal of occipital and frontal petalia and occipital bending, as well as reversal of typical transverse sinus asymmetry. Transverse sinus volume was significantly correlated with several torque measures, such that the smaller transverse sinus was associated with a larger ipsilateral occipital petalia, contralateral occipital bending, and ipsilateral frontal bending. We propose an anatomical mechanism to explain occipital petalia and bending, and conclude that anatomical constraints imposed by the asymmetry of the posterior venous system provide and additional account to elucidate the formation of the human brain torque.

Classification of lung cancer subtypes on CT images with synthetic pathological priors

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case's CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), positive predictive value (PPV) and F1-score.

Novel methods to diagnose rotator cuff tear and predict post-operative Re-tear: Radiomics models

Objective

To validated a classifier to distinguish the status of rotator cuff tear and predict post-operative re-tear by utilizing magnetic resonance imaging (MRI) markers.

Methods

This retrospective study included patients with healthy rotator cuff and patients diagnosed as rotator cuff tear (RCT) by MRI. Radiomics features were identified from the pre-operative shoulder MRI and selected by using maximum relevance minimum redundancy (MRMR) methods. A radiomics model for diagnosis of RCT was constructed, based on the 3D volume of interest (VOI) of supraspinatus. Another model for the prediction of rotator re-tear after rotator cuff repair (Re-RCT) was constructed based on VOI of humerus, supraspinatus, infraspinatus and other clinical parameters.

Results

The model for diagnosing the status of RCT produced an area under the receiver operating characteristic curve (AUC) of 0.989 in the training cohort and 0.979 for the validation cohort. The radiomics model for predicting Re-RCT produced an AUC of 0.923 ± 0.017 for the training dataset and 0.790 ± 0.082 for the validation dataset. The nomogram combining radiomics features and clinical factors yielded an AUC of 0.961 ± 0.020 for the training dataset and 0.808 ± 0.081 for the validation dataset, which displayed the best performance among all models.

Conclusion

Radiomics models for the diagnosis of rotator cuff tear and prediction of post-operative Re-RCT yielded a decent prediction accuracy.

Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network

PURPOSE

23Na MRI can be used to quantify in-vivo tissue sodium concentration (TSC), but the inherently low 23Na signal leads to long scan times and/or noisy or low-resolution images. Reconstruction algorithms such as compressed sensing (CS) have been proposed to mitigate low signal-to-noise ratio (SNR); although, these can result in unnatural images, suboptimal denoising and long processing times. Recently, machine learning has been increasingly used to denoise 1H MRI acquisitions; however, this approach typically requires large volumes of high-quality training data, which is not readily available for 23Na MRI. Here, we propose using 1H data to train a denoising convolutional neural network (CNN), which we subsequently demonstrate on prospective 23Na images of the calf.

METHODS

1893 1H fat-saturated transverse slices of the knee from the open-source fastMRI dataset were used to train denoising CNNs for different levels of noise. Synthetic low SNR images were generated by adding gaussian noise to the high-quality 1H k-space data before reconstruction to create paired training data. For prospective testing, 23Na images of the calf were acquired in 10 healthy volunteers with a total of 150 averages over ten minutes, which were used as a reference throughout the study. From this data, images with fewer averages were retrospectively reconstructed using a non-uniform fast Fourier transform (NUFFT) as well as CS, with the NUFFT images subsequently denoised using the trained CNN.

RESULTS

CNNs were successfully applied to 23Na images reconstructed with 50, 40 and 30 averages. Muscle and skin apparent TSC quantification from CNN-denoised images were equivalent to those from CS images, with <0.9 mM bias compared to reference values. Estimated SNR was significantly higher in CNN-denoised images compared to NUFFT, CS and reference images. Quantitative edge sharpness was equivalent for all images. For subjective image quality ranking, CNN-denoised images ranked equally best with reference images and significantly better than NUFFT and CS images.

CONCLUSION

Denoising CNNs trained on 1H data can be successfully applied to 23Na images of the calf; thus, allowing scan time to be reduced from ten minutes to two minutes with little impact on image quality or apparent TSC quantification accuracy.

Artificial Intelligence Application in Skull Bone Fracture with Segmentation Approach

This study aims to evaluate an AI model designed to automatically classify skull fractures and visualize segmentation on emergent CT scans. The model's goal is to boost diagnostic accuracy, alleviate radiologists' workload, and hasten diagnosis, thereby enhancing patient outcomes. Unique to this research, both pediatric and post-operative patients were not excluded, and diagnostic durations were analyzed. Our testing dataset for the observer studies involved 671 patients, with a mean age of 58.88 years and fairly balanced gender representation. Model 1 of our AI algorithm, trained with 1499 fracture-positive cases, showed a sensitivity of 0.94 and specificity of 0.87, with a DICE score of 0.65. Implementing post-processing rules (specifically Rule B) improved the model's performance, resulting in a sensitivity of 0.94, specificity of 0.99, and a DICE score of 0.63. AI-assisted diagnosis resulted in significantly enhanced performance for all participants, with sensitivity almost doubling for junior radiology residents and other specialists. Additionally, diagnostic durations were significantly reduced (p < 0.01) with AI assistance across all participant categories. Our skull fracture detection model, employing a segmentation approach, demonstrated high performance, enhancing diagnostic accuracy and efficiency for radiologists and clinical physicians. This underlines the potential of AI integration in medical imaging analysis to improve patient care.

Spine-specific sarcopenia: distinguishing paraspinal muscle atrophy from generalized sarcopenia

BACKGROUND CONTEXT

Atrophy of the paraspinal musculature (PM) as well as generalized sarcopenia are increasingly reported as important parameters for clinical outcomes in the field of spine surgery. Despite growing awareness and potential similarities between both conditions, the relationship between "generalized" and "spine-specific" sarcopenia is unclear.

PURPOSE

To investigate the association between generalized and spine-specific sarcopenia.

STUDY DESIGN

Retrospective cross-sectional study.

PATIENT SAMPLE

Patients undergoing lumbar spinal fusion surgery for degenerative spinal pathologies.

OUTCOME MEASURES

Generalized sarcopenia was evaluated with the short physical performance battery (SPPB), grip strength, and the psoas index, while spine-specific sarcopenia was evaluated by measuring fatty infiltration (FI) of the PM.

METHODS

We used custom software written in MATLAB® to calculate the FI of the PM. The correlation between FI of the PM and assessments of generalized sarcopenia was calculated using Spearman's rank correlation coefficient (rho). The strength of the correlation was evaluated according to established cut-offs: negligible: 0-0.3, low: 0.3-0.5, moderate: 0.5-0.7, high: 0.7-0.9, and very high≥0.9. In a Receiver Operating Characteristics (ROC) analysis, the Area Under the Curve (AUC) of sarcopenia assessments to predict severe multifidus atrophy (FI≥50%) was calculated. In a secondary analysis, factors associated with severe multifidus atrophy in nonsarcopenic patients were analyzed.

RESULTS

A total of 125 (43% female) patients, with a median age of 63 (IQR 55-73) were included. The most common surgical indication was lumbar spinal stenosis (79.5%). The median FI of the multifidus was 45.5% (IQR 35.6-55.2). Grip strength demonstrated the highest correlation with FI of the multifidus and erector spinae (rho=-0.43 and -0.32, p<.001); the other correlations were significant (p<.05) but lower in strength. In the AUC analysis, the AUC was 0.61 for the SPPB, 0.71 for grip strength, and 0.72 for the psoas index. The latter two were worse in female patients, with an AUC of 0.48 and 0.49. Facet joint arthropathy (OR: 1.26, 95% CI: 1.11-1.47, p=.001) and foraminal stenosis (OR: 1.54, 95% CI: 1.10-2.23, p=.015) were independently associated with severe multifidus atrophy in our secondary analysis.

CONCLUSION

Our study demonstrates a low correlation between generalized and spine-specific sarcopenia. These findings highlight the risk of misdiagnosis when relying on screening tools for general sarcopenia and suggest that general and spine-specific sarcopenia may have distinct etiologies.

In Vivo Measurement of Rat Brain Water Content at 9.4 T MR Using Super-Resolution Reconstruction: Validation With Ex Vivo Experiments

BACKGROUND

Given that changes in brain water content are often correlated with disease, investigating water content non-invasively and in vivo could lead to a better understanding of the pathogenesis of several neurologic diseases.

PURPOSE

To adapt a super-resolution-based technique, previously developed for humans, to the rat brain and report in vivo high-resolution (HR) water content maps in comparison with ex vivo wet/dry methods.

STUDY TYPE

Prospective.

ANIMAL MODEL

Eight healthy male Wistar rats.

FIELD STRENGTH/SEQUENCE

9.4-T, multi-echo gradient-echo (mGRE) sequence.

ASSESSMENT

Using super-resolution reconstruction (SRR), a HR mGRE image (200 μm isotropic) was reconstructed from three low-resolution (LR) orthogonal whole-brain images in each animal, which was followed by water content mapping in vivo. The animals were subsequently sacrificed, the brains excised and divided into five regions (front left, front right, middle left, middle right, and cerebellum-brainstem regions), and the water content was measured ex vivo using wet/dry measurements as the reference standard. The water content values of the in vivo and ex vivo methods were then compared for the whole brain and also for the different regions separately.

STATISTICAL TESTS

Friedman's non-parametric test was used to test difference between the five regions, and Pearson's correlation coefficient was used for correlation between in vivo and ex vivo measurements. A P-value <0.05 was considered statistically significant.

RESULTS

Water content values derived from in vivo MR measurements showed strong correlations with water content measured ex vivo at a regional level (r = 0.902). Different brain regions showed significantly different water content values. Water content values were highest in the frontal brain, followed by the midbrain, and lowest in the cerebellum and brainstem regions.

DATA CONCLUSION

An in vivo technique to achieve HR isotropic water content maps in the rat brain using SRR was adopted in this study. The MRI-derived water content values obtained using the technique showed strong correlations with water content values obtained using ex vivo wet/dry methods.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 1.

Effects of Positive End-expiratory Pressure on Pulmonary Perfusion Distribution and Intrapulmonary Shunt during One-lung Ventilation in Pigs: A Randomized Crossover Study

BACKGROUND

During one-lung ventilation (OLV), positive end-expiratory pressure (PEEP) can improve lung aeration but might overdistend lung units and increase intrapulmonary shunt. The authors hypothesized that higher PEEP shifts pulmonary perfusion from the ventilated to the nonventilated lung, resulting in a U-shaped relationship with intrapulmonary shunt during OLV.

METHODS

In nine anesthetized female pigs, a thoracotomy was performed and intravenous lipopolysaccharide infused to mimic the inflammatory response of thoracic surgery. Animals underwent OLV in supine position with PEEP of 0 cm H2O, 5 cm H2O, titrated to best respiratory system compliance, and 15 cm H2O (PEEP0, PEEP5, PEEPtitr, and PEEP15, respectively, 45 min each, Latin square sequence). Respiratory, hemodynamic, and gas exchange variables were measured. The distributions of perfusion and ventilation were determined by IV fluorescent microspheres and computed tomography, respectively.

RESULTS

Compared to two-lung ventilation, the driving pressure increased with OLV, irrespective of the PEEP level. During OLV, cardiac output was lower at PEEP15 (5.5 ± 1.5 l/min) than PEEP0 (7.6 ± 3 l/min) and PEEP5 (7.4 ± 2.9 l/min; P = 0.004), while the intrapulmonary shunt was highest at PEEP0 (PEEP0: 48.1% ± 14.4%; PEEP5: 42.4% ± 14.8%; PEEPtitr: 37.8% ± 11.0%; PEEP15: 39.0% ± 10.7%; P = 0.027). The relative perfusion of the ventilated lung did not differ among PEEP levels (PEEP0: 65.0% ± 10.6%; PEEP5: 68.7% ± 8.7%; PEEPtitr: 68.2% ± 10.5%; PEEP15: 58.4% ± 12.8%; P = 0.096), but the centers of relative perfusion and ventilation in the ventilated lung shifted from ventral to dorsal and from cranial to caudal zones with increasing PEEP.

CONCLUSIONS

In this experimental model of thoracic surgery, higher PEEP during OLV did not shift the perfusion from the ventilated to the nonventilated lung, thus not increasing intrapulmonary shunt.

EDITOR’S PERSPECTIVE

Reproducible Spinal Cord Quantitative MRI Analysis with the Spinal Cord Toolbox

The spinal cord plays a pivotal role in the central nervous system, providing communication between the brain and the body and containing critical motor and sensory networks. Recent advancements in spinal cord MRI data acquisition and image analysis have shown a potential to improve the diagnostics, prognosis, and management of a variety of pathological conditions. In this review, we first discuss the significance of standardized spinal cord MRI acquisition protocol in multi-center and multi-manufacturer studies. Then, we cover open-access spinal cord MRI datasets, which are important for reproducible science and validation of new methods. Finally, we elaborate on the recent advances in spinal cord MRI data analysis techniques implemented in the open-source software package Spinal Cord Toolbox (SCT).

MONAI Label: A framework for AI-assisted interactive labeling of 3D medical images

The lack of annotated datasets is a major bottleneck for training new task-specific supervised machine learning models, considering that manual annotation is extremely expensive and time-consuming. To address this problem, we present MONAI Label, a free and open-source framework that facilitates the development of applications based on artificial intelligence (AI) models that aim at reducing the time required to annotate radiology datasets. Through MONAI Label, researchers can develop AI annotation applications focusing on their domain of expertise. It allows researchers to readily deploy their apps as services, which can be made available to clinicians via their preferred user interface. Currently, MONAI Label readily supports locally installed (3D Slicer) and web-based (OHIF) frontends and offers two active learning strategies to facilitate and speed up the training of segmentation algorithms. MONAI Label allows researchers to make incremental improvements to their AI-based annotation application by making them available to other researchers and clinicians alike. Additionally, MONAI Label provides sample AI-based interactive and non-interactive labeling applications, that can be used directly off the shelf, as plug-and-play to any given dataset. Significant reduced annotation times using the interactive model can be observed on two public datasets.

Advancing post-traumatic seizure classification and biomarker identification: Information decomposition based multimodal fusion and explainable machine learning with missing neuroimaging data

A late post-traumatic seizure (LPTS), a consequence of traumatic brain injury (TBI), can potentially evolve into a lifelong condition known as post-traumatic epilepsy (PTE). Presently, the mechanism that triggers epileptogenesis in TBI patients remains elusive, inspiring the epilepsy community to devise ways to predict which TBI patients will develop PTE and to identify potential biomarkers. In response to this need, our study collected comprehensive, longitudinal multimodal data from 48 TBI patients across multiple participating institutions. A supervised binary classification task was created, contrasting data from LPTS patients with those without LPTS. To accommodate missing modalities in some subjects, we took a two-pronged approach. Firstly, we extended a graphical model-based Bayesian estimator to directly classify subjects with incomplete modality. Secondly, we explored conventional imputation techniques. The imputed multimodal information was then combined, following several fusion and dimensionality reduction techniques found in the literature, and subsequently fitted to a kernel- or a tree-based classifier. For this fusion, we proposed two new algorithms: recursive elimination of correlated components (RECC) that filters information based on the correlation between the already selected features, and information decomposition and selective fusion (IDSF), which effectively recombines information from decomposed multimodal features. Our cross-validation findings showed that the proposed IDSF algorithm delivers superior performance based on the area under the curve (AUC) score. Ultimately, after rigorous statistical comparisons and interpretable machine learning examination using Shapley values of the most frequently selected features, we recommend the two following magnetic resonance imaging (MRI) abnormalities as potential biomarkers: the left anterior limb of internal capsule in diffusion MRI (dMRI), and the right middle temporal gyrus in functional MRI (fMRI).

Evaluating the relationship between magnetic resonance image quality metrics and deep learning-based segmentation accuracy of brain tumors

BACKGROUND

Magnetic resonance imaging (MRI) scans are known to suffer from a variety of acquisition artifacts as well as equipment-based variations that impact image appearance and segmentation performance. It is still unclear whether a direct relationship exists between magnetic resonance (MR) image quality metrics (IQMs) (e.g., signal-to-noise, contrast-to-noise) and segmentation accuracy.

PURPOSE

Deep learning (DL) approaches have shown significant promise for automated segmentation of brain tumors on MRI but depend on the quality of input training images. We sought to evaluate the relationship between IQMs of input training images and DL-based brain tumor segmentation accuracy toward developing more generalizable models for multi-institutional data.

METHODS

We trained a 3D DenseNet model on the BraTS 2020 cohorts for segmentation of tumor subregions enhancing tumor (ET), peritumoral edematous, and necrotic and non-ET on MRI; with performance quantified via a 5-fold cross-validated Dice coefficient. MRI scans were evaluated through the open-source quality control tool MRQy, to yield 13 IQMs per scan. The Pearson correlation coefficient was computed between whole tumor (WT) dice values and IQM measures in the training cohorts to identify quality measures most correlated with segmentation performance. Each selected IQM was used to group MRI scans as "better" quality (BQ) or "worse" quality (WQ), via relative thresholding. Segmentation performance was re-evaluated for the DenseNet model when (i) training on BQ MRI images with validation on WQ images, as well as (ii) training on WQ images, and validation on BQ images. Trends were further validated on independent test sets derived from the BraTS 2021 training cohorts.

RESULTS

For this study, multimodal MRI scans from the BraTS 2020 training cohorts were used to train the segmentation model and validated on independent test sets derived from the BraTS 2021 cohort. Among the selected IQMs, models trained on BQ images based on inhomogeneity measurements (coefficient of variance, coefficient of joint variation, coefficient of variation of the foreground patch) and the models trained on WQ images based on noise measurement peak signal-to-noise ratio (SNR) yielded significantly improved tumor segmentation accuracy compared to their inverse models.

CONCLUSIONS

Our results suggest that a significant correlation may exist between specific MR IQMs and DenseNet-based brain tumor segmentation performance. The selection of MRI scans for model training based on IQMs may yield more accurate and generalizable models in unseen validation.

Quantitative Foot Muscle Magnetic Resonance Imaging Reliably Measures Disease Progression in Children and Adolescents with Charcot-Marie-Tooth Disease Type 1A

Quantitative muscle fat fraction (FF) responsiveness is lower in younger Charcot-Marie-Tooth disease type 1A (CMT1A) patients with lower baseline calf-level FF. We investigated the practicality, validity, and responsiveness of foot-level FF in this cohort involving 22 CMT1A patients and 14 controls. The mean baseline foot-level FF was 25.9 ± 20.3% in CMT1A patients, and the 365-day FF (n = 15) increased by 2.0 ± 2.4% (p < 0.001 vs controls). Intrinsic foot-level FF demonstrated large responsiveness (12-month standardized response mean (SRM) of 0.86) and correlated with the CMT examination score (ρ = 0.58, P = 0.01). Intrinsic foot-level FF has the potential to be used as a biomarker in future clinical trials involving younger CMT1A patients. ANN NEUROL 2024;96:170-174.

Motion correction of 3D dynamic contrast-enhanced ultrasound imaging without anatomical B-Mode images: Pilot evaluation in eight patients

BACKGROUND

Dynamic contrast-enhanced ultrasound (DCE-US) is highly susceptible to motion artifacts arising from patient movement, respiration, and operator handling and experience. Motion artifacts can be especially problematic in the context of perfusion quantification. In conventional 2D DCE-US, motion correction (MC) algorithms take advantage of accompanying side-by-side anatomical B-Mode images that contain time-stable features. However, current commercial models of 3D DCE-US do not provide side-by-side B-Mode images, which makes MC challenging.

PURPOSE

This work introduces a novel MC algorithm for 3D DCE-US and assesses its efficacy when handling clinical data sets.

METHODS

In brief, the algorithm uses a pyramidal approach whereby short temporal windows consisting of three consecutive frames are created to perform local registrations, which are then registered to a master reference derived from a weighted average of all frames. We applied the algorithm to imaging studies from eight patients with metastatic lesions in the liver and assessed improvements in original versus motion corrected 3D DCE-US cine using: (i) frame-to-frame volumetric overlap of segmented lesions, (ii) normalized correlation coefficient (NCC) between frames (similarity analysis), and (iii) sum of squared errors (SSE), root-mean-squared error (RMSE), and r-squared (R2) quality-of-fit from fitted time-intensity curves (TIC) extracted from a segmented lesion.

RESULTS

We noted improvements in frame-to-frame lesion overlap across all patients, from 68% ± 13% without correction to 83% ± 3% with MC (p = 0.023). Frame-to-frame similarity as assessed by NCC also improved on two different sets of time points from 0.694 ± 0.057 (original cine) to 0.862 ± 0.049 (corresponding MC cine) and 0.723 ± 0.066 to 0.886 ± 0.036 (p ≤ 0.001 for both). TIC analysis displayed a significant decrease in RMSE (p = 0.018) and a significant increase in R2 goodness-of-fit (p = 0.029) for the patient cohort.

CONCLUSIONS

Overall, results suggest decreases in 3D DCE-US motion after applying the proposed algorithm.

Evaluation of deep learning for detecting intraosseous jaw lesions in cone beam computed tomography volumes

OBJECTIVE

The study aim was to develop and assess the performance of a deep learning (DL) algorithm in the detection of radiolucent intraosseous jaw lesions in cone beam computed tomography (CBCT) volumes.

STUDY DESIGN

A total of 290 CBCT volumes from more than 12 different scanners were acquired. Fields of view ranged from 6 × 6 × 6 cm to 18 × 18 × 16 cm. CBCT volumes contained either zero or at least one biopsy-confirmed intraosseous lesion. 80 volumes with no intraosseous lesions were included as controls and were not annotated. 210 volumes with intraosseous lesions were manually annotated using ITK-Snap 3.8.0. 150 volumes (10 control, 140 positive) were presented to the DL software for training. Validation was performed using 60 volumes (30 control, 30 positive). Testing was performed using the remaining 80 volumes (40 control, 40 positive).

RESULTS

The DL algorithm obtained an adjusted sensitivity by case, specificity by case, positive predictive value by case, and negative predictive value by case of 0.975, 0.825, 0.848, and 0.971, respectively.

CONCLUSIONS

A DL algorithm showed moderate success at lesion detection in their correct locations, as well as recognition of lesion shape and extent. This study demonstrated the potential of DL methods for intraosseous lesion detection in CBCT volumes.

The Hao-Fountain syndrome protein USP7 regulates neuronal connectivity in the brain via a novel p53-independent ubiquitin signaling pathway

Precise control of protein ubiquitination is essential for brain development, and hence, disruption of ubiquitin signaling networks can lead to neurological disorders. Mutations of the deubiquitinase USP7 cause the Hao-Fountain syndrome (HAFOUS), characterized by developmental delay, intellectual disability, autism, and aggressive behavior. Here, we report that conditional deletion of USP7 in excitatory neurons in the mouse forebrain triggers diverse phenotypes including sensorimotor deficits, learning and memory impairment, and aggressive behavior, resembling clinical features of HAFOUS. USP7 deletion induces neuronal apoptosis in a manner dependent of the tumor suppressor p53. However, most behavioral abnormalities in USP7 conditional mice persist despite p53 loss. Strikingly, USP7 deletion in the brain perturbs the synaptic proteome and dendritic spine morphogenesis independently of p53. Integrated proteomics analysis reveals that the neuronal USP7 interactome is enriched for proteins implicated in neurodevelopmental disorders and specifically identifies the RNA splicing factor Ppil4 as a novel neuronal substrate of USP7. Knockdown of Ppil4 in cortical neurons impairs dendritic spine morphogenesis, phenocopying the effect of USP7 loss on dendritic spines. These findings reveal a novel USP7-Ppil4 ubiquitin signaling link that regulates neuronal connectivity in the developing brain, with implications for our understanding of the pathogenesis of HAFOUS and other neurodevelopmental disorders.

Sex-dependent susceptibility to brain metabolic dysfunction and memory impairment in response to pre- and postnatal high-fat diet

The developing brain is sensitive to the impacts of early-life nutritional intake. This study investigates whether maternal high fat diet (HFD) causes glucose metabolism impairment, neuroinflammation, and memory impairment in immature and adult offspring, and whether it may be affected by postweaning diets in a sex-dependent manner in adult offspring. After weaning, female rats were fed HFD (55.9% fat) or normal chow diet (NCD; 10% fat) for 8 weeks before mating, during pregnancy, and lactation. On postnatal day 21 (PND21), the male and female offspring of both groups were split into two new groups, and NCD or HFD feeding was maintained until PND180. On PND21 and PND180, brain glucose metabolism-, inflammation-, and Alzheimer's pathology-related markers were by qPCR. In adult offspring, peripheral insulin resistance parameters, spatial memory performance, and brain glucose metabolism (18F-FDG-PET scan and protein levels of IDE and GLUT3) were assessed. Histological analysis was also performed on PND21 and adult offspring. On PND21, we found that maternal HFD affected transcript levels of glucose metabolism markers in both sexes. In adult offspring, more profoundly in males, postweaning HFD in combination with maternal HFD induced peripheral and brain metabolic disturbances, impaired memory performance and elevated inflammation, dementia risk markers, and neuronal loss. Our results suggest that maternal HFD affects brain glucose metabolism in the early ages of both sexes. Postweaning HFD sex-dependently causes brain metabolic dysfunction and memory impairment in later-life offspring; effects that can be worsened in combination with maternal HFD.

Hunting imaging biomarkers in pulmonary fibrosis: Benchmarks of the AIIB23 challenge

Airway-related quantitative imaging biomarkers are crucial for examination, diagnosis, and prognosis in pulmonary diseases. However, the manual delineation of airway structures remains prohibitively time-consuming. While significant efforts have been made towards enhancing automatic airway modelling, current public-available datasets predominantly concentrate on lung diseases with moderate morphological variations. The intricate honeycombing patterns present in the lung tissues of fibrotic lung disease patients exacerbate the challenges, often leading to various prediction errors. To address this issue, the 'Airway-Informed Quantitative CT Imaging Biomarker for Fibrotic Lung Disease 2023' (AIIB23) competition was organized in conjunction with the official 2023 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). The airway structures were meticulously annotated by three experienced radiologists. Competitors were encouraged to develop automatic airway segmentation models with high robustness and generalization abilities, followed by exploring the most correlated QIB of mortality prediction. A training set of 120 high-resolution computerised tomography (HRCT) scans were publicly released with expert annotations and mortality status. The online validation set incorporated 52 HRCT scans from patients with fibrotic lung disease and the offline test set included 140 cases from fibrosis and COVID-19 patients. The results have shown that the capacity of extracting airway trees from patients with fibrotic lung disease could be enhanced by introducing voxel-wise weighted general union loss and continuity loss. In addition to the competitive image biomarkers for mortality prediction, a strong airway-derived biomarker (Hazard ratio>1.5, p < 0.0001) was revealed for survival prognostication compared with existing clinical measurements, clinician assessment and AI-based biomarkers.

Traumatic brain injury alters the effects of class II invariant peptide (CLIP) antagonism on chronic meningeal CLIP + B cells, neuropathology, and neurobehavioral impairment in 5xFAD mice

BACKGROUND

Traumatic brain injury (TBI) is a significant risk factor for Alzheimer's disease (AD), and accumulating evidence supports a role for adaptive immune B and T cells in both TBI and AD pathogenesis. We previously identified B cell and major histocompatibility complex class II (MHCII)-associated invariant chain peptide (CLIP)-positive B cell expansion after TBI. We also showed that antagonizing CLIP binding to the antigen presenting groove of MHCII after TBI acutely reduced CLIP + splenic B cells and was neuroprotective. The current study investigated the chronic effects of antagonizing CLIP in the 5xFAD Alzheimer's mouse model, with and without TBI.

METHODS

12-week-old male wild type (WT) and 5xFAD mice were administered either CLIP antagonist peptide (CAP) or vehicle, once at 30 min after either sham or a lateral fluid percussion injury (FPI). Analyses included flow cytometric analysis of immune cells in dural meninges and spleen, histopathological analysis of the brain, magnetic resonance diffusion tensor imaging, cerebrovascular analysis, and assessment of motor and neurobehavioral function over the ensuing 6 months.

RESULTS

9-month-old 5xFAD mice had significantly more CLIP + B cells in the meninges compared to age-matched WT mice. A one-time treatment with CAP significantly reduced this population in 5xFAD mice. Importantly, CAP also improved some of the immune, histopathological, and neurobehavioral impairments in 5xFAD mice over the ensuing six months. Although FPI did not further elevate meningeal CLIP + B cells, it did negate the ability of CAP to reduce meningeal CLIP + B cells in the 5xFAD mice. FPI at 3 months of age exacerbated some aspects of AD pathology in 5xFAD mice, including further reducing hippocampal neurogenesis, increasing plaque deposition in CA3, altering microgliosis, and disrupting the cerebrovascular structure. CAP treatment after injury ameliorated some but not all of these FPI effects.

Preoperative CT-based radiomics and deep learning model for predicting risk stratification of gastric gastrointestinal stromal tumors

BACKGROUND

Gastrointestinal stromal tumors (GISTs) are clinically heterogeneous with various malignant potential in different individuals. It is crucial to explore a reliable method for preoperative risk stratification of gastric GISTs noninvasively.

PURPOSE

To establish and evaluate a machine learning model using the combination of computed tomography (CT) morphology, radiomics, and deep learning features to predict the risk stratification of primary gastric GISTs preoperatively.

METHODS

The 193 gastric GISTs lesions were randomly divided into training set, validation set, and test set in a ratio of 6:2:2. The qualitative and quantitative CT morphological features were assessed by two radiologists. The tumors were segmented manually, and then radiomic features were extracted using PyRadiomics and the deep learning features were extracted using pre-trained Resnet50 from arterial phase and venous phase CT images, respectively. Pearson correlation analysis and recursive feature elimination were used for feature selection. Support vector machines were employed to build a classifier for predicting the risk stratification of GISTs. This study compared the performance of models using different pre-trained convolutional neural networks (CNNs) to extract deep features for classification, as well as the performance of modeling features from single-phase and dual-phase images. The arterial phase, venous phase and dual-phase machine learning models were built, respectively, and the morphological features were added to the dual-phase machine learning model to construct a combined model. Receiver operating characteristic (ROC) curves were used to evaluate the efficacy of each model. The clinical application value of the combined model was determined through the decision curve analysis (DCA) and the net reclassification index (NRI) was analyzed.

RESULTS

The area under the curve (AUC) of the dual-phase machine learning model was 0.876, which was higher than that of the arterial phase model or venous phase model (0.813, 0.838, respectively). The combined model had best predictive performance than the above models with an AUC of 0.941 (95% CI: 0.887-0.974) (p = 0.012, Delong test). DCA demonstrated that the combined model had good clinical application value with an NRI of 0.575 (95% CI: 0.357-0.891).

CONCLUSION

In this study, we established a combined model that incorporated dual-phase morphology, radiomics, and deep learning characteristics, which can be used to predict the preoperative risk stratification of gastric GISTs.

Mesostriatal Dopaminergic Circuit Dysfunction in Schizophrenia: A Multimodal Neuromelanin-sensitive MRI and [18F]-DOPA PET Study

BACKGROUND

Striatal hyperdopaminergia is implicated in the pathoetiology of schizophrenia, but how this relates to dopaminergic midbrain activity is unclear. Neuromelanin-sensitive MRI (NM-MRI) provides a marker of long-term dopamine function. We examined if midbrain NM-MRI contrast-to-noise ratio (NM-CNR) was higher in people with schizophrenia relative to controls and if this correlated with dopamine synthesis capacity.

METHODS

N=154 participants (n=74 individuals with schizophrenia and n=80 healthy controls) underwent NM-MRI of the substantia nigra and ventral tegmental area (SN-VTA). A subset of the schizophrenia group (n=38) also received [18F]-DOPA PET to measure dopamine synthesis capacity (Kicer) in the SN-VTA and striatum.

RESULTS

SN-VTA NM-CNR was significantly higher in patients with schizophrenia relative to controls (effect size=0.38, p=0.019). This effect was greatest for voxels in the medial and ventral SN-VTA. In patients, SN-VTA Kicer positively correlated with SN-VTA NM-CNR (r=0.44, p=0.005) and striatal Kicer (r=0.71, p<0.001). Voxelwise analysis demonstrated that SN-VTA NM-CNR was positively associated with striatal Kicer (r=0.53, p=0.005) and that this relationship appeared strongest between the ventral SN-VTA and associative striatum in schizophrenia.

CONCLUSIONS

Our results suggest that neuromelanin levels are higher in patients with schizophrenia relative to controls, particularly in midbrain regions that project to parts of the striatum which receive innervation from the limbic and association cortices. The direct relationship between measures of neuromelanin and dopamine synthesis suggests that these aspects of schizophrenia pathophysiology are linked. Our findings highlight specific mesostriatal circuits as the loci of dopamine dysfunction in schizophrenia and, thus, potential therapeutic targets.

CT imaging-derived phenotypes for abdominal muscle and their association with age and sex in a medical biobank

The study of muscle mass as an imaging-derived phenotype (IDP) may yield new insights into determining the normal and pathologic variations in muscle mass in the population. This can be done by determining 3D abdominal muscle mass from 12 distinct abdominal muscle regions and groups using computed tomography (CT) in a racially diverse medical biobank. To develop a fully automatic technique for assessment of CT abdominal muscle IDPs and preliminarily determine abdominal muscle IDP variations with age and sex in a clinically and racially diverse medical biobank. This retrospective study was conducted using the Penn Medicine BioBank (PMBB), a research protocol that recruits adult participants during outpatient visits at hospitals in the Penn Medicine network. We developed a deep residual U-Net (ResUNet) to segment 12 abdominal muscle groups including the left and right psoas, quadratus lumborum, erector spinae, gluteus medius, rectus abdominis, and lateral abdominals. 110 CT studies were randomly selected for training, validation, and testing. 44 of the 110 CT studies were selected to enrich the dataset with representative cases of intra-abdominal and abdominal wall pathology. The studies were divided into non-overlapping training, validation and testing sets. Model performance was evaluated using the Sørensen-Dice coefficient. Volumes of individual muscle groups were plotted to distribution curves. To investigate associations between muscle IDPs, age, and sex, deep learning model segmentations were performed on a larger abdominal CT dataset from PMBB consisting of 295 studies. Multivariable models were used to determine relationships between muscle mass, age and sex. The model's performance (Dice scores) on the test data was the following: psoas: 0.85 ± 0.12, quadratus lumborum: 0.72 ± 0.14, erector spinae: 0.92 ± 0.07, gluteus medius: 0.90 ± 0.08, rectus abdominis: 0.85 ± 0.08, lateral abdominals: 0.85 ± 0.09. The average Dice score across all muscle groups was 0.86 ± 0.11. Average total muscle mass for females was 2041 ± 560.7 g with a high of 2256 ± 560.1 g (41-50 year old cohort) and a change of - 0.96 g/year, declining to an average mass of 1579 ± 408.8 g (81-100 year old cohort). Average total muscle mass for males was 3086 ± 769.1 g with a high of 3385 ± 819.3 g (51-60 year old cohort) and a change of - 1.73 g/year, declining to an average mass of 2629 ± 536.7 g (81-100 year old cohort). Quadratus lumborum was most highly correlated with age for both sexes (correlation coefficient of - 0.5). Gluteus medius mass in females was positively correlated with age with a coefficient of 0.22. These preliminary findings show that our CNN can automate detailed abdominal muscle volume measurement. Unlike prior efforts, this technique provides 3D muscle segmentations of individual muscles. This technique will dramatically impact sarcopenia diagnosis and research, elucidating its clinical and public health implications. Our results suggest a peak age range for muscle mass and an expected rate of decline, both of which vary between genders. Future goals are to investigate genetic variants for sarcopenia and malnutrition, while describing genotype-phenotype associations of muscle mass in healthy humans using imaging-derived phenotypes. It is feasible to obtain 3D abdominal muscle IDPs with high accuracy from patients in a medical biobank using fully automated machine learning methods. Abdominal muscle IDPs showed significant variations in lean mass by age and sex. In the future, this tool can be leveraged to perform a genome-wide association study across the medical biobank and determine genetic variants associated with early or accelerated muscle wasting.

A high-density 1,024-channel probe for brain-wide recordings in non-human primates

Large-scale neural population recordings with single-cell resolution across the primate brain remain challenging. Here we introduce the Neuroscroll probe that isolates single neuronal activities simultaneously from 1,024 densely spaced channels that are flexibly distributed across the shank of the probe. The Neuroscroll probe length is easily tunable for individual probes from 10 mm to 90 mm, covering the brain size of non-human primates and humans, and the probes remain intact and functional after repeated bending deformations. The Neuroscroll probes provided reliable recordings from large neural populations with high chronic stability up to 105 weeks in rats. Recording with each Neuroscroll probe yielded hundreds of well-isolated single units simultaneously from multiple brain regions distributed across the entire depth of the rhesus macaque brain. With the thousand simultaneously recorded channels, unprecedented probe length, excellent mechanical stability and flexible recording site distribution, the Neuroscroll probes enable a wide range of new experimental paradigms in system neuroscience studies with great versatility.

Network pharmacology and experimental verification to decode the action of Qing Fei Hua Xian Decotion against pulmonary fibrosis

BACKGROUND

Pulmonary fibrosis (PF) is a common interstitial pneumonia disease, also occurred in post-COVID-19 survivors. The mechanism underlying the anti-PF effect of Qing Fei Hua Xian Decotion (QFHXD), a traditional Chinese medicine formula applied for treating PF in COVID-19 survivors, is unclear. This study aimed to uncover the mechanisms related to the anti-PF effect of QFHXD through analysis of network pharmacology and experimental verification.

METHODS

The candidate chemical compounds of QFHXD and its putative targets for treating PF were achieved from public databases, thereby we established the corresponding "herb-compound-target" network of QFHXD. The protein-protein interaction network of potential targets was also constructed to screen the core targets. Furthermore, Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis were used to predict targets, and pathways, then validated by in vivo experiments.

RESULTS

A total of 188 active compounds in QFHXD and 50 target genes were identified from databases. The key therapeutic targets of QFHXD, such as PI3K/Akt, IL-6, TNF, IL-1β, STAT3, MMP-9, and TGF-β1 were identified by KEGG and GO analysis. Anti-PF effects of QFHXD (in a dose-dependent manner) and prednisone were confirmed by HE, Masson staining, and Sirius red staining as well as in vivo Micro-CT and immunohistochemical analysis in a rat model of bleomycin-induced PF. Besides, QFXHD remarkably inhibits the activity of PI3K/Akt/NF-κB and TGF-β1/Smad2/3.

CONCLUSIONS

QFXHD significantly attenuated bleomycin-induced PF via inhibiting inflammation and epithelial-mesenchymal transition. PI3K/Akt/NF-κB and TGF-β1/Smad2/3 pathways might be the potential therapeutic effects of QFHXD for treating PF.

Systematic review and meta-analysis of automated methods for quantifying enlarged perivascular spaces in the brain

Research into magnetic resonance imaging (MRI)-visible perivascular spaces (PVS) has recently increased, as results from studies in different diseases and populations are cementing their association with sleep, disease phenotypes, and overall health indicators. With the establishment of worldwide consortia and the availability of large databases, computational methods that allow to automatically process all this wealth of information are becoming increasingly relevant. Several computational approaches have been proposed to assess PVS from MRI, and efforts have been made to summarise and appraise the most widely applied ones. We systematically reviewed and meta-analysed all publications available up to September 2023 describing the development, improvement, or application of computational PVS quantification methods from MRI. We analysed 67 approaches and 60 applications of their implementation, from 112 publications. The two most widely applied were the use of a morphological filter to enhance PVS-like structures, with Frangi being the choice preferred by most, and the use of a U-Net configuration with or without residual connections. Older adults or population studies comprising adults from 18 years old onwards were, overall, more frequent than studies using clinical samples. PVS were mainly assessed from T2-weighted MRI acquired in 1.5T and/or 3T scanners, although combinations using it with T1-weighted and FLAIR images were also abundant. Common associations researched included age, sex, hypertension, diabetes, white matter hyperintensities, sleep and cognition, with occupation-related, ethnicity, and genetic/hereditable traits being also explored. Despite promising improvements to overcome barriers such as noise and differentiation from other confounds, a need for joined efforts for a wider testing and increasing availability of the most promising methods is now paramount.

SIPAS: A comprehensive susceptibility imaging process and analysis studio

Quantitative susceptibility mapping (QSM) is a rising MRI-based technology and quite a few QSM-related algorithms have been proposed to reconstruct maps of tissue susceptibility distribution from phase images. In this paper, we develop a comprehensive susceptibility imaging process and analysis studio (SIPAS) that can accomplish reliable QSM processing and offer a standardized evaluation system. Specifically, SIPAS integrates multiple methods for each step, enabling users to select algorithm combinations according to data conditions, and QSM maps could be evaluated by two aspects, including image quality indicators within all voxels and region-of-interest (ROI) analysis. Through a sophisticated design of user-friendly interfaces, the results of each procedure are able to be exhibited in axial, coronal, and sagittal views in real-time, meanwhile ROIs can be displayed in 3D rendering visualization. The accuracy and compatibility of SIPAS are demonstrated by experiments on multiple in vivo human brain datasets acquired from 3T, 5T, and 7T MRI scanners of different manufacturers. We also validate the QSM maps obtained by various algorithm combinations in SIPAS, among which the combination of iRSHARP and SFCR achieves the best results on its evaluation system. SIPAS is a comprehensive, sophisticated, and reliable toolkit that may prompt the QSM application in scientific research and clinical practice.

Automated quantification of wrist bone marrow oedema, pre- and post-treatment, in early rheumatoid arthritis

Objective

Bone inflammation (osteitis) in early RA (ERA) manifests as bone marrow oedema (BME) and precedes the development of bone erosion. In this prospective, single-centre study, we developed an automated post-processing pipeline for quantifying the severity of wrist BME on T2-weighted fat-suppressed MRI.

Methods

A total of 80 ERA patients [mean age 54 years (s.d. 12), 62 females] were enrolled at baseline and 49 (40 females) after 1 year of treatment. For automated bone segmentation, a framework based on a convolutional neural network (nnU-Net) was trained and validated (5-fold cross-validation) for 15 wrist bone areas at baseline in 60 ERA patients. For BME quantification, BME was identified by Gaussian mixture model clustering and thresholding. BME proportion (%) and relative BME intensity within each bone area were compared with visual semi-quantitative assessment of the RA MRI score (RAMRIS).

Results

For automated wrist bone area segmentation, overall bone Sørensen-Dice similarity coefficient was 0.91 (s.d. 0.02) compared with ground truth manual segmentation. High correlation (Pearson correlation coefficient r = 0.928, P < 0.001) between visual RAMRIS BME and automated BME proportion assessment was found. The automated BME proportion decreased after treatment, correlating highly (r = 0.852, P < 0.001) with reduction in the RAMRIS BME score.

Conclusion

The automated model developed had an excellent segmentation performance and reliable quantification of both the proportion and relative intensity of wrist BME in ERA patients, providing a more objective and efficient alternative to RAMRIS BME scoring.

Predicting Cognitive Functioning for Patients with a High-Grade Glioma: Evaluating Different Representations of Tumor Location in a Common Space

Cognitive functioning is increasingly considered when making treatment decisions for patients with a brain tumor in view of a personalized onco-functional balance. Ideally, one can predict cognitive functioning of individual patients to make treatment decisions considering this balance. To make accurate predictions, an informative representation of tumor location is pivotal, yet comparisons of representations are lacking. Therefore, this study compares brain atlases and principal component analysis (PCA) to represent voxel-wise tumor location. Pre-operative cognitive functioning was predicted for 246 patients with a high-grade glioma across eight cognitive tests while using different representations of voxel-wise tumor location as predictors. Voxel-wise tumor location was represented using 13 different frequently-used population average atlases, 13 randomly generated atlases, and 13 representations based on PCA. ElasticNet predictions were compared between representations and against a model solely using tumor volume. Preoperative cognitive functioning could only partly be predicted from tumor location. Performances of different representations were largely similar. Population average atlases did not result in better predictions compared to random atlases. PCA-based representation did not clearly outperform other representations, although summary metrics indicated that PCA-based representations performed somewhat better in our sample. Representations with more regions or components resulted in less accurate predictions. Population average atlases possibly cannot distinguish between functionally distinct areas when applied to patients with a glioma. This stresses the need to develop and validate methods for individual parcellations in the presence of lesions. Future studies may test if the observed small advantage of PCA-based representations generalizes to other data.

Transition-zone PSA-density calculated from MRI deep learning prostate zonal segmentation model for prediction of clinically significant prostate cancer

PURPOSE

To develop a deep learning (DL) zonal segmentation model of prostate MR from T2-weighted images and evaluate TZ-PSAD for prediction of the presence of csPCa (Gleason score of 7 or higher) compared to PSAD.

METHODS

1020 patients with a prostate MRI were randomly selected to develop a DL zonal segmentation model. Test dataset included 20 cases in which 2 radiologists manually segmented both the peripheral zone (PZ) and TZ. Pair-wise Dice index was calculated for each zone. For the prediction of csPCa using PSAD and TZ-PSAD, we used 3461 consecutive MRI exams performed in patients without a history of prostate cancer, with pathological confirmation and available PSA values, but not used in the development of the segmentation model as internal test set and 1460 MRI exams from PI-CAI challenge as external test set. PSAD and TZ-PSAD were calculated from the segmentation model output. The area under the receiver operating curve (AUC) was compared between PSAD and TZ-PSAD using univariate and multivariate analysis (adjusts age) with the DeLong test.

RESULTS

Dice scores of the model against two radiologists were 0.87/0.87 and 0.74/0.72 for TZ and PZ, while those between the two radiologists were 0.88 for TZ and 0.75 for PZ. For the prediction of csPCa, the AUCs of TZPSAD were significantly higher than those of PSAD in both internal test set (univariate analysis, 0.75 vs. 0.73, p < 0.001; multivariate analysis, 0.80 vs. 0.78, p < 0.001) and external test set (univariate analysis, 0.76 vs. 0.74, p < 0.001; multivariate analysis, 0.77 vs. 0.75, p < 0.001 in external test set).

CONCLUSION

DL model-derived zonal segmentation facilitates the practical measurement of TZ-PSAD and shows it to be a slightly better predictor of csPCa compared to the conventional PSAD. Use of TZ-PSAD may increase the sensitivity of detecting csPCa by 2-5% for a commonly used specificity level.

Machine learning in predicting pathological complete response to neoadjuvant chemoradiotherapy in rectal cancer using MRI: a systematic review and meta-analysis

OBJECTIVES

To evaluate the performance of machine learning models in predicting pathological complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) in patients with rectal cancer using magnetic resonance imaging.

METHODS

We searched PubMed, Embase, Cochrane Library, and Web of Science for studies published before March 2024. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) was used to assess the methodological quality of the included studies, random-effects models were used to calculate sensitivity and specificity, I2 values were used for heterogeneity measurements, and subgroup analyses were carried out to detect potential sources of heterogeneity.

RESULTS

A total of 1699 patients from 24 studies were included. For machine learning models in predicting pCR to nCRT, the meta-analysis calculated a pooled area under the curve (AUC) of 0.91 (95% CI, 0.88-0.93), pooled sensitivity of 0.83 (95% CI, 0.74-0.89), and pooled specificity of 0.86 (95% CI, 0.80-0.91). We investigated 6 studies that mainly contributed to heterogeneity. After performing meta-analysis again excluding these 6 studies, the heterogeneity was significantly reduced. In subgroup analysis, the pooled AUC of the deep-learning model was 0.93 and 0.89 for the traditional statistical model; the pooled AUC of studies that used diffusion-weighted imaging (DWI) was 0.90 and 0.92 in studies that did not use DWI; the pooled AUC of studies conducted in China was 0.93, and was 0.83 in studies conducted in other countries.

CONCLUSIONS

This systematic study showed that machine learning has promising potential in predicting pCR to nCRT in patients with locally advanced rectal cancer. Compared to traditional machine learning models, although deep-learning-based studies are less predominant and more heterogeneous, they are able to obtain higher AUC.

ADVANCES IN KNOWLEDGE

Compared to traditional machine learning models, deep-learning-based studies are able to obtain higher AUC, although they are less predominant and more heterogeneous. Together with clinical information, machine learning-based models may bring us closer towards precision medicine.

Adults with Treacher Collins Syndrome Share Comparable 3D Upper Airway Dimensions with Nonsyndromic Individuals

Purpose

Sleep apnea symptoms, such as snoring and daytime somnolence, are commonly observed in individuals with Treacher Collins Syndrome (TCS) and may be related to airway obstruction due to micro- and retro-gnathia. This study aims to three-dimensionally evaluate the upper airway using cone-beam computed tomography (CBCT) exams of adolescents (TCS-ADOL) and adults (TCS-ADUL) with TCS compared to a nonsyndromic group (CON).

Materials and Methods

Twenty-six CBCT exams were divided into three groups: TCS-ADOL (n = 7) (13.14 ± 1.67 years): CBCT exams of TCS adolescents; TCS-ADUL (n = 10) (21.80 ± 4.39 years): CBCT exams of TCS adults; and CON (n = 9) (25.33 ± 8.57 years): CBCT exams of adult nonsyndromic individuals with Class II skeletal pattern. The variables analyzed were (1) total upper airway volume; (2) nasal cavity volume; (3) total pharyngeal volume; (4) nasopharyngeal volume; (5) oropharyngeal volume; (6) pharyngeal minimal cross-sectional area; (7) pharyngeal length; and (8) pharyngeal depth. Scans were analyzed by two examiners, and intra- and inter-rater agreement was calculated. A p-value of ≤0.05 was considered significant.

Results

Although not statistically significant, the TCS-ADUL group showed decreased airway volume and minimal cross-sectional areas compared to the CON group. There were also significant differences between TCS-ADOL and TCS-ADUL, with significantly lower airway volumes in the TCS-ADOL group. Strong positive correlations were found between certain airway measurements in the TCS-ADOL group, which were not observed in adults.

Conclusions

The upper airways of adults with TCS are dimensionally similar to those of nonsyndromic individuals, despite absolute value reductions found in the syndromic group. The reduced airway in the adolescent population suggests significant potential for growth, mainly in pharyngeal dimensions.

Identification of clear cell renal cell carcinoma subtypes by integrating radiomics and transcriptomics

Objective

This study aimed to delineate the clear cell renal cell carcinoma (ccRCC) intrinsic subtypes through unsupervised clustering of radiomics and transcriptomics data and to evaluate their associations with clinicopathological features, prognosis, and molecular characteristics.

Methods

Using a retrospective dual-center approach, we gathered transcriptomic and clinical data from ccRCC patients registered in The Cancer Genome Atlas and contrast-enhanced computed tomography images from The Cancer Imaging Archive and local databases. Following the segmentation of images, radiomics feature extraction, and feature preprocessing, we performed unsupervised clustering based on the "CancerSubtypes" package to identify distinct radiotranscriptomic subtypes, which were then correlated with clinical-pathological, prognostic, immune, and molecular characteristics.

Results

Clustering identified three subtypes, C1, C2, and C3, each of which displayed unique clinicopathological, prognostic, immune, and molecular distinctions. Notably, subtypes C1 and C3 were associated with poorer survival outcomes than subtype C2. Pathway analysis highlighted immune pathway activation in C1 and metabolic pathway prominence in C2. Gene mutation analysis identified VHL and PBRM1 as the most commonly mutated genes, with more mutated genes observed in the C3 subtype. Despite similar tumor mutation burdens, microsatellite instability, and RNA interference across subtypes, C1 and C3 demonstrated greater tumor immune dysfunction and rejection. In the validation cohort, the various subtypes showed comparable results in terms of clinicopathological features and prognosis to those observed in the training cohort, thus confirming the efficacy of our algorithm.

Conclusion

Unsupervised clustering based on radiotranscriptomics can identify the intrinsic subtypes of ccRCC, and radiotranscriptomic subtypes can characterize the prognosis and molecular features of tumors, enabling noninvasive tumor risk stratification.

Surface-based morphometry of the corpus callosum in young children of ages 1-5

The corpus callosum (CC) is a large white matter fiber bundle in the brain and is involved in various cognitive, sensory, and motor processes. While implicated in various developmental and psychiatric disorders, much is yet to be uncovered about the normal development of this structure, especially in young children. Additionally, while sexual dimorphism has been reported in prior literature, observations have not necessarily been consistent. In this study, we use morphometric measures including surface tensor-based morphometry (TBM) to investigate local changes in the shape of the CC in children between the ages of 12 and 60 months, in intervals of 12 months. We also analyze sex differences in each of these age groups. We observed larger significant clusters in the earlier ages between 12 v 24 m and between 48 v 60 m and localized differences in the anterior region of the body of the CC. Sex differences were most pronounced in the 12 m group. This study adds to the growing literature of work aiming to understand the developing brain and emphasizes the utility of surface TBM as a useful tool for analyzing regional differences in neuroanatomical morphometry.

Testing quantitative magnetization transfer models with membrane lipids

PURPOSE

Quantitative magnetization transfer (qMT) models aim to quantify the contributions of lipids and macromolecules to the MRI signal. Hence, a model system that relates qMT parameters and their molecular sources may improve the interpretation of the qMT parameters. Here we used membrane lipid phantoms as a meaningful tool to study qMT models. By controlling the fraction and type of membrane lipids, we could test the accuracy, reliability, and interpretability of different qMT models.

METHODS

We formulated liposomes with various lipid types and water-to-lipids fractions and measured their signals with spoiled gradient-echo MT. We fitted three known qMT models and estimated six parameters for every model. We tested the accuracy and reproducibility of the models and compared the dependency among the qMT parameters. We compared the samples' qMT parameters with their water-to-lipid fractions and with a simple MTnorm (= MTon/MToff) calculation.

RESULTS

We found that the three qMT models fit the membrane lipids signals well. We also found that the estimated qMT parameters are highly interdependent. Interestingly, the estimated qMT parameters are a function of the membrane lipid type and also highly related to the water-to-lipid fraction. Finally, we find that most of the lipid sample's information can be captured using the common and easy to estimate MTnorm analysis.

CONCLUSION

qMT parameters are sensitive to both the water-to-lipid fraction and to the lipid type. Estimating the water-to-lipid fraction can improve the characterization of membrane lipids' contributions to qMT parameters. Similar characterizations can be obtained using the MTnorm analysis.