Radiomics Features Based on MRI-ADC Maps of Patients with Breast Cancer: Relationship with Lesion Size, Features Stability, and Model Accuracy.

Objective: To predict breast cancer molecular subtypes with neural networks based on magnetic resonance imaging apparent diffusion coefficient (ADC) radiomics and to detect the relation of lesion size with the stability of radiomics features. Methods: This retrospective study included 221 consecutive patients (224 lesions) with breast cancer imaged between January 2015 and January 2020. Three sample size configurations were identified based on tumor size (experiment 1: all cases, experiment 2: >1 cm3, and experiment 3: >2 cm3). The tumors were segmented by three observers based on diffusion-weighted imaging-registered ADC maps, and the volumetric agreement of these segmentations was evaluated using the Dice coefficient. Stability of radiomics features (n=851) was evaluated with intraclass correlation coefficient (ICC, >0.75) and coefficient of variation (CoV, <0.15). Feature selection was made with variance inflation factor (VIF, <10) and least absolute shrinkage and selection operator regression. Outcomes were identified as molecular subtypes (Luminal A, Luminal B, HER2-enriched, triple-negative). Neural network performance was presented as an area under the curve and accuracies. Results: Of the 851 radiomics features, 611 had ICC >0.75, and 37 remained stable in the first experiment, 49 in the second, and 59 in the third based on CoV and VIF analysis. High accuracy was demonstrated by the Luminal B, HER2-enriched, and triple-negative models in the first experiment (>80%), all models in the second experiment, and HER2-enriched and triple-negative models in the third experiment. Conclusions: A positive stability is indicated by an increased lesion size related to radiomics features. Neural networks may predict moleculer subtypes of breast cancers over 1 cm3 with high accuracy.

Multivariable Diagnostic Prediction Model to Detect Hormone Secretion Profile From T2W MRI Radiomics with Artificial Neural Networks in Pituitary Adenomas.

Objective: This study aims to develop neural networks to detect hormone secretion profiles in the pituitary adenomas based on T2 weighted magnetic resonance imaging (MRI) radiomics. Methods: This retrospective model-development study included a cohort of patients with pituitary adenomas (n=130) from January 2015 to January 2020 in one tertiary center. The mean age was 46.49±13.69 years, and 76/130 (58.46%) were women. Three observers segmented lesions on coronal T2 weighted MRI, and an interrater agreement was evaluated using the Dice coefficient. Predictors were determined as radiomics features (n=851). Feature selection was based on intraclass correlation coefficient, coefficient variance, variance inflation factor, and LASSO regression analysis. Outcomes were identified as 7 hormone secretion profiles [non-functioning pituitary adenoma, growth hormone-secreting adenomas, prolactinomas, adrenocorticotropic hormone-secreting adenomas, pluri-hormonal secreting adenomas (PHA), follicle-stimulating hormone and luteinizing hormone-secreting adenomas, and thyroid-stimulating hormone adenomas]. A multivariable diagnostic prediction model was developed with artificial neural networks (ANN) for 7 outcomes. ANN performance was presented as an area under the receiver operating characteristic curve (AUC) and accepted as successful if the AUC was >0.85 and p-value was <0.01. Results: The performance of the ANN distinguishing prolactinomas from other adenomas was validated (AUC=0.95, p<0.001, sensitivity: 91%, and specificity: 98%). The model distinguishing PHA had the lowest AUC (AUC=0.74 and p<0.001). The AUC values for the other five ANN were >0.85 and p values were <0.001. Conclusions: This study was successful in training neural networks that could differentiate the hormone secretion profile of pituitary adenomas.

Radiological approach to basilar invagination type B: Reliability and accuracy.

OBJECTIVES: This study aims to determine the reliability of the radiological tests used in the diagnosis of basilar invagination (BI). METHODS: Patients diagnosed with type B basilar invagination, who had both magnetic resonance (MR) and computed tomography (CT) imaging between January 2014 and November 2019 were included in this retrospective reliability study. In this study, distance from odontoid apex to Chamberlain's line (OA-CL) was accepted as a reference method for the diagnosis. Forty-two BI cases and 79 controls were included. Three radiologists with different levels of experience individually evaluated OA-CL, Boogard's angle (BoA), clivo-axial angle (CXA), clivo-dens angle (CDA), and clivo-palate angle (CPA) on midsagittal CT and MR images. Statistical analysis was made with the intraclass correlation coefficient (ICC), t-test, and receiver operating characteristic (ROC) curve. RESULTS: The ICC for CT and MR were; 0.977-0.973 (OA-CL), 0.912-0.882 (BoA), 0.845-0.846 (CXA), 0.862-0.864 (CDA), and 0.762-0.747 (CPA) respectively (P < 0.001). The areas under the ROC curve were 0.977 (BoA), 0.832 (CXA), 0.852 (CDA), and 0.719 (CPA) (P < 0.001). The cut-off measures were ≥137.84° (BoA), ≤149.25° (CXA), ≤129.58° (CDA), and ≤61.83° (CPA). The diagnostic accuracies were 0.954 (BoA), 0.664 (CXA), 0.704 (CDA), 0.438 (CPA) (P < 0.001). CONCLUSIONS: OA-CL and BoA express excellent inter-rater agreement than CXA, CDA, and CPA, which are limited due to morphological variations and head spatial position. BoA is the second most reliable diagnostic test. CXA, CDA, should only be used for complementary information. CPA was found inadequate for the diagnosis of BI..

Comprehensive Analysis of Factors Affecting Cochlear Size: A Systematic Review and Meta-analysis.

OBJECTIVES: To determine the cochlea's average size in humans and evaluate the relationships between certain covariates and cochlear size. METHODS: A systematic search on articles on cochlear size and published in English was conducted using Cochrane, PubMed, Web of Science, and Scopus databases up to September 15, 2020. Data were pooled using random-effects with three models. The effect of demographic, clinical, and measurement-related parameters was specifically analyzed. Meta-regression and subgroup analyses were conducted. The overall effect estimation was made for outcomes. RESULTS: The meta-analysis included 4,708 cochleae from 56 studies. The overall length of the organ of Corti was 32.94 mm (95% confidence interval [CI]: 32.51-33.38). The first and second models revealed that age, gender, country, continent, measurement method (direct, indirect), measured structure ("A" value, cochlear lateral wall), origin (in vivo, in vitro), and type (histology specimens, plastic casts, imaging) of the cochlear material did not affect the cochlear size. However, study populations (general population, patients with a cochlear implant, and patients with congenital sensorineural hearing loss [CSNHL]) were found to affect the outcomes. Compared to the other populations, patients with CSNHL had shorter cochleae. Therefore, we developed a third model and found that the general population and patients with cochlear implants did not differ in cochlear size. CONCLUSION: This meta-analysis investigated the factors that could affect the cochlear size and found that patients with CSNHL had significantly shorter cochleae, whereas other covariates had no significant effect. Laryngoscope, 132:188-197, 2022.

The Relation Between the Metopic Suture Persistence and Frontal Sinus Volume and Olfactory Fossa Depth: A Reliability Study with Semiautomatic Volume Measurement.

Objective: This study aims to investigate the relationship of the persistence of metopic suture (PMS), frontal sinus volume (FSV), and olfactory fossa depth (OFD). Methods: Tomography scans of 1,603 patients aged 18-65 years were evaluated for the presence of PMS. In the study, 74 PMS cases and 74 controls were included. The appearance of each individual's frontal sinus was classified as aplasia, hypoplasia, or normal. Two observers independently measured the lateral lamella length (LLL), OFD, and FSV. Interobserver agreement was evaluated with the intraclass correlation coefficient (ICC) and Cohen's kappa coefficient (κ). Results: The prevalence of PMS was found to be 4.99% [95% confidence interval (CI): 4.03-6.17]. The PMS group had five times higher hypoplasia/aplasia than the controls (52.70%, 95% CI: 41.48-63.66 and 10.81%, 95% CI: 5.58-19.91, respectively; p<0.001). An "almost perfect" agreement was detected among observers for the frontal sinus appearance classification: κ=0.807, p<0.001. The ICC of continuous measurements for OFD, LLL, and FSV, respectively, presented "excellent" reliability: 0.956, 0.958, and 0.981, with p<0.001 for each. LLL was shorter, OFD was shallower, and FSV was smaller in the PMS group than the control group (p<0.001). There was a moderate positive correlation between OFD, LLL, and FSV (r=0.306, r=0.302). Conclusions: This study interprets that the presence of PMS is related frontal sinus development and volume. With PMS, a smaller FS, shorter lateral lamella, and shallower olfactory fossa may be expected.

Is Cochlear Length Related to Congenital Sensorineural Hearing Loss: Preliminary Data.

OBJECTIVES: This study used the data from patients with congenital sensorineural hearing loss (CSNHL) and those with normal hearing to measure and compare the length of the cochlea with high-resolution computed tomography (HRCT). MATERIALS AND METHODS: HRCT images of patients who were diagnosed with CSNHL and were candidates for cochlear implantation were evaluated retrospectively. Sixty-three ears of 33 patients were included in the study. The control group comprised 66 ears of 33 individuals. The measurements were conducted by an experienced radiologist, using three-dimensional curved multiplanar reconstruction. All the measurements were performed thrice, and the average was calculated. RESULTS: The data were distributed normally. The lengths of the cochlear components for the CSNHL and control groups were as follows: basal turn 21.66±1.01 (21.30-22.02) and 22.57±0.68 (22.32-22.81) mm, middle turn 11.58±0.69 (11.34-11.83) and 12.39±0.46 (12.23-12.56) mm, and apical turn 6.45±0.92 (6.12-6.77) and 7.12±0.65 (6.89-7.35) mm, respectively. The mean cochlear lateral wall (LW) length was significantly shorter in the CSNHL patients [39.71±1.32 (39.25-40.18) mm] than in the controls [42.09±1.17 (41.67-42.51) mm], (p<0.001). The intra-rater reliability was 0.878 (confidence interval 95%: 0.841-0.908 p<0.001). The cut-off value was 40.81 mm (sensitivity: 0.91, specificity: 0.94, and accuracy: 0.90). CONCLUSION: There were microanatomic dissimilarities between the length of the cochlea in subjects from the CSNHL group and those from the control group.

Role of iliac crest tangent in correct numbering of lumbosacral transitional vertebrae

Background/aim: The iliac crest tangent (ICT) has recently emerged as a reliable landmark to correctly number the lumbosacral transitional vertebrae (LSTV). We retrospectively evaluated the reproducibility and accuracy of the ICT as a landmark in subjects without disc degeneration. Materials and methods: Fifty-eight patients with LSTV [19 female, 41 (26­52) years] and 55 controls without LSTV [23 female, 40 (26­55) years] who had undergone spinal computed tomography were included. The ICT was drawn on the coronal images, with the cursor in the sagittal view set to the posterior ⅓ of the vertebral body located one level above the LSTV. When more than 1.25 vertebral body was counted below the ICT, the LSTV was considered as S1, otherwise it was considered as L5. The gold standard was counting the vertebrae craniocaudally. Results: The interobserver agreement was good for determining ICT level (Cohen's kappa = 0.78, P < 0.001). The rate of correct numbering by ICT in the LSTV group was significantly less than in the controls (43.1% vs. 96.4%, respectively, P < 0.001). Patients with sacralization had a significantly lower correct numbering rate than patients with lumbarization (33.3% vs. 63.2%, respectively, P = 0.03). Conclusion: ICT does not seem to be a reliable landmark for correct numbering of LSTV in patients with no intervertebral disc degeneration.