The Cochlear Size Variations in Incomplete Partitions with Multiplanar Images on Pediatric Temporal Bone CT.

Objectives: The purpose of the study was to evaluate cochlea dimensions by the multiplanar reconstruction of high-resolution computed tomography that could be useful in diagnosing incomplete partition (IP) malformations. Methods: This study included 32 patients with 64 side cochleae diagnosed with IP defect and 38 cochleae as the control without any defect. Basal turn length (BL), cochlear height (CH), Mid-apical length (MAL), Mid-apical height, Cochlear length (A), and Cochlear width (B) were measured on reformat images. Results: Twenty cochleae of these patients have been diagnosed with IP type I, 34 with IP type II, and 10 with IP type III. The MAL values are shorter than the control group in IP types I and III (p<0.001, p<0.001). BL values are shorter in IP type III cases (p<0.001). In IP II cases, BL and MAL values overlapped with the control group. CH did not differ significantly from the control group in any IP type. A and B values were significantly lower than the control group for IP I and III (p<0.01). There is a positive correlation between A and B values for all IP types (p<0.01). Conclusion: Quantitative data about differences in the size and shape of the cochlea in IP cases would help differentiate them from the normal cochlea. Since A and B values showed a positive correlation, it is suggested that A and B values can be used to estimate CDL for IP types.

Diffusion Tensor Imaging of Auditory Pathway: A Comparison of Pediatric Cochlear Implant Candidates and Healthy Cases.

BACKGROUND: We aimed to investigate the changes that may occur in the auditory neural network in pediatric congenital hearing loss cases. METHODS: Fifty-four cochlear implant candidates and 47 normal-hearing controls were included in this retrospective study. Fractional anisotropy, radial diffusivity, and apparent diffusion coefficient maps were generated. We placed region of interest on the cochlear nucleus, superior olivary nucleus, lateral lemniscus, medial geniculate body, auditory radiation, Heschl's gyrus, inferior fronto-occipital fasciculus, superior longitudinal fascicle, and corpus callosum splenium. The area of the cochlear nerve was measured. Diffusion tensor imaging metrics, children's ages, and cochlear nerve area were compared. RESULTS: Apparent diffusion coefficient and radial diffusivity values of patients were higher than the control group in all places except the radial diffusivity values of medial geniculate body. The fractional anisotropy values of the patients in lateral lemniscus, auditory radiation, Heschl's gyrus, inferior fronto-occipital fasciculus, superior longitudinal fascicle, and corpus callosum splenium were lower than the control group. There is a positive correlation between fractional anisotropy and age in both patient and control groups for all locations. The cochlear nerve area is lower in patients (0.88 ± 0.29) than in the control group (1.18 ± 0.14) (P = .000). The cochlear nerve area has a positive correlation with age in the patient group (P = .000) but has not in the control group. The cochlear nerve area positively correlates with fractional anisotropy values of all locations except fractional anisotropy values of medial geniculate body. CONCLUSION: The alterations of diffusion tensor imaging metrics on the auditory pathway reflect the microstructural changes of white matter tracts.

Factors affecting pathological complete response after neoadjuvant chemotherapy in breast cancer: a single-center experience.

OBJECTIVE: The aim of this study was to examine the characteristics of patients admitted to our hospital with a diagnosis of breast cancer who reached pathological complete response after being operated following eight cycles of neoadjuvant chemotherapy. METHODS: Between 2015-2020, patients with pathological complete response who were operated on after neoadjuvant chemotherapy and sent to our clinic for radiotherapy were evaluated. RESULTS: The median age of the patients was 51 years. The most common histological type was invasive ductal cancer. The number of pathological complete response patients was 74 (28%), and the number of non-pathological complete response patients was 188 (72%). Patients with pathological complete response had a smaller tumor diameter than the non-pathological complete response group (p=0.001). For pathological complete response, T1 stage, N1 stage, NG 3, Ki-67 >20%, negative estrogen receptor, negative progesterone receptor, positive Cerb-B2, and adding trastuzumab to chemotherapy were statistically significant (p<0.05). Before neoadjuvant chemotherapy, stage T1-T2 (p=0.036), LN0-1 (p=0.026), Cerb-B2 positivity (p=0.025), and an initial nuclear grade of three (p=0.001) were found to be the factors affecting pathological complete response. CONCLUSIONS: With neoadjuvant chemotherapy, the size of locally advanced tumors decreases, allowing breast conserving surgery. The neoadjuvant chemotherapy response can be used as an early indicator of the prognosis of patients with breast cancer. Today, neoadjuvant chemotherapy is also used for patients with early-stage, operable breast cancer because it has been shown in many studies that reaching pathological complete response is associated with positive long-term results. If we can identify patients who have reached pathological complete response before neoadjuvant chemotherapy, we think we can also determine a patient-specific treatment plan at the beginning of treatment.

Factors affecting pathological complete response after neoadjuvant chemotherapy in breast cancer: a single-center experience

SUMMARY OBJECTIVE: The aim of this study was to examine the characteristics of patients admitted to our hospital with a diagnosis of breast cancer who reached pathological complete response after being operated following eight cycles of neoadjuvant chemotherapy. METHODS: Between 2015-2020, patients with pathological complete response who were operated on after neoadjuvant chemotherapy and sent to our clinic for radiotherapy were evaluated. RESULTS: The median age of the patients was 51 years. The most common histological type was invasive ductal cancer. The number of pathological complete response patients was 74 (28%), and the number of non-pathological complete response patients was 188 (72%). Patients with pathological complete response had a smaller tumor diameter than the non-pathological complete response group (p=0.001). For pathological complete response, T1 stage, N1 stage, NG 3, Ki-67 >20%, negative estrogen receptor, negative progesterone receptor, positive Cerb-B2, and adding trastuzumab to chemotherapy were statistically significant (p<0.05). Before neoadjuvant chemotherapy, stage T1-T2 (p=0.036), LN0-1 (p=0.026), Cerb-B2 positivity (p=0.025), and an initial nuclear grade of three (p=0.001) were found to be the factors affecting pathological complete response. CONCLUSIONS: With neoadjuvant chemotherapy, the size of locally advanced tumors decreases, allowing breast conserving surgery. The neoadjuvant chemotherapy response can be used as an early indicator of the prognosis of patients with breast cancer. Today, neoadjuvant chemotherapy is also used for patients with early-stage, operable breast cancer because it has been shown in many studies that reaching pathological complete response is associated with positive long-term results. If we can identify patients who have reached pathological complete response before neoadjuvant chemotherapy, we think we can also determine a patient-specific treatment plan at the beginning of treatment.

Influence of segmentation margin on machine learning-based high-dimensional quantitative CT texture analysis: a reproducibility study on renal clear cell carcinomas.

OBJECTIVE: To determine the possible influence of segmentation margin on each step (feature reproducibility, selection, and classification) of the machine learning (ML)-based high-dimensional quantitative computed tomography (CT) texture analysis (qCT-TA) of renal clear cell carcinomas (RcCCs). MATERIALS AND METHODS: For this retrospective study, 47 patients with RcCC were included from a public database. Two segmentations were obtained by two radiologists for each tumour: (i) contour-focused and (ii) margin shrinkage of 2 mm. Texture features were extracted from original, filtered, and transformed CT images. Feature selection was done using a correlation-based algorithm. The ML classifier was k-nearest neighbours. Classifications were performed with and without using synthetic minority over-sampling technique. Reference standard was nuclear grade (low versus high). Intraclass correlation coefficient (ICC), Pearson's correlation coefficient, Wilcoxon signed-ranks test, and McNemar's test were used in the analysis. RESULTS: The segmentation with margin shrinkage of 2 mm (772 of 828; 93.2%) yielded more texture features with excellent reproducibility (ICC ≥ 0.9) than contour-focused segmentation (714 of 828; 86.2%), p < 0.0001. The feature selection algorithms resulted in different feature subsets for two segmentation datasets with only one common feature. All ML-based models based on contour-focused segmentation (area under the curve [AUC] range, 0.865-0.984) performed better than those with margin shrinkage of 2 mm (AUC range, 0.745-0.887), p < 0.05. CONCLUSIONS: Each step of the ML-based high-dimensional qCT-TA was susceptible to a slight change of 2 mm in segmentation margin. Despite yielding fewer features with excellent reproducibility, use of the contour-focused segmentation provided better classification performance for distinguishing nuclear grade. KEY POINTS: • Each step of a machine learning (ML)-based high-dimensional quantitative computed tomography texture analysis (qCT-TA) is sensitive to even a slight change of 2 mm in segmentation margin. • Despite yielding fewer texture features with excellent reproducibility, performing the segmentation focusing on the outermost boundary of the tumours provides better classification performance in ML-based qCT-TA of renal clear cell carcinomas for distinguishing nuclear grade. • Findings of an ML-based high-dimensional qCT-TA may not be reproducible in clinical practice even using the same feature selection algorithm and ML classifier unless the possible influence of the segmentation margin is considered.

Radiogenomics in Clear Cell Renal Cell Carcinoma: Machine Learning-Based High-Dimensional Quantitative CT Texture Analysis in Predicting PBRM1 Mutation Status.

OBJECTIVE: The purpose of this study is to evaluate the potential value of machine learning (ML)-based high-dimensional quantitative CT texture analysis in predicting the mutation status of the gene encoding the protein polybromo-1 (PBRM1) in patients with clear cell renal cell carcinoma (RCC). MATERIALS AND METHODS: In this retrospective study, 45 patients with clear cell RCC (29 without the PBRM1 mutation and 16 with the PBRM1 mutation) were identified in The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma database. To create stable ML models and balanced classes, the data were augmented to a total of 161 labeled segmentations (87 without the PBRM1 mutation and 74 with the PBRM1 mutation) by obtaining three to five different samples per patient. Texture features were extracted from corticomedullary phase contrast-enhanced CT images with the use of an open-source software package for the extraction of radiomic data from medical images. Reproducibility analysis (intraclass correlation) was performed by two radiologists. Attribute selection and model optimization were done using a wrapper-based classifier-specific algorithm with nested cross-validation. ML classifiers were an artificial neural network (ANN) algorithm and a random forest (RF) algorithm. The models were validated using 10-fold cross-validation. The reference standard was the PBRM1 mutation status. The main performance metric was the AUC value. RESULTS: Of 828 extracted texture features, 759 had excellent reproducibility. Using 10 selected features, the ANN algorithm correctly classified 88.2% (142 of 161) of the clear cell RCCs in terms of PBRM1 mutation status (AUC value, 0.925). Using five selected features, the RF algorithm correctly classified 95.0% (153 of 161) of the clear cell RCCs (AUC value, 0.987). Overall, the RF algorithm performed better than the ANN algorithm (z score = -2.677; p = 0.007). CONCLUSION: ML-based high-dimensional quantitative CT texture analysis might be a feasible and potential method for predicting PBRM1 mutation status in patients with clear cell RCC.