METHODS: Breast cancer MRI images were classified into BA, BF, BPT, BTA, MDC, MLC, MMC, and MPC using a proposed Deep Learning model with additional 5 fine-tuned Deep learning models consisting of Xception, InceptionV3, VGG16, MobileNet and ResNet50 trained on ImageNet database. The dataset was collected from Kaggle depository for breast cancer detection and classification. That Dataset was boosted using GAN technique. The images in the dataset have 4 magnifications (40X, 100X, 200X, 400X, and Complete Dataset). Thus we evaluated the proposed Deep Learning model and 5 pre-trained models using each dataset individually. That means we carried out a total of 30 experiments. The measurement that was used in the evaluation of all models includes: F1-score, recall, precision, accuracy.
RESULTS: The classification F1-score accuracies of Xception, InceptionV3, ResNet50, VGG16, MobileNet, and Proposed Model (BCCNN) were 97.54%, 95.33%, 98.14%, 97.67%, 93.98%, and 98.28%, respectively.
CONCLUSION: Dataset Boosting, preprocessing and balancing played a good role in enhancing the detection and classification of breast cancer of the proposed model (BCCNN) and the fine-tuned pre-trained models' accuracies greatly. The best accuracies were attained when the 400X magnification of the MRI images due to their high images resolution.
MATERIALS AND METHODS: This study included 50 cases of thyroid lesions (20 cases of colloid goitre, 15 of follicular adenoma, 5 of follicular carcinoma and 10 papillary carcinomas). Digital images of cytologic smears of these cases were captured using a dedicated photomicrography system and nuclear profiles traced manually. With self-designed image analysis software, nuclear morphometric measurements, including texture analysis, were performed. Discriminant analysis was performed including the morphometric parameters and percentage of correctly classified nuclei noted.
RESULTS: Nuclear morphometry parameters showed that papillary thyroid carcinoma had the highest perimeter, area, radius and elongation factor compared to other thyroid lesions. Discriminant analysis revealed that altogether 77.9% of cells could be correctly classified to their lesion category based on the nuclear morphometric and textural parameters. Of the neoplastic cases, 84.5% of cells of follicular neoplasms and 72.5% of papillary carcinoma were classified to the respective category.
CONCLUSION: Nuclear morphometry, including texture analysis, can assist in the cytologic diagnosis of thyroid lesions, considering the high degree of accuracy of classification. Further studies and methodological refinements can achieve higher accuracy.
CASE REPORT: The patient was a 47-year-old woman with no familial history of FAP. A 3.0-cm unifocal mass was identified in the left thyroidal lobe. Fine-needle aspiration cytology revealed papillary clusters of atypical cells with nuclear grooves, which was suspected to be conventional papillary thyroid carcinoma. Histologically, the tumour comprised a papillary and cribriform growth of atypical cells with cytoplasmic accumulation and nuclear translocation of b-catenin. In addition, frequent morule formation was identified.
DISCUSSION: In this case, we performed morule analysis through correlative light and electron microscopy (CLEM), and revealed its ultrastructure. Although CMV is a rare form of thyroid carcinoma, it should be considered along with its distinct clinicopathological characteristics.
MATERIALS AND METHODS: We collected 54 malignant and 65 benign thyroid lesions diagnosed by histology in Universiti Kebangsaan Malaysia Medical Centre between January 2010 and December 2015. All cases were immunohistochemically stained with CK 19 and evaluated by 3 independent observers. The immunostaining patterns were scored based on the intensity and proportion of staining and finally graded as negative, weak positive, moderate positive or strong positive. In addition, the immunostaining scores of the malignant cases were correlated with their TNM pathological tumour stages.
RESULTS: Cytokeratin 19 staining expression was higher in malignant than benign thyroid lesions (p < 0.001) which was most prominent among classical PTC. The four PTC cases that showed negative or weak staining were all follicular variant of PTC. Benign conditions were mostly negative or showed weak positivity. There was no correlation between CK 19 expression and TNM primary tumour stage (pT).
CONCLUSION: Cytokeratin 19 is a useful marker in differentiating malignant from benign thyroid conditions particularly the classical PTC, provided its interpretation is by correlation with morphology and takes into consideration the intensity and proportion of positive staining.