Abstract ▼ AI-Helper

Breast cancer remains the most common type of cancer and the leading cause of cancer-induced mortality among women with 2.4 million new cases diagnosed and 523,000 deaths per year. Historically, a diagnosis has been initially performed using clinical screening followed by histopathological analysis....

Breast cancer remains the most common type of cancer and the leading cause of cancer-induced mortality among women with 2.4 million new cases diagnosed and 523,000 deaths per year. Historically, a diagnosis has been initially performed using clinical screening followed by histopathological analysis. Automated classification of cancers using histopathological images is a challenging task of accurate detection of tumor sub-types. This process could be facilitated by machine learning approaches, which may be more reliable and economical compared to conventional methods. To prove this principle, we applied fine-tuned pre-trained deep neural networks and first attempted to discriminate between different cancer types. Using 6,402 tissue microarrays (TMAs) samples, models including the ResNet V1 50 pretrained model correctly predicted 99.8% of the four cancer types including breast, bladder, lung, and lymphoma. Then, for classification of breast cancer sub-types, this approach was applied to 7,909 images of 82 patients from the BreakHis database. ResNet V1 152 classified benign and malignant breast cancers with an accuracy of 98.7%. In addition, ResNet V1 50 and ResNet V1 152 categorized either benign-(adenosis, fibroadenoma, phyllodes tumor, and tubular adenoma) or malignant-(ductal carcinoma, lobular carcinoma, mucinous carcinoma, and papillary carcinoma) sub-types with 94.8% and 96.4% accuracy, respectively. The confusion matrices revealed high sensitivity values of 1, 0.995 and 0.993 for cancer types, as well as malignant-and benign sub-types respectively. The areas under the curve (AUC) scores were 0.996, 0.973 and 0.996 for cancer types, malignant and benign sub-types, respectively. One of the most significant and striking result to emerge from the data analysis is negligible false positive (FP) and false negative (FN). The optimum results, as shown in Tables (III, IV, V, VI), indicate that FP is between 0 and 4 while FN is between 0 and 8 in which test data including 800, 900, 809, 1000 for given four classes (Table I)