Pathological profile of patients with breast diseases in Shiraz

Age distribution and types of breast lesions among Afghan women diagnosed by fine needle aspiration cytology (FNAC) at a tertiary care centre in Afghanistan: a descriptive cross-sectional study

OBJECTIVES

In Afghanistan, breast diseases are a common reason for women to visit hospitals. This is the first study in Afghanistan aimed to describe the age distribution and types of breast diseases among patients diagnosed by fine needle aspiration cytology.

DESIGN

Descriptive cross-sectional study.

SETTING

French Medical Institute for Mothers and Children, Kabul, Afghanistan.

PARTICIPANTS

The study included 650 patients with breast lesions between 1 April 2015 and 1 April 2019.

RESULTS

The mean age of diagnosis was 35.38 (SD ±13.11) years, ranging from 15 to 75 years. The most common diagnosis was cancer (24% of all cases). The second most common diagnosed lesion was fibroadenoma, constituting 22.4%, and the third most common lesion was fibrocystic changes, with 15.4% of cases. Inflammatory conditions were diagnosed in 9.7% of cases, granulomatous inflammation in 9.1%, lesions only suspicious for malignancy in 5.5%, lipoma in 2.8% and miscellaneous benign lesions in 11.1%. Cancer was diagnosed at the youngest age of 20 years. Cancer was more common on the left side (62%), and only one case (0.9%) was bilateral.

CONCLUSION

Our study showed that cancer was the most commonly diagnosed lesion and was reported at younger ages too. This suggests that physicians should not ignore any breast lump in younger patients and that the possibility of cancer must be considered. Further country-wide studies are suggested to assess breast cancer and associated risk factors.

Assessing Breast Cancer Risk with an Artificial Neural Network

Objectives:

Radiologists face uncertainty in making decisions based on their judgment of breast cancer risk. Artificial intelligence and machine learning techniques have been widely applied in detection/recognition of cancer. This study aimed to establish a model to aid radiologists in breast cancer risk estimation. This incorporated imaging methods and fine needle aspiration biopsy (FNAB) for cyto-pathological diagnosis.

Methods:

An artificial neural network (ANN) technique was used on a retrospectively collected dataset including mammographic results, risk factors, and clinical findings to accurately predict the probability of breast cancer in individual patients. Area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values were used to evaluate discriminative performance.

Result:

The network incorporating the selected features performed best (AUC = 0.955). Sensitivity and specificity of the ANN were respectively calculated as 0.82 and 0.90. In addition, negative and positive predictive values were respectively computed as 0.90 and 0.80.

Conclusion:

ANN has potential applications as a decision-support tool to help underperforming practitioners to improve the positive predictive value of biopsy recommendations.