Digital image analysis and machine learning-assisted prediction of neoadjuvant chemotherapy response in triple-negative breast cancer.

BACKGROUND: Pathological complete response (pCR) is associated with favorable prognosis in patients with triple-negative breast cancer (TNBC). However, only 30-40% of TNBC patients treated with neoadjuvant chemotherapy (NAC) show pCR, while the remaining 60-70% show residual disease (RD). The role of the tumor microenvironment in NAC response in patients with TNBC remains unclear. In this study, we developed a machine learning-based two-step pipeline to distinguish between various histological components in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of TNBC tissue biopsies and to identify histological features that can predict NAC response. METHODS: H&E-stained WSIs of treatment-naïve biopsies from 85 patients (51 with pCR and 34 with RD) of the model development cohort and 79 patients (41 with pCR and 38 with RD) of the validation cohort were separated through a stratified eightfold cross-validation strategy for the first step and leave-one-out cross-validation strategy for the second step. A tile-level histology label prediction pipeline and four machine-learning classifiers were used to analyze 468,043 tiles of WSIs. The best-trained classifier used 55 texture features from each tile to produce a probability profile during testing. The predicted histology classes were used to generate a histology classification map of the spatial distributions of different tissue regions. A patient-level NAC response prediction pipeline was trained with features derived from paired histology classification maps. The top graph-based features capturing the relevant spatial information across the different histological classes were provided to the radial basis function kernel support vector machine (rbfSVM) classifier for NAC treatment response prediction. RESULTS: The tile-level prediction pipeline achieved 86.72% accuracy for histology class classification, while the patient-level pipeline achieved 83.53% NAC response (pCR vs. RD) prediction accuracy of the model development cohort. The model was validated with an independent cohort with tile histology validation accuracy of 83.59% and NAC prediction accuracy of 81.01%. The histological class pairs with the strongest NAC response predictive ability were tumor and tumor tumor-infiltrating lymphocytes for pCR and microvessel density and polyploid giant cancer cells for RD. CONCLUSION: Our machine learning pipeline can robustly identify clinically relevant histological classes that predict NAC response in TNBC patients and may help guide patient selection for NAC treatment.

Evaluation of scoring system in cytological diagnosis and management of breast lesion with review of literature.

BACKGROUND: Fine needle aspiration cytology (FNAC) breast is generally considered as a rapid, reliable, and safe diagnostic tool to distinguish non-neoplastic from neoplastic breast lesions. Masood's Scoring Index has been proposed to help in sub-grouping of breast lesions so as to help in surgical management. AIMS: To assess the accuracy of Modified Masood's Scoring Index (MMSI) in the diagnosis of benign and malignant breast lesions in patients with palpable breast lump, and review of literature. SETTINGS AND DESIGN: A prospective study from a tertiary care center. MATERIAL AND METHODS: This prospective study included a total of 100 cases, both females and males, with palpable breast lump, in the age range of 10-80 years, over a period of 2 years from January 2007 to 2009, who underwent FNAC. They were cytologically grouped into five categories as suggested by Masood et al, and confirmed by histopathology. RESULTS: Evaluation of Masood Scoring Index led to modification (Modified Masood Scoring Index; MMSI) by shifting score 9 from Group I to Group II, thus increasing the diagnostic accuracy of the breast lesions. CONCLUSIONS: MMSI was found to be a useful, easily reproducible scoring method of breast lesions to improve diagnostic accuracy of nonproliferative breast disease and proliferative breast disease without atypia cases, as the prognosis and treatment of these cases varies.

Validity of different cytological grading systems of breast carcinoma--a hospital-based study in South India.

INTRODUCTION: With increase in the incidence of breast carcinoma, fine needle aspiration cytology (FNAC) has began to play a major role in diagnosing and grading. The study was aimed at validating the different cytological grading systems like Hunt's cytological grading (HCG), modified black grading (MBG), Robinson's cytological grading (RCG) and Masood's cytology index (MCI) in comparison with a modified Bloom-Richardson (MBR) histopathological grading. METHODS AND MATERIAL: Fifty breast carcinoma cases were prospectively studied by comparing various cytological grading methods with histopathological grading over a period of three years. All statistical analyses were carried out with the Epi-info package. RESULTS: The concordance rate of RCG was 82% which is highest of all, while that of MBG was 68%. HCG and MCI were not comparable with MBR due to insufficient grading. CONCLUSIONS: RCG for breast carcinoma is validated. A consensus for a standard cytological grading method similar to the gold standard MBR histological grading must be arrived at based on conducted comparative studies and has to be inculcated in routine cytology reports.