Improved breast cancer histological grading using deep learning.

BACKGROUND: The Nottingham histological grade (NHG) is a well-established prognostic factor for breast cancer that is broadly used in clinical decision making. However, ∼50% of patients are classified as grade 2, an intermediate risk group with low clinical value. To improve risk stratification of NHG 2 breast cancer patients, we developed and validated a novel histological grade model (DeepGrade) based on digital whole-slide histopathology images (WSIs) and deep learning. PATIENTS AND METHODS: In this observational retrospective study, routine WSIs stained with haematoxylin and eosin from 1567 patients were utilised for model optimisation and validation. Model generalisability was further evaluated in an external test set with 1262 patients. NHG 2 cases were stratified into two groups, DG2-high and DG2-low, and the prognostic value was assessed. The main outcome was recurrence-free survival. RESULTS: DeepGrade provides independent prognostic information for stratification of NHG 2 cases in the internal test set, where DG2-high showed an increased risk for recurrence (hazard ratio [HR] 2.94, 95% confidence interval [CI] 1.24-6.97, P = 0.015) compared with the DG2-low group after adjusting for established risk factors (independent test data). DG2-low also shared phenotypic similarities with NHG 1, and DG2-high with NHG 3, suggesting that the model identifies morphological patterns in NHG 2 that are associated with more aggressive tumours. The prognostic value of DeepGrade was further assessed in the external test set, confirming an increased risk for recurrence in DG2-high (HR 1.91, 95% CI 1.11-3.29, P = 0.019). CONCLUSIONS: The proposed model-based stratification of patients with NHG 2 tumours is prognostic and adds clinically relevant information over routine histological grading. The methodology offers a cost-effective alternative to molecular profiling to extract information relevant for clinical decisions.

Artificial intelligence as the next step towards precision pathology.

Pathology is the cornerstone of cancer care. The need for accuracy in histopathologic diagnosis of cancer is increasing as personalized cancer therapy requires accurate biomarker assessment. The appearance of digital image analysis holds promise to improve both the volume and precision of histomorphological evaluation. Recently, machine learning, and particularly deep learning, has enabled rapid advances in computational pathology. The integration of machine learning into routine care will be a milestone for the healthcare sector in the next decade, and histopathology is right at the centre of this revolution. Examples of potential high-value machine learning applications include both model-based assessment of routine diagnostic features in pathology, and the ability to extract and identify novel features that provide insights into a disease. Recent groundbreaking results have demonstrated that applications of machine learning methods in pathology significantly improves metastases detection in lymph nodes, Ki67 scoring in breast cancer, Gleason grading in prostate cancer and tumour-infiltrating lymphocyte (TIL) scoring in melanoma. Furthermore, deep learning models have also been demonstrated to be able to predict status of some molecular markers in lung, prostate, gastric and colorectal cancer based on standard HE slides. Moreover, prognostic (survival outcomes) deep neural network models based on digitized HE slides have been demonstrated in several diseases, including lung cancer, melanoma and glioma. In this review, we aim to present and summarize the latest developments in digital image analysis and in the application of artificial intelligence in diagnostic pathology.

Prognostic role of serum thymidine kinase 1 kinetics during neoadjuvant chemotherapy for early breast cancer.

BACKGROUND: Emerging data support the use of thymidine kinase 1 (TK1) activity as a prognostic marker and for monitoring of response in breast cancer (BC). The long-term prognostic value of TK1 kinetics during neoadjuvant chemotherapy is unclear, which this study aimed to elucidate. METHODS: Material from patients enrolled to the single-arm prospective PROMIX trial of neoadjuvant epirubicin, docetaxel and bevacizumab for early BC was used. Ki67 in baseline biopsies was assessed both centrally and by automated digital imaging analysis. TK1 activity was measured from blood samples obtained at baseline and following two cycles of chemotherapy. The associations of TK1 and its kinetics as well as Ki67 with event-free survival and overall survival (OS) were evaluated using multivariable Cox regression models. RESULTS: Central Ki67 counting had excellent correlation with the results of digital image analysis (r = 0.814), but not with the diagnostic samples (r = 0.234), while it was independently prognostic for worse OS [adjusted hazard ratio (HRadj) = 2.72, 95% confidence interval (CI) 1.19-6.21, P = 0.02]. Greater increase in TK1 activity after two cycles of chemotherapy resulted in improved event-free survival (HRadj = 0.50, 95% CI 0.26-0.97, P = 0.04) and OS (HRadj = 0.46, 95% CI 0.95, P = 0.04). There was significant interaction between the prognostic value of TK1 kinetics and Ki67 (pinteraction 0.04). CONCLUSION: Serial measurement of serum TK1 activity during neoadjuvant chemotherapy provides long-term prognostic information in BC patients. The ease of obtaining serial samples for TK1 assessment motivates further evaluation in larger studies.