Development and evaluation of a robust algorithm for computer-assisted detection of sentinel lymph node micrometastases

• Published in: Histopathology Vol. 59; no. 1; pp. 116 - 128
• Main Authors: Clarke, Gina M, Peressotti, Chris, Holloway, Claire M B, Zubovits, Judit T, Liu, Kela, Yaffe, Martin J
• Format: Journal Article
• Language: English
• Published: Oxford, UK Blackwell Publishing Ltd 01.07.2011; Blackwell
• Subjects: Algorithms; anti-cytokeratin immunohistochemistry; Biological and medical sciences; breast cancer; Breast Neoplasms - diagnosis; Cluster Analysis; computer-assisted detection; Diagnosis, Computer-Assisted - statistics & numerical data; Female; Gynecology. Andrology. Obstetrics; Humans; Investigative techniques, diagnostic techniques (general aspects); Lymphatic Metastasis - diagnosis; Mammary gland diseases; Medical sciences; Microscopy; Neoplasm Micrometastasis - diagnosis; Pathology, Clinical - statistics & numerical data; Pathology. Cytology. Biochemistry. Spectrometry. Miscellaneous investigative techniques; Retrospective Studies; Sentinel Lymph Node Biopsy; sentinel lymph node micrometastases; serial sectioning; Tumors; Immunohistochemistry; Cytokeratin; Evaluation; Breast disease; Sentinel lymph node; Breast cancer; Malignant tumor; Algorithm; computer-assisted detection; sentinel lymph node micrometastases; Mammary gland diseases; Anatomic pathology; Development; Micrometastasis; Diagnosis; anti-cytokeratin immunohistochemistry; Detection; Computer aid; serial sectioning; Cancer
• ISSN: 0309-0167; 1365-2559
• DOI: 10.1111/j.1365-2559.2011.03896.x

Clarke G M, Peressotti C, Holloway C M B, Zubovits J T, Liu K & Yaffe M J
(2011) Histopathology59, 116–128 Development and evaluation of a robust algorithm for computer‐assisted detection of sentinel lymph node micrometastases Aims:  Increasing the sectioning rate for breast sentinel lymph nodes can increase the likelihood of detecting micrometastases. To make serial sectioning feasible, we have developed an algorithm for computer‐assisted detection (CAD) with digitized lymph node sections. Methods and results:  K‐means clustering assigned image pixels to one of four areas in a colourspace (representing tumour, unstained background, counterstained background and microtomy artefacts). Four filters then removed ‘false‐positive’ pixels from the tumour cluster. A set of 43 sections containing tumour (a total of 259 foci) and 59 sections negative for malignancy was defined by two pathologists, using light microscopy, and CAD was applied. For the clinically relevant task of identifying the largest focus in each section (micrometastasis in 22/43 sections), the sensitivity and specificity were 100%. Isolated tumour cells (ITCs) were identified in one slide initially considered to be negative. Identification of all 259 foci yielded sensitivities of 57.5% for ITCs (<0.200 mm), 89.5% for micrometastases, and 100% for larger metastases, with one false‐positive. Reduced sensitivity was ascribed to variable staining. Nine additional metastases (<0.01–0.3 mm) that were not initially identified were detected by CAD. Conclusions:  This algorithm is well suited to the task of sentinel lymph node evaluation and may enhance the detection of occult micrometastases.