Wh. Wolberg et al., COMPUTER-DERIVED NUCLEAR FEATURES COMPARED WITH AXILLARY LYMPH-NODE STATUS FOR BREAST-CARCINOMA PROGNOSIS, Cancer cytopathology, 81(3), 1997, pp. 172-179
BACKGROUND. Both axillary lymph node involvement and tumor anaplasia,
as expressed by visually assessed grade, have been shown to be prognos
tically important in breast carcinoma outcome. In this study, axillary
lymph node involvement was used as the standard against which prognos
tic estimations based on computer-derived nuclear features were gauged
, METHODS, The prognostic significance of nuclear morphometric feature
s determined by computer-based image analysis were analyzed in 198 con
secutive preop preoperative samples obtained by fine-needle aspiration
(FNA) from patients with invasive breast carcinoma. A novel multivari
ate prediction method was used to model the time of distant recurrence
as a function of the nuclear features. Prognostic predictions based o
n the nuclear feature data were cross-validated to avoid overly optimi
stic conclusions. The estimated accuracy of these prognostic determina
tions was compared with determinations based on the extent of axillary
lymph node involvement. RESULTS. The predicted outcomes based on nucl
ear features were divided into three groups representing best, interme
diate, and worst prognosis, and compared with the traditional TNM lymp
h node stratification. Nuclear feature stratification better separated
the prognostically best from the intermediate group whereas lymph nod
e stratification better separated the prognostically intermediate from
the worst group. Prognostic accuracy was not increased by adding lymp
h node status or tumor size to the nuclear features. CONCLUSIONS. Comp
uter analysis of a preoperative FNA more accurately identified prognos
tically favorable patients than did pathologic examination of axillary
lymph nodes and may obviate the need for routine axillary lymph node
dissection. (C) 1997 American Cancer Society.