Prognostic impact of isolated tumor cells in breast cancer axillary nodes: single tumor cell(s) versus tumor cell cluster(s) and microanatomic location

Artificial Intelligence-Aided Diagnosis of Breast Cancer Lymph Node Metastasis on Histologic Slides in a Digital Workflow

Identifying lymph node (LN) metastasis in invasive breast carcinoma can be tedious and time-consuming. We investigated an artificial intelligence (AI) algorithm to detect LN metastasis by screening hematoxylin and eosin (H&E) slides in a clinical digital workflow. The study included 2 sentinel LN (SLN) cohorts (a validation cohort with 234 SLNs and a consensus cohort with 102 SLNs) and 1 nonsentinel LN cohort (258 LNs enriched with lobular carcinoma and postneoadjuvant therapy cases). All H&E slides were scanned into whole slide images in a clinical digital workflow, and whole slide images were automatically batch-analyzed using the Visiopharm Integrator System (VIS) metastasis AI algorithm. For the SLN validation cohort, the VIS metastasis AI algorithm detected all 46 metastases, including 19 macrometastases, 26 micrometastases, and 1 with isolated tumor cells with a sensitivity of 100%, specificity of 41.5%, positive predictive value of 29.5%, and negative predictive value (NPV) of 100%. The false positivity was caused by histiocytes (52.7%), crushed lymphocytes (18.2%), and others (29.1%), which were readily recognized during pathologists' reviews. For the SLN consensus cohort, 3 pathologists examined all VIS AI annotated H&E slides and cytokeratin immunohistochemistry slides with similar average concordance rates (99% for both modalities). However, the average time consumed by pathologists using VIS AI annotated slides was significantly less than using immunohistochemistry slides (0.6 vs 1.0 minutes, P = .0377). For the nonsentinel LN cohort, the AI algorithm detected all 81 metastases, including 23 from lobular carcinoma and 31 from postneoadjuvant chemotherapy cases, with a sensitivity of 100%, specificity of 78.5%, positive predictive value of 68.1%, and NPV of 100%. The VIS AI algorithm showed perfect sensitivity and NPV in detecting LN metastasis and less time consumed, suggesting its potential utility as a screening modality in routine clinical digital pathology workflow to improve efficiency.

Occult Tumour Cells in Lymph Nodes from Gastric Cancer Patients: Should Isolated Tumour Cells Also Be Considered?

INTRODUCTION

Regional lymph node metastasis is an important prognostic factor for patients with gastric cancer. Occult tumour cells (OTCs), including either micrometastases (MMs) or isolated tumour cells (ITCs), may be a key factor in the development of cancer recurrence in pN0 patients.

AIMS

We aimed to determine the frequency and prognostic significance for disease recurrence of OTCs.

MATERIALS AND METHODS

This retrospective cohort study included all consecutive patients with pN0 gastric adenocarcinoma between January 2000 and December 2011 (n = 73). Immunohistochemistry using the pan-cytokeratin antibody AE1/AE3 was used to detect OTCs in 1257 isolated lymph nodes.

RESULTS

OTCs were identified in 30 patients (41%), including 20 cases with MMs (27%) and 10 cases with ITCs (14%). Disease recurrence and cancer-related death were observed in 24 (33%) and 20 patients (27%), respectively, and both were significantly associated with the detection of OTCs. A significant difference was also observed for the mean survival time between patients with OTCs and those without OTCs [100 vs 158 months (p = 0.015)]. The presence of OTCs was statistically significantly associated with the Lauren classification, tumour size and lymphatic permeation. Multivariate analyses revealed that only age, T stage and the presence of ITCs in lymph nodes were independent factors for recurrence. The presence of ITCs increased the risk for recurrence by 11.1-fold.

CONCLUSIONS

In a significant proportion of patients diagnosed as stage pN0, OTCs may be identified in lymph nodes if carefully searched for, which can negatively affect their prognosis. The presence of ITCs was found to be an independent factor for recurrence and after proper validation should be considered during lymph node assessment for prognosis definition.

Differential detection of metastatic and inflammatory lymph nodes using intravoxel incoherent motion diffusion-weighted imaging

PURPOSE

This study sought to monitor the dynamic process of lymph node (LN) metastasis with intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI), and to investigate the impact of disease course on the detection of metastatic LNs by IVIM-DWI.

METHODS

Twenty female New Zealand rabbits with 2.5-3.0 kg body weight were studied. VX2 cells and egg yolk emulsion were randomly inoculated into one thigh to induce metastatic and inflammatory popliteal LNs, respectively. Eight rabbits underwent IVIM-DWI (14 b values, 0-2000 s/mm²) 2 h prior to, and 14, 21, and 28 days after inoculation (D0, D14, D21, D28). The apparent diffusion coefficient (ADC), true diffusion coefficient (D), pseudodiffusion coefficient (D*), and perfusion fraction (f) were measured and compared between the metastatic and the inflammatory groups at each time point. Three rabbits randomly chosen from the remaining twelve rabbits were sacrificed at each time point to perform hematoxylin and eosin staining and histologic evaluation.

RESULTS

The patterns of dynamic change of D*, ADC, and D were different between the metastatic and the inflammatory LNs. The metastatic group had a lower D* value at D14 (p = .003), and greater ADC and D values at both D21 (p = .001, p = .001) and D28 (p = .021, p = .001), compared to the inflammatory group. The f value of the metastatic group was greater than that of the inflammatory only at D28 (p = .001).

CONCLUSIONS

IVIM-DWI can reflect the dynamic process of LN metastasis, and disease course has a significant influence on the ability of IVIM-DWI to detect metastatic nodes.

Impact of Deep Learning Assistance on the Histopathologic Review of Lymph Nodes for Metastatic Breast Cancer

Supplemental Digital Content is available in the text.

Advances in the quality of whole-slide images have set the stage for the clinical use of digital images in anatomic pathology. Along with advances in computer image analysis, this raises the possibility for computer-assisted diagnostics in pathology to improve histopathologic interpretation and clinical care. To evaluate the potential impact of digital assistance on interpretation of digitized slides, we conducted a multireader multicase study utilizing our deep learning algorithm for the detection of breast cancer metastasis in lymph nodes. Six pathologists reviewed 70 digitized slides from lymph node sections in 2 reader modes, unassisted and assisted, with a wash-out period between sessions. In the assisted mode, the deep learning algorithm was used to identify and outline regions with high likelihood of containing tumor. Algorithm-assisted pathologists demonstrated higher accuracy than either the algorithm or the pathologist alone. In particular, algorithm assistance significantly increased the sensitivity of detection for micrometastases (91% vs. 83%, P=0.02). In addition, average review time per image was significantly shorter with assistance than without assistance for both micrometastases (61 vs. 116 s, P=0.002) and negative images (111 vs. 137 s, P=0.018). Lastly, pathologists were asked to provide a numeric score regarding the difficulty of each image classification. On the basis of this score, pathologists considered the image review of micrometastases to be significantly easier when interpreted with assistance (P=0.0005). Utilizing a proof of concept assistant tool, this study demonstrates the potential of a deep learning algorithm to improve pathologist accuracy and efficiency in a digital pathology workflow.

Convolutional neural network initialized active contour model with adaptive ellipse fitting for nuclear segmentation on breast histopathological images

Automated detection and segmentation of nuclei from high-resolution histopathological images is a challenging problem owing to the size and complexity of digitized histopathologic images. In the context of breast cancer, the modified Bloom-Richardson Grading system is highly correlated with the morphological and topological nuclear features are highly correlated with Modified Bloom-Richardson grading. Therefore, to develop a computer-aided prognosis system, automated detection and segmentation of nuclei are critical prerequisite steps. We present a method for automated detection and segmentation of breast cancer nuclei named a convolutional neural network initialized active contour model with adaptive ellipse fitting (CoNNACaeF). The CoNNACaeF model is able to detect and segment nuclei simultaneously, which consist of three different modules: convolutional neural network (CNN) for accurate nuclei detection, (2) region-based active contour (RAC) model for subsequent nuclear segmentation based on the initial CNN-based detection of nuclear patches, and (3) adaptive ellipse fitting for overlapping solution of clumped nuclear regions. The performance of the CoNNACaeF model is evaluated on three different breast histological data sets, comprising a total of 257 H&E-stained images. The model is shown to have improved detection accuracy of F-measure 80.18%, 85.71%, and 80.36% and average area under precision-recall curves (AveP) 77%, 82%, and 74% on a total of 3 million nuclei from 204 whole slide images from three different datasets. Additionally, CoNNACaeF yielded an F-measure at 74.01% and 85.36%, respectively, for two different breast cancer datasets. The CoNNACaeF model also outperformed the three other state-of-the-art nuclear detection and segmentation approaches, which are blue ratio initialized local region active contour, iterative radial voting initialized local region active contour, and maximally stable extremal region initialized local region active contour models.