Nonmetastatic Axillary Lymph Nodes Have Distinct Morphology and Immunophenotype in Obese Patients with Breast Cancer at Risk for Metastasis

Computational methods for metastasis detection in lymph nodes and characterization of the metastasis-free lymph node microarchitecture: A systematic-narrative hybrid review

“…The authors trained the model using WSI crops at 2.5x, 5x and 10x magnifications, concluding that a mixture of different slide magnifications during training improved the final U-Net model performance. Song et al 98 utilized ResNet model to classify breast cancer LNs into either obese, metastatic, or metastasis-free achieving 0.67 AUC classification score. The slide tiles deemed the most representative by the model were further processed via rule base filtering to quantify adipocytes, erythrocytes, and lymphoid white space leading to a conclusion that increased size of all three components was observed in metastasis-free LNs of metastatic patients.…”

“…In total, we found 27 distinct model architectures with 23 models describing patch classification and the remaining 4 models describing pixel-level segmentation studies. Among patch classifiers, ResNet models were utilized most frequently (15 studies), 27 , 46 , 47 , 48 , 49 , 50 , 51 , 52 , 53 , 54 , 55 , 56 , 72 , 84 , 98 followed by MIL ( n =9), 31 , 41 , 77 , 78 , 79 , 80 , 81 , 82 , 99 VGG models ( n =8), 36 , 37 , 44 , 46 , 51 , 84 , 100 , 101 and others as shown in Fig. 4 B. Amongst pixel-level classification methods, U-Net was the most commonly used (10 studies) 26 , 27 , 30 , 59 , 60 , 61 , 62 , 71 , 96 , 102 followed by DeepLabv3 ( n =7), 28 , 29 , 62 , 63 , 64 , 65 , 66 Mask-RCNN ( n =1), 16 and proprietary Visiopharm AI metastasis model 90 as can be seen in Fig.…”

“…However, these results require validation in studies in LNs from other types of cancer. In a recent study by Song et al, 98 authors indicated the importance of prognostic LN structure size evaluation, concluding that the size of adipocytes, red blood cell conglomerates, and white gaps in LN have a prognostic significance when distinguishing patients by pN status and obesity stage. There was only a single study where the segmentation of HEVs was attempted.…”