Diagnosis of lymph node metastasis in head and neck squamous cell carcinoma using deep learning

Abstract

Background: To build an automatic pathological diagnosis model to assess the lymph node metastasis status of head and neck squamous cell carcinoma (HNSCC) based on deep learning algorithms. Study Design: A retrospective study. Methods: A diagnostic model integrating two-step deep learning networks was trained to analyze the metastasis status in 85 images of HNSCC lymph nodes. The diagnostic model was tested in a test set of 21 images with metastasis and 29 images without metastasis. All images were scanned from HNSCC lymph node sections stained with hematoxylin-eosin (HE).Results: In the test set, the overall accuracy, sensitivity, and specificity of the diagnostic model reached 86%, 100%, and 75.9%, respectively.Conclusions: Our two-step diagnostic model can be used to automatically assess the status of HNSCC lymph node metastasis with high sensitivity.

Artificial intelligence in head and neck cancer diagnosis

“…Regarding the performance of AI tools in histology, all studies reported an accuracy over 90%, except for 2 papers. 24 , 27 They also reported excellent performance via AUC calculations, as well as high sensitivity and specificity. Different types of AI algorithms were tested in the included studies, from supervised machine learning systems (e.g., SVM) to deep learning systems such as CNNs.…”

“…In general, performance of the development dataset were 100% for accuracy, sensitivity, and specificity; whereas in the test dataset sensitivity was 100%, specificity 75.9%, and accuracy 86%. 27 Only 1 study regarded salivary glands tumors. Lopez-Janeiro et al used a tree model algorithm to diagnose different histotypes of malignant tumors on 115 samples of salivary glands.…”

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

“…Only 12 studies (19%) out of 63 studies investigating LN metastasis provided a detailed analysis of false-positive predictions in metastatic LN detection. Based on the gathered data, LN sinus histiocytes were the most common false positively identified region mentioned by six studies 29 , 31 , 56 , 68 , 90 , 94 followed by secondary lymphoid follicles (germinal centers), 56 , 64 , 94 connective tissue, 31 , 64 out-of-focus areas, 68 and slide artifacts. 50 The most common metastatic regions misclassified as negative were micrometastatic lesions 61 , 64 as well as histiocyte-like tumor cells.…”

“…When designing an automated diagnostic tool, it is important to minimize the chance of false-negative decision, where a metastatic LN is assigned to a “healthy” metastasis-free class, which is reflected by sensitivity metric. Two studies in our analysis proposed ResNet-based solutions that achieved a perfect 1.00 sensitivity in gastric cancer 55 and head and neck cancer 56 datasets consisting of 40 gastric cancer patients and 50 head and neck cancer images, respectively. The proposed metastasis detection systems reached lower yet still competitive false-positivity (specificity) scores of 0.9994 in gastric cancer and 0.759 in head and neck cancer studies, respectively.…”

“…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.…”