Computer‐aided diagnostic models to classify lymph node metastasis and lymphoma involvement in enlarged cervical lymph nodes using PET/CT

Abstract

Background It is a clinical problem to identify histological component in enlarged cervical lymph nodes, particularly in differentiation between lymph node metastasis and lymphoma involvement. Purpose To construct two kinds of deep learning (DL)‐based computer‐aided diagnosis (CAD) systems including DL‐convolutional neural networks (DL‐CNN) and DL‐machine learning for pathological diagnosis of cervical lymph nodes by positron emission tomography (PET)/computed tomography (CT) images. Methods We collected CT, PET, and PET/CT images series from 165 patients with enlarged cervical lymph nodes receiving examinations from January 2014 to June 2018. Six CNNs pretrained on ImageNet as DL architectures were used for two kinds of DL‐based CAD models, including DL‐CNN and DL‐machine learning models. The DL‐CNN models were constructed via transfer learning for classification of lymphomatous and metastatic lymph nodes. The DL‐machine learning models were developed by DL‐based features extractors and support vector machine (SVM) classifier. As for DL‐SVM models, we also evaluate the effect of handcrafted radiomics features in combination of DL‐based features. Results The DL‐CNN model with ResNet50 architecture on PET/CT images had the best diagnostic performance among all six algorithms with an area under the receiver operating characteristic curve (AUC) of 0.845 and accuracy of 78.13% in the testing cohort. The DL‐SVM model on ResNet50 extractor showed great performance for the testing cohort with an AUC of 0.901, accuracy of 86.96%, sensitivity of 76.09%, and specificity of 94.20%. The combination of DL‐based and handcrafted features yielded the improvement of diagnostic performance. Conclusions Our DL‐based CAD systems on PET/CT images were developed for classifying metastatic and lymphomatous involvement with favorable diagnostic performance in enlarged cervical lymph nodes. Further clinical practice of our systems may improve quality of the following therapeutic interventions and optimize patients’ outcomes.

A comparison of 18F-FDG PET-based radiomics and deep learning in predicting regional lymph node metastasis in patients with resectable lung adenocarcinoma: a cross-scanner and temporal validation study

“…Our findings suggest that the performance of the DL model may be affected when applied across different PET cameras, and the difference in performance may be attributed to the differences between the characteristics of digital and analog PET scanners. Another possibility is that the DL model likely performs better in the training cohort than in the testing cohort [38]. Therefore, this may be another explanation for the difference of DL model performance between analog and digital PET cohorts.…”

“…The output of the last block connects to a sigmoid function layer to generate the prediction [38]. ResNet-50 exhibited the best diagnostic performance in classifying lymph node metastasis among different DL-CNN architectures [38]. During the training step, random rotation (−45° to 45°), reflection (x- and y- direction), and scaling (0.9 to 1.1) were applied to the images to avoid overfitting.…”

“…The residual connection is from the beginning to the end of the block. The output of the last block connects to a sigmoid function layer to generate the prediction [38]. ResNet-50 exhibited the best diagnostic performance in classifying lymph node metastasis among different DL-CNN architectures [38].…”

Clinical application of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics-based machine learning analyses in the field of oncology

“…Further, the authors showed that the constructed ML model with the RF algorithm had good performance in differentiating malignant lymphoma and sarcoidosis, with an AUC of 0.94. Yang et al [ 79 ] revealed that the ML model with the SVM algorithm constructed according to combined CNN-based features and PET-radiomics had a great potential in distinguishing malignant lymphoma from enlarged metastatic cervical lymph nodes (AUC: 0.948).…”

“…AUC: 0.94 2. AUC: 0.95 Yang et al [ 79 ] 2023 Cervical lymph node Malignant lymphoma vs. metastasis n = 165 CNN model Combined PET radiomics-based + CNN-based model alone SVM Combined model Training and validation cohorts AUC: 0.948 Cui et al [ 80 ] 2023 Brain tumor Malignant lymphoma vs. metastasis n = 51 PET radiomics-based model alone RF – Training and validation cohorts AUC: 0.93 Predicting treatment response or survival Frood et al [ 84 ] 2022 DLBCL Recurrence after chemotherapy n = 229 Combined clinical + PET radiomics-based model alone Ridge regression – Training and validation cohorts AUC: 0.73 Cui et al [ 85 ] 2022 DLBCL PFS after chemotherapy n = 271 Clinical model PET radiomics-based model Combined clinical + PET radiomics-based model alone RF + cox proportional hazard Combined model Training and validation cohorts C-index: 0.853 Frood et al [ 86 ] 2022 HD Recurrence after chemotherapy or RT n = 289 Combined clinical + PET radiomics-based model alone …”