Transfer Learning of Pre- Trained Inception-V3 Model for Colorectal Cancer Lymph Node Metastasis Classification

The classification of colorectal cancer (CRC) lymph node metastasis (LNM) is a vital clinical issue related to recurrence and design of treatment plans. However, it remains unclear which method is effective in automatically classifying CRC LNM. Hence, this study compared the performance of existing classification methods, i.e., machine learning, deep learning, and deep transfer learning, to identify the most effective method. A total of 3,364 samples (1,646 positive and 1,718 negative) from Harbin Medical University Cancer Hospital were collected. All patches were manually segmented by experienced radiologists, and the image size was based on the lesion to be intercepted. Two classes of global features and one class of local features were extracted from the patches. These features were used in eight machine learning algorithms, while the other models used raw data. Experiment results showed that deep transfer learning was the most effective method with an accuracy of 0.7583 and an area under the curve of 0.7941. Furthermore, to improve the interpretability of the results from the deep learning and deep transfer learning models, the classification heat-map features were used, which displayed the region of feature extraction by superposing with raw data. The research findings are expected to promote the use of effective methods in CRC LNM detection and hence facilitate the design of proper treatment plans.

Download Full-text

Application of Deep Transfer Learning to the Classification of Colorectal Cancer Lymph Node Metastasis

Journal of Imaging Science and Technology ◽

10.2352/j.imagingsci.technol.2021.65.3.030401 ◽

2020 ◽

Author(s):

Jin Li ◽

Peng Wang ◽

Yang Zhou ◽

Hong Liang ◽

Kuan Luan

Keyword(s):

Colorectal Cancer ◽

Lymph Node ◽

Lymph Node Metastasis ◽

Transfer Learning ◽

High Efficiency ◽

Original Data ◽

Training Dataset ◽

Feature Map ◽

Node Metastasis

Accurate classifications of colorectal cancer (CRC) lymph node metastasis (LNM) could assist radiologists in increasing the diagnostic accuracy and help surgeons establish a correct surgical plan. This study aims to present an efficient pipeline with deep transfer learning for CRC LNM classification. Hence, 11 deep pre-trained models have been investigated on a CRC LN dataset. The dataset of this experiment is from Harbin Medical University Cancer Hospital. This dataset contains samples of 619 patients. Among these samples, 312 were positive and 307 were negative. In addition, datasets with different dimensions and various training epochs were also studied to ascertain the minimum training dataset and training times. In order to improve the interpretability of the model classification performance, a visual convolution layer feature map was first established to compute the similarity distance between the feature map and original data. The experimental results revealed that resnet_152 was the best deep pre-trained model for the classification of CRC LNM, with an accuracy of 97.2%, with 600 raw data samples being the minimum dimension of a dataset and 30 epochs the minimum training times in the CRC LNM classification. This study suggests that the proposed deep transfer learning pipeline could classify the CRC LNM with high efficiency, without requiring sophisticated computational knowledge for radiologists.

Download Full-text

Microenvironmental markers are correlated with lymph node metastasis in invasive submucosal colorectal cancer

Histopathology ◽

10.1111/his.14388 ◽

2021 ◽

Author(s):

Tamotsu Sugai ◽

Noriyuki Yamada ◽

Mitsumasa Osakabe ◽

Mai Hashimoto ◽

Noriyuki Uesugi ◽

...

Keyword(s):

Colorectal Cancer ◽

Lymph Node ◽

Lymph Node Metastasis ◽

Node Metastasis ◽

Submucosal Colorectal Cancer

Download Full-text

Increased Expression of VANGL1 is Predictive of Lymph Node Metastasis in Colorectal Cancer: Results from a 20-Gene Expression Signature

Journal of Personalized Medicine ◽

10.3390/jpm11020126 ◽

2021 ◽

Vol 11 (2) ◽

pp. 126

Author(s):

Noshad Peyravian ◽

Stefania Nobili ◽

Zahra Pezeshkian ◽

Meysam Olfatifar ◽

Afshin Moradi ◽

...

Keyword(s):

Gene Expression ◽

Colorectal Cancer ◽

Lymph Node ◽

Lymph Node Metastasis ◽

Candidate Genes ◽

Case Series ◽

Gene Expression Signature ◽

Gene Panel ◽

Expression Levels ◽

Node Metastasis

This study aimed at building a prognostic signature based on a candidate gene panel whose expression may be associated with lymph node metastasis (LNM), thus potentially able to predict colorectal cancer (CRC) progression and patient survival. The mRNA expression levels of 20 candidate genes were evaluated by RT-qPCR in cancer and normal mucosa formalin-fixed paraffin-embedded (FFPE) tissues of CRC patients. Receiver operating characteristic curves were used to evaluate the prognosis performance of our model by calculating the area under the curve (AUC) values corresponding to stage and metastasis. A total of 100 FFPE primary tumor tissues from stage I–IV CRC patients were collected and analyzed. Among the 20 candidate genes we studied, only the expression levels of VANGL1 significantly varied between patients with and without LNMs (p = 0.02). Additionally, the AUC value of the 20-gene panel was found to have the highest predictive performance (i.e., AUC = 79.84%) for LNMs compared with that of two subpanels including 5 and 10 genes. According to our results, VANGL1 gene expression levels are able to estimate LNMs in different stages of CRC. After a proper validation in a wider case series, the evaluation of VANGL1 gene expression and that of the 20-gene panel signature could help in the future in the prediction of CRC progression.

Download Full-text

16. Apical lymph node metastasis and survival in resected colorectal cancer

Pathology ◽

10.1097/01.pat.0000461625.51675.14 ◽

2015 ◽

Vol 47 ◽

pp. S105

Author(s):

Nav Gill ◽

Christopher W. Toon ◽

Nicole Watson ◽

Anthony J. Gill

Keyword(s):

Colorectal Cancer ◽

Lymph Node ◽

Lymph Node Metastasis ◽

Node Metastasis

Download Full-text

Tumor Budding and Pathological Differentiation Are Predictive Markers for Lymph Node Metastasis in T1 Colorectal Cancer

Gastrointestinal Endoscopy ◽

10.1016/j.gie.2006.03.538 ◽

2006 ◽

Vol 63 (5) ◽

pp. AB216 ◽

Cited By ~ 1

Author(s):

Hitoshi Yamauchi ◽

Kazutomo Togashi ◽

Hiroshi Kawamura ◽

Junichi Sasaki ◽

Masaki Okada ◽

...

Keyword(s):

Colorectal Cancer ◽

Lymph Node ◽

Lymph Node Metastasis ◽

Predictive Markers ◽

Tumor Budding ◽

Node Metastasis ◽

Pathological Differentiation ◽

T1 Colorectal Cancer

Download Full-text

Pure Well-Differentiated Adenocarcinoma Is a Safe Factor for Lymph Node Metastasis in T1 and T2 Colorectal Cancer: A Pilot Study

Gastroenterology Research and Practice ◽

10.1155/2018/8798405 ◽

2018 ◽

Vol 2018 ◽

pp. 1-9 ◽

Cited By ~ 2

Author(s):

Naohisa Yoshida ◽

Masayoshi Nakanishi ◽

Ken Inoue ◽

Ritsu Yasuda ◽

Ryohei Hirose ◽

...

Keyword(s):

Colorectal Cancer ◽

Lymph Node ◽

Lymph Node Metastasis ◽

Venous Invasion ◽

Lymphatic Invasion ◽

Clinicopathological Factors ◽

Node Metastasis ◽

Kappa Value ◽

T1 And T2 ◽

Well Differentiated

Background and Aims. Various risk factors for lymph node metastasis (LNM) have been reported in colorectal T1 cancers. However, the factors available are insufficient for predicting LNM. We therefore investigated the utility of the new histological factor “pure well-differentiated adenocarcinoma” (PWDA) as a safe factor for predicting LNM in T1 and T2 cancers. Materials and Methods. We reviewed 115 T2 cancers and 202 T1 cancers in patients who underwent surgical resection in our center. We investigated the rates of LNM among various clinicopathological factors, including PWDA. PWDA was defined as a lesion comprising only well-differentiated adenocarcinoma. The consistency of the diagnosis of PWDA was evaluated among two pathologists. In addition, 72 T1 cancers with LNM from 8 related hospitals over 10 years (2008–2017) were also analyzed. Results. The rates of LNM and PWDA were 23.5% and 20.0%, respectively, in T2 cancers. Significant differences were noted between patients with and without LNM regarding lymphatic invasion (81.5% vs. 36.4%, p<0.001), poor histology (51.9% vs. 19.3%, p=0.008), and PWDA (3.7% vs. 25.0%, p=0.015). The rates of LNM and PWDA were 8.4% and 36.1%, respectively, in T1 cancers. Regarding the 73 PWDA cases and 129 non-PWDA cases, the rates of LNM were 0.0% and 13.2%, respectively (p<0.001). Among the 97 cases with lymphatic or venous invasion, the rates of LNM in 29 PWDA cases and 68 non-PWDA were 0% and 14.7%, respectively (p=0.029). The agreement of the two pathologists for the diagnosis of PWDA was acceptable (kappa value > 0.5). A multicenter review showed no cases of PWDA among 72 T1 cancers with LNM. Conclusions. PWDA is considered to be a safe factor for LNM in T1 cancer.

Download Full-text