scholarly journals Radiomics AI prediction for head and neck squamous cell carcinoma (HNSCC) prognosis and recurrence with target volume approach

BJR|Open ◽  
2021 ◽  
Vol 3 (1) ◽  
pp. 20200073
Author(s):  
Tang FH ◽  
Chu CYW ◽  
Cheung EYW

Objectives: To evaluate the performance of radiomics features extracted from planning target volume (PTV) and gross tumor volume (GTV) in the prediction of the death prognosis and cancer recurrence rate for head and neck squamous cell carcinoma (HNSCC). Methods: 188 HNSCC patients’ planning CT images with radiotherapy structures sets were acquired from Cancer Imaging Archive (TCIA). The 3D slicer (v. 4.10.2) with the PyRadiomics extension (Computational Imaging and Bioinformatics Lab, Harvard medical School) was used to extract radiomics features from the radiotherapy planning images. An in-house developed deep learning artificial neural networks (DL-ANN) model was used to predict death prognosis and cancer recurrence rate based on the features extracted from GTV and PTV of the CT images. Results: The PTV radiomics features with DL-ANN model could achieve 77.7% accuracy with overall AUC equal to 0.934 and 0.932 when predicting HNSCC-related death prognosis and cancer recurrence respectively. Furthermore, the DL-ANN model can achieve an accuracy of 74.3% with AUC equal to 0.947 and 0.956 for the HNSCC-related death prognosis and cancer recurrence respectively using GTV features. Conclusion: Using both GTV and PTV radiomics features in the DL-ANN model, can aid in predicting HNSCC-related death prognosis and cancer recurrence. Clinicians may find it helpful in formulating different treatment regimens and facilitate personized medicine based on the predicted outcome when performing GTV and PTV delineation. Advances in knowledge: Radiomics features of GTV and PTV are reliable prognosis and recurrence predicting tools, which may help clinicians in GTV and PTV delineation to facilitate delivery of personalized treatment.

2016 ◽  
Vol 46 (1) ◽  
pp. 53
Author(s):  
Azwar Azwar ◽  
Sofia Mubarika ◽  
Agus Surono

Latar belakang: Karsinoma sel skuamosa kepala dan leher merupakan salah satu kanker terseringdi seluruh dunia. Pendekatan pengobatan agresif dan multidisiplin telah dilakukan, namun belum adapeningkatan yang signifikan dalam kelangsungan hidup 5 tahun, selama 20 tahun terakhir. Kegagalanpengobatan terjadi dalam bentuk kekambuhan lokoregional, metastasis jauh, dan/atau tumor primer kedua.Berbagai penanda molekular tumor telah diteliti untuk mengetahui potensinya dalam memprediksi hasilpenyakit atau respon terhadap terapi.Tujuan: Mengetahui hubungan ekspresi protein p53, Bcl-2, c-Myc,dan MMP-9 berdasarkan gambaran klinikopatologis karsinoma sel skuamosa kepala dan leher di RumahSakit dr. Zainoel Abidin.Metode: Studi menggunakan desain cross sectional. Sampel terdiri dari 60blok parafin karsinoma sel skuamosa kepala dan leher. Prosedur pewarnaan imunohistokimia dilakukandengan menggunakan antibodi monoklonal terhadap p53, Bcl-2, c-Myc, dan MMP-9. Ekspresi proteinp53, Bcl-2, c-Myc, dan MMP-9 dianalisis secara imunohistokimia pada karsinoma sel skuamosa kepaladan leher kemudian hasilnya dihubungkan dengan parameter klinikopatologis seperti usia, jenis kelamin,lokasi tumor, diferensiasi tumor, metastasis kelenjar getah bening dan stadium tumor, kemudian dianalisisstatistik dengan Chi square.Hasil: Hasil penelitian menunjukkan terdapat hubungan bermakna tingkatekspresi p53 dengan metastasis lokal (p=0,021) dan ada hubungan bermakna tingkat ekspresi MMP-9dengan lokasi tumor (p=0,026). Tidak terdapat hubungan ekspresi p53, Bcl-2, cMyc, dan MMP-9 terhadapusia, jenis kelamin, stadium tumor, diferensiasi histologi, tingkat T, N, dan metastasis jauh.Kesimpulan:Ada hubungan ekpresi p53 dengan metastasis kelenjar limfe regional dan ekspresi MMP-9 dengan lokasitumor pada karsinoma sel skuamosa kepala dan leher. Kata kunci: Karsinoma sel skuamosa kepala dan leher, p53, Bcl-2, c-Myc, MMP-9 ABSTRACTBackground: Head and neck squamous cell carcinoma (HNSCC) is one of the most commoncancers world wide. Although aggressive and multidisciplinary approach to the treatment has been done,there is no significant improvement in 5-year survival in the last 20 years. Treatment failure occurredin the form of locoregional recurrence, distant metastasis, and/or a second primary tumor. A variety oftumor molecular markers have been studied to determine their potential in predicting disease outcome orresponse to the therapy. Purpose: To investigate correlation p53, Bcl-2, c-Myc, and MMP-9 expressionto clinicopathologic parameter in head and neck squamous cell carcinoma patient in dr. Zainoel Abidinhospital. Methods: Cross sectional design study. The sample was consisted of 60 paraffin blocks ofhead and neck squamous cell carcinoma. Procedure of immunohistochemical staining used monoclonalantibodies against p53, Bcl-2, c-Myc, and MMP-9. Expression of p53 protein, Bcl-2, c-Myc, and MMP-9were analyzed by immunohistochemistry in head and neck squamous cell carcinoma. Then, the results were linked to clinicopathologic parameters such as age, sex, tumor location, tumor differentiation,lymph node metastasis and tumor stage, and statistically analyzed with Chi square. Results: The resultsshowed there were significant correlation between p53 expression level with local metastasis (p=0,021)and significant correlation of MMP-9 expression levels with tumor location (p=0,026). There were norelationship of p53, Bcl-2, cMyc and MMP-9 expressions based on age, sex, stage tumor, histologicdifferentiation, level of T, N, and distant metastases. Conclusion: There were relationships between p53expression with local metastasis and MMP-9 expression with tumor location in head and neck squamouscell carcinoma. Keywords: Head and neck squamous cell carcinoma, p53, Bcl-2, c-Myc, MMP-9


Sign in / Sign up

Export Citation Format

Share Document