Research presented at the 2022 World Cancer Congress shows that deep learning algorithm outperformed radiologists in detecting head and neck cancer spread. The algorithm was able to detect small areas of cancer spread that were not detected by the radiologists. This is a potentially important finding, as early detection of cancer spread can lead to better outcomes for patients.
Head and neck cancers kill about 400,000 people a year worldwide. Radiation with or without chemotherapy or surgery followed by chemotherapy is the most common treatment strategy. An extracapsular extension, or even an extracapsular spread, occurs when metastatic tumor cells within a lymph node break through the nodal capsule and spread into surrounding tissues through the extracapsular extension.
It is also well established that the extracapsular spread of tumors from neck nodes to the regional lymph nodes is an important prognostic factor associated with poor outcomes in locally advanced head and neck cancers. In addition, there is a further issue in that it is difficult to diagnose ENE reliably from the pathology of the postoperative period, and should, if present, be treated with chemotherapy in conjunction with radiation therapy as part of an adjuvant treatment plan. CT scans can detect ENE, but they’re not very accurate.
Deep Learning Algorithm to Predict Cancer Spread
A deep learning algorithm (DLA) was found to be better at predicting pathologic microscopic and macroscopic extranodal extension (ENE), a sign of cancer spread, than radiologists.
Previously the researchers developed a deep learning algorithm that was capable of predicting ENE with an area under the receiver operating characteristic curve (AUC) of 0.91, enabling them to conclude that such a model may be useful in helping to guide the management of patients with head and neck cancer as a clinical decision-making tool.
A question addressed in the present study was whether this deep learning-based model could be generalized to more high-risk patients. Specifically, the team analyzed the data gathered as part of the E3311 trial, which was a phase II randomized trial of reduced- or standard-dose radiotherapy for people with resected stage III-IVa, human papillomavirus-associated oropharynx cancers. Researchers used pre-treatment CT scan information and surgical pathology reports from E3311 patients to determine if patients with ENE were at high risk. Patients with these results were given chemotherapy and high-dose radiation after transoral surgery. The model was assessed for predictive ability based on AUC and four head and neck radiologists as comparisons.
Extranodal Extension (ENE) Prediction
In 177 scans, 311 lymph nodes were annotated, 23% had ENE and 13% had ENE >1 mm. The deep learning algorithm correctly classified 85% (95% CI 80 – 89%) of the nodes as having ENE, whereas the highest AUC for a radiologist was 70% (64 – 76%) for the same set of nodes. Additionally, the model was better than all four radiologists at detecting ENE >1 mm (model AUC = 85% vs. a mean of 68% for the radiologists, p 0.001).
The study looked at a deep learning algorithm’s ability to predict pathologic ENE in a cohort of HPV-associated oropharyngeal carcinoma (HPV-OPC). The algorithm was found to be more accurate than radiologists in predicting pathologic microscopic and macroscopic ENE.
The findings of this study suggest that deep learning algorithms could potentially be used to improve the accuracy of cancer diagnosis and treatment.
While more research is needed to confirm these findings, the use of deep learning algorithms in the medical field is a promising area of research that could potentially improve the accuracy of the diagnosis and treatment of various diseases.
Story Sources: Reference Paper | Reference Article
Top Bioinformatics Books ↗
Learn more to get deeper insights into the field of bioinformatics.
Top Free Online Bioinformatics Courses ↗
Freely available courses to learn each and every aspect of bioinformatics.
Latest Bioinformatics Breakthroughs ↗
Stay updated with the latest discoveries in the field of bioinformatics.
Dr. Tamanna Anwar is a Scientist and Co-founder of the Centre of Bioinformatics Research and Technology (CBIRT). She is a passionate bioinformatics scientist and a visionary entrepreneur. Dr. Tamanna has worked as a Young Scientist at Jawaharlal Nehru University, New Delhi. She has also worked as a Postdoctoral Fellow at the University of Saskatchewan, Canada. She has several scientific research publications in high-impact research journals. Her latest endeavor is the development of a platform that acts as a one-stop solution for all bioinformatics related information as well as developing a bioinformatics news portal to report cutting-edge bioinformatics breakthroughs.
[…] Read the complete article at: cbirt.net […]