Predicting Soft Tissue Sarcoma Response to Neoadjuvant Chemotherapy Using an MRI-Based Delta-Radiomics Approach.
Brandon K K FieldsNatalie L DemirjianSteven Y CenBino A VargheseDarryl H HwangXiaomeng LeiBhushan DesaiVinay DuddalwarGeorge R MatcukPublished in: Molecular imaging and biology (2023)
Overall, while our result was not able to separate NAC responders from non-responders, our analyses did identify a subset of LTE-derived metrics that show promise for further investigations. Future studies will likely benefit from larger sample size constructions so as to avoid the need for data filtering and feature selection techniques, which have the potential to significantly bias the machine learning procedures.
Keyphrases
- neoadjuvant chemotherapy
- machine learning
- big data
- contrast enhanced
- artificial intelligence
- locally advanced
- lymph node
- sentinel lymph node
- magnetic resonance imaging
- transcription factor
- deep learning
- current status
- diffusion weighted imaging
- electronic health record
- lymph node metastasis
- case control
- magnetic resonance
- squamous cell carcinoma
- computed tomography
- rectal cancer
- radiation therapy
- human health
- early stage
- genome wide analysis
- neural network