A Few-Shot Learning Approach Assists in the Prognosis Prediction of Magnetic Resonance-Guided Focused Ultrasound for the Local Control of Bone Metastatic Lesions

Hsu, Fang‐Chi; Lee, Hsin-Lun; Chen, Yin‐Ju; Shen, Yao; Tsai, Yi-Chieh; Wu, Meng; Kuo, Chia‐Chun; Lu, Long‐Sheng; Yeh, Shauh-Der; Huang, Wen-Sheng; Shen, Chia‐Ning; Chiou, Jeng‐Fong

doi:10.3390/cancers14020445

Cited by 6 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few-shot learning (FSL) was more suitable to help classify high-dimensional cytokine data from a small sample size ( 16 ). To better predict MPR, we constructed a filtering algorithm to rank the features and selected the most efficient model from seven FSL machine-learning classifiers ( 17 ): k -nearest neighbor (classif.kknn), random forest (classif.ranger), Gaussian processes (classif.gausspr), Naive Bayes processes (classif.naive_bayes), factorization machine supported neural network (classif.fnn), support vector machines (classif.svm), and logistic regression (classif.log_reg).…”

Section: Methodsmentioning

confidence: 99%

Neoadjuvant tislelizumab and tegafur/gimeracil/octeracil (S-1) plus oxaliplatin in patients with locally advanced gastric or gastroesophageal junction cancer: Early results of a phase 2, single-arm trial

Yin

Yang

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

BackgroundRecently, the combination of immunotherapy with chemotherapy has been recommended as first-line treatment of metastatic gastric/gastroesophageal junction (G/GEJ) in the clinical guidelines of many countries; the therapeutic potential of this application needs to be further investigated for neoadjuvant therapy of advanced G/GEJ cancer patients.MethodsWe performed a prospective, single-arm, open-label, phase 2 trial of the PD-1 inhibitor tislelizumab combined with S-1 plus oxaliplatin (SOX) in patients with advanced LAG/GEJ cancer. All patients underwent the three-cycle (21 days/cycle) treatment except for one patient who underwent two cycles. The primary endpoints were tumor major pathology response (MPR) and other events of tumor response assessed by the RECIST 1.1 and Becker criteria. Moreover, we constructed a few-shot learning model to predict the probability of MPR, which could screen those patients who might benefit from the neoadjuvant immunotherapy–chemotherapy scheme. This study was registered at https://clinicaltrials.gov/ct2/show/NCT0-4890392.ResultsThirty-two patients were enrolled; 17 patients (53.1%) achieved MPR (≤10% viable tumor cells) after treatment, and among them, 8 (25.0%) had a pathological complete response (pCR). The 1-year overall survival (OS) rate was 91.4% and the 1-year recurrence-free survival (RFS) rate was 90.0%. Adverse events occurred in 24 patients (65.6%) and grade III–IV adverse events were observed in 4 patients (12.5%) during the neoadjuvant period. Furthermore, we found commonly used preoperative assessment tools such as CT and EUS, which presented limited accuracy of tumor therapeutic response in this study; thus, we developed a therapeutic response predictive model that consisted of TNFα, IFNγ, IL-10, CD4, and age of patient, and the AUC of this FSL model was 0.856 (95% CI: 0.823–0.884).DiscussionOur study showed that the neoadjuvant PD-1 inhibitor tislelizumab combined with SOX had promising application potential and presented no increasing treatment-related adverse events in patients with advanced G/GEJ cancer. Moreover, the predictive model could help therapists to evaluate the therapeutic response of this scheme accurately.Clinical Trial Registrationhttps://clinicaltrials.gov/ct2/show/NCT0-4890392, identifier [NCT04890392].

show abstract

Section: Methodsmentioning

confidence: 99%

Neoadjuvant tislelizumab and tegafur/gimeracil/octeracil (S-1) plus oxaliplatin in patients with locally advanced gastric or gastroesophageal junction cancer: Early results of a phase 2, single-arm trial

Yin

Yang

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…A few-shot machine learning approach was proposed as a prognosis prediction model for pain palliation for patients treated with MR-HIFU. This model took into consideration Karnofsky performance status (KPS), IL-6, INFγ, TNFα and vascular endothelial growth factor (VEGF) levels and had an accuracy of 95%, an area under the curve (AUC) of 0.95 and Akaike information criteria (AIC) of 17.14 [35].…”

Section: Treatment Of Bone Metastasismentioning

confidence: 99%

High Intensity Focused Ultrasound for Treatment of Bone Malignancies—20 Years of History

Yeo

Bratke

Grüll

2022

Cancers

View full text Add to dashboard Cite

High Intensity Focused Ultrasound (HIFU) is the only non-invasive method for percutaneous thermal ablation of tissue, with treatments typically performed either under magnetic resonance imaging or ultrasound guidance. Since this method allows efficient heating of bony structures, it has found not only early use in treatment of bone pain, but also in local treatment of malignant bone tumors. This review of 20 years of published studies shows that HIFU is a very efficient method for rapid pain relief, can provide local tumor control and has a very patient-friendly safety profile.

show abstract

“…Few-shot learning is a deep learning approach that is particularly useful in drug resistance research (12,13). This approach is designed to address the problem of limited data availability, which is a common challenge in biomarker discovery.…”

Section: Introductionmentioning

confidence: 99%

Multiomics Approach to Understanding Olaparib Resistance and Predicting Drug Response

Lim¹,

Kim²,

Oh³

et al. 2023

Preprint

View full text Add to dashboard Cite

We aimed to uncover genetic factors affecting resistance to the cancer drug olaparib. To do this, we utilized multiomics matrix factorization (MOFA), a multiomics approach, to explore omic-based features that might become biomarker candidates. Our results showed that 17 damaging mutations, 6 gene expression signatures, 17 DNA methylations, and 26 transcription-factor activities can impact the refractory response to olaparib. To verify the potential utility of the identified biomarker candidates, we generated a predictive model to differentiate between olaparib responding and nonresponding cell lines using machine learning techniques, including support vector machine algorithms, random forest algorithms, and Siamese neural networks. The model was centered around six gene-expression biomarker candidates and validated using the Genomics of Drug Sensitivity in Cancer database. Our findings suggest that using a multiomics approach with machine learning methods can lead to a better understanding of the mechanism of drug resistance and identify biomarkers, which will ultimately facilitate the appropriate administration of drugs to patients. The source codes can be found at https://github.com/wjlim/DrugResistance.

show abstract

A Few-Shot Learning Approach Assists in the Prognosis Prediction of Magnetic Resonance-Guided Focused Ultrasound for the Local Control of Bone Metastatic Lesions

Cited by 6 publications

References 39 publications

Neoadjuvant tislelizumab and tegafur/gimeracil/octeracil (S-1) plus oxaliplatin in patients with locally advanced gastric or gastroesophageal junction cancer: Early results of a phase 2, single-arm trial

Neoadjuvant tislelizumab and tegafur/gimeracil/octeracil (S-1) plus oxaliplatin in patients with locally advanced gastric or gastroesophageal junction cancer: Early results of a phase 2, single-arm trial

High Intensity Focused Ultrasound for Treatment of Bone Malignancies—20 Years of History

Multiomics Approach to Understanding Olaparib Resistance and Predicting Drug Response

Contact Info

Product

Resources

About