Machine learning for prediction of chemoradiation therapy response in rectal cancer using pre-treatment and mid-radiation multi-parametric MRI

Shi, Lei; Zhang, Yang; Nie, Ke; Sun, Xin; Niu, Tianye; Yue, Ning J.; Kwong, Tiffany C.; Chang, Peter D.; Chow, Daniel; Chen, Jeon Hor; Su, Min

doi:10.1016/j.mri.2019.05.003

Cited by 86 publications

(61 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, our observations are similar with the findings of Liu et al and Yang et al, which reported AUCs of 0.908 and 0.83 respectively for predicting resistant rectal adenocarcinoma using ADC maps as a basis for feature extraction [ 62 , 63 ]. Additionally, our study was relatively in line with the prior investigations of Yi et al and Shi et al, whose radiomics models achieved AUCs of 0.90 and 0.91 respectively for distinguishing good responders from non-good responders, although their classification of non-responders was slightly different than ours [ 57 , 58 ]. In our research, the multivariate analysis indicated that the radiomics score was the only independent predictor for the differentiation of LARC non-responders, having an odds ratio of 6.52.…”

Section: Discussionsupporting

confidence: 91%

“…The majority of studies focused on predicting the pathological complete response, using a single MRI sequence (T2-WI or apparent diffusion coefficient (ADC) maps) or a multiparametric approach [ 49 , 50 , 51 , 52 , 53 , 54 , 55 ]. Additionally, there are several studies that investigated the performance of radiomic features to discriminate good responders [ 56 , 57 , 58 , 59 , 60 ]. In contrast to our research, these investigations either used other pathologic classifications for the quantification of tumor regression grade such as Dworak [ 57 ] or Mandard [ 59 ] or the authors divided their study population different from our approach, including in the non-responders’ group both patients with a TRG score of 2 and 3 [ 56 , 58 , 60 ].…”

Section: Discussionmentioning

confidence: 99%

“…Additionally, there are several studies that investigated the performance of radiomic features to discriminate good responders [ 56 , 57 , 58 , 59 , 60 ]. In contrast to our research, these investigations either used other pathologic classifications for the quantification of tumor regression grade such as Dworak [ 57 ] or Mandard [ 59 ] or the authors divided their study population different from our approach, including in the non-responders’ group both patients with a TRG score of 2 and 3 [ 56 , 58 , 60 ]. In our research, we used the Ryan TRG classification and we considered patients with a TRG score of 3 as non-responders, while patients with TRG 2 were included in the responders’ group.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Pre-Treatment T2-WI Based Radiomics Features for Prediction of Locally Advanced Rectal Cancer Non-Response to Neoadjuvant Chemoradiotherapy: A Preliminary Study

Petresc

Lebovici

Caraiani

et al. 2020

Cancers

View full text Add to dashboard Cite

Locally advanced rectal cancer (LARC) response to neoadjuvant chemoradiotherapy (nCRT) is very heterogeneous and up to 30% of patients are considered non-responders, presenting no tumor regression after nCRT. This study aimed to determine the ability of pre-treatment T2-weighted based radiomics features to predict LARC non-responders. A total of 67 LARC patients who underwent a pre-treatment MRI followed by nCRT and total mesorectal excision were assigned into training (n = 44) and validation (n = 23) groups. In both datasets, the patients were categorized according to the Ryan tumor regression grade (TRG) system into non-responders (TRG = 3) and responders (TRG 1 and 2). We extracted 960 radiomic features/patient from pre-treatment T2-weighted images. After a three-step feature selection process, including LASSO regression analysis, we built a radiomics score with seven radiomics features. This score was significantly higher among non-responders in both training and validation sets (p < 0.001 and p = 0.03) and it showed good predictive performance for LARC non-response, achieving an area under the curve (AUC) = 0.94 (95% CI: 0.82–0.99) in the training set and AUC = 0.80 (95% CI: 0.58–0.94) in the validation group. The multivariate analysis identified the radiomics score as an independent predictor for the tumor non-response (OR = 6.52, 95% CI: 1.87–22.72). Our results indicate that MRI radiomics features could be considered as potential imaging biomarkers for early prediction of LARC non-response to neoadjuvant treatment.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Pre-Treatment T2-WI Based Radiomics Features for Prediction of Locally Advanced Rectal Cancer Non-Response to Neoadjuvant Chemoradiotherapy: A Preliminary Study

Petresc

Lebovici

Caraiani

et al. 2020

Cancers

View full text Add to dashboard Cite

show abstract

“…For each case, the smallest square bounding box containing the entire tumor was generated. This was done by projecting the segmented tumor ROIs from all slices together, and the smallest square box covering the projected boundary was generated . In order to evaluate the diagnostic role of peritumor tissues, five different input boxes were used, including 1) the tumor alone by setting all outside tumor pixels in the box as zero, 2) the smallest bounding box, 3) enlarged box by 1.2 times, 4) enlarged box by 1.5 times, and 5) enlarged box by 2.0 times.…”

Section: Methodsmentioning

confidence: 99%

Diagnosis of Benign and Malignant Breast Lesions on DCE‐MRI by Using Radiomics and Deep Learning With Consideration of Peritumor Tissue

Zhou

Zhang

Chang

et al. 2019

Magnetic Resonance Imaging

Self Cite

145

123

View full text Add to dashboard Cite

Background: Computer-aided methods have been widely applied to diagnose lesions detected on breast MRI, but fullyautomatic diagnosis using deep learning is rarely reported. Purpose: To evaluate the diagnostic accuracy of mass lesions using region of interest (ROI)-based, radiomics and deeplearning methods, by taking peritumor tissues into consideration. Study Type: Retrospective. Population: In all, 133 patients with histologically confirmed 91 malignant and 62 benign mass lesions for training (74 patients with 48 malignant and 26 benign lesions for testing). Field Strength/Sequence: 3T, using the volume imaging for breast assessment (VIBRANT) dynamic contrast-enhanced (DCE) sequence. Assessment: 3D tumor segmentation was done automatically by using fuzzy-C-means algorithm with connectedcomponent labeling. A total of 99 texture and histogram parameters were calculated for each case, and 15 were selected using random forest to build a radiomics model. Deep learning was implemented using ResNet50, evaluated with 10-fold crossvalidation. The tumor alone, smallest bounding box, and 1.2, 1.5, 2.0 times enlarged boxes were used as inputs. Statistical Tests: The malignancy probability was calculated using each model, and the threshold of 0.5 was used to make a diagnosis. Results: In the training dataset, the diagnostic accuracy was 76% using three ROI-based parameters, 84% using the radiomics model, and 86% using ROI + radiomics model. In deep learning using the per-slice basis, the area under the receiver operating characteristic (ROC) was comparable for tumor alone, smallest and 1.2 times box (AUC = 0.97-0.99), which were significantly higher than 1.5 and 2.0 times box (AUC = 0.86 and 0.71, respectively). For per-lesion diagnosis, the highest accuracy of 91% was achieved when using the smallest bounding box, and that decreased to 84% for tumor alone and 1.2 times box, and further to 73% for 1.5 times box and 69% for 2.0 times box. In the independent testing dataset, the perlesion diagnostic accuracy was also the highest when using the smallest bounding box, 89%. Data Conclusion: Deep learning using ResNet50 achieved a high diagnostic accuracy. Using the smallest bounding box containing proximal peritumor tissue as input had higher accuracy compared to using tumor alone or larger boxes. Level of Evidence: 3 Technical Efficacy: Stage 2

show abstract

“…ML is increasingly used in the medical community, particularly in the field of oncology. Previous studies have demonstrated that ML models can provide better accuracy and discrimination for the prediction of prognoses for lung adenocarcinoma (12) and breast cancer (13), chemoradiation therapy response in rectal cancer (14), radiotherapy response for acromegaly (15), surgical outcomes for head and neck cancer (16), and diagnosis for leukemia (17). For sellar region tumors, ML could be more effective for predicting a patient's clinical outcome and could provide better clinical decision support for neuroendocrinologists and neurosurgeons (18).…”

Section: Introductionmentioning

confidence: 99%

Development and Interpretation of Multiple Machine Learning Models for Predicting Postoperative Delayed Remission of Acromegaly Patients During Long-Term Follow-Up

Dai

Fan

et al. 2020

Front. Endocrinol.

View full text Add to dashboard Cite

Background: Some patients with acromegaly do not reach the remission standard in the short term after surgery but achieve remission without additional postoperative treatment during long-term follow-up; this phenomenon is defined as postoperative delayed remission (DR). DR may complicate the interpretation of surgical outcomes in patients with acromegaly and interfere with decision-making regarding postoperative adjuvant therapy. Objective: We aimed to develop and validate machine learning (ML) models for predicting DR in acromegaly patients who have not achieved remission within 6 months of surgery. Methods: We enrolled 306 acromegaly patients and randomly divided them into training and test datasets. We used the recursive feature elimination (RFE) algorithm to select features and applied six ML algorithms to construct DR prediction models. The performance of these ML models was validated using receiver operating characteristics analysis. We used permutation importance, SHapley Additive exPlanations (SHAP), and local interpretable model-agnostic explanation (LIME) algorithms to determine the importance of the selected features and interpret the ML models. Results: Fifty-five (17.97%) acromegaly patients met the criteria for DR, and five features (post-1w rGH, post-1w nGH, post-6m rGH, post-6m IGF-1, and post-6m nGH) were significantly associated with DR in both the training and the test datasets. After the RFE feature selection, the XGboost model, which comprised the 15 important features, had the greatest discriminatory ability (area under the curve = 0.8349, sensitivity = 0.8889, Youden's index = 0.6842). The XGboost model showed good discrimination ability and provided significantly better estimates of DR of patients with acromegaly compared with using only the Knosp grade. The results obtained from permutation importance, SHAP, and LIME algorithms showed that post-6m IGF-1 is the most important feature in XGboost algorithm prediction and showed the reliability and the clinical practicability of the XGboost model in DR prediction. Dai et al. ML Models Predict Acromegaly DR Conclusions: ML-based models can serve as an effective non-invasive approach to predicting DR and could aid in determining individual treatment and follow-up strategies for acromegaly patients who have not achieved remission within 6 months of surgery.

show abstract

Machine learning for prediction of chemoradiation therapy response in rectal cancer using pre-treatment and mid-radiation multi-parametric MRI

Cited by 86 publications

References 32 publications

Pre-Treatment T2-WI Based Radiomics Features for Prediction of Locally Advanced Rectal Cancer Non-Response to Neoadjuvant Chemoradiotherapy: A Preliminary Study

Pre-Treatment T2-WI Based Radiomics Features for Prediction of Locally Advanced Rectal Cancer Non-Response to Neoadjuvant Chemoradiotherapy: A Preliminary Study

Diagnosis of Benign and Malignant Breast Lesions on DCE‐MRI by Using Radiomics and Deep Learning With Consideration of Peritumor Tissue

Development and Interpretation of Multiple Machine Learning Models for Predicting Postoperative Delayed Remission of Acromegaly Patients During Long-Term Follow-Up

Contact Info

Product

Resources

About