Machine learning for lung texture analysis on thin-section CT: Capability for assessments of disease severity and therapeutic effect for connective tissue disease patients in comparison with expert panel evaluations

2021 ◽  
pp. 028418512110449
Author(s):  
Yoshiharu Ohno ◽  
Kota Aoyagi ◽  
Daisuke Takenaka ◽  
Takeshi Yoshikawa ◽  
Yasuko Fujisawa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Texture Analysis ◽  
Disease Severity ◽  
Thin Section ◽  
Ct Scans ◽  
Normal Lung ◽  
Quantitative Index ◽  
Serial Ct ◽  
Ct Texture Analysis

Background The need for quantitative assessment of interstitial lung involvement on thin-section computed tomography (CT) has arisen in interstitial lung diseases including connective tissue disease (CTD). Purpose To evaluate the capability of machine learning (ML)-based CT texture analysis for disease severity and treatment response assessments in comparison with qualitatively assessed thin-section CT for patients with CTD. Material and Methods A total of 149 patients with CTD-related ILD (CTD-ILD) underwent initial and follow-up CT scans (total 364 paired serial CT examinations), pulmonary function tests, and serum KL-6 level tests. Based on all follow-up examination results, all paired serial CT examinations were assessed as “Stable” (n = 188), “Worse” (n = 98) and “Improved” (n = 78). Next, quantitative index changes were determined by software, and qualitative disease severity scores were assessed by consensus of two radiologists. To evaluate differences in each quantitative index as well as in disease severity score between paired serial CT examinations, Tukey's honestly significant difference (HSD) test was performed among the three statuses. Stepwise regression analyses were performed to determine changes in each pulmonary functional parameter and all quantitative indexes between paired serial CT scans. Results Δ% normal lung, Δ% consolidation, Δ% ground glass opacity, Δ% reticulation, and Δdisease severity score showed significant differences among the three statuses ( P < 0.05). All differences in pulmonary functional parameters were significantly affected by Δ% normal lung, Δ% reticulation, and Δ% honeycomb (0.16 ≤r2 ≤0.42; P < 0.05). Conclusion ML-based CT texture analysis has better potential than qualitatively assessed thin-section CT for disease severity assessment and treatment response evaluation for CTD-ILD.

Early ischemic lesion on computed tomography: predictor of poor outcome among survivors of aneurysmal subarachnoid hemorrhage

2007 ◽  
Vol 107 (6) ◽  
pp. 1074-1079 ◽  
Author(s):  
Jari Siironen ◽  
Matti Porras ◽  
Joona Varis ◽  
Kristiina Poussa ◽  
Juha Hernesniemi ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Subarachnoid Hemorrhage ◽  
Independent Predictor ◽  
Aneurysmal Subarachnoid Hemorrhage ◽  
Ct Scans ◽  
Ischemic Lesion ◽  
Poor Outcome ◽  
Serial Ct ◽  
Early Lesion

Object Identifying ischemic lesions after subarachnoid hemorrhage (SAH) is important because the appearance of these lesions on follow-up imaging correlates with a poor outcome. The effect of ischemic lesions seen on computed tomography (CT) scans during the first days of treatment remains unknown, however. Methods In 156 patients with SAH, clinical course and outcome, as well as the appearance of ischemic lesions on serial CT scans, were prospectively monitored for 3 months. At 3 months after SAH, magnetic resonance imaging was performed to detect permanent lesions that had not been visible on CT. Results Of the 53 patients with no lesions on any of the follow-up CT scans, four (8%) had a poor outcome. Of the 52 patients with a new hypodense lesion on the first postoperative day CT, 23 (44%) had a poor outcome. Among the remaining 51 patients with a lesion appearing later than the first postoperative morning, 10 (20%) had a poor outcome (p < 0.001). After adjusting for patient age; clinical condition on admission; amounts of subarachnoid, intracerebral, and intraventricular blood; and plasma glucose and D-dimer levels, a hypodense lesion on CT on the first postoperative morning was an independent predictor of poor outcome after SAH (odds ratio 7.27, 95% confidence interval 1.54–34.37, p < 0.05). Conclusions A new hypodense lesion on early postoperative CT seems to be an independent risk factor for poor outcome after SAH, and this early lesion development may be more detrimental to clinical outcome than a later lesion occurrence.

Predictive role of CT texture analysis in patients with metastatic urothelial cancer treated with PD-1/PD-L1 inhibitors.

2019 ◽  
Vol 37 (7_suppl) ◽  
pp. 424-424
Author(s):  
Francesco Alessandrino ◽  
Rahul Gujrathi ◽  
Amin Nassar ◽  
Arwa Alzaghal ◽  
Arvind Ravi ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Urothelial Cancer ◽  
Stepwise Logistic Regression ◽  
Stepwise Logistic Regression Analysis ◽  
Contrast Enhanced Ct ◽  
Specificity And Sensitivity ◽  
Metastatic Urothelial Cancer ◽  
Ct Texture Analysis

424 Background: Reliable biomarkers to predict response of urothelial cancer to PD-1/PD-L1 inhibitors are still being investigated. Texture analysis represents underlying tumor heterogeneity and may serve as a predictor of response in urothelial cancer. The purpose of this study was to assess predictive ability of CT texture analysis for disease progression in patients with metastatic urothelial cancer treated with PD-1/PD-L1 inhibitor. Methods: In this IRB-approved HIPAA-compliant retrospective study, from total 93 consecutive patients with metastatic urothelial cancer treated with PD-1/PD-L1 inhibitors from 2013-2018, 43 patients with measurable disease per RECIST 1.1 criteria who had contrast-enhanced CT performed within three months after starting treatment were included. Progression-free survival was calculated based on serial follow-up CTs, and 11 patients without progression who did not reach 1 year follow-up were excluded. Texture features of measurable lesions on first follow-up CT were extracted (TexRAD Ltd, Feedback Plc, Cambridge, UK). Stepwise logistic regression analysis to identify patients who had progressive disease (PD) at 12 months was performed and performance assessed using receiver operator curves. Results: Of 32 included patients (24 men, 8 women; median age: 65 years) who had total 80 measurable lesions, 22 progressed by 12 months. On first follow-up CT, the entropy and mean of the lesions were higher (p = 0.04, p = 0.02) for patients with PD by 12 months. Calculated specificity and sensitivity of entropy (AUC = 0.79) were 90%, and 63%; of mean (AUC = 0.81) were 90%, and 50%. A predictive model including mean and entropy yielded 95% sensitivity, 80% specificity, 91% PPV, 89% NPV and 91% accuracy (AUC = 0.863) to identify patients with PD at 12 months. Conclusions: Texture analysis of CT performed within three months after starting PD-1/PD-L1 can help predict patients who progress by 12 months with high accuracy. Further studies investigating the correlation of texture analysis with survival endpoints may help validate the role of texture analysis as a biomarker to predict response to PD1/PD-L1 inhibitors.

Radiomics features on CT scans to predict response to HER2-targeted therapy of hepatic metastases from colorectal cancer.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e15086-e15086
Author(s):  
Valentina Giannini ◽  
Simone Mazzetti ◽  
Arianna Defeudis ◽  
Giovanni Cappello ◽  
Lorenzo Vassallo ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Texture Analysis ◽  
Hepatic Metastases ◽  
Texture Features ◽  
Response To Therapy ◽  
Ct Scans ◽  
Imaging Biomarkers ◽  
Test Set ◽  
Extended Analysis ◽  
Ct Texture Analysis

e15086 Background: Metastatic Colorectal cancer (mCRC) is the 2nd cause of cancer death worldwide. Repeated cycles of therapies, combined with surgery in oligo-metastatic cases, are the therapeutic standard in mCRC. However, this strategy is seldom resolutive. Different lesions in in the same patient could have different responses to systemic therapy. Recently, CT texture analysis (CTTA) had been shown to potentially provide with prognostic and predictive markers, overcoming the limitations of biopsy sampling in defining tumor heterogeneity. The aim of this study is to use CT texture analysis (CTTA) to identify imaging biomarkers of HER2+ mCRC able to predict lesion response to therapy. Methods: The dataset is composed of 39 extended RAS wild type patients with amplified HER2 mCRC enrolled in the HERACLES trial (NCT03225937) that received either a lapatinib+trastuzumab treatment (n = 23) or a pertuzumab+ trastuzumab-emtansine treatment (n = 16). All patients underwent CT examination every 8 weeks, until disease progression. All mCRC on baseline CT were semi-automatically segmented and quantitative features extracted: size, mean, percentiles, 28 texture features. A logistic regression model was created using: (i) the whole dataset of mCRC as training and test set and (ii) 100 randomly generated training sets (with 70% of responder (R+) mCRC and an equal number of non-responder (R-) mCRC), and 100 test sets including the remaining mCRC. A mCRC was classified as R+ if size decreased (-10%) or was stable (±10%); as R- if size increased (+10%), during subsequent CT scans. Results: A total of 199 metastases were included (75R+ and 124R-). The training set was composed of 53R+ and 53R- mCRC and the test set of 22R+ and 71R- mCRC. Using the whole dataset, the model reached an AUC = 0.82 (sensitivity = 84%, specificity = 70%), while it reached a mean AUC of 0.70 (sensitivity = 68%, specificity = 67%) within the 100 repetitions. Conclusions: CTTA might help in stratifying different behaviors of mCRC, opening the way for lesion-specific therapies, with conceivable cost and life savings. Further extended analysis is needed to better characterize and validate predictive value of these biomarkers.

Machine learning for CT texture analysis in chemosensitivity of colorectal liver metastases: Initial results.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e15148-e15148
Author(s):  
Yuji Miyamoto ◽  
Takeshi Nakaura ◽  
Yukiharu Hiyoshi ◽  
Hideo Baba
Keyword(s):  
Colorectal Cancer ◽  
Machine Learning ◽  
Prediction Model ◽  
Liver Metastases ◽  
Texture Analysis ◽  
Gray Level ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Chemotherapeutic Response ◽  
Ct Texture Analysis

e15148 Background: Despite advances in cancer treatment over the last decades, more efficacious biomarkers are needed in patients with metastatic colorectal cancer. Several studies have reported that CT texture analysis is a useful prognostic biomarker for patients with colorectal cancer liver metastases (CRLM), however, little study has been done to explore those efficacies using machine learning methods. The present study aimed to evaluate the clinical efficacy of CT texture analysis using machine learning methods as a predictive marker of systemic chemotherapy in patients with CRLM. Methods: Sixty-four patients with CRLM who received first-line chemotherapy were included. Texture analysis was performed on 92 features (First Order Statistics, Gray Level Cooccurrence Matrix, Gray Level Run Length Matrix, Gray Level Size Zone Matrix, Neighbouring Gray Tone Difference Matrix and Gray Level Dependence Matrix) using CT within 1 month before treatment. We evaluated the association between those features and chemotherapeutic response by RECIST (CR+PR vs. SD+PD+NE). We performed eXtreme gradient boost (XGBoost) as a machine learning method to predict the chemotherapeutic response and used the receiver operating characteristic curves to evaluate this prediction model. Results: Main characteristics were the following: male/female = 36/28; median age = 63.5. Patients were treated with oxaliplatin-based chemotherapy (80% of patients), bevacizumab (77%) and anti-EGFR antibody (23%). Thirty-nine patients had confirmed responders, for an overall response rate of 61%, whereas 25 patients (39%) were classified as non-responders (CR: PR: SD: PD: NE = 0: 39: 20: 4: 1). The area under curve of this prediction model was 0.771. Conclusions: We confirmed that CT texture analysis using machine learning for CRLM was feasible. Further analyses are ongoing.

Sign in / Sign up

Export Citation Format

Share Document