Radiomic signatures from T2W and DWI MRI are predictive of tumour hypoxia in colorectal liver metastases.

BACKGROUND: Tumour hypoxia is a negative predictive and prognostic biomarker in colorectal cancer typically assessed by invasive sampling methods, which suffer from many shortcomings. This retrospective proof-of-principle study explores the potential of MRI-derived imaging markers in predicting tumour hypoxia non-invasively in patients with colorectal liver metastases (CLM). METHODS: A single-centre cohort of 146 CLMs from 112 patients were segmented on preoperative T2-weighted (T2W) images and diffusion-weighted imaging (DWI). HIF-1 alpha immunohistochemical staining index (high/low) was used as a reference standard. Radiomic features were extracted, and machine learning approaches were implemented to predict the degree of histopathological tumour hypoxia. RESULTS: Radiomic signatures from DWI b200 (AUC = 0.79, 95% CI 0.61-0.93, p = 0.002) and ADC (AUC = 0.72, 95% CI 0.50-0.90, p = 0.019) were significantly predictive of tumour hypoxia. Morphological T2W TE75 (AUC = 0.64, 95% CI 0.42-0.82, p = 0.092) and functional DWI b0 (AUC = 0.66, 95% CI 0.46-0.84, p = 0.069) and b800 (AUC = 0.64, 95% CI 0.44-0.82, p = 0.071) images also provided predictive information. T2W TE300 (AUC = 0.57, 95% CI 0.33-0.78, p = 0.312) and b = 10 (AUC = 0.53, 95% CI 0.33-0.74, p = 0.415) images were not predictive of tumour hypoxia. CONCLUSIONS: T2W and DWI sequences encode information predictive of tumour hypoxia. Prospective multicentre studies could help develop and validate robust non-invasive hypoxia-detection algorithms. CRITICAL RELEVANCE STATEMENT: Hypoxia is a negative prognostic biomarker in colorectal cancer. Hypoxia is usually assessed by invasive sampling methods. This proof-of-principle retrospective study explores the role of AI-based MRI-derived imaging biomarkers in non-invasively predicting tumour hypoxia in patients with colorectal liver metastases (CLM).

Prognostic Value of Deep Learning-Mediated Treatment Monitoring in Lung Cancer Patients Receiving Immunotherapy.

BACKGROUND: Checkpoint inhibitors provided sustained clinical benefit to metastatic lung cancer patients. Nonetheless, prognostic markers in metastatic settings are still under research. Imaging offers distinctive advantages, providing whole-body information non-invasively, while routinely available in most clinics. We hypothesized that more prognostic information can be extracted by employing artificial intelligence (AI) for treatment monitoring, superior to 2D tumor growth criteria. METHODS: A cohort of 152 stage-IV non-small-cell lung cancer patients (NSCLC) (73 discovery, 79 test, 903CTs), who received nivolumab were retrospectively collected. We trained a neural network to identify morphological changes on chest CT acquired during patients' follow-ups. A classifier was employed to link imaging features learned by the network with overall survival. RESULTS: Our results showed significant performance in the independent test set to predict 1-year overall survival from the date of image acquisition, with an average area under the curve (AUC) of 0.69 (p < 0.01), up to AUC 0.75 (p < 0.01) in the first 3 to 5 months of treatment, and 0.67 AUC (p = 0.01) for durable clinical benefit (6 months progression-free survival). We found the AI-derived survival score to be independent of clinical, radiological, PDL1, and histopathological factors. Visual analysis of AI-generated prognostic heatmaps revealed relative prognostic importance of morphological nodal changes in the mediastinum, supraclavicular, and hilar regions, lung and bone metastases, as well as pleural effusions, atelectasis, and consolidations. CONCLUSIONS: Our results demonstrate that deep learning can quantify tumor- and non-tumor-related morphological changes important for prognostication on serial imaging. Further investigation should focus on the implementation of this technique beyond thoracic imaging.

Locoregional CT staging of colon cancer: does a learning curve exist?

PURPOSE: To evaluate the learning curve for locoreginal staging of colon cancer in radiologist trainees. METHODS: Eighty-eight cases of colon cancer CT were included in this retrospective study. Four senior radiology residents staged the CTs according to TNM classification. Two out of four radiologists received feedback after reading every 20 cases. Radiologic staging was compared with pathologic staging and the learning curve, diagnostic performance, reader confidence and reading time were evaluated and compared between the two groups (feedback vs. no feedback). Generalized estimating equations logistic regression, QICu statistic, ANOVA and t test/Mann-Whitney test were utilized. RESULTS: Radiologists demonstrated a significant increase in their performance to distinguish between ≤ T2 and ≥ T3 and reached an inflection point at 38 cases, with a significant association with increased number of cases reviewed (P < 0.001). Sensitivity (P < 0.001), specificity (P = 0.030) and NPV (P = 0.002) demonstrated significant associations with increased experience. The overall reader's confidence was significantly higher in the group which received feedback (P < 0.001). There was no significant improvement in performance nor in reader's confidence for N staging (N0 vs. ≥ N1) for all readers. Reading time decreased with experience and showed a significant negative association with experience (P < 0.001). CONCLUSION: Diagnostic performance of senior radiology trainees in differentiating between T2 and T3 colon cancer on CTs improved with increased experience. In contrast, evaluation of lymph node involvement did not improve with more experience. Feedback had no significant effect on improvement of diagnostic performances.

Factors Associated With Local Tumor Control and Complications After Thermal Ablation of Colorectal Cancer Liver Metastases: A 15-year Retrospective Cohort Study.

INTRODUCTION: The purpose of this study was to identify risk factors associated with local tumor progression-free survival (LTPFS) and complications after colorectal liver metastases (CLM) thermal ablation (TA). PATIENTS AND METHODS: This retrospective analysis included 286 patients with 415 CLM undergoing TA (radiofrequency and microwave ablation) in 378 procedures from January 2003 to July 2017. Prior hepatic artery infusion (HAI), bevacizumab, pre-existing biliary dilatation, ablation modality, minimal ablation margin (MM), prior hepatectomy, CLM number, and size were analyzed as factors influencing complications and LTPFS. Statistical analysis included the Kaplan-Meier method, Cox proportional hazards model, competing risk analysis, univariate/multivariate logistic/exact logistic regressions, and the Fisher exact test. Complications were reported according to modified Society of Interventional Radiology guidelines. RESULTS: The median follow-up was 31 months. There was no LTP for MM > 10 mm. Smaller tumor size, increased MM, and prior hepatectomy correlated with longer LTPFS. The major complications occurred following 28 (7%) of 378 procedures. There were no biliary complications in HAI-naive patients, versus 11% in HAI patients (P < .001), of which 7% were major. Biliary complications predictors in HAI patients included biliary dilatation, bevacizumab, and MM > 10 mm. In HAI patients, ablation with 6 to 10 mm and > 10 mm MM resulted in major biliary complication rates of 4% and 21% (P = .0011), with corresponding LTP rates of 24% and 0% (P = .0033). In HAI-naive patients, the LTP rates for 6 to 10 mm and > 10 mm MM were 27% and 0%, respectively. CONCLUSIONS: No LTP was seen for MM > 10 mm. Biliary complications occurred only in HAI patients, especially in those with biliary dilatation, bevacizumab, and MM > 10 mm. In HAI patients, MM of 6 to 10 mm resulted in 76% local tumor control and 4% major biliary complications incidence.

Factors Affecting Oncologic Outcomes of 90Y Radioembolization of Heavily Pre-Treated Patients With Colon Cancer Liver Metastases.

INTRODUCTION: The purpose of this study was to identify predictors of overall (OS) and liver progression-free survival (LPFS) following Yttrium-90 radioembolization (RAE) of heavily pretreated patients with colorectal cancer liver metastases (CLM), as well as to create and validate a predictive nomogram for OS. MATERIALS AND METHODS: Metabolic, anatomic, laboratory, pathologic, genetic, primary disease, and procedure-related factors, as well as pre- and post-RAE therapies in 103 patients with CLM treated with RAE from September 15, 2009 to March 21, 2017 were analyzed. LPFS was defined by Response Evaluation Criteria In Solid Tumors 1.1 and European Organization for Research and Treatment of Cancer criteria. Prognosticators of OS and LPFS were selected using univariate Cox regression, adjusted for clustering and competing risk analysis (for LPFS), and subsequently tested in multivariate analysis (MVA). The nomogram was built using R statistical software and internally validated using bootstrap resampling. RESULTS: Patients received RAE at a median of 30.9 months (range, 3.4-161.7 months) after detection of CLM. The median OS and LPFS were 11.3 months (95% confidence interval, 7.9-15.1 months) and 4 months (95% confidence interval, 3.3-4.8 months), respectively. Of the 40 parameters tested, 6 were independently associated with OS in MVA. These baseline parameters included number of extrahepatic disease sites (P < .001), carcinoembryonic antigen (P < .001), albumin (P = .005), alanine aminotransferase level (P < .001), tumor differentiation level (P < .001), and the sum of the 2 largest tumor diameters (P < .001). The 1-year OS of patients with total points of < 25 versus > 80 was 90% and 10%, respectively. Bootstrap resampling showed good discrimination (optimism corrected c-index = 0.745) and calibration (mean absolute prediction error = 0.299) of the nomogram. Only baseline maximum standardized uptake value was significant in MVA for LPFS prediction (P < .001; SHR = 1.06). CONCLUSION: The developed nomogram included 6 pre-RAE parameters and provided good prediction of survival post-RAE in heavily pretreated patients. Baseline maximum standardized uptake value was the single significant predictor of LPFS.

The Role of Percutaneous Image-Guided Thermal Ablation for the Treatment of Pulmonary Malignancies.

OBJECTIVE: Image-guided thermal ablation is a minimally invasive treatment option for patients with primary and secondary pulmonary malignancies. Modalities include radiofrequency ablation, microwave ablation, and cryoablation. CONCLUSION: Although no large randomized studies exist comparing ablation to surgery or radiotherapy, numerous studies have reported safety and efficacy for the treatment of both primary and metastatic disease in select patients. Future studies will refine patient selection, procedural technique, and assessment for local recurrence and will evaluate long-term survival.