Reproducing RECIST lesion selection via machine learning: Insights into intra and inter-radiologist variation.

Background: The Response Evaluation Criteria in Solid Tumors (RECIST) aims to provide a standardized approach to assess treatment response in solid tumors. However, discrepancies in the selection of measurable and target lesions among radiologists using these criteria pose a significant limitation to their reproducibility and accuracy. This study aimed to understand the factors contributing to this variability. Methods: Machine learning models were used to replicate, in parallel, the selection process of measurable and target lesions by two radiologists in a cohort of 40 patients from an internal pan-cancer dataset. The models were trained on lesion characteristics such as size, shape, texture, rank, and proximity to other lesions. Ablation experiments were conducted to evaluate the impact of lesion diameter, volume, and rank on the selection process. Results: The models successfully reproduced the selection of measurable lesions, relying primarily on size-related features. Similarly, the models reproduced target lesion selection, relying mostly on lesion rank. Beyond these features, the importance placed by different radiologists on different visual characteristics can vary, specifically when choosing target lesions. Worth noting that substantial variability was still observed between radiologists in both measurable and target lesion selection. Conclusions: Despite the successful replication of lesion selection, our results still revealed significant inter-radiologist disagreement. This underscores the necessity for more precise guidelines to standardize lesion selection processes and minimize reliance on individual interpretation and experience as a means to bridge existing ambiguities.

Multi-omics staging of locally advanced rectal cancer predicts treatment response: a pilot study.

Treatment response assessment of rectal cancer patients is a critical component of personalized cancer care and it allows to identify suitable candidates for organ-preserving strategies. This pilot study employed a novel multi-omics approach combining MRI-based radiomic features and untargeted metabolomics to infer treatment response at staging. The metabolic signature highlighted how tumor cell viability is predictively down-regulated, while the response to oxidative stress was up-regulated in responder patients, showing significantly reduced oxoproline values at baseline compared to non-responder patients (p-value < 10-4). Tumors with a high degree of texture homogeneity, as assessed by radiomics, were more likely to achieve a major pathological response (p-value < 10-3). A machine learning classifier was implemented to summarize the multi-omics information and discriminate responders and non-responders. Combining all available radiomic and metabolomic features, the classifier delivered an AUC of 0.864 (± 0.083, p-value < 10-3) with a best-point sensitivity of 90.9% and a specificity of 81.8%. Our results suggest that a multi-omics approach, integrating radiomics and metabolomic data, can enhance the predictive value of standard MRI and could help to avoid unnecessary surgical treatments and their associated long-term complications.

A whirl of radiomics-based biomarkers in cancer immunotherapy, why is large scale validation still lacking?

The search for understanding immunotherapy response has sparked interest in diverse areas of oncology, with artificial intelligence (AI) and radiomics emerging as promising tools, capable of gathering large amounts of information to identify suitable patients for treatment. The application of AI in radiology has grown, driven by the hypothesis that radiology images capture tumor phenotypes and thus could provide valuable insights into immunotherapy response likelihood. However, despite the rapid growth of studies, no algorithms in the field have reached clinical implementation, mainly due to the lack of standardized methods, hampering study comparisons and reproducibility across different datasets. In this review, we performed a comprehensive assessment of published data to identify sources of variability in radiomics study design that hinder the comparison of the different model performance and, therefore, clinical implementation. Subsequently, we conducted a use-case meta-analysis using homogenous studies to assess the overall performance of radiomics in estimating programmed death-ligand 1 (PD-L1) expression. Our findings indicate that, despite numerous attempts to predict immunotherapy response, only a limited number of studies share comparable methodologies and report sufficient data about cohorts and methods to be suitable for meta-analysis. Nevertheless, although only a few studies meet these criteria, their promising results underscore the importance of ongoing standardization and benchmarking efforts. This review highlights the importance of uniformity in study design and reporting. Such standardization is crucial to enable meaningful comparisons and demonstrate the validity of biomarkers across diverse populations, facilitating their implementation into the immunotherapy patient selection process.

Artificial intelligence in immunotherapy PET/SPECT imaging.

OBJECTIVE: Immunotherapy has dramatically altered the therapeutic landscape for oncology, but more research is needed to identify patients who are likely to achieve durable clinical benefit and those who may develop unacceptable side effects. We investigated the role of artificial intelligence in PET/SPECT-guided approaches for immunotherapy-treated patients. METHODS: We performed a scoping review of MEDLINE, CENTRAL, and Embase databases using key terms related to immunotherapy, PET/SPECT imaging, and AI/radiomics through October 12, 2022. RESULTS: Of the 217 studies identified in our literature search, 24 relevant articles were selected. The median (interquartile range) sample size of included patient cohorts was 63 (157). Primary tumors of interest were lung (n = 14/24, 58.3%), lymphoma (n = 4/24, 16.7%), or melanoma (n = 4/24, 16.7%). A total of 28 treatment regimens were employed, including anti-PD-(L)1 (n = 13/28, 46.4%) and anti-CTLA-4 (n = 4/28, 14.3%) monoclonal antibodies. Predictive models were built from imaging features using univariate radiomics (n = 7/24, 29.2%), radiomics (n = 12/24, 50.0%), or deep learning (n = 5/24, 20.8%) and were most often used to prognosticate (n = 6/24, 25.0%) or describe tumor phenotype (n = 5/24, 20.8%). Eighteen studies (75.0%) performed AI model validation. CONCLUSION: Preliminary results suggest broad potential for the application of AI-guided immunotherapy management after further validation of models on large, prospective, multicenter cohorts. CLINICAL RELEVANCE STATEMENT: This scoping review describes how artificial intelligence models are built to make predictions based on medical imaging and explores their application specifically in the PET and SPECT examination of immunotherapy-treated cancers. KEY POINTS: • Immunotherapy has drastically altered the cancer treatment landscape but is known to precipitate response patterns that are not accurately accounted for by traditional imaging methods. • There is an unmet need for better tools to not only facilitate in-treatment evaluation but also to predict, a priori, which patients are likely to achieve a good response with a certain treatment as well as those who are likely to develop side effects. • Artificial intelligence applied to PET/SPECT imaging of immunotherapy-treated patients is mainly used to make predictions about prognosis or tumor phenotype and is built from baseline, pre-treatment images. Further testing is required before a true transition to clinical application can be realized.

Artificial Intelligence-based Quantification of Pleural Plaque Volume and Association With Lung Function in Asbestos-exposed Patients.

PURPOSE: Pleural plaques (PPs) are morphologic manifestations of long-term asbestos exposure. The relationship between PP and lung function is not well understood, whereas the time-consuming nature of PP delineation to obtain volume impedes research. To automate the laborious task of delineation, we aimed to develop automatic artificial intelligence (AI)-driven segmentation of PP. Moreover, we aimed to explore the relationship between pleural plaque volume (PPV) and pulmonary function tests. MATERIALS AND METHODS: Radiologists manually delineated PPs retrospectively in computed tomography (CT) images of patients with occupational exposure to asbestos (May 2014 to November 2019). We trained an AI model with a no-new-UNet architecture. The Dice Similarity Coefficient quantified the overlap between AI and radiologists. The Spearman correlation coefficient ( r ) was used for the correlation between PPV and pulmonary function test metrics. When recorded, these were vital capacity (VC), forced vital capacity (FVC), and diffusing capacity for carbon monoxide (DLCO). RESULTS: We trained the AI system on 422 CT scans in 5 folds, each time with a different fold (n = 84 to 85) as a test set. On these independent test sets combined, the correlation between the predicted volumes and the ground truth was r = 0.90, and the median overlap was 0.71 Dice Similarity Coefficient. We found weak to moderate correlations with PPV for VC (n = 80, r = -0.40) and FVC (n = 82, r = -0.38), but no correlation for DLCO (n = 84, r = -0.09). When the cohort was split on the median PPV, we observed statistically significantly lower VC ( P = 0.001) and FVC ( P = 0.04) values for the higher PPV patients, but not for DLCO ( P = 0.19). CONCLUSION: We successfully developed an AI algorithm to automatically segment PP in CT images to enable fast volume extraction. Moreover, we have observed that PPV is associated with loss in VC and FVC.

How Does Target Lesion Selection Affect RECIST? A Computer Simulation Study.

OBJECTIVES: Response Evaluation Criteria in Solid Tumors (RECIST) is grounded on the assumption that target lesion selection is objective and representative of the change in total tumor burden (TTB) during therapy. A computer simulation model was designed to challenge this assumption, focusing on a particular aspect of subjectivity: target lesion selection. MATERIALS AND METHODS: Disagreement among readers and the disagreement between individual reader measurements and TTB were analyzed as a function of the total number of lesions, affected organs, and lesion growth. RESULTS: Disagreement rises when the number of lesions increases, when lesions are concentrated on a few organs, and when lesion growth borders the thresholds of progressive disease and partial response. There is an intrinsic methodological error in the estimation of TTB via RECIST 1.1, which depends on the number of lesions and their distributions. For example, for a fixed number of lesions at 5 and 15, distributed over a maximum of 4 organs, the error rates are observed to be 7.8% and 17.3%, respectively. CONCLUSIONS: Our results demonstrate that RECIST can deliver an accurate estimate of TTB in localized disease, but fails in cases of distal metastases and multiple organ involvement. This is worsened by the "selection of the largest lesions," which introduces a bias that makes it hardly possible to perform an accurate estimate of the TTB. Including more (if not all) lesions in the quantitative analysis of tumor burden is desirable.

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).

Circulating Extracellular Vesicles: Their Role in Patients with Abdominal Aortic Aneurysm (AAA) Undergoing EndoVascular Aortic Repair (EVAR).

Abdominal aortic aneurysm (AAA) is a frequent aortic disease. If the diameter of the aorta is larger than 5 cm, an open surgical repair (OSR) or an endovascular aortic repair (EVAR) are recommended. To prevent possible complications (i.e., endoleaks), EVAR-treated patients need to be monitored for 5 years following the intervention, using computed tomography angiography (CTA). However, this radiological method involves high radiation exposure in terms of CTA/year. In such a context, the study of peripheral-blood-circulating extracellular vesicles (pbcEVs) has great potential to identify biomarkers for EVAR complications. We analyzed several phenotypes of pbcEVs using polychromatic flow cytometry in 22 patients with AAA eligible for EVAR. From each enrolled patient, peripheral blood samples were collected at AAA diagnosis, and after 1, 6, and 12 months following EVAR implantation, i.e. during the diagnostic follow-up protocol. Patients developing an endoleak displayed a significant decrease in activated-platelet-derived EVs between the baseline condition and 6 months after EVAR intervention. Furthermore, we also observed, that 1 month after EVAR implantation, patients developing an endoleak showed higher concentrations of activated-endothelial-derived EVs than patients who did not develop one, suggesting their great potential as a noninvasive and specific biomarker for early identification of EVAR complications.

Development of a Prognostic AI-Monitor for Metastatic Urothelial Cancer Patients Receiving Immunotherapy.

Background: Immune checkpoint inhibitor efficacy in advanced cancer patients remains difficult to predict. Imaging is the only technique available that can non-invasively provide whole body information of a patient's response to treatment. We hypothesize that quantitative whole-body prognostic information can be extracted by leveraging artificial intelligence (AI) for treatment monitoring, superior and complementary to the current response evaluation methods. Methods: To test this, a cohort of 74 stage-IV urothelial cancer patients (37 in the discovery set, 37 in the independent test, 1087 CTs), who received anti-PD1 or anti-PDL1 were retrospectively collected. We designed an AI system [named prognostic AI-monitor (PAM)] able to identify morphological changes in chest and abdominal CT scans acquired during follow-up, and link them to survival. Results: Our findings showed significant performance of PAM 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 0.73 (p < 0.001) for abdominal imaging, and 0.67 AUC (p < 0.001) for chest imaging. Subanalysis revealed higher accuracy of abdominal imaging around and in the first 6 months of treatment, reaching an AUC of 0.82 (p < 0.001). Similar accuracy was found by chest imaging, 5-11 months after start of treatment. Univariate comparison with current monitoring methods (laboratory results and radiological assessments) revealed higher or similar prognostic performance. In multivariate analysis, PAM remained significant against all other methods (p < 0.001), suggesting its complementary value in current clinical settings. Conclusions: Our study demonstrates that a comprehensive AI-based method such as PAM, can provide prognostic information in advanced urothelial cancer patients receiving immunotherapy, leveraging morphological changes not only in tumor lesions, but also tumor spread, and side-effects. Further investigations should focus beyond anatomical imaging. Prospective studies are warranted to test and validate our findings.

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.

MRI-based clinical-radiomics model predicts tumor response before treatment in locally advanced rectal cancer.

Neoadjuvant chemo-radiotherapy (CRT) followed by total mesorectal excision (TME) represents the standard treatment for patients with locally advanced (≥ T3 or N+) rectal cancer (LARC). Approximately 15% of patients with LARC shows a complete response after CRT. The use of pre-treatment MRI as predictive biomarker could help to increase the chance of organ preservation by tailoring the neoadjuvant treatment. We present a novel machine learning model combining pre-treatment MRI-based clinical and radiomic features for the early prediction of treatment response in LARC patients. MRI scans (3.0 T, T2-weighted) of 72 patients with LARC were included. Two readers independently segmented each tumor. Radiomic features were extracted from both the "tumor core" (TC) and the "tumor border" (TB). Partial least square (PLS) regression was used as the multivariate, machine learning, algorithm of choice and leave-one-out nested cross-validation was used to optimize hyperparameters of the PLS. The MRI-Based "clinical-radiomic" machine learning model properly predicted the treatment response (AUC = 0.793, p = 5.6 × 10-5). Importantly, the prediction improved when combining MRI-based clinical features and radiomic features, the latter extracted from both TC and TB. Prospective validation studies in randomized clinical trials are warranted to better define the role of radiomics in the development of rectal cancer precision medicine.

Machine learning-based analysis of CT radiomics model for prediction of colorectal metachronous liver metastases.

PURPOSE: Early identification of patients at risk of developing colorectal liver metastases can help personalizing treatment and improve oncological outcome. The aim of this study was to investigate in patients with colorectal cancer (CRC) whether a machine learning-based radiomics model can predict the occurrence of metachronous metastases. METHODS: In this multicentre study, the primary staging portal venous phase CT of 91 CRC patients were retrospectively analysed. Two groups were assessed: patients without liver metastases at primary staging, or during follow-up of ≥ 24 months (n = 67) and patients without liver metastases at primary staging but developed metachronous liver metastases < 24 months after primary staging (n = 24). After liver parenchyma segmentation, 1767 radiomics features were extracted for each patient. Three predictive models were constructed based on (1) radiomics features, (2) clinical features and (3) a combination of clinical and radiomics features. Stability of features across hospitals was assessed by the Kruskal-Wallis test and inter-correlated features were removed if their correlation coefficient was higher than 0.9. Bayesian-optimized random forest with wrapper feature selection was used for prediction models. RESULTS: The three predictive models that included radiomics features, clinical features and a combination of radiomics with clinical features resulted in an AUC in the validation cohort of 86% (95%CI 85-87%), 71% (95%CI 69-72%) and 86% (95% CI 85-87%), respectively. CONCLUSION: A machine learning-based radiomics analysis of routine clinical CT imaging at primary staging can provide valuable biomarkers to identify patients at high risk for developing colorectal liver metastases.

Modern MR Imaging Technology in Rectal Cancer; There Is More Than Meets the Eye.

MR imaging (MRI) is now part of the standard work up of patients with rectal cancer. Restaging MRI has been traditionally used to plan the surgical approach. Its role has recently increased and been adopted as a valuable tool to assist the clinical selection of clinical (near) complete responders for organ preserving treatment. Recently several studies have addressed new imaging biomarkers that combined with morphological provides a comprehensive picture of the tumor. Diffusion-weighted MRI (DWI) has entered the clinics and proven useful for response assessment after chemoradiotherapy. Other functional (quantitative) MRI technologies are on the horizon including artificial intelligence modeling. This narrative review provides an overview of recent advances in rectal cancer (re)staging by imaging with a specific focus on response prediction and evaluation of neoadjuvant treatment response. Furthermore, directions are given for future research.

Radiomics performs comparable to morphologic assessment by expert radiologists for prediction of response to neoadjuvant chemoradiotherapy on baseline staging MRI in rectal cancer.

PURPOSE: To compare the performance of advanced radiomics analysis to morphological assessment by expert radiologists to predict a good or complete response to chemoradiotherapy in rectal cancer using baseline staging MRI. MATERIALS AND METHODS: We retrospectively assessed the primary staging MRIs [prior to chemoradiotherapy (CRT)] of 133 rectal cancer patients from 2 centers. First, two expert radiologists subjectively estimated the likelihood of achieving a "complete response" (ypT0) and "good response" (TRG 1-2), using a 5-point score (based on TN-stage, MRF/EMVI-status, size/signal/shape). Next, tumor volumes were segmented on high b value DWI (semi-automated, corrected by 2 non-expert and 2-expert readers, resulting in 5 segmentations), copied to the remaining sequences after which a total of 2505 radiomic features were extracted from T2W, low and high b value DWI and ADC. Stability of features for noise due to inter-reader and inter-scanner and protocol variations was assessed using intraclass correlation (ICC) and the Kruskal-Wallis test. Using data from center 1 (n = 86; training set), top 9 features were selected using minimum Redundancy Maximum Relevance and combined in a logistic regression model. Finally, diagnostic performance of the fitted models was assessed on data from center 2 (n = 47; validation set) and compared to the performance of the radiologists. RESULTS: The Radiomic models resulted in AUCs of 0.69-0.79 (with similar results for the segmentations performed by expert/non-expert readers) to predict response, results similar to the morphologic prediction by the expert radiologists (AUC 0.67-0.83). Radiomics using semi-automatically generated segmentations (without manual input) did not result in significant predictive performance. CONCLUSIONS: Radiomics could predict response to therapy with comparable diagnostic performance as expert radiologists, regardless of whether image segmentation was performed by non-expert or expert readers, indicating that expert input is not required in order for the radiomics workflow to produce significant predictive performance.

Tumor detectability and conspicuity comparison of standard b1000 and ultrahigh b2000 diffusion-weighted imaging in rectal cancer.

PURPOSE: To compare tumor detectability and conspicuity of standard b = 1000 s/mm2 (b1000) versus ultrahigh b = 2000 s/mm2 (b2000) diffusion-weighted imaging (DWI) in rectal cancer. METHODS: Fifty-five patients for a total of 81 3T DWI-MR scans were retrospectively evaluated by two differently experienced readers. A comparison between b1000 and b2000 for tumor detectability and conspicuity was performed. The conspicuity was qualitatively and quantitatively assessed by using three-point scale and whole tumor volume manual delineation, respectively. Receiver-operating characteristic curve (ROC) with area under the curve (AUC) analysis provided diagnostic accuracy in tumor detectability of restaging MR scans. Qualitative scores and quantitative features including mean signal intensity, variance, 10th percentile and 90th percentile, were compared using the Wilcoxon test. Interobserver agreement (IOA) for qualitative and quantitative data was calculated using Cohen's Kappa and intraclass correlation coefficient (ICC) respectively. RESULTS: Diagnostic accuracy was comparable between b1000 and b2000 for both readers (p > 0.05). Overall quality scores were significantly better for b2000 than b1000 (2.29 vs 1.65 Reader 1, p = 0.01; 2.18 vs 1.69 Reader 2, p = 0.04). IOA was equally good for both b values (k = 0.86 b1000, k = 0.86 b2000). Quantitative analysis revealed more uniform signal (measured in variance) of b2000 in both healthy surrounding tissue (p < 0.05) and tumor (p < 0.05), with less outliers (measured using 10th and 90th percentile). Additionally, b2000 offered lower mean signal intensity in tissue sorrounding the tumor (p < 0.05). Finally, ICC improved from 0.92 (b1000) to 0.97 (b2000). CONCLUSION: Ultrahigh b value (b2000) may improve rectal cancer conspicuity and introbserver agreement maintaining comparable diagnostic accuracy to standard b1000.

Radiogenomics: bridging imaging and genomics.

From diagnostics to prognosis to response prediction, new applications for radiomics are rapidly being developed. One of the fastest evolving branches involves linking imaging phenotypes to the tumor genetic profile, a field commonly referred to as "radiogenomics." In this review, a general outline of radiogenomic literature concerning prominent mutations across different tumor sites will be provided. The field of radiogenomics originates from image processing techniques developed decades ago; however, many technical and clinical challenges still need to be addressed. Nevertheless, increasingly accurate and robust radiogenomic models are being presented and the future appears to be bright.

Radiomics: a critical step towards integrated healthcare.

Medical imaging is a vital part of the clinical decision-making process, especially in an oncological setting. Radiology has experienced a great wave of change, and the advent of quantitative imaging has provided a unique opportunity to analyse patient images objectively. Leveraging radiomics and deep learning, there is increased potential for synergy between physicians and computer networks-via computer-aided diagnosis (CAD), computer-aided prediction of response (CARP), and computer-aided biological profiling (CABP). The ongoing digitalization of other specialties further opens the door for even greater multidisciplinary integration. We envision the development of an integrated system composed of an aggregation of sub-systems interoperating with the aim of achieving an overarching functionality (in this case' better CAD, CARP, and CABP). This will require close multidisciplinary cooperation among the clinicians, biomedical scientists, and (bio)engineers as well as an administrative framework where the departments will operate not in isolation but in successful harmony. KEY POINTS: • The advent of quantitative imaging provides a unique opportunity to analyse patient images objectively. • Radiomics and deep learning allow for a more detailed overview of the tumour (i.e., CAD, CARP, and CABP) from many different perspectives. • As it currently stands, different medical disciplines have developed different stratification methods, primarily based on their own field-often to the exclusion of other departments. • The digitalization of other specialties further opens the door for multidisciplinary integration. • The long-term vision for precision medicine should focus on the development of integration strategies, wherein data derived from the patients themselves (via multiple disciplines) can be used to guide clinical decisions.

Author Correction: Deep Learning for Fully-Automated Localization and Segmentation of Rectal Cancer on Multiparametric MR.

A correction to this article has been published and is linked from the HTML version of this paper. The error has been fixed in the paper.

Diffusion tensor image features predict IDH genotype in newly diagnosed WHO grade II/III gliomas.

We hypothesized that machine learning analysis based on texture information from the preoperative MRI can predict IDH mutational status in newly diagnosed WHO grade II and III gliomas. This retrospective study included in total 79 consecutive patients with a newly diagnosed WHO grade II or III glioma. Local binary pattern texture features were generated from preoperative B0 and fractional anisotropy (FA) diffusion tensor imaging. Using a training set of 59 patients, a single hidden layer neural network was then trained on the texture features to predict IDH status. The model was validated based on the prediction accuracy calculated in a previously unseen set of 20 gliomas. Prediction accuracy of the generated model was 92% (54/59 cases; AUC = 0.921) in the training and 95% (19/20; AUC = 0.952) in the validation cohort. The ten most important features were comprised of tumor size and both B0 and FA texture information, underlining the joint contribution of imaging data to classification. Machine learning analysis of DTI texture information and tumor size reliably predicts IDH status in preoperative MRI of gliomas. Such information may increasingly support individualized surgical strategies, supplement pathological analysis and highlight the potential of radiogenomics.

Deep Learning for Fully-Automated Localization and Segmentation of Rectal Cancer on Multiparametric MR.

Multiparametric Magnetic Resonance Imaging (MRI) can provide detailed information of the physical characteristics of rectum tumours. Several investigations suggest that volumetric analyses on anatomical and functional MRI contain clinically valuable information. However, manual delineation of tumours is a time consuming procedure, as it requires a high level of expertise. Here, we evaluate deep learning methods for automatic localization and segmentation of rectal cancers on multiparametric MR imaging. MRI scans (1.5T, T2-weighted, and DWI) of 140 patients with locally advanced rectal cancer were included in our analysis, equally divided between discovery and validation datasets. Two expert radiologists segmented each tumor. A convolutional neural network (CNN) was trained on the multiparametric MRIs of the discovery set to classify each voxel into tumour or non-tumour. On the independent validation dataset, the CNN showed high segmentation accuracy for reader1 (Dice Similarity Coefficient (DSC = 0.68) and reader2 (DSC = 0.70). The area under the curve (AUC) of the resulting probability maps was very high for both readers, AUC = 0.99 (SD = 0.05). Our results demonstrate that deep learning can perform accurate localization and segmentation of rectal cancer in MR imaging in the majority of patients. Deep learning technologies have the potential to improve the speed and accuracy of MRI-based rectum segmentations.