The Impact of Resampling and Denoising Deep Learning Algorithms on Radiomics in Brain Metastases MRI

Radiomics based on HRCT can predict RP-ILD and mortality in anti-MDA5 + dermatomyositis patients: a multi-center retrospective study

OBJECTIVES

To assess the effectiveness of HRCT-based radiomics in predicting rapidly progressive interstitial lung disease (RP-ILD) and mortality in anti-MDA5 positive dermatomyositis-related interstitial lung disease (anti-MDA5 + DM-ILD).

METHODS

From August 2014 to March 2022, 160 patients from Institution 1 were retrospectively and consecutively enrolled and were randomly divided into the training dataset (n = 119) and internal validation dataset (n = 41), while 29 patients from Institution 2 were retrospectively and consecutively enrolled as external validation dataset. We generated four Risk-scores based on radiomics features extracted from four areas of HRCT. A nomogram was established by integrating the selected clinico-radiologic variables and the Risk-score of the most discriminative radiomics model. The RP-ILD prediction performance of the models was evaluated by using the area under the receiver operating characteristic curves, calibration curves, and decision curves. Survival analysis was conducted with Kaplan-Meier curves, Mantel-Haenszel test, and Cox regression.

RESULTS

Over a median follow-up time of 31.6 months (interquartile range: 12.9-49.1 months), 24 patients lost to follow-up and 46 patients lost their lives (27.9%, 46/165). The Risk-score based on bilateral lungs performed best, attaining AUCs of 0.869 and 0.905 in the internal and external validation datasets. The nomogram outperformed clinico-radiologic model and Risk-score with AUCs of 0.882 and 0.916 in the internal and external validation datasets. Patients were classified into low- and high-risk groups with 50:50 based on nomogram. High-risk group patients demonstrated a significantly higher risk of mortality than low-risk group patients in institution 1 (HR = 4.117) and institution 2 cohorts (HR = 7.515).

CONCLUSION

For anti-MDA5 + DM-ILD, the nomogram, mainly based on radiomics, can predict RP-ILD and is an independent predictor of mortality.

Artificial intelligence solution to accelerate the acquisition of MRI images: Impact on the therapeutic care in oncology in radiology and radiotherapy departments

PURPOSE

MRI is essential in the management of brain tumours. However, long waiting times reduce patient accessibility. Reducing acquisition time could improve access but at the cost of spatial resolution and diagnostic quality. A commercially available artificial intelligence (AI) solution, SubtleMR™, can increase the resolution of acquired images. The objective of this prospective study was to evaluate the impact of this algorithm that halves the acquisition time on the detectability of brain lesions in radiology and radiotherapy.

MATERIAL AND METHODS

The T1/T2 MRI of 33 patients with brain metastases or meningiomas were analysed. Images acquired quickly have a matrix divided by two which halves the acquisition time. The visual quality and lesion detectability of the AI images were evaluated by radiologists and radiation oncologist as well as pixel intensity and lesions size.

RESULTS

The subjective quality of the image is lower for the AI images compared to the reference images. However, the analysis of lesion detectability shows a specificity of 1 and a sensitivity of 0.92 and 0.77 for radiology and radiotherapy respectively. Undetected lesions on the IA image are lesions with a diameter less than 4mm and statistically low average gadolinium-enhancement contrast.

CONCLUSION

It is possible to reduce MRI acquisition times by half using the commercial algorithm to restore the characteristics of the image and obtain good specificity and sensitivity for lesions with a diameter greater than 4mm.

Uncertainty-aware deep-learning model for prediction of supratentorial hematoma expansion from admission non-contrast head computed tomography scan

Hematoma expansion (HE) is a modifiable risk factor and a potential treatment target in patients with intracerebral hemorrhage (ICH). We aimed to train and validate deep-learning models for high-confidence prediction of supratentorial ICH expansion, based on admission non-contrast head Computed Tomography (CT). Applying Monte Carlo dropout and entropy of deep-learning model predictions, we estimated the model uncertainty and identified patients at high risk of HE with high confidence. Using the receiver operating characteristics area under the curve (AUC), we compared the deep-learning model prediction performance with multivariable models based on visual markers of HE determined by expert reviewers. We randomly split a multicentric dataset of patients (4-to-1) into training/cross-validation (n = 634) versus test (n = 159) cohorts. We trained and tested separate models for prediction of ≥6 mL and ≥3 mL ICH expansion. The deep-learning models achieved an AUC = 0.81 for high-confidence prediction of HE≥6 mL and AUC = 0.80 for prediction of HE≥3 mL, which were higher than visual maker models AUC = 0.69 for HE≥6 mL (p = 0.036) and AUC = 0.68 for HE≥3 mL (p = 0.043). Our results show that fully automated deep-learning models can identify patients at risk of supratentorial ICH expansion based on admission non-contrast head CT, with high confidence, and more accurately than benchmark visual markers.

Reducing the risk of hallucinations with interpretable deep learning models for low-dose CT denoising: comparative performance analysis

Objective.Reducing CT radiation dose is an often proposed measure to enhance patient safety, which, however results in increased image noise, translating into degradation of clinical image quality. Several deep learning methods have been proposed for low-dose CT (LDCT) denoising. The high risks posed by possible hallucinations in clinical images necessitate methods which aid the interpretation of deep learning networks. In this study, we aim to use qualitative reader studies and quantitative radiomics studies to assess the perceived quality, signal preservation and statistical feature preservation of LDCT volumes denoised by deep learning. We aim to compare interpretable deep learning methods with classical deep neural networks in clinical denoising performance.Approach.We conducted an image quality analysis study to assess the image quality of the denoised volumes based on four criteria to assess the perceived image quality. We subsequently conduct a lesion detection/segmentation study to assess the impact of denoising on signal detectability. Finally, a radiomic analysis study was performed to observe the quantitative and statistical similarity of the denoised images to standard dose CT (SDCT) images.Main results.The use of specific deep learning based algorithms generate denoised volumes which are qualitatively inferior to SDCT volumes(p< 0.05). Contrary to previous literature, denoising the volumes did not reduce the accuracy of the segmentation (p> 0.05). The denoised volumes, in most cases, generated radiomics features which were statistically similar to those generated from SDCT volumes (p> 0.05).Significance.Our results show that the denoised volumes have a lower perceived quality than SDCT volumes. Noise and denoising do not significantly affect detectability of the abdominal lesions. Denoised volumes also contain statistically identical features to SDCT volumes.

Statistical Analysis on Impact of Image Preprocessing of CT Texture Patterns and Its CT Radiomic Feature Stability: A Phantom Study

AIM

To examine computed tomography (CT) radiomic feature stability on various texture patterns during pre-processing utilizing the Credence Cartridge Radiomics (CCR) phantom textures.

MATERIALS AND METHODS

Imaging Biomarker Explorer (IBEX) expansion for the abbreviation IBEX extracted 51 radiomic features of 4 categories from 11 textures image regions of interest (ROI) of the phantom. 19 software pre-processing algorithms processed each CCR phantom ROI. All ROI texture processed image features were retrieved. Pre-processed CT image radiomic features were compared to non-processed features to measure its textural influence. Wilcoxon T-tests measured the pre-processing relevance of CT radiomic features on various textures. Hierarchical cluster analysis (HCA) was performed to cluster processer potency and texture impression likeness.

RESULTS

The pre-processing filter, CT texture Cartridge, and feature category affect the CCR phantom CT image's radiomic properties. Pre-processing is statistically unaltered by Gray Level Run Length Matrix (GLRLM ) expansion  for the abbreviation GLRLM and Neighborhood Intensity Difference matrix (NID) expansion for the abbreviation NID feature categories. The 30%, 40%, and 50% honeycomb are regular directional textures and smooth 3D-printed plaster resin, most of the image pre-processing feature alterations exhibited significant p-values in the histogram feature category. The Laplacian Filter, Log Filter, Resample, and Bit Depth Rescale Range pre-processing algorithms hugely influenced histogram and Gray Level Co-occurrence Matrix (GLCM) image features.

CONCLUSION

We found that homogenous intensity phantom inserts, CT radiomic feature, are less sensitive to feature swaps during pre-processing than normal directed honeycomb and regular projected smooth 3D-printed plaster resin CT image textures. Because they lose fewer information during image enhancement, This feature concentration empowerment of the images also enhances texture pattern recognition.

More than Meets the Eye: Integration of Radiomics with Transcriptomics for Reconstructing the Tumor Microenvironment and Predicting Response to Therapy

For over a decade, large cancer-related datasets (big data) have continuously been produced and made publicly available to the scientific community [...]

A transformer-based deep-learning approach for classifying brain metastases into primary organ sites using clinical whole-brain MRI images

Treatment decisions for brain metastatic disease rely on knowledge of the primary organ site and are currently made with biopsy and histology. Here, we develop a deep-learning approach for accurate non-invasive digital histology with whole-brain magnetic resonance imaging (MRI) data. Contrast-enhanced T1-weighted and fast spoiled gradient echo brain MRI exams (n = 1,582) were preprocessed and input to the proposed deep-learning workflow for tumor segmentation, modality transfer, and primary site classification into one of five classes. Tenfold cross-validation generated an overall area under the receiver operating characteristic curve (AUC) of 0.878 (95% confidence interval [CI]: 0.873,0.883). These data establish that whole-brain imaging features are discriminative enough to allow accurate diagnosis of the primary organ site of malignancy. Our end-to-end deep radiomic approach has great potential for classifying metastatic tumor types from whole-brain MRI images. Further refinement may offer an invaluable clinical tool to expedite primary cancer site identification for precision treatment and improved outcomes.