X-rays radiomics-based machine learning classification of atypical cartilaginous tumour and high-grade chondrosarcoma of long bones.

BACKGROUND: Atypical cartilaginous tumour (ACT) and high-grade chondrosarcoma (CS) of long bones are respectively managed with active surveillance or curettage and wide resection. Our aim was to determine diagnostic performance of X-rays radiomics-based machine learning for classification of ACT and high-grade CS of long bones. METHODS: This retrospective, IRB-approved study included 150 patients with surgically treated and histology-proven lesions at two tertiary bone sarcoma centres. At centre 1, the dataset was split into training (n = 71 ACT, n = 24 high-grade CS) and internal test (n = 19 ACT, n = 6 high-grade CS) cohorts, respectively, based on the date of surgery. At centre 2, the dataset constituted the external test cohort (n = 12 ACT, n = 18 high-grade CS). Manual segmentation was performed on frontal view X-rays, using MRI or CT for preliminary identification of lesion margins. After image pre-processing, radiomic features were extracted. Dimensionality reduction included stability, coefficient of variation, and mutual information analyses. In the training cohort, after class balancing, a machine learning classifier (Support Vector Machine) was automatically tuned using nested 10-fold cross-validation. Then, it was tested on both the test cohorts and compared to two musculoskeletal radiologists' performance using McNemar's test. FINDINGS: Five radiomic features (3 morphology, 2 texture) passed dimensionality reduction. After tuning on the training cohort (AUC = 0.75), the classifier had 80%, 83%, 79% and 80%, 89%, 67% accuracy, sensitivity, and specificity in the internal (temporally independent) and external (geographically independent) test cohorts, respectively, with no difference compared to the radiologists (p ≥ 0.617). INTERPRETATION: X-rays radiomics-based machine learning accurately differentiates between ACT and high-grade CS of long bones. FUNDING: AIRC Investigator Grant.

Using Radiomics and Machine Learning Applied to MRI to Predict Response to Neoadjuvant Chemotherapy in Locally Advanced Cervical Cancer.

Neoadjuvant chemotherapy plus radical surgery could be a safe alternative to chemo-radiation in cervical cancer patients who are not willing to receive radiotherapy. The response to neoadjuvant chemotherapy is the main factor influencing the need for adjunctive treatments and survival. In the present paper we aim to develop a machine learning model based on cervix magnetic resonance imaging (MRI) images to stratify the single-subject risk of cervical cancer. We collected MRI images from 72 subjects. Among these subjects, 28 patients (38.9%) belonged to the "Not completely responding" class and 44 patients (61.1%) belonged to the 'Completely responding' class according to their response to treatment. This image set was used for the training and cross-validation of different machine learning models. A robust radiomic approach was applied, under the hypothesis that the radiomic features could be able to capture the disease heterogeneity among the two groups. Three models consisting of three ensembles of machine learning classifiers (random forests, support vector machines, and k-nearest neighbor classifiers) were developed for the binary classification task of interest ("Not completely responding" vs. "Completely responding"), based on supervised learning, using response to treatment as the reference standard. The best model showed an ROC-AUC (%) of 83 (majority vote), 82.3 (mean) [79.9-84.6], an accuracy (%) of 74, 74.1 [72.1-76.1], a sensitivity (%) of 71, 73.8 [68.7-78.9], and a specificity (%) of 75, 74.2 [71-77.5]. In conclusion, our preliminary data support the adoption of a radiomic-based approach to predict the response to neoadjuvant chemotherapy.

A Radiomic-Based Machine Learning System to Diagnose Age-Related Macular Degeneration from Ultra-Widefield Fundus Retinography.

The present study was conducted to investigate the potential of radiomics to develop an explainable AI-based system to be applied to ultra-widefield fundus retinographies (UWF-FRTs) with the objective of predicting the presence of the early signs of Age-related Macular Degeneration (AMD) and stratifying subjects with low- versus high-risk of AMD. The ultimate aim was to provide clinicians with an automatic classifier and a signature of objective quantitative image biomarkers of AMD. The use of Machine Learning (ML) and radiomics was based on intensity and texture analysis in the macular region, detected by a Deep Learning (DL)-based macular detector. Two-hundred and twenty six UWF-FRTs were retrospectively collected from two centres and manually annotated to train and test the algorithms. Notably, the combination of the ML-based radiomics model and the DL-based macular detector reported 93% sensitivity and 74% specificity when applied to the data of the centre used for external testing, capturing explainable features associated with drusen or pigmentary abnormalities. In comparison to the human operator's annotations, the system yielded a 0.79 Cohen κ, demonstrating substantial concordance. To our knowledge, these results are the first provided by a radiomic approach for AMD supporting the suitability of an explainable feature extraction method combined with ML for UWF-FRT.

MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor of the extremities.

PURPOSE: To determine diagnostic performance of MRI radiomics-based machine learning for classification of deep-seated lipoma and atypical lipomatous tumor (ALT) of the extremities. MATERIAL AND METHODS: This retrospective study was performed at three tertiary sarcoma centers and included 150 patients with surgically treated and histology-proven lesions. The training-validation cohort consisted of 114 patients from centers 1 and 2 (n = 64 lipoma, n = 50 ALT). The external test cohort consisted of 36 patients from center 3 (n = 24 lipoma, n = 12 ALT). 3D segmentation was manually performed on T1- and T2-weighted MRI. After extraction and selection of radiomic features, three machine learning classifiers were trained and validated using nested fivefold cross-validation. The best-performing classifier according to previous analysis was evaluated and compared to an experienced musculoskeletal radiologist in the external test cohort. RESULTS: Eight features passed feature selection and were incorporated into the machine learning models. After training and validation (74% ROC-AUC), the best-performing classifier (Random Forest) showed 92% sensitivity and 33% specificity in the external test cohort with no statistical difference compared to the radiologist (p = 0.474). CONCLUSION: MRI radiomics-based machine learning may classify deep-seated lipoma and ALT of the extremities with high sensitivity and negative predictive value, thus potentially serving as a non-invasive screening tool to reduce unnecessary referral to tertiary tumor centers.

Radiomics and Molecular Classification in Endometrial Cancer (The ROME Study): A Step Forward to a Simplified Precision Medicine.

Molecular/genomic profiling is the most accurate method to assess prognosis of endometrial cancer patients. Radiomic profiling allows for the extraction of mineable high-dimensional data from clinical radiological images, thus providing noteworthy information regarding tumor tissues. Interestingly, the adoption of radiomics shows important results for screening, diagnosis and prognosis, across various radiological systems and oncologic specialties. The central hypothesis of the prospective trial is that combining radiomic features with molecular features might allow for the identification of various classes of risks for endometrial cancer, e.g., predicting unfavorable molecular/genomic profiling. The rationale for the proposed research is that once validated, radiomics applied to ultrasonographic images would be an effective, innovative and inexpensive method for tailoring operative and postoperative treatment modalities in endometrial cancer. Patients with newly diagnosed endometrial cancer will have ultrasonographic evaluation and radiomic analysis of the ultrasonographic images. We will correlate radiomic features with molecular/genomic profiling to classify prognosis.

Development and Validation of an AI-driven Mammographic Breast Density Classification Tool Based on Radiologist Consensus.

Mammographic breast density (BD) is commonly visually assessed using the Breast Imaging Reporting and Data System (BI-RADS) four-category scale. To overcome inter- and intraobserver variability of visual assessment, the authors retrospectively developed and externally validated a software for BD classification based on convolutional neural networks from mammograms obtained between 2017 and 2020. The tool was trained using the majority BD category determined by seven board-certified radiologists who independently visually assessed 760 mediolateral oblique (MLO) images in 380 women (mean age, 57 years ± 6 [SD]) from center 1; this process mimicked training from a consensus of several human readers. External validation of the model was performed by the three radiologists whose BD assessment was closest to the majority (consensus) of the initial seven on a dataset of 384 MLO images in 197 women (mean age, 56 years ± 13) obtained from center 2. The model achieved an accuracy of 89.3% in distinguishing BI-RADS a or b (nondense breasts) versus c or d (dense breasts) categories, with an agreement of 90.4% (178 of 197 mammograms) and a reliability of 0.807 (Cohen κ) compared with the mode of the three readers. This study demonstrates accuracy and reliability of a fully automated software for BD classification. Keywords: Mammography, Breast, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2022.

A Machine Learning Ensemble Based on Radiomics to Predict BI-RADS Category and Reduce the Biopsy Rate of Ultrasound-Detected Suspicious Breast Masses.

We developed a machine learning model based on radiomics to predict the BI-RADS category of ultrasound-detected suspicious breast lesions and support medical decision-making towards short-interval follow-up versus tissue sampling. From a retrospective 2015-2019 series of ultrasound-guided core needle biopsies performed by four board-certified breast radiologists using six ultrasound systems from three vendors, we collected 821 images of 834 suspicious breast masses from 819 patients, 404 malignant and 430 benign according to histopathology. A balanced image set of biopsy-proven benign (n = 299) and malignant (n = 299) lesions was used for training and cross-validation of ensembles of machine learning algorithms supervised during learning by histopathological diagnosis as a reference standard. Based on a majority vote (over 80% of the votes to have a valid prediction of benign lesion), an ensemble of support vector machines showed an ability to reduce the biopsy rate of benign lesions by 15% to 18%, always keeping a sensitivity over 94%, when externally tested on 236 images from two image sets: (1) 123 lesions (51 malignant and 72 benign) obtained from two ultrasound systems used for training and from a different one, resulting in a positive predictive value (PPV) of 45.9% (95% confidence interval 36.3-55.7%) versus a radiologists' PPV of 41.5% (p < 0.005), combined with a 98.0% sensitivity (89.6-99.9%); (2) 113 lesions (54 malignant and 59 benign) obtained from two ultrasound systems from vendors different from those used for training, resulting into a 50.5% PPV (40.4-60.6%) versus a radiologists' PPV of 47.8% (p < 0.005), combined with a 94.4% sensitivity (84.6-98.8%). Errors in BI-RADS 3 category (i.e., assigned by the model as BI-RADS 4) were 0.8% and 2.7% in the Testing set I and II, respectively. The board-certified breast radiologist accepted the BI-RADS classes assigned by the model in 114 masses (92.7%) and modified the BI-RADS classes of 9 breast masses (7.3%). In six of nine cases, the model performed better than the radiologist did, since it assigned a BI-RADS 3 classification to histopathology-confirmed benign masses that were classified as BI-RADS 4 by the radiologist.

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters.

Reflectance Spectroscopy (RS) and Fiber Optics Reflectance Spectroscopy (FORS) are well-established techniques for the investigation of works of art with particular attention to paintings. Most modern museums put at the disposal of their research groups portable equipment that, together with the intrinsic non-invasiveness of RS and FORS, makes possible the in situ collection of reflectance spectra from the surface of artefacts. The comparison, performed by experts in pigments and painting materials, of the experimental data with databases of reference spectra drives the characterization of the palettes and of the techniques used by the artists. However, this approach requires specific skills and it is time consuming especially if the number of the spectra to be investigated becomes large as is the case of Hyperspectral Reflectance Imaging (HRI) datasets. The HRI experimental setups are multi-dimensional cameras that associate the spectral information, given by the reflectance spectra, with the spatial localization of the spectra over the painted surface. The resulting datasets are 3D-cubes (called hypercubes or data-cubes) where the first two dimensions locate the spectrum over the painting and the third is the spectrum itself (i.e., the reflectance of that point of the painted surface versus the wavelength in the operative range of the detector). The capability of the detector to simultaneously collect a great number of spectra (typically much more than 10,000 for each hypercube) makes the HRI datasets large reservoirs of information and justifies the need for the development of robust and, possibly, automated protocols to analyze the data. After the description of the procedure designed for the data acquisition, we present an analysis method that systematically exploits the potential of the hypercubes. Based on Spectral Angle Mapper (SAM) and on the manipulation of the collected spectra, the algorithm handles and analyzes thousands of spectra while at the same time it supports the user to unveil the features of the samples under investigation. The power of the approach is illustrated by applying it to Quarto Stato, the iconic masterpiece by Giuseppe Pellizza da Volpedo, held in the Museo del Novecento in Milan (Italy).

A decision support system based on radiomics and machine learning to predict the risk of malignancy of ovarian masses from transvaginal ultrasonography and serum CA-125.

BACKGROUND: To evaluate the performance of a decision support system (DSS) based on radiomics and machine learning in predicting the risk of malignancy of ovarian masses (OMs) from transvaginal ultrasonography (TUS) and serum CA-125. METHODS: A total of 274 consecutive patients who underwent TUS (by different examiners and with different ultrasound machines) and surgery, with suspicious OMs and known CA-125 serum level were used to train and test a DSS. The DSS was used to predict the risk of malignancy of these masses (very low versus medium-high risk), based on the US appearance (solid, liquid, or mixed) and radiomic features (morphometry and regional texture features) within the masses, on the shadow presence (yes/no), and on the level of serum CA-125. Reproducibility of results among the examiners, and performance accuracy, sensitivity, specificity, and area under the curve were tested in a real-world clinical setting. RESULTS: The DSS showed a mean 88% accuracy, 99% sensitivity, and 77% specificity for the 239 patients used for training, cross-validation, and testing, and a mean 91% accuracy, 100% sensitivity, and 80% specificity for the 35 patients used for independent testing. CONCLUSIONS: This DSS is a promising tool in women diagnosed with OMs at TUS, allowing to predict the individual risk of malignancy, supporting clinical decision making.

Radiomics and gene expression profile to characterise the disease and predict outcome in patients with lung cancer.

OBJECTIVE: The objectives of our study were to assess the association of radiomic and genomic data with histology and patient outcome in non-small cell lung cancer (NSCLC). METHODS: In this retrospective single-centre observational study, we selected 151 surgically treated patients with adenocarcinoma or squamous cell carcinoma who performed baseline [18F] FDG PET/CT. A subgroup of patients with cancer tissue samples at the Institutional Biobank (n = 74/151) was included in the genomic analysis. Features were extracted from both PET and CT images using an in-house tool. The genomic analysis included detection of genetic variants, fusion transcripts, and gene expression. Generalised linear model (GLM) and machine learning (ML) algorithms were used to predict histology and tumour recurrence. RESULTS: Standardised uptake value (SUV) and kurtosis (among the PET and CT radiomic features, respectively), and the expression of TP63, EPHA10, FBN2, and IL1RAP were associated with the histotype. No correlation was found between radiomic features/genomic data and relapse using GLM. The ML approach identified several radiomic/genomic rules to predict the histotype successfully. The ML approach showed a modest ability of PET radiomic features to predict relapse, while it identified a robust gene expression signature able to predict patient relapse correctly. The best-performing ML radiogenomic rule predicting the outcome resulted in an area under the curve (AUC) of 0.87. CONCLUSIONS: Radiogenomic data may provide clinically relevant information in NSCLC patients regarding the histotype, aggressiveness, and progression. Gene expression analysis showed potential new biomarkers and targets valuable for patient management and treatment. The application of ML allows to increase the efficacy of radiogenomic analysis and provides novel insights into cancer biology.

Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia.

We assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 98 subjects without either COVID-19 or CAP, collected in two Italian hospitals. The system was tested on two independent cohorts, namely, 148 patients (COVID-19, CAP, or negative) collected by one of the two hospitals (independent testing I) and 820 COVID-19 patients collected by a multicenter study (independent testing II). On the training and cross-validation dataset, sensitivity, specificity, and area under the curve (AUC) were 0.91, 0.87, and 0.93 for COVID-19 versus negative subjects, 0.85, 0.82, and 0.94 for COVID-19 versus CAP. On the independent testing I, sensitivity, specificity, and AUC were 0.98, 0.88, and 0.98 for COVID-19 versus negative subjects, 0.97, 0.96, and 0.98 for COVID-19 versus CAP. On the independent testing II, the system correctly diagnosed 652 COVID-19 patients versus negative subjects (0.80 sensitivity) and correctly differentiated 674 COVID-19 versus CAP patients (0.82 sensitivity). This system appears promising for the diagnosis and differential diagnosis of COVID-19, showing its potential as a second opinion tool in conditions of the variable prevalence of different types of infectious pneumonia.

Advanced Imaging Analysis in Prostate MRI: Building a Radiomic Signature to Predict Tumor Aggressiveness.

Radiomics allows the extraction quantitative features from imaging, as imaging biomarkers of disease. The objective of this exploratory study is to implement a reproducible radiomic-pipeline for the extraction of a magnetic resonance imaging (MRI) signature for prostate cancer (PCa) aggressiveness. One hundred and two consecutive patients performing preoperative prostate multiparametric magnetic resonance imaging (mpMRI) and radical prostatectomy were enrolled. Multiparametric images, including T2-weighted (T2w), diffusion-weighted and dynamic contrast-enhanced images, were acquired at 1.5 T. Ninety-three imaging features (Ifs) were extracted from segmentation of index lesion. Ifs were ranked based on a stability rank and redundant Ifs were excluded. Using unsupervised hierarchical clustering, patients were grouped on the basis of similar radiomic patterns, whose association with Gleason Grade Group (GGG), extracapsular extension (ECE), and nodal involvement (pN) was tested. Signatures composed by IFs from T2w-images and Apparent Diffusion Coefficient (ADC) maps were tested for the prediction of GGG, ECE, and pN. T2w radiomic pattern was associated with pN, ECE, and GGG (p = 0.027, 0.05, 0.03) and ADC radiomic pattern was associated with GGG (p = 0.004). The best performance was reached by the signature combing IFs from multiparametric images (0.88, 0.89, and 0.84 accuracy for GGG, pN, and ECE). A reliable multiparametric MRI radiomic signature was extracted, potentially able to predict PCa aggressiveness, to be further validated on an independent sample.

AI applications to medical images: From machine learning to deep learning.

PURPOSE: Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context. METHODS: A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections. RESULTS: We first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way. CONCLUSIONS: Biomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.

Machine learning applied on chest x-ray can aid in the diagnosis of COVID-19: a first experience from Lombardy, Italy.

BACKGROUND: We aimed to train and test a deep learning classifier to support the diagnosis of coronavirus disease 2019 (COVID-19) using chest x-ray (CXR) on a cohort of subjects from two hospitals in Lombardy, Italy. METHODS: We used for training and validation an ensemble of ten convolutional neural networks (CNNs) with mainly bedside CXRs of 250 COVID-19 and 250 non-COVID-19 subjects from two hospitals (Centres 1 and 2). We then tested such system on bedside CXRs of an independent group of 110 patients (74 COVID-19, 36 non-COVID-19) from one of the two hospitals. A retrospective reading was performed by two radiologists in the absence of any clinical information, with the aim to differentiate COVID-19 from non-COVID-19 patients. Real-time polymerase chain reaction served as the reference standard. RESULTS: At 10-fold cross-validation, our deep learning model classified COVID-19 and non-COVID-19 patients with 0.78 sensitivity (95% confidence interval [CI] 0.74-0.81), 0.82 specificity (95% CI 0.78-0.85), and 0.89 area under the curve (AUC) (95% CI 0.86-0.91). For the independent dataset, deep learning showed 0.80 sensitivity (95% CI 0.72-0.86) (59/74), 0.81 specificity (29/36) (95% CI 0.73-0.87), and 0.81 AUC (95% CI 0.73-0.87). Radiologists' reading obtained 0.63 sensitivity (95% CI 0.52-0.74) and 0.78 specificity (95% CI 0.61-0.90) in Centre 1 and 0.64 sensitivity (95% CI 0.52-0.74) and 0.86 specificity (95% CI 0.71-0.95) in Centre 2. CONCLUSIONS: This preliminary experience based on ten CNNs trained on a limited training dataset shows an interesting potential of deep learning for COVID-19 diagnosis. Such tool is in training with new CXRs to further increase its performance.

Predicting Outcome of Acquired Brain Injury by the Evolution of Paroxysmal Sympathetic Hyperactivity Signs.

In this multi-center study, we provide a systematic evaluation of the clinical variability associated with paroxysmal sympathetic hyperactivity (PSH) in patients with acquired brain injury (ABI) to determine how these signs can impact outcomes. A total of 156 ABI patients with a disorder of consciousness (DoC) were admitted to neurorehabilitation subacute units (intensive rehabilitation unit; IRU) and evaluated at baseline (T0), after 4 months from event (T1), and at discharge (T2). The outcome measure was the Glasgow Outcome Scale-Extended, whereas age, sex, etiology, Coma Recovery Scale-Revised (CRS-r), Rancho Los Amigos Scale (RLAS), Early Rehabilitation Barthel Index (ERBI), PSH-Assessment Measure (PSH-AM) scores and other clinical features were considered as predictive factors. A machine learning (ML) approach was used to identify the best predictive model of clinical outcomes. The etiology was predominantly vascular (50.8%), followed by traumatic (36.2%). At admission, prevalence of PSH was 31.3%, which decreased to 16.6% and 4.4% at T1 and T2, respectively. At T2, 2.8% were dead and 61.1% had a full recovery of consciousness, whereas 36.1% remained in VS or MCS. A support vector machine (SVM)-based ML approach provides the best model with 82% accuracy in predicting outcomes. Analysis of variable importance shows that the most important clinical factors influencing the outcome are the PSH-AM scores measured at T0 and T1, together with neurological diagnosis, CRS-r, and RLAS scores measured at T0. This joint multi-center effort provides a comprehensive picture of the clinical impact of PSH signs in ABI patients, demonstrating its predictive value in comparison with other well-known clinical measurements.

The Adoption of Radiomics and machine learning improves the diagnostic processes of women with Ovarian MAsses (the AROMA pilot study).

PURPOSE: To develop and evaluate the performance of a radiomic and machine learning model applied to ultrasound images in predicting the risk of malignancy of ovarian masses (OMs). METHODS: Single-center retrospective evaluation of consecutive patients who underwent transvaginal ultrasound (US) with images storage and surgery for ovarian masses. Radiomics methodology was applied to US images according to the International Biomarker Standardization Initiative guidelines. OMs were divided into three homogeneous groups: solid, cystic and motley. TRACE4© radiomic platform was used thus obtaining a full-automatic radiomic workflow. Three different classification systems were created and accuracy, sensitivity, specificity, AUC and standard deviation were defined for each group. RESULTS: A total of 241 women were recruited. OMs were divided in the three groups: 95 (39.5%) solid, 66 (27.5%) cystic, 80 (33%) motley. For solid OMs, 269 radiomic features were used for the training-validation-testing of the model with accuracy 80%, sensitivity 78%, specificity 83%, AUC 87%. For cystic OMs, 278 radiomic features were used for the training-validation-testing of the model with accuracy 87%, sensitivity 75%, specificity 90%, AUC 88%. For mixed OMs, 306 radiomic features were used for the training-validation-testing of the model with accuracy 81%, sensitivity 81%, specificity 81%, AUC 89%. CONCLUSION: Radiomics is a promising tool in improving preoeprative work-up of women diagnosed with OMs. Even in the absence of the subjective impression of expert ultrasound examiner, radiomics allows to easily identify patients with ovarian cancer. Future validation studies on larger series are needed.

Comparison of Transfer Learning and Conventional Machine Learning Applied to Structural Brain MRI for the Early Diagnosis and Prognosis of Alzheimer's Disease.

Alzheimer's Disease (AD) is the most common neurodegenerative disease, with 10% prevalence in the elder population. Conventional Machine Learning (ML) was proven effective in supporting the diagnosis of AD, while very few studies investigated the performance of deep learning and transfer learning in this complex task. In this paper, we evaluated the potential of ensemble transfer-learning techniques, pretrained on generic images and then transferred to structural brain MRI, for the early diagnosis and prognosis of AD, with respect to a fusion of conventional-ML approaches based on Support Vector Machine directly applied to structural brain MRI. Specifically, more than 600 subjects were obtained from the ADNI repository, including AD, Mild Cognitive Impaired converting to AD (MCIc), Mild Cognitive Impaired not converting to AD (MCInc), and cognitively-normal (CN) subjects. We used T1-weighted cerebral-MRI studies to train: (1) an ensemble of five transfer-learning architectures pretrained on generic images; (2) a 3D Convolutional Neutral Network (CNN) trained from scratch on MRI volumes; and (3) a fusion of two conventional-ML classifiers derived from different feature extraction/selection techniques coupled to SVM. The AD-vs-CN, MCIc-vs-CN, MCIc-vs-MCInc comparisons were investigated. The ensemble transfer-learning approach was able to effectively discriminate AD from CN with 90.2% AUC, MCIc from CN with 83.2% AUC, and MCIc from MCInc with 70.6% AUC, showing comparable or slightly lower results with the fusion of conventional-ML systems (AD from CN with 93.1% AUC, MCIc from CN with 89.6% AUC, and MCIc from MCInc with AUC in the range of 69.1-73.3%). The deep-learning network trained from scratch obtained lower performance than either the fusion of conventional-ML systems and the ensemble transfer-learning, due to the limited sample of images used for training. These results open new prospective on the use of transfer learning combined with neuroimages for the automatic early diagnosis and prognosis of AD, even if pretrained on generic images.

AI-based applications in hybrid imaging: how to build smart and truly multi-parametric decision models for radiomics.

INTRODUCTION: The quantitative imaging features (radiomics) that can be obtained from the different modalities of current-generation hybrid imaging can give complementary information with regard to the tumour environment, as they measure different morphologic and functional imaging properties. These multi-parametric image descriptors can be combined with artificial intelligence applications into predictive models. It is now the time for hybrid PET/CT and PET/MRI to take the advantage offered by radiomics to assess the added clinical benefit of using multi-parametric models for the personalized diagnosis and prognosis of different disease phenotypes. OBJECTIVE: The aim of the paper is to provide an overview of current challenges and available solutions to translate radiomics into hybrid PET-CT and PET-MRI imaging for a smart and truly multi-parametric decision model.

Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions.

Aim: To evaluate reproducibility and stability of radiomic features as effects of the use of different volume segmentation methods and reconstruction settings. The potential of radiomics in really capturing the presence of heterogeneous tumor uptake and irregular shape was also investigated. Materials and Methods: An anthropomorphic phantom miming real clinical situations including synthetic lesions with irregular shape and nonuniform radiotracer uptake was used. 18F-FDG PET/CT measurements of the phantom were performed including 38 lesions of different shape, size, lesion-to-background ratio, and radiotracer uptake distribution. Different reconstruction parameters and segmentation methods were considered. COVs were calculated to quantify feature variations over the different reconstruction settings. Friedman test was applied to the values of the radiomic features obtained for the considered segmentation approaches. Two sets of test-retest measurement were acquired and the pairwise intraclass correlation coefficient was calculated. Fifty-eight morphological and statistical features were extracted from the segmented lesion volumes. A Mann-Whitney test was used to evaluate significant differences among each feature when calculated from heterogeneous versus homogeneous uptake. The significance of each radiomic feature in terms of capturing heterogeneity was evaluated also by testing correlation with gold standard indexes of heterogeneity and sphericity. Results: The choice of the segmentation method has a strong impact on the stability of radiomic features (less than 20% can be considered stable features). Reconstruction affects the estimate of radiomic features (only 26% are stable). Thirty-one radiomic features (53%) resulted to be reproducible, 11 of them are able to discriminate heterogeneity. Among these, we found a subset of 3 radiomic features strongly correlated with GS heterogeneity index that can be suggested as good features for retrospective evaluations.

A Method for Manufacturing Oncological Phantoms for the Quantification of 18F-FDG PET and DW-MRI Studies.

The aim of this work was to develop a method to manufacture oncological phantoms for quantitation purposes in 18F-FDG PET and DW-MRI studies. Radioactive and diffusion materials were prepared using a mixture of agarose and sucrose radioactive gels. T2 relaxation and diffusion properties of gels at different sucrose concentrations were evaluated. Realistic oncological lesions were created using 3D-printed plastic molds filled with the gel mixture. Once solidified, gels were extracted from molds and immersed in a low-radioactivity gel simulating normal background tissue. A breast cancer phantom was manufactured using the proposed method as an exploratory feasibility study, including several realistic oncological configurations in terms of both radioactivity and diffusion. The phantom was acquired in PET with 18F-FDG, immediately after solidification, and in DW-MRI the following day. Functional volumes characterizing the simulated BC lesions were segmented from PET and DW-MRI images. Measured radioactive uptake and ADC values were compared with gold standards. Phantom preparation was straightforward, and the time schedule was compatible with both PET and MRI measurements. Lesions appeared on 18F-FDG PET and DW-MRI images as expected, without visible artifacts. Lesion functional parameters revealed the phantom's potential for validating quantification methods, in particular for new generation hybrid PET-MRI systems.