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.

Unveiling the Diagnostic Potential of Linguistic Markers in Identifying Individuals with Parkinson's Disease through Artificial Intelligence: A Systematic Review

While extensive research has documented the cognitive changes associated with Parkinson's disease (PD), a relatively small portion of the empirical literature investigated the language abilities of individuals with PD. Recently, artificial intelligence applied to linguistic data has shown promising results in predicting the clinical diagnosis of neurodegenerative disorders, but a deeper investigation of the current literature available on PD is lacking. This systematic review investigates the nature of language disorders in PD by assessing the contribution of machine learning (ML) to the classification of patients with PD. A total of 10 studies published between 2016 and 2023 were included in this review. Tasks used to elicit language were mainly structured or unstructured narrative discourse. Transcriptions were mostly analyzed using Natural Language Processing (NLP) techniques. The classification accuracy (%) ranged from 43 to 94, sensitivity (%) ranged from 8 to 95, specificity (%) ranged from 3 to 100, AUC (%) ranged from 32 to 97. The most frequent optimal linguistic measures were lexico-semantic (40%), followed by NLP-extracted features (26%) and morphological consistency features (20%). Artificial intelligence applied to linguistic markers provides valuable insights into PD. However, analyzing measures derived from narrative discourse can be time-consuming, and utilizing ML requires specialized expertise. Moving forward, it is important to focus on facilitating the integration of both narrative discourse analysis and artificial intelligence into clinical practice.

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.

MRI-based artificial intelligence to predict infection following total hip arthroplasty failure

PURPOSE

To investigate whether artificial intelligence (AI) can differentiate septic from non-septic total hip arthroplasty (THA) failure based on preoperative MRI features.

MATERIALS AND METHODS

We included 173 patients (98 females, age: 67 ± 12 years) subjected to first-time THA revision surgery after preoperative pelvis MRI. We divided the patients into a training/validation/internal testing cohort (n = 117) and a temporally independent external-testing cohort (n = 56). MRI features were used to train, validate and test a machine learning algorithm based on support vector machine (SVM) to predict THA infection on the training-internal validation cohort with a nested fivefold validation approach. Machine learning performance was evaluated on independent data from the external-testing cohort.

RESULTS

MRI features were significantly more frequently observed in THA infection (P < 0.001), except bone destruction, periarticular soft-tissue mass, and fibrous membrane (P > 0.005). Considering all MRI features in the training/validation/internal-testing cohort, SVM classifier reached 92% sensitivity, 62% specificity, 79% PPV, 83% NPV, 82% accuracy, and 81% AUC in predicting THA infection, with bone edema, extracapsular edema, and synovitis having been the best predictors. After being tested on the external-testing cohort, the classifier showed 92% sensitivity, 79% specificity, 89% PPV, 83% NPV, 88% accuracy, and 89% AUC in predicting THA infection. SVM classifier showed 81% sensitivity, 76% specificity, 66% PPV, 88% NPV, 80% accuracy, and 74% AUC in predicting THA infection in the training/validation/internal-testing cohort based on the only presence of periprosthetic bone marrow edema on MRI, while it showed 68% sensitivity, 89% specificity, 93% PPV, 60% NPV, 75% accuracy, and 79% AUC in the external-testing cohort.

CONCLUSION

AI using SVM classifier showed promising results in predicting THA infection based on MRI features. This model might support radiologists in identifying THA infection.

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 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 approach in the neurodegenerative brain

As claimed by Robert Gilles et al., "Images are more than pictures, they are data". This statement refers to the power of imaging to provide large amounts of quantitative features for improving diagnosis, prognosis and therapy response. The conversion of digital medical images into high-dimensional mineable data is called radiomics. Radiomics analysis is based on data-characterisation algorithms which have the potential to uncover disease heterogeneity characteristics that might escape from the expert evaluation. This method has been widely applied in oncology and genetic fields, while the literature on neurodegenerative disorders is in its relative infancy. Here, we provide a preliminary evaluation of the main results reached applying radiomics analyses on well-established MRI features of patients with Alzheimer's Disease and Parkinson's disease.

Using rADioMIcs and machine learning with ultrasonography for the differential diagnosis of myometRiAL tumors (the ADMIRAL pilot study). Radiomics and differential diagnosis of myometrial tumors

OBJECTIVE

To develop and evaluate the performance of a radiomics and machine learning model applied to ultrasound (US) images in predicting the risk of malignancy of a uterine mesenchymal lesion.

METHODS

Single-center retrospective evaluation of consecutive patients who underwent surgery for a malignant uterine mesenchymal lesion (sarcoma) and a control group of patients operated on for a benign uterine mesenchymal lesion (myoma). Radiomics was applied to US preoperative images according to the International Biomarker Standardization Initiative guidelines to create, validate and test a classification model for the differential diagnosis of myometrial tumors. The TRACE4 radiomic platform was used thus obtaining a full-automatic radiomic workflow. Definitive histology was considered as gold standard. Accuracy, sensitivity, specificity, AUC and standard deviation of the created classification model were defined.

RESULTS

A total of 70 women with uterine mesenchymal lesions were recruited (20 with histological diagnosis of sarcoma and 50 myomas). Three hundred and nineteen radiomics IBSI-compliant features were extracted and 308 radiomics features were found stable. Different machine learning classifiers were created and the best classification system showed Accuracy 0.85 ± 0.01, Sensitivity 0.80 ± 0.01, Specificity 0.87 ± 0.01, AUC 0.86 ± 0.03.

CONCLUSIONS

Radiomics applied to US images shows a great potential in differential diagnosis of mesenchymal tumors, thus representing an interesting decision support tool for the gynecologist oncologist in an area often characterized by uncertainty.

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.

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.

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.

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.

Artificial intelligence and neuropsychological measures: The case of Alzheimer's disease

One of the current challenges in the field of Alzheimer's disease (AD) is to identify patients with mild cognitive impairment (MCI) that will convert to AD. Artificial intelligence, in particular machine learning (ML), has established as one of more powerful approach to extract reliable predictors and to automatically classify different AD phenotypes. It is time to accelerate the translation of this knowledge in clinical practice, mainly by using low-cost features originating from the neuropsychological assessment. We performed a meta-analysis to assess the contribution of ML and neuropsychological measures for the automated classification of MCI patients and the prediction of their conversion to AD. The pooled sensitivity and specificity of patients' classifications was obtained by means of a quantitative bivariate random-effect meta-analytic approach. Although a high heterogeneity was observed, the results of meta-analysis show that ML applied to neuropsychological measures can lead to a successful automatic classification, being more specific as screening rather than prognosis tool. Relevant categories of neuropsychological tests can be extracted by ML that maximize the classification accuracy.

Anthropogenic Marine Debris assessment with Unmanned Aerial Vehicle imagery and deep learning: A case study along the beaches of the Republic of Maldives

Anthropogenic Marine Debris (AMD) is one of the major environmental issues of our planet to date, and plastic accounts for 80% of total AMD. Beaches represent one of the main marine compartment where AMD accumulates, but few and scattered regional assessments are available from literature reporting quantitative estimation of AMD distributed on the shorelines. However, accessing information on the AMD accumulation rate on beaches, and the associated spatiotemporal oscillations, would be crucial to refining global estimation on the dispersal mechanisms. In our work, we address this issue by proposing an ad-hoc methodology for monitoring and automatically quantifying AMD, based on the combined use of a commercial Unmanned Aerial Vehicle (UAV) (equipped with an RGB high-resolution camera) and a deep-learning based software (i.e.: PlasticFinder). Remote areas were monitored by UAV and were inspected by operators on the ground to check and to categorise all AMD dispersed on the beach. The high-resolution images obtained from UAV allowed to visually detect a percentage of the objects on the shores higher than 87.8%, thus providing suitable images to populate training and testing datasets, as well as gold standards to evaluate the software performance. PlasticFinder reached a Sensitivity of 67%, with a Positive Predictive Value of 94%, in the automatic detection of AMD, but a limitation was found, due to reduced sunlight conditions, thus restricting to the use of the software in its present version. We, therefore, confirmed the efficiency of commercial UAVs as tools for AMD monitoring and demonstrated - for the first time - the potential of deep learning for the automatic detection and quantification of AMD.

Texture descriptors and voxels for the early diagnosis of Alzheimer's disease

BACKGROUND AND OBJECTIVE

Early and accurate diagnosis of Alzheimer's Disease (AD) is critical since early treatment effectively slows the progression of the disease thereby adding productive years to those afflicted by this disease. A major problem encountered in the classification of MRI for the automatic diagnosis of AD is the so-called curse-of-dimensionality, which is a consequence of the high dimensionality of MRI feature vectors and the low number of training patterns available in most MRI datasets relevant to AD.

METHODS

A method for performing early diagnosis of AD is proposed that combines a set of SVMs trained on different texture descriptors (which reduce dimensionality) extracted from slices of Magnetic Resonance Image (MRI) with a set of SVMs trained on markers built from the voxels of MRIs. The dimension of the voxel-based features is reduced by using different feature selection algorithms, each of which trains a separate SVM. These two sets of SVMs are then combined by weighted-sum rule for a final decision.

RESULTS

Experimental results show that 2D texture descriptors improve the performance of state-of-the-art voxel-based methods. The evaluation of our system on the four ADNI datasets demonstrates the efficacy of the proposed ensemble and demonstrates a contribution to the accurate prediction of AD.

CONCLUSIONS

Ensembles of texture descriptors combine partially uncorrelated information with respect to standard approaches based on voxels, feature selection, and classification by SVM. In other words, the fusion of a system based on voxels and an ensemble of texture descriptors enhances the performance of voxel-based approaches.

MRI Characterizes the Progressive Course of AD and Predicts Conversion to Alzheimer's Dementia 24 Months Before Probable Diagnosis

There is no disease-modifying treatment currently available for AD, one of the more impacting neurodegenerative diseases affecting more than 47.5 million people worldwide. The definition of new approaches for the design of proper clinical trials is highly demanded in order to achieve non-confounding results and assess more effective treatment. In this study, a cohort of 200 subjects was obtained from the Alzheimer's Disease Neuroimaging Initiative. Subjects were followed-up for 24 months, and classified as AD (50), progressive-MCI to AD (50), stable-MCI (50), and cognitively normal (50). Structural T1-weighted MRI brain studies and neuropsychological measures of these subjects were used to train and optimize an artificial-intelligence classifier to distinguish mild-AD patients who need treatment (AD + pMCI) from subjects who do not need treatment (sMCI + CN). The classifier was able to distinguish between the two groups 24 months before AD definite diagnosis using a combination of MRI brain studies and specific neuropsychological measures, with 85% accuracy, 83% sensitivity, and 87% specificity. The combined-approach model outperformed the classification using MRI data alone (72% classification accuracy, 69% sensitivity, and 75% specificity). The patterns of morphological abnormalities localized in the temporal pole and medial-temporal cortex might be considered as biomarkers of clinical progression and evolution. These regions can be already observed 24 months before AD definite diagnosis. The best neuropsychological predictors mainly included measures of functional abilities, memory and learning, working memory, language, visuoconstructional reasoning, and complex attention, with a particular focus on some of the sub-scores of the FAQ and AVLT tests.

The Utility of a Computerized Algorithm Based on a Multi-Domain Profile of Measures for the Diagnosis of Attention Deficit/Hyperactivity Disorder

The current gold standard for diagnosis of attention deficit/hyperactivity disorder (ADHD) includes subjective measures, such as clinical interview, observation, and rating scales. The significant heterogeneity of ADHD symptoms represents a challenge for this assessment and could prevent an accurate diagnosis. The aim of this work was to investigate the ability of a multi-domain profile of measures, including blood fatty acid (FA) profiles, neuropsychological measures, and functional measures from near-infrared spectroscopy (fNIRS), to correctly recognize school-aged children with ADHD. To answer this question, we elaborated a supervised machine-learning method to accurately discriminate 22 children with ADHD from 22 children with typical development by means of the proposed profile of measures. To assess the performance of our classifier, we adopted a nested 10-fold cross validation, where the original dataset was split into 10 subsets of equal size, which were used repeatedly for training and testing. Each subset was used once for performance validation. Our method reached a maximum diagnostic accuracy of 81% through the combining of the predictive models trained on neuropsychological, FA profiles, and deoxygenated-hemoglobin features. With respect to the analysis of a single-domain dataset per time, the most discriminant neuropsychological features were measures of vigilance, focused and sustained attention, and cognitive flexibility; the most discriminating blood FAs were linoleic acid and the total amount of polyunsaturated fatty acids. Finally, with respect to the fNIRS data, we found a significant advantage of the deoxygenated-hemoglobin over the oxygenated-hemoglobin data in terms of predictive accuracy. These preliminary findings show the feasibility and applicability of our machine-learning method in correctly identifying children with ADHD based on multi-domain data. The present machine-learning classification approach might be helpful for supporting the clinical practice of diagnosing ADHD, even fostering a computer-aided diagnosis perspective.

Randomized comparison of power Doppler ultrasonography-guided core-needle biopsy with open surgical biopsy for the characterization of lymphadenopathies in patients with suspected lymphoma

The sensitivity of lymph node core-needle biopsy under imaging guidance requires validation. We employed power Doppler ultrasonography (PDUS) to select the lymph node most suspected of malignancy and to histologically characterize it through the use of large cutting needle. Institutional review board approval and informed consent were obtained for this randomized clinical trial. In a single center between 1 January 2009 and 31 December 2015, patients with lymph node enlargement suspected for lymphoma were randomly assigned (1:1) to biopsy with either standard surgery or PDUS-guided 16-gauge modified Menghini needle. The primary endpoint was the superiority of sensitivity for the diagnosis of malignancy for core-needle cutting biopsy (CNCB). Secondary endpoints were times to biopsy, complications, and costs. A total of 376 patients were randomized into the two arms and received allocated biopsy. However, four patients undergoing CNCB were excluded for inadequate samples; thus, 372 patients were analyzed. Sensitivity for the detection of malignancy was significantly better for PDUS-guided CNCB [98.8%; 95% confidence interval (CI), 95.9–99.9] than standard biopsy (88.7%; 95% CI, 82.9–93; P < 0.001). For all secondary endpoints, the comparison was significantly disadvantageous for conventional approach. In particular, estimated cost per biopsy performed with standard surgery was 24-fold higher compared with that performed with CNCB. The presence of satellite enlarged reactive and/or necrotic lymph nodes may impair the success of an open surgical biopsy (OSB). PDUS and CNCB with adequate gauge are diagnostic tools that enable effective, safe, fast, and low-cost routine biopsy for patients with suspected lymphoma, avoiding psychological and physical pain of an unnecessary surgical intervention.

Frontiers for the Early Diagnosis of AD by Means of MRI Brain Imaging and Support Vector Machines

The emergence of Alzheimer's Disease (AD) as a consequence of increasing aging population makes urgent the availability of methods for the early and accurate diagnosis. Magnetic Resonance Imaging (MRI) could be used as in vivo, non invasive tool to identify sensitive and specific markers of very early AD progression. In recent years, multivariate pattern analysis (MVPA) and machine- learning algorithms have attracted strong interest within the neuroimaging community, as they allow automatic classification of imaging data with higher performance than univariate statistical analysis. An exhaustive search of PubMed, Web of Science and Medline records was performed in this work, in order to retrieve studies focused on the potential role of MRI in aiding the clinician in early diagnosis of AD by using Support Vector Machines (SVMs) as MVPA automated classification method. A total of 30 studies emerged, published from 2008 to date. This review aims to give a state-of-the-art overview about SVM for the early and differential diagnosis of AD-related pathologies by means of MRI data, starting from preliminary steps such as image pre-processing, feature extraction and feature selection, and ending with classification, validation strategies and extraction of MRI-related biomarkers. The main advantages and drawbacks of the different techniques were explored. Results obtained by the reviewed studies were reported in terms of classification performance and biomarker outcomes, in order to shed light on the parameters that accompany normal and pathological aging. Unresolved issues and possible future directions were finally pointed out.

Magnetic resonance imaging biomarkers for the early diagnosis of Alzheimer's disease: a machine learning approach

Determination of sensitive and specific markers of very early AD progression is intended to aid researchers and clinicians to develop new treatments and monitor their effectiveness, as well as to lessen the time and cost of clinical trials. Magnetic Resonance (MR)-related biomarkers have been recently identified by the use of machine learning methods for the in vivo differential diagnosis of AD. However, the vast majority of neuroimaging papers investigating this topic are focused on the difference between AD and patients with mild cognitive impairment (MCI), not considering the impact of MCI patients who will (MCIc) or not convert (MCInc) to AD. Morphological T1-weighted MRIs of 137 AD, 76 MCIc, 134 MCInc, and 162 healthy controls (CN) selected from the Alzheimer's disease neuroimaging initiative (ADNI) cohort, were used by an optimized machine learning algorithm. Voxels influencing the classification between these AD-related pre-clinical phases involved hippocampus, entorhinal cortex, basal ganglia, gyrus rectus, precuneus, and cerebellum, all critical regions known to be strongly involved in the pathophysiological mechanisms of AD. Classification accuracy was 76% AD vs. CN, 72% MCIc vs. CN, 66% MCIc vs. MCInc (nested 20-fold cross validation). Our data encourage the application of computer-based diagnosis in clinical practice of AD opening new prospective in the early management of AD patients.

Combination of gene expression and genome copy number alteration has a prognostic value for breast cancer

Specific genome copy number alterations, such as deletions and amplifications are an important factor in tumor development and progression, and are also associated with changes in gene expression. By combining analyses of gene expression and genome copy number we identified genes as candidate biomarkers of BC which were validated as prognostic factors of the disease progression. These results suggest that the proposed combined approach may become a valuable method for BC prognosis.

Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear Palsy

BACKGROUND

Supervised machine learning has been proposed as a revolutionary approach for identifying sensitive medical image biomarkers (or combination of them) allowing for automatic diagnosis of individual subjects. The aim of this work was to assess the feasibility of a supervised machine learning algorithm for the assisted diagnosis of patients with clinically diagnosed Parkinson's disease (PD) and Progressive Supranuclear Palsy (PSP).

METHOD

Morphological T1-weighted Magnetic Resonance Images (MRIs) of PD patients (28), PSP patients (28) and healthy control subjects (28) were used by a supervised machine learning algorithm based on the combination of Principal Components Analysis as feature extraction technique and on Support Vector Machines as classification algorithm. The algorithm was able to obtain voxel-based morphological biomarkers of PD and PSP.

RESULTS

The algorithm allowed individual diagnosis of PD versus controls, PSP versus controls and PSP versus PD with an Accuracy, Specificity and Sensitivity>90%. Voxels influencing classification between PD and PSP patients involved midbrain, pons, corpus callosum and thalamus, four critical regions known to be strongly involved in the pathophysiological mechanisms of PSP.

COMPARISON WITH EXISTING METHODS

Classification accuracy of individual PSP patients was consistent with previous manual morphological metrics and with other supervised machine learning application to MRI data, whereas accuracy in the detection of individual PD patients was significantly higher with our classification method.

CONCLUSIONS

The algorithm provides excellent discrimination of PD patients from PSP patients at an individual level, thus encouraging the application of computer-based diagnosis in clinical practice.

A Decision Support System for the assisted diagnosis of brain tumors: a feasibility study for ¹⁸F-FDG PET preclinical studies

Decision support systems for the assisted medical diagnosis offer the main feature of giving assessments which are poorly affected from arbitrary clinical reasoning. Aim of this work was to assess the feasibility of a decision support system for the assisted diagnosis of brain cancer, such approach presenting potential for early diagnosis of tumors and for the classification of the degree of the disease progression. For this purpose, a supervised learning algorithm combined with a pattern recognition method was developed and cross-validated in ¹⁸F-FDG PET studies of a model of a brain tumour implantation.

A comparative study of cellular and molecular pharmacology of doxorubicin and MEN 10755, a disaccharide analogue11Abbreviations: DOX, doxorubicin; DNA-SSB, single-strand breaks; and DNA-DSB, double-strand breaks

MEN 10755 is a disaccharide anthracycline endowed with a broader spectrum of antitumour activity than doxorubicin (DOX). To investigate the cellular and molecular basis of its action, cytotoxic activity, drug uptake, subcellular localisation, induction of DNA damage, and apoptosis were assessed in the human A2780 ovarian carcinoma cell line. Experiments with radiolabelled anthracyclines indicated that MEN 10755 exhibited reduced cellular accumulation and a different subcellular distribution (higher cytoplasmic/nuclear ratio) than DOX. In spite of the lower nuclear concentration, MEN 10755 was as potent as DOX in eliciting DNA single- and double-strand breaks, G2/M cell arrest, and apoptosis. Sequencing of drug-induced topoisomerase II cleavage sites showed a common DNA cleavage pattern for MEN 10755 and DOX. Cleavage sites were always characterised by the presence of adenine in -1 position. However, the extent of DNA cleavage stimulation induced by MEN 10755 was greater than that produced by DOX. Reversibility studies showed that MEN 10755-stimulated DNA cleavage sites were more persistent than those induced by DOX, thus suggesting a more stable interaction of the drug in the ternary complex. As a whole, the study indicated that the cellular pharmacokinetics of MEN 10755 substantially differs from that of DOX, showing a lower uptake and a different subcellular disposition. In spite of the apparently unfavourable cellular pharmacokinetics, MEN 10755 was still as potent as DOX in inducing topoisomerase-mediated DNA damage. Although the extent and persistence of protein-associated DNA breaks may contribute to the cytotoxic effects, the drug's efficacy as apoptosis inducer and antitumour agent could not be adequately explained on the basis of DNA damage mediated by the known target (i.e. topoisomerase II), thus supporting additional cellular effects that may be relevant in cellular response.

Primary tumours neoangiogenesis and P53 expression in oral carcinoma patients

Paraffin embebbed tumour tissues from 47 T1-2 N0-1 M0 primary oral squamous carcinoma have been utilized for immunohistochemical analysis of p53 expression (moab DO-7) and microvessel density (MVD) analysis (moab CD34). Fifty percent of cases showed p53 immunostaining with an average of 21% of p53 positive cells. A strong trend for a longer survival in patients with tumor p53- versus p53+ was evidenced (median survival: 12 months versus not reached, respectively; p=0.08 by log-rank test). A mean value of 27 MVD was found. The probability of overall survival did not result significantly different in the subgroups of tumours with high and low MVD (median survival: 6 months versus 6 months, respectively; p=0.24). Cox multivariate analysis confirmed that the only prognostic factor significantly related to the overall survival was clinical nodal status (O.R.=2.7; 95% C.I. 1.09-6.9), while p53 status only approached the statistical significance (O.R.=2.5; 95% C.I. 0.96-6.5; p=0.06).

[The clinical efficacy of magnetic resonance with diffusion-weighted sequences in the assessment of acute cerebral ischemia]

PURPOSE

To evaluate the efficacy of diffusion weighted Magnetic Resonance Imaging in the diagnosis of acute ischemic infarction and correlate the signal changes observed in the acute phase with final brain damage.

MATERIAL AND METHODS

Fifteen patients (six women and nine men: mean age 68 years) with acute ischemic stroke (within 12 hours) underwent diffusion MRI. All the patients were selected on the basis of sudden focal neurologic symptoms and CT findings excluding other conditions than ischemia. MRI was performed with a 1.5 T magnet with echo-planar gradients. All the patients underwent follow-up CT and/or MRI.

RESULTS

Diffusion MRI, performed in the acute phase, showed signal changes in all the patients whose infarction was later confirmed by CT or MRI. In 10 of 12 patients with positive diffusion imaging, CT was normal. FLAIR sequences showed the lesions in 4 of 12 cases. In the 2 patients with transient ischemic attack diffusion MRI was normal as well as follow-up examinations. Apparent Diffusion Coefficients values in the infarcted area were almost half those of the contralateral normal brain. Final damage (as assessed by CT or MRI) was larger than observed in acute diffusion images in all cases but one.

CONCLUSION

Because of its high sensitivity and specificity, diffusion MRI is going to play a more important role in the management of acute ischemic stroke patients.

FCE 24517-resistant MCF-7 human breast cancer cell line: selection and characterization

We have developed a stable line of the human breast carcinoma cell line MCF-7 by in vitro continuous exposure to increasing concentrations of the antitumoral alkylating agent FCE 24517 (tallimustine). The selected line, MCF-7/24517(1), was resistant to the selecting agent (RI=10) and to a lesser degree to melphalan, MEN 10710 (a related dystamycin analog), doxorubicin and etoposide, but not to m-AMSA. MCF-7/24517(1) cells did not express the multidrug-resistant phenotype, evaluated in terms of mRNA for mdr-1 and gp170 glycoprotein. A significant, albeit modest, increase in the cellular content of glutathione was measured and therefore other resistance mechanism(s) should be operative. We conclude that the MCF-7/24517(1) line is a valuable model to investigate the mechanisms of resistance of FCE 24517 and its derivatives.

Configurational requirements of the sugar moiety for the pharmacological activity of anthracycline disaccharides

The amino sugar is recognized to be a critical determinant of the activity of anthracycline monosaccharides related to doxorubicin and daunorubicin. In an attempt to improve the pharmacological properties of such agents, novel anthracycline disaccharides have been designed in which the amino sugar, daunosamine, is separated from the aglycone by another carbohydrate moiety. In the present study, we examined the influence of the orientation of the second sugar residue on drug biochemical and biological properties in a series of closely related analogs. This structure-activity relationship study showed that the substitution of the daunosamine for the disaccharide moiety dramatically reduced the cytotoxic potency of the drug in the 4-methoxy series (daunorubicin analogs). In contrast, in the 4-demethoxy series (idarubicin analogs), the C-4 axial, but not the equatorial, configuration conferred a cytotoxic potency and antitumor activity comparable to that of doxorubicin. The configuration also influenced the drug's ability to stimulate topoisomerase II alpha-mediated DNA cleavage. Indeed, the glycosides with the equatorial orientation were ineffective as topoisomerase II poisons, whereas the compounds with axial orientation were active, although the daunorubicin analog exhibited a lower activity than the idarubicin analog. It is conceivable that the axial orientation allows an optimal interaction of the drug with the DNA-enzyme complex only in the absence of the methoxy group. Our results are consistent with a critical role of the sugar moiety in drug interaction with the target enzyme in the ternary complex.

Nonpeptide oxytocin antagonists: analogs of L-371,257 with improved potency

Structure-activity studies on the oxytocin antagonist 1 (L-371,257; Ki = 9.3 nM) have led to the identification of a related series of compounds containing an ortho-trifluoroethoxyphenylacetyl core which are orally bioavailable and have significantly improved potency in vitro and in vivo, e.g., compound 8 (L-374,943; Ki = 1.4 nM).

Improved efficacy and enlarged spectrum of activity of a novel anthracycline disaccharide analogue of doxorubicin against human tumor xenografts

On the basis of a structure-activity study of a new series of anthracycline disaccharides, we recently identified a doxorubicin analogue (MEN 10755) with a promising antitumor activity. In the present study, to better support the pharmacological interest of MEN 10755, we extended the preclinical evaluation of antitumor efficacy to a large panel of 16 human tumor xenografts, which originated from different clinicopathological types. Tumors with typical multidrug-resistant phenotype were excluded because MEN 10755 was found unable to overcome resistance mediated by transport systems. In the doxorubicin-responsive series, MEN 10755 exhibited a higher activity in three of five tumors, as documented by a more marked tumor growth inhibition and an increased value of log-cell kill. In the series of doxorubicin-resistant tumors, MEN 10755 was found effective in 6 of 11 tumors (1 breast, 3 lung, and 2 prostate carcinomas). The overall response rates were 31% and 69% for doxorubicin and MEN 10755, respectively. The improvement in drug efficacy was also supported by a substantial increase in the long-term survivor rate of animals implanted with responsive tumors. Most of the tumors refractory to doxorubicin and responsive to MEN 10755 were characterized by overexpression of the antiapoptotic protein Bcl-2. In one of these tumors (MX-1 breast carcinoma), we examined the ability of MEN 10755 to induce phosphorylation of Bcl-2 after a single treatment with therapeutic doses. The results indicated that, unlike doxorubicin, MEN 10755 induced protein phosphorylation. A similar modification was produced by Taxol, which is known to be very effective against the tumor. The correlation between drug efficacy and Bcl-2 phosphorylation may underly a peculiar feature related to improvement of efficacy of the disaccharide analogue. In conclusion, the present study supports some favorable features of the novel doxorubicin analogue in terms of both efficacy and tolerability with comparison to doxorubicin, although the improvement is somewhat tumor- and schedule-dependent.

Trans-sphenoidal treatment of postsurgical cerebrospinal fluid fistula: CT-guided closure

Cerebrospinal fluid (CSF) leakage after trans-sphenoidal surgery is a troublesome complication with a risk of meningitis and pneumocephalus. We suggest CT-guided intrasphenoidal injection of fibrin sealant through a 12-gauge needle as a simple alternative to surgical management of CSF fistulae. We treated eight patients, operated via the trans-sphenoidal route (five pituitary adenomas, three craniopharyngiomas), for a postoperative CSF leak by CT-guided intrasphenoidal injection of fibrin sealant alone in three cases and fibrin sealant and autologous blood in 5. CT was obtained 10 days after the procedure in all cases. In four patients, the CSF leak was closed successfully at the first attempt. The procedure was repeated on the four remaining patients because only a reduction in leakage was obtained at the first attempt. This procedure preserves olfaction and avoids the risk of frontal lobe damage. It could therefore represent the treatment of choice in many cases of anterior cranial fossa postsurgical CSF leaks.

[The Studer ileal bladder and the Paduan ileal bladder: comparison of 2 techniques]

Between January 1988 and December 1995 48 orthotopic detubularized and reconfigured ileal neobladder were carried out with two distinct surgical procedures in the same Hospital. 33 underwent lower urinary tract reconstruction using Studer's technique with an afferent ileal tubular isoperistaltic segment; in 15 patients the ileal substitution of the bladder was performed with Paduan ileal bladder (VIP). In any case an ileal low pressure reservoir was obtained with similar functional capacity (400 ml. at the urodynamic control), as using the same length of ileum (40 cm) for the reconstruction of the reservoir itself. In order to other functional aspects (e.g. diurnal and nocturnal continence) results were analogous if a correct rehabilitation program was observed. Significant post-voiding residual and late neobladder decompensation was prevented with adequate mictional training. Early and late complications (globally 19-24%) were evaluated: strictures of ureteroileal and ileo-urethral anastomoses were rare; an ileoureteral reflux was observed at a cystographic control in 50% of Studer group, but never clinically significant and only in 20% of VIPs. No clinically significant metabolic changes were found. Survival was satisfactory at a mean follow-up of 48 months.

Cytotoxic and antitumor activity of MEN 10710, a novel alkylating derivative of distamycin

MEN 10710 is a new synthetic distamycin derivative possessing four pyrrole rings and a bis-(2-chloroethyl)aminophenyl moiety linked to the oligopyrrole backbone by a flexible butanamido chain. Its biological properties have been investigated in comparison with the structurally related compound, tallimustine (FCE24517), and the classical alkylating agent, melphalan (L-PAM). Cytotoxic potency of MEN 10710 was increased from 10- to 100-fold, as compared to tallimustine or L-PAM in murine L1210, human LoVo and MCF7 tumor cell lines. MEN 10710 was still active against L1210/L-PAM leukemic cells, while a partial cross-resistance was observed in LoVo/DX and in MCF7/DX cells selected for resistance to doxorubicin and expressing a MDR phenotype. Treatment with verapamil (VRP) reduced the resistance to tallimustine, but not to MEN 10710, in MCF7/DX cells. The cytotoxic effects reflect in vivo antitumor potency and toxicity in the treatment of human tumor xenografts. MEN 10710 was more effective in A2780/DDP, an ovarian carcinoma selected for resistance to cisplatin. On the other hand, the IC30 for inhibiting murine granulocyte/macrophage colony formation was 50 times higher for MEN 10710 than for tallimustine, suggesting a lower myelotoxic potential. In conclusion, the particular biological profile of MEN 10710 characterized by a marked cytotoxic potency, an interesting antitumor efficacy and a reduced in vitro myelosuppressive action may represent a further improvement in the rational design of a novel distamycin-related alkylating compound.

Doxorubicin disaccharide analogue: apoptosis-related improvement of efficacy in vivo

BACKGROUND

Although doxorubicin remains one of the most effective agents for the treatment of solid tumors, there is an intensive effort to synthesize doxorubicin analogues (compounds with similar chemical structures) that may have improved antitumor properties. We have synthesized a novel doxorubicin disaccharide analogue (MEN 10755) and have characterized some of its relevant biochemical, biologic, and pharmacologic properties.

METHODS

The antitumor activity of this compound (MEN 10755) was studied in a panel of human tumor xenografts, including xenografts of A2780 ovarian tumor cells, MX-1 breast carcinoma cells, and POVD small-cell lung cancer cells. MEN 10755 was compared with doxorubicin according to the optimal dose and schedule for each drug. The drug's cytotoxic effects, induction of DNA damage, and intracellular accumulation were studied in A2780 cells. DNA cleavage mediated by the enzyme topoisomerase II was investigated in vitro by incubating fragments of simian virus 40 DNA with the purified enzyme at various drug concentrations and analyzing the DNA cleavage-intensity patterns. Drug-induced apoptosis (programmed cell death) in tumors was determined with the use of MX-1 and POVD tumor-bearing athymic Swiss nude mice.

RESULTS

MEN 10755 was more effective than doxorubicin as a topoisomerase II poison and stimulated DNA fragmentation at lower intracellular concentrations. In addition, MEN 10755 exhibited striking antitumor activity in the treatment of human tumor xenografts, including those of the doxorubicin-resistant breast carcinoma cell line MX-1.

CONCLUSIONS

The high antitumor activity of MEN 10755 in human tumor xenografts, including doxorubicin-resistant xenografts, and its unique pharmacologic and biologic properties make this disaccharide analogue a promising candidate for clinical evaluation.

[Magnetic resonance features in cerebral primary lymphomas in non-immunocompromised subjects]

In the past few years, non-Hodgkin's lymphomas have been paid increasing attention to because of their recently increasing frequency. We reviewed the MR images of 17 patients with histologically proved primary CNS lymphoma, all of them immunocompetent at diagnosis. We studied the site, number and shape of the lesions, the presence and grade of edema and possible periventricular spread. The exams were performed with 0.5 T and 1.5 T MR units, using SE sequences on the sagittal, axial and coronal planes, before and after Gd-DTPA administration. The most typical neuroradiologic signs which may suggest the diagnosis of CNS lymphoma are deep or periventricular lesion site, diffuse and marked contrast enhancement, poorly defined borders, moderate edema surrounding the mass and a tendency to periventricular spread. MRI demonstrated 35 lesions in 17 patients. The lymphoma was unifocal in 9 cases (53%) and 7 lesions were localized in subtentorial site. Lesion size did not exceed 2 cm in 49% of cases, ranged 2-4 cm in 40% and exceeded 4 cm in 11% of cases only. These lesions and hypo- to isointense on T1-weighted images (97%) and their signal intensity varies on T2-weighted images, with mainly iso-/hypointense patterns (79%). All lesions enhanced after Gd-DTPA administration, 74% of them markedly and 26% moderately; enhancement was mostly homogeneous (80% of cases). Perilesional edema was observed in 74% of cases. In conclusion, MRI yields some useful information for the diagnosis of primary CNS lymphoma, but the clinical and radiologic signs of this lesion may exhibit aspecific signal features, meaning that no correct diagnosis can be made even in immuno-competent patients.

[Urinary PSA (uPSA) in the monitoring of local recurrence following radical prostatectomy]

The level of urinary PSA (PSAu) was measured for use as a marker in some clinical situations involving prostate cancer patients. Limits of physiological and pathological values, a quantity of which comes from the urethral glands and the umbilical median ligament (urachus), are still unknown. To establish the quantity of PSA secretion in the urethra, female PSAu was measured and found to be significantly low (< 0.1 ng/ml). The Authors report on 25 PR patients with negative margins and who had not received hormonal therapy for 30 months. The PSAu and the PSAs were measured on the 30th and the 60th day, and every 3 months thereafter in the first year and every 6 months in the second year. In 5 cases we observed an increase of PSAu between the 5th and 18th months. In 3 cases the PSAs increased 2 to 6 months later compared to the PSAu. In these 3 cases the biopsy indicated the presence of a localized relapse. Therefore the Authors recommend measuring the PSAu (cut-off 0.1 ng/ml) in the follow-up of the PR patients because the measurement may both identify a localized relapse earlier than the PSAs and indicate the localized response to hormonal or radiotherapy.

Biochemical and pharmacological activity of novel 8-fluoroanthracyclines: influence of stereochemistry and conformation

In an attempt to better understand the role of the cyclohexene ring (ring A) in the biochemical and pharmacological properties of anthracyclines related to doxorubicin and daunorubicin, we investigated the effects of introduction of a fluorine atom at position 8 of idarubicin (4-demethoxydaunorubicin) on drug molecular conformation and biochemical and pharmacological activities. The study showed that the stereochemistry of the substituent at position 8 influenced the "half-chair" conformation, so that in the (8R)-fluoroepimer the A ring retained the alpha half-chair conformation, which is the most stable for natural compounds (i.e., daunorubicin and doxorubicin), and the (8S)-fluoroepimers preferred the beta half-chair conformation. The (8R)-fluoroepimer was more effective than the (8S)-fluoroepimer and idarubicin in stimulating topoisomerase II-mediated DNA cleavage. Similarly, the epimer with the alpha conformation was markedly more potent than the (8S)-epimer as a cytotoxic agent in a variety of human tumor cell lines and was more effective as an antitumor agent in the treatment of an ovarian carcinoma xenograft. In addition, 8-fluoro derivatives were able to overcome the resistance to doxorubicin in a number of human tumor cell lines expressing different mechanisms of resistance. In conclusion, these findings provide evidence that drug interactions involving the external (nonintercalating) moiety of the anthracycline chromophore play an important role in determining pharmacological properties, including drug ability to induce DNA cleavage, and therefore their antitumor efficacy.