Towards Automation in Radiotherapy Planning: A Deep Learning Approach for the Delineation of Parotid Glands in Head and Neck Cancer.

The delineation of parotid glands in head and neck (HN) carcinoma is critical to assess radiotherapy (RT) planning. Segmentation processes ensure precise target position and treatment precision, facilitate monitoring of anatomical changes, enable plan adaptation, and enhance overall patient safety. In this context, artificial intelligence (AI) and deep learning (DL) have proven exceedingly effective in precisely outlining tumor tissues and, by extension, the organs at risk. This paper introduces a DL framework using the AttentionUNet neural network for automatic parotid gland segmentation in HN cancer. Extensive evaluation of the model is performed in two public and one private dataset, while segmentation accuracy is compared with other state-of-the-art DL segmentation schemas. To assess replanning necessity during treatment, an additional registration method is implemented on the segmentation output, aligning images of different modalities (Computed Tomography (CT) and Cone Beam CT (CBCT)). AttentionUNet outperforms similar DL methods (Dice Similarity Coefficient: 82.65% ± 1.03, Hausdorff Distance: 6.24 mm ± 2.47), confirming its effectiveness. Moreover, the subsequent registration procedure displays increased similarity, providing insights into the effects of RT procedures for treatment planning adaptations. The implementation of the proposed methods indicates the effectiveness of DL not only for automatic delineation of the anatomical structures, but also for the provision of information for adaptive RT support.

An Automated Prognostic Model for Pancreatic Ductal Adenocarcinoma.

Pancreatic ductal adenocarcinoma (PDAC) constitutes a leading cause of cancer-related mortality despite advances in detection and treatment methods. While computed tomography (CT) serves as the current gold standard for initial evaluation of PDAC, its prognostic value remains limited, as it relies on diagnostic stage parameters encompassing tumor size, lymph node involvement, and metastasis. Radiomics have recently shown promise in predicting postoperative survival of PDAC patients; however, they rely on manual pancreas and tumor delineation by clinicians. In this study, we collected a dataset of pre-operative CT scans from a cohort of 40 PDAC patients to evaluate a fully automated pipeline for survival prediction. Employing nnU-Net trained on an external dataset, we generated automated pancreas and tumor segmentations. Subsequently, we extracted 854 radiomic features from each segmentation, which we narrowed down to 29 via feature selection. We then combined these features with the Tumor, Node, Metastasis (TNM) system staging parameters, as well as the patient's age. We trained a random survival forest model to perform an overall survival prediction over time, as well as a random forest classifier for the binary classification of two-year survival, using repeated cross-validation for evaluation. Our results exhibited promise, with a mean C-index of 0.731 for survival modeling and a mean accuracy of 0.76 in two-year survival prediction, providing evidence of the feasibility and potential efficacy of a fully automated pipeline for PDAC prognostication. By eliminating the labor-intensive manual segmentation process, our streamlined pipeline demonstrates an efficient and accurate prognostication process, laying the foundation for future research endeavors.

Independent component analysis: a reliable alternative to general linear model for task-based fMRI.

Background: Functional magnetic resonance imaging (fMRI) is a valuable tool for the presurgical evaluation of patients undergoing neurosurgeries. Although many pre-processing steps have been modified according to advances in recent years, statistical analysis has remained largely the same since the first days of fMRI. In this study, we examined the ability of Independent Component Analysis (ICA) to separate the activation of a language task in fMRI, and we compared it with the results of the General Lineal Model (GLM). Methods: Sixty patients undergoing evaluation for brain surgery due to various brain lesions and/or epilepsy and 20 control subjects completed an fMRI language mapping protocol that included three tasks, resulting in 259 fMRI scans. Depending on brain lesion characteristics, patients were allocated to (1) static/chronic not-expanding lesions (Group 1) and (2) progressive/expanding lesions (Group 2). GLM and ICA statistical maps were evaluated by fMRI experts to assess the performance of each technique. Results: In the control group, ICA and GLM maps were similar without any superiority of either technique. In Group 1 and Group 2, ICA performed statistically better than GLM, with a p-value of < 0.01801 and < 0.0237, respectively. This indicated that ICA performs as well as GLM when the subjects are able to cooperate well (less movement, good task performance), but ICA could outperform GLM in the patient groups. When both techniques were combined, 240 out of 259 scans produced reliable results, showing that the sensitivity of task-based fMRI can be increased when both techniques are integrated with the clinical setup. Conclusion: ICA may be slightly more advantageous, compared to GLM, in patients with brain lesions, across the range of pathologies included in our population and independent of symptoms chronicity. Our findings suggest that GLM analysis may be more susceptible to brain activity perturbations induced by a variety of lesions or scanner-induced artifacts due to motion or other factors. In our research, we demonstrated that ICA is able to provide fMRI results that can be used in surgery, taking into account patient and task-wise aspects that differ from those when fMRI is used in research.

Deep Learning Approaches to Osteosarcoma Diagnosis and Classification: A Comparative Methodological Approach.

BACKGROUND: Osteosarcoma is the most common primary malignancy of the bone, being most prevalent in childhood and adolescence. Despite recent progress in diagnostic methods, histopathology remains the gold standard for disease staging and therapy decisions. Machine learning and deep learning methods have shown potential for evaluating and classifying histopathological cross-sections. METHODS: This study used publicly available images of osteosarcoma cross-sections to analyze and compare the performance of state-of-the-art deep neural networks for histopathological evaluation of osteosarcomas. RESULTS: The classification performance did not necessarily improve when using larger networks on our dataset. In fact, the smallest network combined with the smallest image input size achieved the best overall performance. When trained using 5-fold cross-validation, the MobileNetV2 network achieved 91% overall accuracy. CONCLUSIONS: The present study highlights the importance of careful selection of network and input image size. Our results indicate that a larger number of parameters is not always better, and the best results can be achieved on smaller and more efficient networks. The identification of an optimal network and training configuration could greatly improve the accuracy of osteosarcoma diagnoses and ultimately lead to better disease outcomes for patients.

A Novel Approach for Estimating Ovarian Cancer Tissue Heterogeneity through the Application of Image Processing Techniques and Artificial Intelligence.

PURPOSE: Tumor heterogeneity may be responsible for poor response to treatment and adverse prognosis in women with HGOEC. The purpose of this study is to propose an automated classification system that allows medical experts to automatically identify intratumoral areas of different cellularity indicative of tumor heterogeneity. METHODS: Twenty-two patients underwent dedicated pelvic MRI, and a database of 11,095 images was created. After image processing techniques were applied to align and assess the cancerous regions, two specific imaging series were used to extract quantitative features (radiomics). These features were employed to create, through artificial intelligence, an estimator of the highly cellular intratumoral area as defined by arbitrarily selected apparent diffusion coefficient (ADC) cut-off values (ADC < 0.85 × 10-3 mm2/s). RESULTS: The average recorded accuracy of the proposed automated classification system was equal to 0.86. CONCLUSION: The proposed classification system for assessing highly cellular intratumoral areas, based on radiomics, may be used as a tool for assessing tumor heterogeneity.

MARGINAL: An Automatic Classification of Variants in BRCA1 and BRCA2 Genes Using a Machine Learning Model.

Implementation of next-generation sequencing (NGS) for the genetic analysis of hereditary diseases has resulted in a vast number of genetic variants identified daily, leading to inadequate variant interpretation and, consequently, a lack of useful clinical information for treatment decisions. Herein, we present MARGINAL 1.0.0, a machine learning (ML)-based software for the interpretation of rare BRCA1 and BRCA2 germline variants. MARGINAL software classifies variants into three categories, namely, (likely) pathogenic, of uncertain significance and (likely) benign, implementing the criteria established by the American College of Medical Genetics and Genomics and the Association for Molecular Pathology (ACMG-AMP). We first annotated BRCA1 and BRCA2 variants using various sources. Then, we automatically implemented the ACMG-AMP criteria, and we finally constructed the ML model for variant classification. To maximize accuracy, we compared the performance of eight different ML algorithms in a classification scheme based on a serial combination of two classifiers. The model showed high predictive abilities with maximum accuracy of 92% and 98%, recall of 92% and 98% and specificity of 90% and 98% for the first and second classifiers, respectively. Our results indicate that using a gene and disease-specific ML automated software for clinical variant evaluation can minimize conflicting interpretations.

Early Prediction of Planning Adaptation Requirement Indication Due to Volumetric Alterations in Head and Neck Cancer Radiotherapy: A Machine Learning Approach.

BACKGROUND: During RT cycles, the tumor response pattern could affect tumor coverage and may lead to organs at risk of overdose. As such, early prediction of significant volumetric changes could therefore reduce potential radiation-related adverse effects. Nevertheless, effective machine learning approaches based on the radiomic features of the clinically used CBCT images to determine the tumor volume variations due to RT not having been implemented so far. METHODS: CBCT images from 40 HN cancer patients were collected weekly during RT treatment. From the obtained images, the Clinical Target Volume (CTV) and Parotid Glands (PG) regions of interest were utilized to calculate 104 delta-radiomics features. These features were fed on a feature selection and classification procedure for the early prediction of significant volumetric alterations. RESULTS: The proposed framework was able to achieve 0.90 classification performance accuracy while detecting a small subset of discriminative characteristics from the 1st week of RT. The selected features were further analyzed regarding their effects on temporal changes in anatomy and tumor response modeling. CONCLUSION: The use of machine learning algorithms offers promising perspectives for fast and reliable early prediction of large volumetric deviations as a result of RT treatment, exploiting hidden patterns in the overall anatomical characteristics.

A Comparative Analysis of White Matter Structural Networks on SCLC Patients After Chemotherapy.

Previous sMRI, DTI and rs-fMRI studies in small cell lung cancer (SCLC) patients have reported that patients after chemotherapy had gray and white matter structural alterations along with functional deficits. Nonetheless, few are known regarding the potential alterations in the topological organization of the WM structural network in SCLC patients after chemotherapy. In this context, the scope of the present study is to evaluate the WM structural network of 20 SCLC patients after chemotherapy and to 14 healthy controls, by applying a combination of DTI with graph theory. The results revealed that both SCLC and healthy controls groups demonstrated small world properties. The SCLC patients had decreased values in the clustering coefficient, local efficiency and degree metrics as well as increased shortest path length when compared to the healthy controls. Moreover, the two groups reported different topological reorganization of hub distribution. Lastly, the SCLC patients exhibited significantly decreased structural connectivity in comparison to the healthy group. These results underline that the topological organization of the WM structural network in SCLC patients was disrupted and hence constitute new vital information regarding the effects that chemotherapy and cancer may have in the patients' brain at network level.

A decision support system for the identification of metastases of Metastatic Melanoma using whole-body FDG PET/CT images.

Metastatic Melanoma (MM) is an aggressive type of cancer which produces metastases throughout the body with very poor survival rates. Recent advances in immunotherapy have shown promising results for controlling disease's progression. Due to the often rapid progression, fast and accurate diagnosis and treatment response assessment is vital for the whole patient management. These procedures prerequisite accurate, whole-body tumor identification. This can be offered by the imaging modality Positron Emission Tomography (PET)/Computed Tomography (CT) with the radiotracer F 18-Fluorodeoxyglucose (FDG). However, manual segmentation of PET/CT images is a very time-consuming and labor intensive procedure that requires expert knowledge. Most of the previously published segmentation techniques focus on a specific type of tumor or part of the body and require a great amount of manually labeled data, which is, however, difficult for MM. Multimodal analysis of PET/CT is also crucial because FDG-PET contains only the functional information of tumors which can be complemented by the anatomical information of CT. In this paper, we propose a whole-body segmentation framework capable of efficiently identifying the highly heterogeneous tumor lesions of MM from the whole-body 3D FDG-PET/CT images. The proposed decision support system begins with an Ensemble Unsupervised Segmentation of regions of high FDG-uptake based on Fuzzy C-means and a custom region growing algorithm. Then, a region classification model based on radiomics features and Neural Networks classifies these regions as tumors or not. Experimental results showed high performance in the identification of MM lesions with Sensitivity 83.68%, Specificity 91.82%, F1-score 75.42%, AUC 94.16% and Balanced accuracy 87.75% which were also supported by the public dataset evaluation.

Vertebrae, IVD and spinal canal boundary extraction on MRI, utilizing CT-trained active shape models.

PURPOSE: Vertebrae, intervertebral disc (IVD) and spinal canal (SC) displacements are in the root of several spinal cord pathologies. The localization and boundary extraction of these structures, along with the quantification of their displacements, provide valuable clues for assessing each pathological condition. In this work, we propose a computational method for boundary extraction of vertebrae, IVD and SC in magnetic resonance images (MRI). METHOD: Vertebrae shape priors derived from computed tomography (CT) images are used to guide vertebrae, IVD and SC boundary extraction in MRI. This strategy is dictated by three considerations: (1) CT is the modality of choice for highlighting solid structures such as vertebrae, (2) vertebrae boundaries indirectly impose constraints on the boundaries of neighbouring structures (IVD and SC), and (3) it can be observed that edges are similarly located in CT and MR images; therefore, gradient profiles and shape priors learned by active shape models (ASMs) from CT are also valid in MRI. RESULTS: Experimental comparisons on two MR image datasets demonstrate that the proposed approach obtains segmentation results, which are comparable to the state of the art. Moreover, the adopted bimodal strategy is validated by demonstrating that CT-derived shape priors lead to more accurate boundary extraction than MRI-derived shape priors, even in the case of MR image applications. CONCLUSION: Unlike existing bimodal methods, the proposed one is not dependent on the availability of CT/MR image pairs, which are not usually acquired from the same patient. In addition, unlike state-of-the-art deep learning-based methods, it is not dependent on large amounts of training data. The proposed method requires a limited amount of user intervention.

Fractal and Multifractal Analysis of PET-CT Images for Therapy Assessment of Metastatic Melanoma Patients under PD-1 Inhibitors: A Feasibility Study.

Longitudinal whole-body PET-CT scans with F-18-fluorodeoxyglucose (18F-FDG) in patients suffering from metastatic melanoma were analyzed and the tracer distribution in patients was compared with that of healthy controls. Nineteen patients with metastatic melanoma were scanned before, after two and after four cycles of treatment with PD-1 inhibitors (pembrolizumab, nivolumab) applied as monotherapy or as combination treatment with ipilimumab. For comparison eight healthy controls were analyzed. As quantitative measures for the comparison between controls and patients, the nonlinear fractal dimension (FD) and multifractal spectrum (MFS) were calculated from the digitized PET-CT scans. The FD and MFS measures, which capture the dispersion of the tracer in the body, decreased with disease progression, since the tracer particles tended to accumulate around metastatic sites in patients, while the measures increased when the patients' clinical condition ameliorate. The MFS measure gave better predictions and were consistent with the PET Response Evaluation Criteria for Immunotherapy (PERCIMT) in 81% of the cases, while FD agreed in 77% of all cases. These results agree, qualitatively, with a previous study of our group when treatment with ipilimumab monotherapy was considered.

Deformable image registration to assist clinical decision for radiotherapy treatment adaptation for head and neck cancer patients.

Head and neck (H&N) cancer patients often present anatomical and geometrical changes in tumors and organs at risk (OARs) during radiotherapy treatment. These changes may result in the need to adapt the existing treatment planning, using an expert's subjective opinion, for offline adaptive radiotherapy and a new treatment planning before each treatment, for online adaptive radiotherapy. In the present study, a fast methodology is proposed to assist in planning adaptation clinical decision using tumor and parotid glands percentage volume changes during treatment. The proposed approach was applied to 40 Η&Ν cases, with one planning Computed Tomography (pCT) image and CBCT scans for 6 weeks of treatment per case. Deformable registration was used for each patient's pCT image alignment to its weekly CBCT. The calculated transformations were used to align each patient's anatomical structures to the weekly anatomy. Clinical target volume (CTV) and parotid gland volume percentage changes were calculated in each case. The accuracy of the achieved image alignment was validated qualitatively and quantitatively. Furthermore, statistical analysis was performed to test if there is a statistically significant correlation between CTV and parotid glands volume percentage changes. Average MDA for CTV and parotid glands between corresponding structures defined by an expert in CBCTs and automatically calculated through registration was 1.4 ± 0.1 mm and 1.5 ± 0.1 mm, respectively. The mean registration time of the first CBCT image registration for 40 cases was lower than 3.4 min. Five patients show more than 20% tumor volume change. Six patients show more than 30% parotid glands volume change. Ten out of 40 patients proposed for planning adaptation. All the statistical tests performed showed no correlation between CTV/parotid glands percentage volume changes. The aim to assist in clinical decision making on a fast and automatic way was achieved using the proposed methodology, thereby reducing workload in clinical practice.

Chemotherapy-Induced Brain Effects in Small-Cell Lung Cancer Patients: A Multimodal MRI Study.

The golden standard of treating Small Cell Lung Cancer (SCLC) entails application of platinum-based chemotherapy, is often accompanied by Prophylactic Cranial Irradiation (PCI), which have been linked to neurotoxic side-effects in cognitive functions. The related existing neuroimaging research mainly focuses on the effect of PCI treatment in life quality and expectancy, while little is known regarding the distinct adverse effects of chemotherapy. In this context, a multimodal MRI analysis based on structural and functional brain data is proposed in order to evaluate chemotherapy-specific effects on SCLC patients. Data from 20 patients (after chemotherapy and before PCI) and 14 healthy controls who underwent structural MRI, DTI and resting state fMRI were selected in this study. From a structural aspect, the proposed analysis included volumetry and thickness measurements on structural MRI data for assessing gray matter dissimilarities, as well as deterministic tractography and Tract-Based Spatial Statistics (TBSS) on DTI data, aiming to investigate potential white matter abnormalities. Functional data were also processed on the basis of connectivity analysis, evaluating brain network parameters to identify potential manifestation of functional inconsistencies. By comparing patients to healthy controls, the obtained results revealed statistically significant differences, with the patients' brains presenting reduced volumetry/thickness and fractional anisotropy values, accompanied by prominent differences in functional connectivity measurements. All above mentioned findings were observed in patients that underwent chemotherapy.

3D dental image registration using exhaustive deformable models: a comparative study.

OBJECTIVES: Image registration is commonly used in dental applications for aligning imaging data sets, which is particularly useful when assessing the progression or regression of particular pathomorphic conditions. However, due to the nature of the processed data or the data acquisition process itself, rigid body registration may be insufficient to accurately align the processed data sets. In such cases, deformable models are employed. This study presents a comparison of four well-established deformable models for aligning CBCT volumes. METHODS: The compared models include the original Demons algorithm, symmetric forces Demons, diffeomorphic Demons and level-set motion. The compared techniques are incorporated into a general image registration scheme featuring two distinct stages: a common, fast, rigid-based alignment for pre-registering the data and a finer elastic registration phase, based on the four compared deformation models. RESULTS: The proposed framework was applied to a total of 40 CBCT volume pairs with known and unknown initial differences. CONCLUSIONS: After both qualitative and quantitative assessment of the produced aligned data, it was concluded that the level-set motion method outperformed all other techniques for data pairs with both unknown initial differences, as well as with known elastic deviations based on fixed sinusoidal models and B-splines.

Computational Construction of Antibody-Drug Conjugates Using Surface Lysines as the Antibody Conjugation Site and a Non-cleavable Linker.

Antibody-drug conjugates (ADCs) constitute a category of anticancer targeted therapy that has gathered great interest during the last few years because of their potential to kill cancer cells while causing significantly fewer side effects than traditional chemotherapy. In this paper, a process of computational construction of ADCs is described, using the surface lysines of an antibody and a non-covalent linker molecule, as well as a cytotoxic substance, as files in Protein Data Bank format. Also, aspects related to the function, properties, and development of ADCs are discussed.

Classification of histological images of the endometrium using texture features.

OBJECTIVE: To present a texture analysis method in order to achieve texture classification for 240 histological images of the endometrium. STUDY DESIGN: A total of 128 patients with endometrial cancer and 112 subjects with no pathological condition were imaged. For each image 190 texture features were initially extracted, derived from the wavelets, the Gabor filters, and the Law's masks, which were reduced after feature selection in only 4 features. RESULTS: The images were classified into 2 categories using artificial neural networks, and the reported classification accuracy was 98.1%. CONCLUSION: The results showed that there was a strong discrimination between histological images of cancerous and normal tissue of the endometrium, based on the proposed set of texture features.

Classification of hysteroscopical images using texture and vessel descriptors.

In recent years, hysteroscopy, used as an outpatient office procedure, in combination with endometrial biopsy, has demonstrated its great potential as the method of first choice in the diagnosis of various gynecological abnormalities including abnormal uterine bleeding (AUB) and endometrial cancer (CA). In patients suffering with AUB, the blood vessels of the endometrium are hypertrophic, whereas in the case of CA vascularization is irregular or anarchic. In this paper, a methodology for the classification of hysteroscopical images of endometrium using vessel and texture features is presented. A total of 28 patients with abnormal uterine bleeding, 10 patients with endometrial cancer and 39 subjects with no pathological condition were imaged. 16 of the patients with AUB were premenopausal and 12 postmenopausal, all with CA were postmenopausal, and all with no pathological condition were premenopausal. All images were examined for the appearance of endometrial vessels and non-vascular structures. For each image, 167 texture and vessel's features were initially extracted, which were reduced after feature selection in only 4 features. The images were classified into three categories using artificial neural networks and the reported classification accuracy was 91.2 %, while the specificity and sensitivity were 83.8 and 93.6 % respectively.

A decision support system for assisting fine needle aspiration diagnosis of thyroid malignancy.

OBJECTIVE: To assist diagnosis of thyroid malignancy, implementing a decision support system (DSS) using fine needle aspiration biopsy (FNAB) data. STUDY DESIGN: The set of 2,035 thyroid smears contained 1,886 smears of nonmalignancy (class 1) and 150 smears of malignancy (class 2) verified histologically. For each smear, 67 medical features were considered by the expert, forming 2,036 feature vectors, which were fed into a DSS for discriminating between malignant and nonmalignant smears. The DSS comprised a feature selection and classification module using a combination of three classifiers, the artificial neural network, the support vector machines, and the k-nearest neighbor, under the majority vote procedure. RESULTS: The overall classification accuracy of the DSS was 98.6%, marginally better than the FNAB (97.3%). The DSS had lower sensitivity (89.1%) and better specificity (99.4%) compared to the FNAB. Regarding the smears characterized as "suspicious" by FNAB, a significant improvement of overall accuracy was obtained by the proposed DSS system (84.6%) compared to the FNAB (50.0%). CONCLUSION: The proposed DSS provides significant improvement compared to FNAB regarding discrimination of smears characterized by an expert as "suspicious," reducing the number of patients undergoing surgical procedures.

Computer-aided diagnosis of thyroid malignancy using an artificial immune system classification algorithm.

The diagnosis of thyroid malignancy by fine needle aspiration (FNA) examination has been proven to show wide variations of sensitivity and specificity. This paper proposes the utilization of a computer-aided diagnosis system based on a supervised classification algorithm from the artificial immune systems to assist the task of thyroid malignancy diagnosis. The core of the proposed algorithm is the so-called BoxCells, which are defined as parallelepipeds in the feature space. Properly defined operators act on the BoxCells in order to convert them into individual, elementary classifiers. The proposed algorithm is applied on FNA data from 2016 subjects with verified diagnosis and has exhibited average specificity higher than 99%, 90% sensitivity, and 98.5% accuracy. Furthermore, 24% of the cases that are characterized as "suspicious" by FNA and are histologically proven nonmalignancies have been classified correctly.

ESTERR-PRO: a setup verification software system using electronic portal imaging.

The purpose of the paper is to present and evaluate the performance of a new software-based registration system for patient setup verification, during radiotherapy, using electronic portal images. The estimation of setup errors, using the proposed system, can be accomplished by means of two alternate registration methods. (a) The portal image of the current fraction of the treatment is registered directly with the reference image (digitally reconstructed radiograph (DRR) or simulator image) using a modified manual technique. (b) The portal image of the current fraction of the treatment is registered with the portal image of the first fraction of the treatment (reference portal image) by applying a nearly automated technique based on self-organizing maps, whereas the reference portal has already been registered with a DRR or a simulator image. The proposed system was tested on phantom data and on data from six patients. The root mean square error (RMSE) of the setup estimates was 0.8 +/- 0.3 (mean value +/- standard deviation) for the phantom data and 0.3 +/- 0.3 for the patient data, respectively, by applying the two methodologies. Furthermore, statistical analysis by means of the Wilcoxon nonparametric signed test showed that the results that were obtained by the two methods did not differ significantly (P value >0.05).