Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI.

BACKGROUND: The purpose of this study is to investigate the use of radiomics and deep features obtained from multiparametric magnetic resonance imaging (mpMRI) for grading prostate cancer. We propose a novel approach called multi-flavored feature extraction or tensor, which combines four mpMRI images using eight different fusion techniques to create 52 images or datasets for each patient. We evaluate the effectiveness of this approach in grading prostate cancer and compare it to traditional methods. METHODS: We used the PROSTATEx-2 dataset consisting of 111 patients' images from T2W-transverse, T2W-sagittal, DWI, and ADC images. We used eight fusion techniques to merge T2W, DWI, and ADC images, namely Laplacian Pyramid, Ratio of the low-pass pyramid, Discrete Wavelet Transform, Dual-Tree Complex Wavelet Transform, Curvelet Transform, Wavelet Fusion, Weighted Fusion, and Principal Component Analysis. Prostate cancer images were manually segmented, and radiomics features were extracted using the Pyradiomics library in Python. We also used an Autoencoder for deep feature extraction. We used five different feature sets to train the classifiers: all radiomics features, all deep features, radiomics features linked with PCA, deep features linked with PCA, and a combination of radiomics and deep features. We processed the data, including balancing, standardization, PCA, correlation, and Least Absolute Shrinkage and Selection Operator (LASSO) regression. Finally, we used nine classifiers to classify different Gleason grades. RESULTS: Our results show that the SVM classifier with deep features linked with PCA achieved the most promising results, with an AUC of 0.94 and a balanced accuracy of 0.79. Logistic regression performed best when using only the deep features, with an AUC of 0.93 and balanced accuracy of 0.76. Gaussian Naive Bayes had lower performance compared to other classifiers, while KNN achieved high performance using deep features linked with PCA. Random Forest performed well with the combination of deep features and radiomics features, achieving an AUC of 0.94 and balanced accuracy of 0.76. The Voting classifiers showed higher performance when using only the deep features, with Voting 2 achieving the highest performance, with an AUC of 0.95 and balanced accuracy of 0.78. CONCLUSION: Our study concludes that the proposed multi-flavored feature extraction or tensor approach using radiomics and deep features can be an effective method for grading prostate cancer. Our findings suggest that deep features may be more effective than radiomics features alone in accurately classifying prostate cancer.

Auto-segmentation of head and neck tumors in positron emission tomography images using non-local means and morphological frameworks.

Purpose: Accurately segmenting head and neck cancer (HNC) tumors in medical images is crucial for effective treatment planning. However, current methods for HNC segmentation are limited in their accuracy and efficiency. The present study aimed to design a model for segmenting HNC tumors in three-dimensional (3D) positron emission tomography (PET) images using Non-Local Means (NLM) and morphological operations. Material and Methods: The proposed model was tested using data from the HECKTOR challenge public dataset, which included 408 patient images with HNC tumors. NLM was utilized for image noise reduction and preservation of critical image information. Following pre-processing, morphological operations were used to assess the similarity of intensity and edge information within the images. The Dice score, Intersection Over Union (IoU), and accuracy were used to evaluate the manual and predicted segmentation results. Results: The proposed model achieved an average Dice score of 81.47 ± 3.15, IoU of 80 ± 4.5, and accuracy of 94.03 ± 4.44, demonstrating its effectiveness in segmenting HNC tumors in PET images. Conclusions: The proposed algorithm provides the capability to produce patient-specific tumor segmentation without manual interaction, addressing the limitations of current methods for HNC segmentation. The model has the potential to improve treatment planning and aid in the development of personalized medicine. Additionally, this model can be extended to effectively segment other organs from limited annotated medical images.

Thyroid function following radiation therapy in breast cancer patients: risk of radiation-induced hypothyroidism.

Background: Radiation exposure to the thyroid gland seems unavoidable in breast cancer (BC) patients receiving radiation therapy (RT) to the supraclavicular (SC) region. Hence, this study aimed to evaluate the effects of SC region RT on thyroid function and the prevalence of radiation-induced hypothyroidism (RIHT) in BC patients at regular intervals post-treatment. Materials and methods: Twenty-one patients with BC were enrolled in this analytical cross-sectional study by simple and convenient sampling, from March 2019 to March 2020. Thyroid function and the prevalence of RIHT were evaluated and compared by measuring the serum of thyroid-stimulating hormone (TSH) and free thyroxine hormone (fT4) levels before radiation therapy (pre-RT) and 3 and 6 months after radiation therapy (post-RT). The patients underwent 3 dimensional conformal. radiation therapy (3D CRT) of breast/chest wall, axillary, and supraclavicular lymph nodes with 50 Gy/25 fractions/5 weeks. The collected data were analyzed using SPSS software (version 20). Results: Serum levels of TSH increased at 3 and 6 months post-RT, this increase was not statistically significant (p > 0.05). Nevertheless, serum levels of fT4 were significantly elevated at 3 and 6 months post-RT (p < 0.01). A correlation was observed between the follow-up period and the incidence of RIHT, where it was 0% at 3 months and 9.5% at 6 months post-RT. RIHT was not significantly associated with any factors, including patient's age, type of surgery, thyroid gland dose, and thyroid gland volume. Conclusions: It seems that SC region RT does not have a significant adverse effect on the thyroid function among BC patients at 3 and 6 months post-treatment. Hence, a long-term follow-up with a larger sample size is suggested.

Breast cancer prediction with transcriptome profiling using feature selection and machine learning methods.

BACKGROUND: We used a hybrid machine learning systems (HMLS) strategy that includes the extensive search for the discovery of the most optimal HMLSs, including feature selection algorithms, a feature extraction algorithm, and classifiers for diagnosing breast cancer. Hence, this study aims to obtain a high-importance transcriptome profile linked with classification procedures that can facilitate the early detection of breast cancer. METHODS: In the present study, 762 breast cancer patients and 138 solid tissue normal subjects were included. Three groups of machine learning (ML) algorithms were employed: (i) four feature selection procedures are employed and compared to select the most valuable feature: (1) ANOVA; (2) Mutual Information; (3) Extra Trees Classifier; and (4) Logistic Regression (LGR), (ii) a feature extraction algorithm (Principal Component Analysis), iii) we utilized 13 classification algorithms accompanied with automated ML hyperparameter tuning, including (1) LGR; (2) Support Vector Machine; (3) Bagging; (4) Gaussian Naive Bayes; (5) Decision Tree; (6) Gradient Boosting Decision Tree; (7) K Nearest Neighborhood; (8) Bernoulli Naive Bayes; (9) Random Forest; (10) AdaBoost, (11) ExtraTrees; (12) Linear Discriminant Analysis; and (13) Multilayer Perceptron (MLP). For evaluating the proposed models' performance, balance accuracy and area under the curve (AUC) were used. RESULTS: Feature selection procedure LGR + MLP classifier achieved the highest prediction accuracy and AUC (balanced accuracy: 0.86, AUC = 0.94), followed by an LGR + LGR classifier (balanced accuracy: 0.84, AUC = 0.94). The results showed that achieved AUC for the LGR + LGR classifier belonged to the 20 biomarkers as follows: TMEM212, SNORD115-13, ATP1A4, FRG2, CFHR4, ZCCHC13, FLJ46361, LY6G6E, ZNF323, KRT28, KRT25, LPPR5, C10orf99, PRKACG, SULT2A1, GRIN2C, EN2, GBA2, CUX2, and SNORA66. CONCLUSIONS: The best performance was achieved using the LGR feature selection procedure and MLP classifier. Results show that the 20 biomarkers had the highest score or ranking in breast cancer detection.

Machine learning approach for automated predicting of COVID-19 severity based on clinical and paraclinical characteristics: Serum levels of zinc, calcium, and vitamin D.

BACKGROUND & AIMS: Considering that no standard therapy has yet been found for the novel coronavirus disease (COVID-19), identifying severe cases as early as possible, and such that treatment procedures can be escalated seems necessary. Hence, the present study aimed to develop a machine learning (ML) approach for automated severity assessment of COVID-19 based on clinical and paraclinical characteristics like serum levels of zinc, calcium, and vitamin D. METHODS: In this analytical cross-sectional study which was conducted from May 2020 to May 2021, clinical and paraclinical data sets of COVID-19-positive patients with known outcomes were investigated by combining statistical comparison and correlation methods with ML algorithms, including Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM). RESULTS: Our work revealed that some patients' characteristics including age, gender, cardiovascular diseases as an underlying condition, and anorexia as disease symptoms, and also some parameters which are measurable in blood samples including FBS and serum levels of calcium are factors that can be considered in predicting COVID-19 severity. In this regard, we developed ML predictive models that indicated accuracy and precision scores >90% for disease severity prediction. The SVM algorithm indicated better results than other algorithms by having a precision of 95.5%, recall of 94%, F1 score of 94.8%, the accuracy of 95%, and AUC of 94%. CONCLUSIONS: Our results indicated that clinical and paraclinical features like calcium serum levels can be used for automated severity assessment of COVID-19.

Investigation of how stimulation intensity of rTMS affects magneto permeabilization of the Blood-Brain Barrier (BBB).

The present study aimed to assess the effect of the rTMS (repetitive Transcranial Magnetic Stimulation) intensity on the permeability of the BBB for brain-targeted drug delivery. For this purpose, different rTMS intensities including 70%, 100%, and 130% of Resting Motor Threshold (RMT) assessed in three groups of rats (three groups of 5 rats). Stimulation applied over the right hemisphere of the animals. The first phase of the study was composed of intravenous administration of Evans Blue Dye (EBD), rTMS stimulation and EBD uptake measurement in both brain hemispheres. The second examination was included rTMS stimulation, injection of the MRI Contrast Agent (CA), and signal intensity measurement in post-contrast images. Each exam also included five rats in a sham group. Thus, the total of 40 male Wistar rats enrolled in this study. There was no significant difference in the amount of EBD accumulated between the right hemisphere of the brain in the sham group and the group with 70% RMT magnetic stimulation, while this figure was significantly higher than the sham group for both 100 and 130% RMT groups. There was also a significant difference in this index between 100 and 130% groups. All of the results from the first phase of the study were consistent with the second assessment representing an upward trend of induced permeability by rising rTMS intensity. The results of this study imply that to cause an effective temporary disruption in the BBB the intensity of 100% RMT or above should be used for stimulation.

Pulsed high magnetic field-induced reversible blood-brain barrier permeability to enhance brain-targeted drug delivery.

The present study aimed to select an effective Pulsed High Magnetic Field (PHMF) stimulation protocol that would induce the Blood-Brain Barrier's (BBB) reversible permeability to enhance brain-targeted drug delivery. PHMF was applied to the skull over the right hemisphere of 60 Wistar rats. The sham group contained other 10 rats that did not receive PHMF stimulation. The investigated parameters were repetition frequencies (0.25, 1, and 4 Hz as well as the effective low frequency combined with 10 Hz) and numbers of pulses in each train. Evans Blue Dye (EBD) uptake within the brain parenchyma was measured to select an effective PHMF stimulation protocol. BBB reversibility was evaluated by measuring EBD uptake and Gadobutrol retention, through MRI signal intensity enhancement, within brain parenchyma after exposure to the effective PHMF stimulation protocol at different time points including 0.5, 1, and 24 hours. The obtained results showed that the PHMF stimulation increased the BBB's reversible permeability; this increase was more significant for 28 pulses with 1 Hz frequency (P < .0001). Changes in EBD uptake and MRI signal intensity in the exposed side (right hemisphere) peaked within 0.5-1 hour and returned to normal levels 24 hours after exposure to the effective protocol of PHMF stimulation (28 pulses with 1 Hz frequency). The Contrast-Enhanced MRI (CE-MRI) signal intensity confirmed the changes in EBD concentration. PHMF stimulation can be used as an effective protocol for enhancing the permeability reversibly of BBB, hence considered a potential clinical approach to brain-targeted drug delivery.

Comparative study of the effects of venlafaxine and duloxetine on chemotherapy-induced peripheral neuropathy.

OBJECTIVE: One of the complications of chemotherapy is peripheral neuropathy. Various studies have shown that potent norepinephrine and serotonin reuptake inhibitors such as gabapentin, venlafaxine and duloxetine have therapeutic effects on neuropathy. The aim of this study was to compare the effects of venlafaxine vs. duloxetine on chemotherapy-induced peripheral neuropathy. METHODS: In this clinical trial, cancer patients who were suffering from chemotherapy-induced peripheral neuropathy comprised the study population. They were randomly assigned to three pharmacotherapy groups including venlafaxine, duloxetine and placebo. Cranial, sensory, motor neuropathies as well as neuropathic pain were evaluated on day 1, week 2, and week 4 after enrollment. RESULTS: Grade of cranial, motor, sensory and neuropathic pain decreased significantly in venlafaxine and duloxetine groups. This reduction was more considerable in duloxetine group compared to venlafaxine group (P < 0.05). CONCLUSION: Duloxetine seems to be more effective than venlafaxine in decreasing the symptoms of chemotherapy-induced peripheral neuropathy. Duloxetine was more effective than venlafaxine in decreasing motor neuropathy and neuropathic pain grade.

Influence of the contrast agents on treatment planning dose calculations of prostate and rectal cancers.

AIM: The aim of the present study is to quantify differences in dose calculations caused by using CA and determine if the resulting differences are clinically significant. BACKGROUND: The influence of contrast agents (CA) on radiation dose calculations must be taken into account in treatment planning. MATERIALS AND METHODS: Eleven patients with pelvic cancers were included in this study and two sets of CTs were taken for each patient (without and with CA) in the same position and coordinates. Both sets of images were transferred to the DosiSoft ISOgray treatment planning system for contouring and calculating the dose distribution and monitor units (MUs) with Collapsed Cone and Superposition algorithms, respectively. All plans were generated on pre-contrast CT and subsequently copied to the post-contrast CT. Radiation dose calculations from the two sets of CTs were compared using a paired sample t-test. RESULTS: The results showed a statistically insignificant difference between pre- and post-contrast CT treatment plans for target volume and OARs (p > 0.05), except bladder organ in the prostate region (p < 0.05) but the relative mean dose and MU differences were less than 2% in any patient for 18 MV photon beam. CONCLUSIONS: Treatment planning on contrasted images generally showed a lower radiation dose to both target volume and OARs than plans on non-contrasted images. The results of this research showed that the small radiation dose differences between the plans for the CT scans with and without CA seem to be clinically insignificant; therefore, contrast-enhanced CT can be used for both target delineation and treatment planning of prostate and rectal cancers.

Suicide Attempts Among Patients Admited to Hospital of Kermanshah University of Medical Sciences.

BACKGROUND: Suicide is a modern-age human challenge considered as a social and mental health problem acquiring enormous attention on primary and secondary heath care plans. OBJECTIVES: The current study aimed to investigate frequency of suicide attempts and related social factors among patients admitted in Hospital of Kermanshah University of Medical Sciences. PATIENTS AND METHODS: This cross-sectional study was descriptive-analytical type carried out on 251 patients admitted at medical centers of Kermanshah University of Medical Sciences after failed suicide attempts. Data collection was done through filling forms. RESULTS: Average age of the population was 29 ± 11.6 years. Female were more prone to commit suicide whereas the patients had a variety of social lifestyles and crisis such as divorce, drug abuse, and domestic problems. The most frequent method of committing suicide was the use of burning materials. CONCLUSIONS: In reference to the young age of the statistical population of attempters and frequent personal-life crisis among them, educational, welfare and consultation facilities are suggested.