Osteosarcoma of Head and Neck Region: Tertiary Cancer Care Center Experience.

Head and neck osteosarcoma is an uncommon yet aggressive tumor which presents therapeutic challenges to get favourable results. Surgery remained the most effective treatment modality in this entity eventhough chemoradiotherapy have been tried in various studies for better outcome but still not yet becomes the standard in the management of these cases unlike in extremity osteosarcoma. We present our experience in the management of this uncommon yet lethal malignant tumor, i.e. head and neck osteosarcoma. To study the clinicopathological and prognostic features of Osteosarcoma in head and neck subsite. Retrospective study of patients diagnosed with head and neck osteosarcoma between 2003 and 2019. Total of 25 patients were included in our study. Mean age of our population is 27.5 years with slight male predominant. Mandible is the most commonly involved site. Multimodal treatment applied with surgical resection forms the main part in the management. Median DFS and OS were 16 and 36 months respectively with 5 year overall survival of 42%. Out of the various factors studied, absence of surgery, margin positivity are the principle features affecting the prognosis. Head and neck osteosarcoma is generally a jaw bone tumor commonly occurs in young adults with poor outcome. Since there is no universal guidelines to address this uncommon tumor, multiple studies have shown various results in the management. Till date, surgery remained the curative modality with mixed response on the role of chemotherapy and radiotherapy.

The expert's knowledge combined with AI outperforms AI alone in seizure onset zone localization using resting state fMRI.

We evaluated whether integration of expert guidance on seizure onset zone (SOZ) identification from resting state functional MRI (rs-fMRI) connectomics combined with deep learning (DL) techniques enhances the SOZ delineation in patients with refractory epilepsy (RE), compared to utilizing DL alone. Rs-fMRI was collected from 52 children with RE who had subsequently undergone ic-EEG and then, if indicated, surgery for seizure control (n = 25). The resting state functional connectomics data were previously independently classified by two expert epileptologists, as indicative of measurement noise, typical resting state network connectivity, or SOZ. An expert knowledge integrated deep network was trained on functional connectomics data to identify SOZ. Expert knowledge integrated with DL showed a SOZ localization accuracy of 84.8 ± 4.5% and F1 score, harmonic mean of positive predictive value and sensitivity, of 91.7 ± 2.6%. Conversely, a DL only model yielded an accuracy of <50% (F1 score 63%). Activations that initiate in gray matter, extend through white matter, and end in vascular regions are seen as the most discriminative expert-identified SOZ characteristics. Integration of expert knowledge of functional connectomics can not only enhance the performance of DL in localizing SOZ in RE but also lead toward potentially useful explanations of prevalent co-activation patterns in SOZ. RE with surgical outcomes and preoperative rs-fMRI studies can yield expert knowledge most salient for SOZ identification.

Isolated trigeminal neuralgia: An early weird presentation of carcinoma breast.

We report an interesting case of a 52-year-old postmenopausal female who presented with a 2-month history of headache, tingling sensation, and sharp shooting pain over the left face, followed by left facial paresthesia with pain over the maxillary region. Magnetic resonance imaging scan revealed presence of enplaque altered signal intensity soft-tissue lesion along the left 5th nerve from its origin at pons, and positron emission tomography with concurrent computed tomography showed a 2.9 cm × 2.6 cm intensely 18F-fluorodeoxyglucose-avid breast mass, in the upper outer quadrant of the right breast. Core-needle biopsy revealed infiltrating ductal carcinoma. Her estrogen receptor, progesterone receptor, and Her2-neu analysis suggested triple-negative breast cancer. She was managed with cranial radiotherapy and palliative chemotherapy. The patient responded very well to radiotherapy and chemotherapy with complete improvement in her neurological symptoms and now she is under regular follow-up for chemotherapy for 8 months without any subjective or objective progression of the disease. Isolated cranial neuropathy may be an early harbinger of metastatic breast cancer, so we should search for the primary malignancy. TNBC is associated with early central nervous system metastasis because of heterogeneity in the biology of the disease. Whole-brain radiotherapy and palliative chemotherapy are the best available treatment modalities.

Automated seizure onset zone locator from resting-state functional MRI in drug-resistant epilepsy.

Objective: Accurate localization of a seizure onset zone (SOZ) from independent components (IC) of resting-state functional magnetic resonance imaging (rs-fMRI) improves surgical outcomes in children with drug-resistant epilepsy (DRE). Automated IC sorting has limited success in identifying SOZ localizing ICs in adult normal rs-fMRI or uncategorized epilepsy. Children face unique challenges due to the developing brain and its associated surgical risks. This study proposes a novel SOZ localization algorithm (EPIK) for children with DRE. Methods: EPIK is developed in a phased approach, where fMRI noise-related biomarkers are used through high-fidelity image processing techniques to eliminate noise ICs. Then, the SOZ markers are used through a maximum likelihood-based classifier to determine SOZ localizing ICs. The performance of EPIK was evaluated on a unique pediatric DRE dataset (n = 52). A total of 24 children underwent surgical resection or ablation of an rs-fMRI identified SOZ, concurrently evaluated with an EEG and anatomical MRI. Two state-of-art techniques were used for comparison: (a) least squares support-vector machine and (b) convolutional neural networks. The performance was benchmarked against expert IC sorting and Engel outcomes for surgical SOZ resection or ablation. The analysis was stratified across age and sex. Results: EPIK outperformed state-of-art techniques for SOZ localizing IC identification with a mean accuracy of 84.7% (4% higher), a precision of 74.1% (22% higher), a specificity of 81.9% (3.2% higher), and a sensitivity of 88.6% (16.5% higher). EPIK showed consistent performance across age and sex with the best performance in those < 5 years of age. It helped achieve a ~5-fold reduction in the number of ICs to be potentially analyzed during pre-surgical screening. Significance: Automated SOZ localization from rs-fMRI, validated against surgical outcomes, indicates the potential for clinical feasibility. It eliminates the need for expert sorting, outperforms prior automated methods, and is consistent across age and sex.

Tolerance of Radical Radiotherapy Among Elderly Head and Neck Cancer Patients.

Head and neck cancers usually occur in the elderly age group and about half of the cases occur at the age > 60 years with majority detected in an advanced stage with increased morbidity and decreasing compliance to therapy. Since there are limited data available for the adequate treatment of elderly head and neck cancer patients, we proposed a study to analyze tolerance and response based on age, site, modality of treatment received, and implication of nutrition vs weight loss during treatment. Fifty-five patients were enrolled in this study, which was conducted between November 2015 and April 2017, and those who met the eligibility criteria were evaluated with a detailed history and physical examination, and biochemical, pathological, and radiological investigations. Patients were staged based on TNM staging and treated as per the standard guidelines. Patients were assessed with the weekly routine blood investigation, weight loss, and toxicity. The response was assessed after 6 weeks and documented as per RECIST criteria. 52/55 (94.5%) patients completed the treatment, and 48/55 (92.3%) had a complete response at 6 weeks (p value 0.000) with a mean treatment duration of 46.67 days and mean weight loss of 5.44 kg with 55.4% having GR-II mucositis, 40% having GRIII mucositis at the time of completion of treatment. Sixty-eight percent having GRII and 38.2% having GR I dermatitis and 80% had moderate pain. Subgroup analysis was done based on age, site, and treatment modality. Patients were also assessed for nutrition vs weight loss. We concluded that elderly patients tolerate and respond well to radical treatment with acceptable toxicities; hence, age should not be a barrier to decide treatment.

A System-Driven Taxonomy of Attacks and Defenses in Adversarial Machine Learning.

Machine Learning (ML) algorithms, specifically supervised learning, are widely used in modern real-world applications, which utilize Computational Intelligence (CI) as their core technology, such as autonomous vehicles, assistive robots, and biometric systems. Attacks that cause misclassifications or mispredictions can lead to erroneous decisions resulting in unreliable operations. Designing robust ML with the ability to provide reliable results in the presence of such attacks has become a top priority in the field of adversarial machine learning. An essential characteristic for rapid development of robust ML is an arms race between attack and defense strategists. However, an important prerequisite for the arms race is access to a well-defined system model so that experiments can be repeated by independent researchers. This paper proposes a fine-grained system-driven taxonomy to specify ML applications and adversarial system models in an unambiguous manner such that independent researchers can replicate experiments and escalate the arms race to develop more evolved and robust ML applications. The paper provides taxonomies for: 1) the dataset, 2) the ML architecture, 3) the adversary's knowledge, capability, and goal, 4) adversary's strategy, and 5) the defense response. In addition, the relationships among these models and taxonomies are analyzed by proposing an adversarial machine learning cycle. The provided models and taxonomies are merged to form a comprehensive system-driven taxonomy, which represents the arms race between the ML applications and adversaries in recent years. The taxonomies encode best practices in the field and help evaluate and compare the contributions of research works and reveals gaps in the field.

Molecular Marker as a Prognostic Indicator in Head and Neck Cancer Patients.

Head and neck cancer forms the major burden of cancer in the developing countries. Despite advancement in the treatment approach of head and neck cancer in terms of surgery, chemotherapy and radiotherapy overall long-term survival remains low due to uncontrollable persistent and recurrent disease. This low survival rate has demanded for the need for newer treatment approaches and prognostic markers. In a previously published study "impact of molecular predictors on the response rates in head and neck Cancer patients" by Koushik et al. assessed the impact of molecular markers like HPV, P53, and EGFR status along with other prognostic factors like tobacco use, age, sex, and socioeconomic status on response to treatment of head and neck cancer patients. Our present study is intent to provide update of the impact of those molecular markers on survival. Objective of our study is to correlate the HPV, EGFR, and P53 status with the survival rate of the head and neck cancer patients. Twenty-five histologically proven head and neck cancer patients were assessed for HPV, EGFR, and P53 status who underwent chemoradiation to a dose of 66 Gy in 33 fraction along with weekly cisplatin of 40 mg/m2, and all treated patients were followed up to a minimum of 3 years and analyzed for the survival. We found that 3-year survival for complete responders after treatment is 61.5% and partial responders, 57.1%; stable disease is 33.3%, and progressive disease is 0%. A 3-year survival for HPV-positive patients is 57.4% (p = 0.973), EGFR-mutated patients is 47.62% (p = 0.593), and P53-mutated patients is 57.89% (p = 0.378).

Permanency analysis on human electroencephalogram signals for pervasive Brain-Computer Interface systems.

Brain-Computer Interface (BCI) systems use some permanent features of brain signals to recognize their corresponding cognitive states with high accuracy. However, these features are not perfectly permanent, and BCI system should be continuously trained over time, which is tedious and time consuming. Thus, analyzing the permanency of signal features is essential in determining how often to repeat training. In this paper, we monitor electroencephalogram (EEG) signals, and analyze their behavior through continuous and relatively long period of time. In our experiment, we record EEG signals corresponding to rest state (eyes open and closed) from one subject everyday, for three and a half months. The results show that signal features such as auto-regression coefficients remain permanent through time, while others such as power spectral density specifically in 5-7 Hz frequency band are not permanent. In addition, eyes open EEG data shows more permanency than eyes closed data.