Microfluidics-based EGFR mutation detection and its implication in the resource-limited clinical setting.

Management of lung cancer today obligates a mutational analysis of the epidermal growth factor receptor (EGFR) gene particularly when Tyrosine Kinase Inhibitor (TKI) therapy is being considered as part of prognostic stratification. This study evaluates the performance of automated microfluidics-based EGFR mutation detection and its significance in clinical diagnostic settings. Formalin-fixed, paraffin-embedded (FFPE) samples from NSCLC patients (n = 174) were included in a two-phase study. Phase I: Validation of the platform by comparing the results with conventional real-time PCR and next-generation sequencing (NGS) platform. Phase II: EGFR mutation detection on microfluidics-based platform as part of routine diagnostics workup. The microfluidics-based platform demonstrates 96.5% and 89.2% concordance with conventional real-time PCR and NGS, respectively. The system efficiently detects mutations across the EGFR gene with 88.23% sensitivity and 100% specificity. Out of 144 samples analysed in phase II, the platform generated valid results in 94% with mutation detected in 41% of samples. This microfluidics-based platform can detect as low as 5% mutant allele fractions from the FFPE samples. Therefore the microfluidics-based platform is a rapid, complete walkaway, with minimum tissue requirement (two sections of 5 µ thickness) and technical skill requirement. The method can detect clinically actionable EGFR mutations efficiently and can be considered a reliable diagnostic platform in resource-limited settings. From receiving samples to reporting the results this platform provides accurate data without much manual intervention. The study helped to devise an algorithm that emphasizes effective screening of the NSCLC cases for EGFR mutations with varying tumour content. Thus it helps in triaging the cases judiciously before proceeding with multigene testing.

Automatic Breathing Pattern Analysis from Reading-Speech Signals.

As the speech production mechanism is related to the breathing process, speech signals and breathing patterns impact each other. Breathing patterns are the physiological signals which help in understanding the psychological, physiological and cognitive states of an individual. Capturing such patterns relies on the availability of equipment such as respiratory belts, which are costly and uncomfortable to wear for long duration. In this paper, we attempt to extract the breathing patterns from speech signals, which are easily available and can be recorded using a smartphone's microphone. In the presented work, simultaneous speech and breath signals are captured from 100 Indians of the age group 20 to 25 years while they read a phonetically balanced passage in English language. We have identified five distinct breathing templates; following two broad speech-breath categories, exhibited by the speakers while they read the same passage. For one of the two categories, the time domain features with regression network can extract the breathing patterns from speech with a Pearson correlation coefficient of 0.70. By computational modelling, we distinguish these two breathing categories from speech with a classification accuracy of 79%.

Deep Modelling Strategies for Human Confidence Classification using Audio-visual Data.

Human behavior expressions such as of confidence are time-varying entities. Both vocal and facial cues that convey the human confidence expressions keep varying throughout the duration of analysis. Although, the cues from these two modalities are not always in synchrony, they impact each other and the fused outcome as well. In this paper, we present a deep fusion technique to combine the two modalities and derive a single outcome to infer human confidence. Fused outcome improves the classification performance by capturing the temporal information from both the modalities. The analysis of time-varying nature of expressions in the conversations captured in an interview setup is also presented. We collected data from 51 speakers who participated in interview sessions. The average area under the curve (AUC) of uni-modal models using speech and facial expressions is 70.6% and 69.4%, respectively, for classifying confident videos from non-confident ones in 5-fold cross-validation analysis. Our deep fusion model improves the performance giving an average AUC of 76.8%.

Mature Teratoma with Somatic-Type Malignancy: An Entity of Unacquaintance-A Case Report.

Primary intracranial teratomas are nongerminomatous germ cell tumors. They are infrequent lesions along the craniospinal axis, with their malignant transformation extremely uncommon. A 50-year-old-male patient presented with one episode of generalized tonic-clonic seizure (GTCS), without any neurological deficit. Radiological imaging revealed a large lesion in the pineal region. He underwent gross total excision of the lesion. Histopathological examination was representative of teratoma with adenocarcinomatous malignant transformation. He underwent adjuvant radiation therapy and had an excellent clinical outcome. The present case highlights the rarity of malignant transformation of the primary intracranial mature teratoma.

Targeted molecular profiling of solid tumours-Indian tertiary cancer centre experience.

PURPOSE: Molecular Profiling of solid tumours is extensively used for prognostic, theranostic, and risk prediction. Next generation sequencing (NGS) has emerged as powerful method for molecular profiling. The present study was performed to identify molecular alterations present in solid tumours in Indian tertiary cancer centre. METHODS: Study included 1140 formalin Fixed paraffin embedded samples. NGS was performed using two targeted gene panels viz. Ampliseq Focus panel and Sophia Solid Tumor Plus Solution. Data was analyzed using Illumina's Local Run Manager and SOPHiA DDM software. Variant interpretation and annotations were done as per AMP/ACMG guidelines. RESULTS: Total 896 cases were subjected to NGS after excluding cases with suboptimal nucleic acid quality/quantity. DNA alterations were detected in 64.9% and RNA fusions in 6.9% cases. Among detected variants, 86.7% were clinically relevant aberrations. Mutation frequency among different solid tumours was 70.8%, 67.4%, 64.4% in non-small cell lung (NSCLC), lung squamous cell carcinomas and head neck tumours respectively. EGFR, KRAS, BRAF, ALK and ROS1were commonly altered in NSCLC. Gastrointestinal tumours showed mutations in 63.6% with predominant alterations in pancreatic (88.2%), GIST (87.5%), colorectal (78.7%), cholangiocarcinoma (52.9%), neuroendocrine (45.5%), gall bladder (36.7%) and gastric adenocarcinomas (16.7%). The key genes affected were KRAS, NRAS, BRAF and PIK3CA. NGS evaluation identified co-occurring alterations in 37.7% cases otherwise missed by conventional assays. Resistance mutations were detected in progressive lung tumours (39.5%) against EGFR TKIs and ALK/ROS inhibitors. CONCLUSION: This is the largest Indian study on molecular profiling of solid tumours providing extensive information about mutational signatures using NGS.

AI-Based human audio processing for COVID-19: A comprehensive overview.

The Coronavirus (COVID-19) pandemic impelled several research efforts, from collecting COVID-19 patients' data to screening them for virus detection. Some COVID-19 symptoms are related to the functioning of the respiratory system that influences speech production; this suggests research on identifying markers of COVID-19 in speech and other human generated audio signals. In this article, we give an overview of research on human audio signals using 'Artificial Intelligence' techniques to screen, diagnose, monitor, and spread the awareness about COVID-19. This overview will be useful for developing automated systems that can help in the context of COVID-19, using non-obtrusive and easy to use bio-signals conveyed in human non-speech and speech audio productions.

COVID-19 Biomarkers in Speech: On Source and Filter Components.

This paper analyses the source of excitation and vocal tract influenced filter components to identify the biomarkers of COVID-19 in the human speech signal. The source-filter separated components of cough and breathing sounds collected from healthy and COVID-19 positive subjects are also analyzed. The source-filter separation techniques using cepstral, and phase domain approaches are compared and validated by using them in a neural network for the detection of COVID-19 positive subjects. A comparative analysis of the performance exhibited by vowels, cough, and breathing sounds is also presented. We use the public Coswara database for the reproducibility of our findings.

Remote Reporting from Home for Primary Diagnosis in Surgical Pathology: A Tertiary Oncology Center Experience during the COVID-19 Pandemic.

BACKGROUND: The COVID-19 pandemic accelerated the widespread adoption of digital pathology (DP) for primary diagnosis in surgical pathology. This paradigm shift is likely to influence how we function routinely in the postpandemic era. We present learnings from early adoption of DP for a live digital sign-out from home in a risk-mitigated environment. MATERIALS AND METHODS: We aimed to validate DP for remote reporting from home in a real-time environment and evaluate the parameters influencing the efficiency of a digital workflow. Eighteen pathologists prospectively validated DP for remote use on 567 biopsy cases including 616 individual parts from 7 subspecialties over a duration from March 21, 2020, to June 30, 2020. The slides were digitized using Roche Ventana DP200 whole-slide scanner and reported from respective homes in a risk-mitigated environment. RESULTS: Following re-review of glass slides, there was no major discordance and 1.2% (n = 7/567) minor discordance. The deferral rate was 4.5%. All pathologists reported from their respective homes from laptops with an average network speed of 20 megabits per second. CONCLUSION: We successfully validated and adopted a digital workflow for remote reporting with available resources and were able to provide our patients, an undisrupted access to subspecialty expertise during these unprecedented times.

Primary intracranial Ewing sarcoma/ peripheral primitive neuroectodermal tumor, an entity of unacquaintance: a series of 8 cases.

PURPOSE: The purpose is to highlight the primary intracranial (meningeal-based) occurrence of Ewing sarcoma/primitive neuroectodermal tumor (ES/PNET). METHODS: This report is a collation of clinicopathological features of eight cases of molecularly and clinicoradiologically confirmed primary (non-metastatic) intracranial (non-osseous) meningeal ES/PNET. RESULTS: The age range was 1 to 33 years with a median age of 9 years. Male to female ratio was 0.6:1. All patients were diagnosed on the debulking surgical material (gross total resection, 2 cases; subtotal resection, 6 cases) and showed primitive embryonal histomorphology with diffuse membranous CD99 immunoexpression and EWSR1 gene rearrangement by fluorescence in situ hybridization. Seven of them showed a typical FISH pattern of split signals with break-apart probe, while one showed an unusual signal pattern of loss of green signals. EFT-2001 adjuvant protocol was followed along with focal radiotherapy (RT) in all cases (except case 8, full course of chemotherapy could not be completed). Two cases had local recurrence-one of them died of disease recurrence before the administration of further treatment. CONCLUSION: This series adds non-osseous intracranial site to the list of uncommon sites of occurrence for ES/PNET and more importantly emphasizes the need to be considered in a differential list of primary intracranial primitive embryonal tumors before embarking as primary central nervous system (CNS) embryonal tumor, NOS.

Detecting emotional valence using time-domain analysis of speech signals.

Mental health is a growing concern and its problems range from inability to cope with day-to-day stress to severe conditions like depression. Ability to detect these symptoms heavily relies on accurate measurements of emotion and its components, such as emotional valence comprising of positive, negative and neutral affect. Speech as a bio-signal to measure valence is interesting because of the ubiquity of smartphones that can easily record and process speech signals. Speech-based emotion detection uses a broad spectrum of features derived from audio samples including pitch, energy, Mel Frequency Cepstral Coefficients (MFCCs), Linear Predictive Cepstral Coefficients, Log frequency power coefficients, spectrograms and so on. Despite the array of features and classifiers, detecting valence from speech alone remains a challenge. Further, the algorithms for extracting some of these features are computeintensive. This becomes a problem particularly in smartphone applications where the algorithms have to be executed on the device itself. We propose a novel time-domain feature that not only improves the valence detection accuracy, but also saves 10% of the computational cost of extraction as compared to that of MFCCs. A Random Forest Regressor operating on the proposed feature-set detects speaker-independent valence on a non-acted database with 70% accuracy. The algorithm also achieves 100% accuracy when tested with the acted speech database, Emo-DB.

Comparing Manual and Machine Annotations of Emotions in Non-acted Speech.

Psychological well-being at the workplace has increased the demand for detecting emotions with higher accuracies. Speech, one of the most non-obtrusive modes of capturing emotions at the workplace, is still in need of robust emotion annotation mechanisms for non-acted speech corpora. In this paper, we extend our experiments on our non-acted speech database in two ways. First, we report how participants themselves perceive the emotion in their voice after a long gap of about six months, and how a third person, who has not heard the clips earlier, perceives the emotion in the same utterances. Both annotators also rated the intensity of the emotion. They agreed better in neutral (84%) and negative clips (74%) than in positive ones (38%). Second, we restrict our attention to those samples that had agreement and show that the classification accuracy of 80% by machine learning, an improvement of 7% over the state-of-the-art results for speakerdependent classification. This result suggests that the high-level perception of emotion does translate to the low-level features of speech. Further analysis shows that the silently expressed positive and negative emotions are often misinterpreted as neutral. For the speaker-independent test set, we report an overall accuracy of 61%.