SRM-AP All News
ALL News
- Detecting Breast cancer subtypes using an innovatory ensemble of SwinTs December 6, 2022
Breast cancer (BC) is one of the most common types of cancer among women with a high mortality rate. Histopathological analysis facilitates the detection and diagnosis of BC but is a highly time-consuming specialised task, dependent on the experience of the pathologists. Hence, there is a dire need for computer-assisted diagnosis (CAD) to relieve the workload on pathologists. Dr Sudhakar Tummala, Assistant Professor, Department of Electronics and Communication Engineering, has conducted breakthrough research on this domain in his paper titled BreaST-Net: Multi-Class Classification of Breast Cancer from Histopathological Images Using Ensemble of Swin Transformers published in the Q1 Journal Mathematics, having an Impact Factor of 2.6.
Abstract
Breast cancer (BC) is one of the deadly forms of cancer and a major cause of female mortality worldwide. The standard imaging procedures for screening BC involve mammography and ultrasonography. However, these imaging procedures cannot differentiate subtypes of benign and malignant cancers. Therefore, histopathology images could provide better sensitivity toward benign and malignant cancer subtypes. Recently, vision transformers are gaining attention in medical imaging due to their success in various computer vision tasks. Swin transformer (SwinT) is a variant of vision transformer that works on the concept of non-overlapping shifted windows and is a proven method for various vision detection tasks. Hence, in this study, we have investigated the ability of an ensemble of SwinTs for the 2- class classification of benign vs. malignant and 8-class classification of four benign and four malignant subtypes, using an openly available BreaKHis dataset containing 7909 histopathology images acquired at different zoom factors of 40×, 100×, 200× and 400×. The ensemble of SwinTs (including tiny, small, base, and large) demonstrated an average test accuracy of 96.0% for the 8-class and 99.6% for the 2-class classification, outperforming all the previous works. Hence, an ensemble of SwinTs could identify BC subtypes using histopathological images and may lead to pathologist relief.
A brief summary of the research in layperson’s terms
Breast cancer (BC) is the second deadliest cancer after lung cancer, causing morbidity and mortality worldwide in the women population. Its incidence may increase by more than 50% by the year 2030 in the United States. The non-invasive diagnostic procedures for BC involve a physical examination and imaging techniques such as mammography, ultrasonography and magnetic resonance imaging. However, the physical examination may not detect it early, and Imaging procedures offer low sensitivity for a more comprehensive assessment of cancerous regions and identification of cancer subtypes. Histopathological imaging via breast biopsy, even though minimally invasive, may provide accurate identification of the cancer subtype and precise localization of the lesion. However, this manual examination by the pathologist could be tiresome and prone to errors. Therefore, automated methods for BC subtype classification are warranted.
Deep learning has revolutionised many areas in the last decade, including healthcare for various tasks such as accurate disease diagnosis, prognosis, and robotic-assisted surgery. There were studies based on deep convolutional neural networks (CNN) for detecting BC using the aforementioned imaging procedures. However, CNNs exhibit inherent inductive bias and are variant to translation, rotation, and location of the object of interest in the image. Therefore, image augmentation is generally applied while training CNN models, although the data augmentation may not provide expected variations in the training set. Hence, self-attention based deep learning models that are more robust towards the orientation and location of an object of interest in the image are rapidly growing.
SwinTs are an improved version of earlier vision transformer (ViT) architecture and are hierarchical vision transformers using shifted windows that work based on self-attention. For efficient modelling, self-attention within local windows was proposed and computed, and to evenly partition the image, the windows are arranged in a non-overlapping manner. The window-based self-attention has linear complexity and is scalable. However, the modelling power of window-based self-attention is limited because it lacks connections across windows. Therefore, a shifted window partitioning approach that alternates between the partitioning configurations in consecutive Swin transformer blocks was proposed to allow cross-window connections while maintaining the efficient computation of non-overlapping windows. The shifted window scheme in Swin transformers offers increased efficiency by restricting self- attention computation to local windows that are non-overlapping while also facilitating a cross-window connection. Overall, the SwinT network’s performance was superior to that of the standard ViTs.
Therefore, the paper analyses the ability of an ensemble of Swin transformer models (BreaST-Net) for the automated multi-class classification of BC by investigating histopathological images. The work dealt with both benign and malignant subtypes. Further, the benign cancer subtypes include fibroadenoma, tubular adenoma, phyllodes tumour, and adenosis. Whereas the malignant subtypes contain ductal carcinoma, papillary carcinoma, lobular carcinoma, and mucinous carcinoma.
Social implications of the research
Dr Sudhaker Tummala explains that the computer-aided subtyping of breast cancer from histopathology images using an ensemble of fine-tuned SwinT models can be an alternative to manual diagnoses, thereby reducing the burden on clinical pathologists.
Collaborations
- Prof. Seifedine Kadry, Department of Applied Data Science, Noroff University College, Kristiansand, Norway
- Dr Jungeun Kim, Division of Computer Science, Department of Software, Kongju National University, Korea
In the future, Dr Tummala will advance his research to add explainability to the ensemble model predictions and also to develop models that can work on fewer data samples.
Continue reading → - Three international offers in Japan: Placement 2022 hits a new peak December 6, 2022
Japan boasts the third-largest economy in the world. Being an incredible destination for aspirants, Japan proffers limitless opportunities and a rewarding career. The International offers in Japan are the brand-new addition to the success saga of placement 2022 at SRM University-AP. Three students from the class of 2022 have been placed with the international firm PVP in Japan with a lucrative salary package of 45 LPA. Alex Martin Mason, Ravi Srihitha, and Sahitha Yalamanchili of the Department of Computer Science and Engineering and Electronics and Communication Engineering are making the institution proud with their academic rigour and industrial skillset.
Japan is well known for its concrete work ethic and fascinating culture. For students to be placed in Japan, more than just technical training, Japanese language proficiency and cultural knowledge are equally important. The Directorate of Corporate Relations and Career Services made sure to equip the students with intensive training in the Japanese language and culture. The international placement is also a commendable achievement for the team working exclusively on Japanese placements.
Continue reading → - Bioinspired GO/Au nanocomposite synthesis November 28, 2022
Nanocomposites are the heterogeneous materials that are produced by the mixtures of polymers with inorganic solids that are multi-phased with two or three dimensions of less than 100 nanometers (nm). Nanocomposites offer advanced technologies in enhancing several industrial sectors like automobile, construction, electronics and electrical, food packaging, and technology transfer, yet its sustainable and environment-friendly nature provides a great deal for mankind. Dr Imran Uddin, Post Doctoral fellow, Department of Physics, has published a paper titled “Bioinspired GO/Au nanocomposite synthesis: Characteristics and use as a high-performance dielectric material in nanoelectronics” in the South African Journal of Botany, having an impact factor of 3.11. The paper demonstrated that GO-based materials are better constituents for nanocomposite synthesis and facilitate in enhancing the performance of electrical devices and energy storage systems.
Abstract
A bioinspired method was used to synthesise a graphene oxide (GO) based noble metal (Au) nanocomposite (GO/Au nanocomposite) using chemically exfoliated graphene oxide as the base matrix and gold (Au) nanoparticles. GO’s structural properties and morphology and the GO/Au nanocomposite were determined using XRD, TEM, SEM, EDAX, FTIR, and TGA analysis. LCR analysis was used to characterise the electrical characteristics of GO dielectric features as a function of frequency. The dielectric permittivity and electrical conductivity of GO were very frequency-driven. The results demonstrated that GO has direct current and Correlated Barrier Hopping conductivity processes in the low and high-frequency bands. The dielectric constant of the GO/Au nanocomposite shows that the bioinspired approach includes organic macromolecules capable of modest GO reduction and so modifying the C/O ratio, resulting in an enhancement in the matrix’s dielectric characteristics. This work shows that GO-based materials can be used to scale up high-performance electronic devices, as well as electrical and energy storage systems.
Explanation of the research in layperson’s terms
Energy consumption has increased multifold over the past few years. With increased consumption, the need for energy production and storage has become a pressing priority in the current generation. Dr Imran Uddin’s work aims to propose an idea to synthesise a mixture of two energy-storing materials (gold and carbon) at room temperature. Keeping in view the mentioned aim, he has used plant seeds to create this energy-storing mixture, also known as dielectric material in scientific terms. Through various analyses, he has noticed that this material is able to store electric energy at a lower frequency than the parent material. The superiority of this material comes into play in that when it expires, it can be easily disposed of without creating pollution, which goes hand in hand with the ultimate aim to develop sustainable energy-storing devices.
Dr Imran Uddin has mentioned the practical implication of the groundbreaking research. Capacitors are electronic devices that store electric energy in the form of charges. When a capacitor is linked to a charging circuit, it can store electric energy and release that stored energy when attached to an external circuit (like cars, fans, nuclear weapons, etc.), allowing it to be used as a temporary battery. Moreover, the synthetic GO/Au nanocomposite has the potential to be used as a capacitor material in biomedical applications (defibrillators, blood gas analyzers, pacemakers, biomedicines, etc.), as well as other fields where non-toxicity is essential.
The future prospects of Dr Imran Uddin’s research view an ambitious plan to manufacture more materials at room temperature using the green synthesis root. He also intends to investigate the electrochemical characteristics of environmentally benign materials in the field of electrochemical energy storage, such as supercapacitors and batteries.
Collaborations
University of Pannonia, Hungary
Continue reading → - The war of drones: A workshop on the latest potent technology November 28, 2022
Drones are steadily evolving technology with a wide array of applications in various sectors that, over the next decade, will change in ways that are unimagined. The War of Drones, a workshop on drone technology organised by the Directorate of Entrepreneurship and Innovation, got off the ground on Monday, November 14, 2022. The three-day-long sessions were under the guidance of Sri Gopi Raja, CEO of Fopple Technology Pvt Ltd. Andra Pradesh. The workshop came to an end after the theory, assembling of drones, and the final drone flying sessions that lasted for three days.
“If someone wants to talk about Drones, they need to talk about Andhra Pradesh,” said Sri Gopi Raja as he addressed the students by highlighting the hand of the state in promoting and modifying the technology nationwide. He highlighted the amplifying relevance of drone technology in the field of agriculture by explaining the various pathbreaking methods and their benefits. He also hinted at the chances for launching a Drones Centre of Excellence at the university.
Honourable Vice Chancellor Prof Manoj K Arora and other dignitaries graced the workshop’s final day with their presence. About 110 students participated in the exciting and engaging workshop to advance their understanding of the latest and promising technology of drones. Students were fascinated by the idea of flying a drone by the end of the workshop. The sessions conferred on the various aspects and applications of drones and allied technologies. The experimental event allowed students to get insights into drone technology from industry experts. They were exposed to hand on assembling and operations of drones. Furthermore, the future and scope of the promising technology were also discussed during the workshop.
Continue reading → - Novel antenna-duplexer for off-body communication November 28, 2022
With the recent advancements in modern wireless body area network (WBAN) communication, the demand for compact low-profile wireless computing devices has witnessed a vast increase. Consequently, the antennas which play a critical role in this network are developed with different polarization in distinct frequency bands so as to maintain better reliability of communication links. Dr Divya Chaturvedi, Assistant Professor, Department of Electronics and Communication Engineering, has published a paper titled, “A Dual-Band Dual-Polarized SIW Cavity-Backed Antenna-Duplexer for Off-body Communication” as first author in the Q1 Journal AEJ – Alexandria Engineering Journal having an impact factor of 6.77. The paper discusses the self-duplexing antennas, offering two channels for concurrent transmission and reception, leading to a simple and compact transceiver.
Abstract
A novel dual-band, dual-polarized antenna-duplexer scheme is intended to be used for WLAN 802.11a and ISM band applications using Substrate Integrated Waveguide (SIW) Technology. The antenna consists of two planar SIW cavities of different dimensions where a smaller sized diamond- shaped cavity is inserted inside the larger rectangular cavity to share the common aperture area. The diamond-ring shaped slots are etched in each cavity for radiation. The larger diamond ring slot is excited with a microstrip feedline to operate at 5.2 GHz while the smaller slot is excited with a coaxial probe to operate at 5.8 GHz. The antenna produces linear polarization at 5.2 GHz (5.1–5.3 GHz) due to the merging of TE 110 and TE 120 cavity modes while circular polarization around 5.8 GHz due to orthogonally excited TM100 and TM010 modes (5.68–5.95 GHz). The slots are excited in an orthogonal fashion to maintain a better decoupling between the ports (i.e. –23 dB). The performance of the antenna has been verified in free space as well as in the vicinity of the human body. The antenna offers the gain of 6.2 dBi /6.6 dBi in free space and 5.8 dBi / 6.4 dBi on-body at lower-/ higher frequency-bands, respectively. Also, the specific absorption rate (SAR) is obtained < 0.245 W/Kg for 0.5 W input power averaged over 10 mW/g mass of the tissue. The proposed design is a low-profile, compact single-layered design, which is a suitable option for off-body communication.
Explanation of the research in layperson’s terms
- This antenna can operate in dual radio frequency bands at 5.2 GHz and 5.8 GHz respectively.
- The antenna can be used in the medical instrument to make it wire-free.
- The antenna is compact in size, thus can be accommodated in a small space.
- The antenna can operate simultaneously at both the frequency bands, thus at the same time it can help in forming links with another on-body antenna and makes the link with Wi-Fi.
- The antenna is validated in terms of Specific absorption rate, hence it is safe to use on the human body.
The paper further expounds on the social implication of this innovative research. Dr Chaturvedi explains that the antenna, being dual-band and dual-polarized, can function as a transceiver circuit. Due to different polarization, it can operate in both the frequency bands simultaneously without affecting the performance. In the first frequency band at 5.2 GHz, it can link with Wi-Fi and in the second frequency band at 5.8 GHz, it is able to communicate with antennas placed in other medical instruments which are used in the vicinity of the human body.
Collaborations
1. Dr Arvind Kumar, Assis. Professor, b Department of Electronics and Communication
Engineering, VNIT Nagpur, India2. Dr Ayman A Althuwayb, Department of Electrical Engineering, College of Engineering,
Continue reading →
Jouf University, Sakaka, Aljouf 72388, Saudi Arabia - Acing national-level innovation marathon November 23, 2022
Vishal and Akanksha, students of SRM University- AP, won the National level VOIS for Tech Innovation Marathon 2022, which began on October 14 in Pune. They received a cash prize of Rs.2 lakhs, along with certificates and mementoes. Vodafone India, Voice, and Connecting Dreams Foundation jointly organised the Technology Marathon-2022 competition to bring out the latent technological creativity among engineering students.
Five hundred sixty teams from all over the country participated in the competition. Third-year Computer Science Engineering students Vishal Kumar Singh and Akanksha Patil participated in the competition on behalf of SRM University- AP. Both showed excellent talent and bagged the first position in the three-stage project presentation, Q&A, and review competitions. The organisers rewarded them with Rs.2 lakh and other souvenirs.
The winners, Vishal and Akanksha, were felicitated by President Dr P Satyanarayanan, Vice Chancellor Prof Manoj K Arora, and Registrar Dr Prem Kumar of SRM University- AP on Tuesday.
Continue reading → - One World, Many Cultures, One Home November 23, 2022
International Students’ Day is a global celebration of the student community that takes place on November 17 every year. Universities observe this day as a non-political celebration of the multiculturalism of their international students. The Directorate of International Relations and Higher Studies at SRM University- AP celebrated multiculturalism, diversity, and traditions with students from more than 30 countries across the globe on International Students’ Day.
“You are not international students; you are students of SRM AP. Once you are students of SRM AP, there is no differentiation between Domestic and International students”, said Vice Chancellor Prof Manoj K Arora addressing the students. On the occasion, Prof. Arora launched the Annual Magazine and International Students Handbook prepared by the Directorate of International Relations and Higher Studies. Dr P Naga Swetha, Associate Director, International Relations and Higher Studies, highlighted the importance of celebrating diversity and promoting creativity through cultural events. “At SRM AP, diversity is an essential binding agent of the interdisciplinary approach to education, as well as to the greater life experience”, she added.
Students enthusiastically talked about the facilities, curriculum, and support they receive at SRM AP. “I have no words to express how well I am treated on campus”, said Sara, a Syrian student in MBA Programme. “This is a very welcoming place, and I have made the right decision by choosing SRM AP to study in India”, added Muskan from Nepal. Tanira from Srilanka expressed his happiness in witnessing a variety of cultural programmes that foster respect and open-mindedness for other cultures.
To mark this occasion, international students showcased their rich culture through music, folk dance performances, and by identifying themselves in the traditional attires of their native countries. The students also presented a Nukkad Natak emphasising the significance of ‘one world, many cultures, one home’.
Aiming for significant global impact, the Directorate of International Relations and Higher Studies at SRM University-AP encourages the spirit of curiosity in students and faculty for multidisciplinary collaborations, inbound and outbound exchanges, research, and outreach programmes. A centralised portal to access/share international opportunities, higher studies training and support for students was launched by Mr Surendra Tipparaju, Director-Data and Artificial Intelligence at Microsoft recently.
Continue reading → - Classification of brain tumours using fine tuned ensemble of ViTs November 11, 2022
Primary brain tumours make up less than 2% of cancers and statistically occur in around 250,000 people a year globally. Medical resonance imaging (MRI) plays a pivotal role in the diagnosis of brain tumours and advanced imaging techniques can precisely detect brain tumours. On this note, Dr Sudhakar Tummala, Assistant Professor, Department of Electronics and Computer Engineering, has published a paper titled, “Classification of Brain Tumour from Magnetic Resonance Imaging using Vision Transformers Ensembling” in the journal Current Oncology having an impact factor of 3.1. The paper highlights the pioneering breakthrough made in the development of vision transformers (ViT) in enhancing MRI for efficient classification of brain tumours, thus reducing the burden on radiologists.
Abstract of the paper
The automated classification of brain tumours plays an important role in supporting radiologists in decision making. Recently, vision transformer (ViT)-based deep neural network architectures have gained attention in the computer vision research domain owing to the tremendous success of transformer models in natural language processing. Hence, in this study, the ability of an ensemble of standard ViT models for the diagnosis of brain tumours from T1-weighted (T1w) magnetic resonance imaging (MRI) is investigated. Pretrained and fine tuned ViT models (B/16, B/32, L/16, and L/32) on ImageNet were adopted for the classification task. A brain tumour dataset from figshare, consisting of 3064 T1w contrast-enhanced (CE) MRI slices with meningiomas, gliomas, and pituitary tumours, was used for the cross-validation and testing of the ensemble ViT model’s ability to perform a three-class classification task. The best individual model was L/32, with an overall test accuracy of 98.2% at 384 × 384 resolution. The ensemble of all four ViT models demonstrated an overall testing accuracy of 98.7% at the same resolution, outperforming individual model’s ability at both resolutions and their ensemble at 224 × 224 resolution. In conclusion, an ensemble of ViT models could be deployed for the computer-aided diagnosis of brain tumours based on T1w CE MRI, leading to radiologist relief.
A brief summary of the research in layperson’s terms
Brain tumours (BTs) are characterised by the abnormal growth of neural and glial cells. BTs causes several medical conditions, including the loss of sensation, hearing and vision problems, headaches, nausea, and seizures. There exist several types of brain tumours, and the most prevalent cases include meningiomas (originate from the membrane surrounding the brain), which are non-cancerous; gliomas (start from glial cells and the spinal cord); and glioblastomas (grow from the brain), which are cancerous. Sometimes, cancer can spread from other parts of the body, which is called brain metastasis. A pituitary tumour is another type of brain tumour that develops in the pituitary gland in the brain, and this gland primarily regulates other glands in the body. Magnetic resonance imaging (MRI) is a versatile imaging method that enables one to noninvasively visualise inside the body, and is in extensive use in the field of neuroimaging.
There exist several structural MRI protocols to visualise inside the brain, but the prime modalities include T1-weighted (T1w), T2-weighted, and T1w contrast-enhanced (CE) MRI. BTs appear with altered pixel intensity contrasts in structural MRI images compared with neighbouring normal tissues, enabling clinical radiologists to diagnose them. Several previous studies have attempted to automatically classify brain tumours using MRI images, starting with traditional machine learning classifiers, such as support vector machines (SVMs), k-nearest-neighbour (kNN), and Random Forest, from hand-crafted features of MRI slices. With the rise of convolutional neural network (CNN) deep learning model architectures since 2012, in addition to emerging advanced computational resources, such as GPUs and TPUs, during the past decade, several methods have been proposed for the classification of brain tumours based on the finetuning of the existing state-of-the-art CNN models, such as AlexNet, VGG16, ResNets, Inception, DenseNets, and Xception, which had already been found to be successful for various computer vision tasks.
Despite the tremendous success of CNNs, they generally have inductive biases, i.e., the translation equivariance of the local receptive field. Due to these inductive biases, CNN models have issues when learning long-range information; moreover, data augmentation is generally required for CNNs to improve their performance due to their dependency on local pixel variations during learning.Therefore, in this work, the ability of pretrained and fine tuned ViT models, both individually and in an ensemble manner, is evaluated for the classification of meningiomas, gliomas, and pituitary tumours from T1w CE MRI at both 224 × 224 and 384 × 384 image resolutions.
Dr Sudhakar Tummala has mentioned the social implications of the research by expounding that the computer-aided diagnosis of brain tumours from T1w CE MRI using an ensemble of fine tuned ViT models can be an alternative to manual diagnoses, thereby reducing the burden on clinical radiologists. He also explains the future prospects of his research, which is to add explainability to the ensemble model predictions and to develop methods for precise contouring of tumour boundaries.
Details of Collaborations
Prof Seifedine Kadry, Department of Applied Data Science, Noroff University College, Kristiansand, Norway.
Dr Syed Ahmad Chan Bukhari, Division of Computer Science, Mathematics and Science, Collins College of Professional Studies, St. John’s University, New York, USA.
Continue reading → - Doctoral scholar secures visiting fellowship November 9, 2022
Exposure to international research opportunities promotes empirical learning at an impeccable level. International research ventures aid scholars to explore novel research avenues enabling a transformative progress for society through the field of science. The Department of Chemistry is glad to announce that Ms Jayasree K, PhD scholar, has been accepted for Short-Term Research Internship (STRI) for a period of six months from the Research Center of Environmental Medicine, Kaohsiung Medical University, Taiwan.
Ms Jayasree has been elevated in receiving the offer and delightfully keen on the new avenues she could explore through this opportunity. She is currently working in the field of surface-enhanced Raman spectroscopy (SERS). In this particular research area, her major research objective is the design and development of a novel SERS substrate for food and bioanalysis.
“My internship mentor, Prof. Vinoth Kumar, KMU University is an expert in mass spectroscopy and High-performance liquid chromatography (HPLC). Therefore, I have an option to hyphenate the Raman technique along with mass spectroscopy which leads Raman research to the next level for various applications”, commented Ms Jayasree on this incredible opportunity.
Her internship at Kaohsiung Medical University (KMU) is based on the motive of research on food and environmental toxicity which would provide guidance on her first research project in the field of food analysis.
She has offered her sincere gratitude to her supervisor, Dr Rajapandiyan JP, Department of Chemistry for his constant support and advice from the application process to proposal writing, experimental planning etc. She also thanked SRM University- AP in providing support through the process and extending travel allowance and guidance.
Ms Jayasree utilizes this great opportunity to explore and discover herself, developing both personally and professionally. Through this internship she hopes to learn new skills, expand her knowledge in the field of research and explore career options in Taiwan.
Continue reading → - The prevalence of digital divide and agrarian crisis in rural India November 7, 2022
Eminent Columnist P Sainath addressed the gathering of scientists and researchers from various parts of the country in the Public Lecture Telling the stories of rural Indians in the digital age: The People’s Archive of Rural India. The lecture was organised as a part of the 88th Annual Meeting of the Indian Academy of Sciences at SRM University-AP, Andhra Pradesh.
P Sainath talked about the People’s Archive of Rural India (PARI), which brings together science, technology, culture and literature. PARI is a free digital space wholly dedicated to rural India, publishing in 14 languages in India with a huge volunteer force of translators. Though rural India accounts for 69% of the total population of India, their representation in the frontier of national dailies are limited to a meagre total of 0.67 percent. P Sainath commented on this ostracization by calling out the tainted and prejudiced rationale of media houses on neglecting rural life as they offered no credible revenue for their media coverage.
Mr Sainath also talked about the content of his upcoming book The Last Heroes: Foot Soldiers of Indian Freedom expressing that, “It is a gigantic tragedy that this generation and the coming generation won’t be seeing our freedom fighters”. He further talked about the alarming status of India in the environmental performance index and global hunger index and the need to address the agrarian crisis and the growing digital divide in society. “Equitable distribution of opportunities paramount to the democratisation of digital content “, affirmed P Sainath as a concern about online education. IASc President Prof. Umesh Waghmare thanked Mr P Sainath for sensitising the scientific community about the pertinent issues around them.
Continue reading →