IC STORIES
Intern Story #8: Sanchari’s Summer Research Internship at IIT Delhi
Sanchari Saha is currently a final year undergraduate student of the Department of Computer Science and Technology at Indian Institute of Engineering Science and Technology (IIEST), Shibpur.
I am an explorer by choice — academically passionate and innately curious. I am obsessed with staying organized and I believe in determination, sincerity and persistency. My interests include learning new programming languages and reading books.
My love for Machine Learning began in my initial college years. I had to do a mini project on the performance comparison of various clustering algorithms using different datasets. At this point, I got hooked and wanted to go deeper. I was driven by basic curiosity — what is AI and “Machine Learning” exactly? What can it do? So I did some reading and video-watching and got to know the basics. I also finally understood what some of the key terms mean — like label, features, example, model, training, inference. It felt so exciting! So I wanted to go to the next level.
In my second year, I got the opportunity to undertake a Machine Learning project under one of the professors of my college. The topic — CNN Based Approach for Post-Disaster Damage Assessment was equally challenging and engrossing. I am still a novice and learning every day since AI has opened up a new universe with vast possibilities.
IIT Delhi has instituted a prestigious Summer Fellowship Research Programme (SFRP-2020) for the UG/PG engineering students of approved TEQIP-III engineering college/ institutions to interact and work with IIT Delhi faculty and get exposure to the equipment and lab facilities associated with the faculty. I came to know about this opportunity from my Department Head. The applications begin in the months of Feb-March.
One has to fill in the application provided in their website with all the details and the names of professors whose projects seem appealing to you, get it forwarded by the Head of the institution and send it to their office via post along with your resume. Usually, the internship takes place in person during the summer break from May to July. However, due to the global pandemic, I was very anxious regarding the Fellowship Programme. To my disbelief, I received the mail announcing my selection in June.
IIT Delhi indeed did a credible job conducting the internship in online mode. However, at that time I was already halfway through my industry internship at CESC Limited. My mentor generously agreed to let me start at a later date in July. The duration of the internship was 6 weeks.
I think having a decent CGPA, a proposed project statement and reputation of your parent institute always helps. Having a prior research experience is always an edge although it is not asked in the application form.
My guide Dr. Anup Singh is known for his contribution in the field of Biomedical Engineering. My work at IITD was to find ways for the Automatic Detection of tumour tissues in MRI images using Deep Learning. This was a great topic to work with since the early diagnosis of brain tumours plays an important role in improving treatment possibilities and increases the survival rate of the patients.
Manual segmentation of the brain tumours for cancer diagnosis, from a large amount of MRI images generated in clinical routine, is a difficult and time-consuming task. There is a need for automatic brain tumour image segmentation. With a surge in the brain related ailments in the world, every year over 2,500 of the Indian children suffer from medulloblastoma, a pediatric malignant primary brain tumour which spreads through the cerebrospinal fluid (CSF) and frequently metastasizes to different locations along the surface of the brain and spinal cord, doctors have said. According to them, in India, every year 40,000–50,000 persons are diagnosed with brain tumours. Of these 20 per cent are children. Until a year ago, the figure was only somewhere around 5 per cent. The doctors said that if the cases are detected early, then 90 per cent of the tumour cases are curable, provided the treatment protocol is followed correctly. Automatic segmentation of gliomas is a very challenging problem. Tumour-bearing brain MRI data is a 3D data where tumour shapes, size and location can vary greatly from patient to patient.
The dataset used was BRATS data and the model was U-Net architecture. We were able to successfully perform segmentation of the MRI scans.
This experience has added a lot of value to my knowledge and learning. Although the internship was a remote one, my guide was extremely motivating, flexible and patient throughout the process and I would in future love to go there and experience the work culture closely. For the 2 whole months, you will be only interacting with your guide and your lab-mate. But believe me, these people are great sources of knowledge and you can extract information comparable to that gained from field trips and lecture series.
My advice would be to carefully choose the research topic such that you have prior experience in that field which will enhance your chances of selection and let you shine among other applicants. Also, while sending the documents by post, be assured that all the formalities are properly done. And finally, do not lose hope. Keep working hard and a chance might come soon. Once you get it, do not let the opportunity go in vain. Do your research and ask for help whenever required. Moreover, try identifying what you are passionate about at the earliest and make it shine in your resume.
Loved reading Sanchari’s story? Show some love by clapping 👏 on the article! (did you know you can clap up to 50 times on a Medium blog?)
Have a story to share with 2000+ readers? Feel free to reach out to us.
You may also want to read
Support our work if you like what you read!
We’ll see you in the next story! Ciao :)
