Research — MIT Media Lab

Association between COVID-19 Outcomes and Mask Mandates, Adherence, and Attitudes

We extend previous studies on the impact of masks on COVID-19 outcomes by investigating an unprecedented breadth and depth of health outc...

Archived

Conformable Decoders

Converting the patterns of nature and the human body into beneficial signals and energy

Artificial Intelligence and Machine Learning in Clinical Development: A Translational Perspective

Technical summary: Future of clinical development is on the verge of a major transformation due to convergence of large new digital data ...

Deep Learning to Develop and Analyze Computational Hematoxylin and Eosin Staining of Tissue Images for Digital Biopsies

Staining of tissues sections using chemical and biological dyes has been used for over a century for visualizing various tissue types and...

Automated End-to-End Deep Learning Framework for Classification and Tumor Localization from Native Non-stained Pathology Images

This study reports an end-to-end deep learning framework for virtual H&E staining, automatic classification, and localization of pros...

Automated end-to-end deep learning framework for classification and tumor localization from native nonstained pathology images

Akram Bayat, Connor Anderson and Pratik Shah. "Automated end-to-end deep learning framework for classification and tumor localization from native nonstained pathology images," Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 115960A (15 February 2021); doi: 10.1117/12.2582303

conformable Facial Code Extrapolation Sensor (cFaCES)

AbstractDevices that facilitate nonverbal communication typically require high computational loads or have rigid and bulky form factors&n...

A tailored, electronic textile conformable suit for large-scale spatiotemporal physiological sensing in vivo

The rapid advancement of electronic devices and fabrication technologies has further promoted the field of wearables and smart textiles. ...

Sensors woven into a shirt can monitor vital signs

Comfortable, form-fitting garments could be used to remotely track patients’ health.

MIT develops machine-washable sensors that embed in clothing for constant vital sign monitoring

Its potential here on Earth has much more widespread benefit potential, particularly in the era of COVID-19.

Post Research

Frequently Asked Questions: A tailored, electronic textile conformable suit for large-scale spatiotemporal physiological sensing in vivo

Decoding of Facial Strains via Conformable Piezoelectric Interfaces

Sun, T.*, Tasnim, F.*, McIntosh, R. T., Amiri, N., Solav, D., Anbarani, M. T., Sadat, S., Zhang, L., Gu, Y., Karami, M. A., Dagdeviren, C.†, “Decoding of Facial Strains via Conformable Piezoelectric Interfaces”, Nature Biomedical Engineering, 4, 954–972, 2020.

New surgery may enable better control of prosthetic limbs

Reconnecting muscle pairs during amputation gives patients more sensory feedback from the limb.

Self-Reconfigurable Micro-Implants

New technology for next-generation wireless + batteryless micro-implantsThese wireless batteryless micro-chips can reprogram themselves i...

Biomechatronics

Enhancing human physical capability

Essence Wearables: Biometric Olfactory Interfaces for Day and Night

Human-computer interaction (HCI) has traditionally focused on designing and investigating interfaces that provide explicit visual, audito...

Self-Learning AI Model Learns from Patient Data to Design Novel Clinical Trials

Technical summaryUnstructured learning problems without well-defined rewards are unsuitable for current reinforcement learning (RL) appro...

On-Face Olfactory Interfaces

We envision that a close-to-nose interface could be used as a complementary or alternative wearable method to nasal cannulas or mask...

Machine learning algorithms for classification of microcirculation images from septic and non-septic patients

Perikumar Javia, Rana A, Shapiro NI, Shah P. IEEE Xplore, Proceedings of 17th International Conference on Machine Learning and Applications (2018) (Conference acceptance rate: 14%). DOI: 10.1109/ICMLA.2018.00097

Computational histological staining and destaining of prostate core biopsy RGB images with generative adversarial neural networks

Aman Rana, Yauney G, Lowe A, Shah P. IEEE Xplore, Proceedings of 17th International Conference on Machine Learning and Applications (2018) (Conference acceptance rate: 14%). DOI: 10.1109/ICMLA.2018.00133

Helping Emergency Care Physicians Diagnose Sepsis and Bacterial Infections with Machine Learning and Vision

General overview:Sepsis, a life-threatening complication of bacterial infection, leads to millions of worldwide deaths requires significa...

AI Methods for Rapid Automated Staining and Destaining of Tissue Biopsies in Hospitals

General OverviewStaining of tissues sections using chemical and biological dyes has been used for over a century for visualizing various ...

Digital Clinical Trials with Novel Machine Learning and AI Architectures

Dr. Shah was an invited speaker and a contributor at The National Cancer Policy Forum developed workshop series at the The National Acade...

Doze: On-skin Scent Diffusion and Drug Delivery Patch

Doze is an IoT enabled platform for personalized scent diffusion and on-skin drug delivery. Leveraging a hydrogel technology, the Doze sy...

Democratizing prosthetic and diabetic care: A resilient model for healthcare delivery

We are engineering a better healthcare system for people with diabetes and limb loss such that we can physically bridge gaps to...

A wearable sensor to help ALS patients communicate

Researchers have designed a skin-like device that can measure small facial movements in patients who have lost the ability to speak.

Agonist-antagonist Myoneural Interface (AMI)

Humans can accurately sense the position, speed, and torque of their limbs, even with their eyes shut. This sense, known as proprioceptio...

Low-latency tracking of multiple permanent magnets

C. R. Taylor, H. G. Abramson, and H. M. Herr, “Low-Latency Tracking of Multiple Permanent Magnets,” IEEE Sensors Journal, pp. 1–11, 2019.

ORBIT (Olfactory Response Baseline Identification Test)

I am currently developing a new approach in conducting sensory examinations via the Olfactory Response Baseline Identification Test (O.R....

Molecular Machines

Engineering at the limits of complexity with molecular-scale parts

Gamma SENSE: Sensory Engaging Nebulised Scent Experience

The Gamma SENSE (Sensory Engaging Nebulised Scent Experience) is a pioneering instrumental addition to the gamma instrument series. The d...

Center for Extreme Bionics

Designer molecular mops: Water-soluble cytokine receptors fused with Fc domain of IgG may be therapeutic for cytokine storms

In April 2019, Shuguang Zhang's lab started to use the QTY code to design a class of water-soluble cytokine receptors, including interfer...

QTY code designs for water-soluble beta-barrel transmembrane proteins

In collaboration with Prof. Tao Fei’s lab (Shanghai Jiaotong University, China)In addition to a large number of membrane proteins that co...

QTY CXCR4 becomes more hydrophilic and retains cell signaling activity

In collaboration with Prof. Horst Vogel and Dr. Horst Pick (EPFL, Lausanne, Switzerland).G protein-coupled receptors (GPCRs) are vital fo...

The QTY code: A simple tool for protein design

Structure and function studies of membrane proteins, particularly G protein-coupled receptors (GPCRs) and multipass transmembrane protein...

Proteins may halt the severe cytokine storms seen in Covid-19 patients

Team designs antibody-like receptor proteins that can bind to cytokines, as possible strategy for treating coronavirus and other infections.

Water-soluble transmembrane protein receptors with exchangeable and tunable ligand affinity

There are 20 chemokine receptors that bind their respective chemokines. It is not currently understood how these structurally similar rec...

Archived

Ethics

Ethics Initiative

Beyond Bias: Contextualizing “ethical AI” within the history of exploitation and innovation in medical research

"It’s time for us to move beyond 'bias' as the anchor point for our efforts to build ethical and fair algorithms."

Machine learning shows no difference in angina symptoms between men and women

Finding could help overturn the prevailing notion that men and women experience angina differently.

Lensing: Cardiolinguistics for Atypical Angina

Conversations between two individuals—whether between doctor and patient, mental health therapist and client, or between two people roman...

Archived

Deep Reinforcement Learning for Pain Management

Opioid therapy is the cornerstone of management of pain in the ICU. However, opioids present numerous side effects and are highly addicti...

Archived