Try : Insurtech, Application Development










Dev Ops(2)

Enterprise Solution(20)




AI in Insurance(26)


Product Innovation(34)


Augmented Reality(7)

Customer Journey(7)


User Experience(21)

Artificial Intelligence(95)



Cognitive Computing(7)

Computer Vision(6)

Data Science(14)


Intelligent Automation(25)

Machine Learning(43)

Natural Language Processing(10)




Telehealth Care(1)

HealthTech 101: How are Healthcare Technologies Reinventing Patient Care

4 minutes, 58 seconds read

Technological advancements and innovations are disrupting the healthcare industry. Smart health monitoring systems, apps, wearables and handheld devices are already in use. The prevailing Covid-19 pandemic has created an urgency to adopt digital. Healthcare technologies will cover many more conditions than before. Dr. John Halamka, President, Mayo Clinic Platform expects more than 60% of healthcare services to go virtual

This revolution in healthcare is not discretionary. This is the need of time. Currently, segregating meaningful data collected through various sources like medical records, wearables, apps, etc. is a challenge. But very soon, HealthTech will evolve across the globe. With Cloud, AI and advanced data analytics, patients and healthcare institutions will be able to access and utilize the right information in a fraction of seconds.

Let’s delve deeper into the new healthcare technologies that will disrupt patient care.

1. Telehealth

Telehealth corresponds to the accessibility of health services and information over the internet and telecommunication. Telehealth care allows remote or long-distance patient care through clinician contact, consultations, reminders, monitoring, and remote admissions. Simply put, telehealth care is the virtualization of most of the physical interactions between doctors and patients. 

Today, HealthTech underpins telehealth, as it enables robotic surgeries through remote access, physical therapy via remote monitoring instruments, home monitoring and live feeds, and video telephony. 

Recent advancements in AI and cloud-based technologies are enhancing remote healthcare experiences for patients. Solutions like chatbots, voice interfaces, and augmented reality are making digital experiences more intuitive for users.

Advancements in TeleHealth

2. Interoperability

To deliver informed and better care, healthcare organizations need to access patient health information over a distributed network. However, due to prevailing privacy regulations and lack of standardization in healthcare institutions, necessary information is still not available when required. That’s why interoperability has become a crucial aspect of HealthTech. 

Interoperability is the ability to exchange, interpret, use, and annotate patients’ health information including medical reports, images (X-rays, CT Scans, Radiographs, etc.) and treatment information through secure communication channels.

Health data standardization is necessary to ensure interoperability. So far, many different standards development organizations (SDOs) create, update, and maintain health data standards. For example, the Interoperability Standards Advisory (ISA) is one of the institutions that define interoperability standards and implementation specifications for the industry to fulfill specific clinical health IT interoperability needs. DICOM (Digital Imaging and Communications in Medicine) is one of the methods of medical image sharing. Using the DICOM system, health management professionals, physicians, and radiologists access medical images in a secure distributed environment.

[Related: Medical Image Management: DICOM Images Sharing Process]

However, to create an ecosystem of connected healthcare services, information needs to be available on the cloud and in a uniform format. There are three levels of interoperability:

  1. Foundational: Here, one system can share information with the other. The receiving system cannot interpret the information but can acknowledge the receipt.
  2. Structural: Here, the receiving system can interpret and use the information but cannot modify it.
  3. Semantic: Here, both the sender and receiver can interpret, use, and annotate the information. Semantic interoperability is the most desirable system in today’s time.

Interoperability across healthcare service providers can also reduce the time and cost of lab tests. For instance, many health checkups are valid for about a year. In case of emergencies, instead of advising patients tests, medical professionals can access previous test information and start procedures — reducing the overall treatment time.

3. Biomedical Computing

Biomedical computing is the application of computer science in medicine. It involves medical data management, medical imaging systems, developing advanced user interfaces for medical professionals, remote monitoring systems, medical diagnosis, scientific visualizations, and other computer-aided medical solutions.

The advanced application of biomedical computing involves using machine learning models for cancer detection and grading, predictive biomarkers and accelerating drug discovery processes. For example, Seg3D, a volume segmentation & processing tool allows segmentation, contouring to plan complex surgeries.

Seg3D - biomedical computing software

4. Health Forecasting

The right information is important for delivering care, products, and services to people in need. Today, many devices generate health data — home assistants, fitness bands, health and sleep trackers, diabetes monitors, and other ailment specific apps. However, predicting a condition and preparing for it requires reliable data and appropriate analytical tools. 

Extreme events test the efficiency of a healthcare system. Not all traditional techniques (e.g. analytics models that rely on historical data) can be applied to forecasting future conditions. The HealthTech systems call for probabilistic health forecasting methods to prepare institutions with information, finance, resources, drugs, equipment, and staff to serve any unforeseen event with the least possible lag.

The Future of Healthcare Technologies

Technologies like Augmented Reality, Virtual Reality, AI, Machine Learning will play a crucial role in transforming patient experience as well as augmenting skills and education of future doctors. For example, Cleveland Clinic at Case Western Reserve University is already using AR to train human anatomy and surgery through 3D human models.

HealthTech in India will soon control patient care over traditional OPD services. Although critical medical surgeries will still require the dexterity of medical professionals, patient support and routine consultations will be accomplished through telehealth services. This will also make health services available in remote areas where setting up and managing a full-fledged hospital facility is not feasible. 

To know about how healthcare industry is bringing hospitals to a customer’s doorstep, watch our webinar on Digital Health Beyond COVID-19.

Mantra Labs has been helping diagnostic and healthcare organizations like Manipal Hospitals, Suraksha Diagnostics in developing holistic patient management systems. We’ve also helped healthcare technology firms like PathomIQ in developing machine learning models for AI-based cancer detection segmentation and classification.

For your specific requirement, please feel free to write to us at hello@mantralabsglobal.com

Common FAQs

What is HealthTech?

HealthTech or Healthcare Technology is the application of knowledge and skills to solve a health problem and improve quality of life. It involves devices, medicines, vaccines, procedures and systems. WHO.

What is Telehealth?

Telehealth is making healthcare services and information available to the public through the internet and telecommunications. It involves online or video consultations, remote monitoring, reminders to take medicine, remote mental health therapy, patient support, SOS alerts and more.

What is interoperability in healthcare?

Interoperability corresponds to healthcare systems working together irrespective of geographical location. For example, medical images sharing via DICOM; guided permission to share patient data across clinics, labs, hospitals, and pharmacies.


Knowledge thats worth delivered in your inbox

Tabular Data Extraction from Invoice Documents

5 minutes, 12 seconds read

The task of extracting information from tables is a long-running problem statement in the world of machine learning and image processing. Although the latest accomplishments in the field of deep learning have seen a lot of success, tabular data extraction still remains a challenge due to the vast amount of ways in which tables are represented both visually and structurally. Below are some of the examples: 

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Invoice Documents

Many companies process their bills in the form of invoices which contain tables that hold information about the items along with their prices and quantities. This information is generally required to be stored in databases while these invoices get processed.

Traditionally, this information is required to be hand filled into a database software however, this approach has some drawbacks:

1. The whole process is time consuming.

2. Certain errors might get induced during the data entry process.

3. Extra cost of manual data entry.

 An invoice automation system can be deployed to address these shortcomings. The idea is to upload the invoice document and the system will read and generate the tabular information in the digital format making the whole process faster and more cost-effective for companies.

Fig. 6

Fig. 6 shows a sample invoice that contains some regular invoice details such as Invoice No, Invoice Date, Company details, and two tables holding transaction information. Now, our goal is to extract the information present in the two tables.

Tabular Information

The problem of extracting tables from invoices can be condensed into 2 main subtasks.

1. Table Detection

2. Tabular Structure Extraction.

 What is Table Detection?

 Table Detection is the process of identifying and locating tables that are present in a document, usually an image. There are multiple ways to detect tables in an image. Some of the approaches make use of image processing toolkits like OpenCV while some of the other approaches use statistical models on features extracted from the documents such as Text Position and Text Characteristics. Recently more deep learning approaches have been used to detect tables using trained neural networks similar to the ones used in Object Detection.

What is Table Structure Extraction?

Table Structure Extraction is the process of extracting the tabular information once the boundaries of the table are detected through Table Detection. The information within the rows and columns is then extracted and transferred to the desired format, usually CSV or Excel file.

Table Detection using Faster RCNN

Faster RCNN is a neural network model that comes from the RCNN family. It is the successor of Fast RCNN created by Ross Girshick in 2015. The name Faster RCNN is to signify an improvement over the previous model both in terms of training speed and detection speed. 

To read more about the model framework, one can access the paper Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

 There are many other object detection model architectures that are available for use today. Each model comes with certain advantages and disadvantages in terms of prediction accuracy, model parameter size, inference speed, etc.

For the task of detecting tables in invoice documents, we will select the Faster RCNN model with FPN(Feature Pyramid Network) as a feature extraction network. The model is pre-trained on the ImageNet corpus using ResNET 101 architecture. The ImageNet corpus is a public dataset that consists of more than 20,000 image categories of everyday objects.  We will therefore make use of a Pytorch framework to train and test the model.

The above mentioned model gives us a fast inference time and a high Mean Average Precision. It is preferred for cases where a quick real time detection is desired.

First, the model is to be trained using public datasets for Table Detection such as Marmot and UNLV datasets. Next, we further fine-tune the model with our custom labeled dataset. For the purpose of labeling, we will follow the COCO annotation format.

Once trained, the model displayed an accuracy close to 86% on our custom dataset. There are certain scenarios where the model fails to locate the tables such as cases containing watermarks and/or overlapping texts. Tables without borders are also missed in a few instances. However, the model has shown its ability to learn from examples and detect tables in multiple different invoice documents. 

Fig. 7

After running inference on the sample invoice from Fig 6, we can see two table boundaries being detected by the model in Fig 7. The first table gets detected with 100% accuracy and the second table is detected with 99% accuracy.

Table Structure Extraction

Once the boundaries of the table are detected by the model, an OCR (Optical Character Reader) mechanism is used to extract the text within the boundaries. The text is then processed using the information that is part of a unique table.

We were able to extract the correct structure of the table, including its headers and line items using logics derived from the invoices. The difficulty of this process depends on the type of invoice format at hand.

There are multiple challenges that one may encounter while building an algorithm to extract structure. Some of them are:

  1. The span of some table columns may overlap making it difficult to determine the boundaries between columns.
  2. The fonts and sizes present within tables may vary from one table to another. The algorithm should be able to accomodate for this variation.
  3. The tables might get split into two pages and detecting the continuation of a table might be challenging.

Certain deep learning approaches have also been published recently to determine the structure of a table. However, training them on custom datasets still remains a challenge. 

Fig 8

The final result is then stored in a CSV file and can be edited or stored according to one’s convenience as shown in Fig 8 which displays the first table information.


The deep learning approach to extracting information from structured documents is a step in the right direction. With high accuracy and low running time, the systems can only learn to perform better with more data. The recent and upcoming advancements in computer vision approaches have made processes such as invoice automation significantly accessible and robust.

About the author:

Prateek Sethi is a Data Scientist working at Mantra Labs. His work involves leveraging Artificial Intelligence to create data-driven solutions. Apart from his work he takes a keen interest in football and exploring the outdoors.

Further Reading:


Knowledge thats worth delivered in your inbox

Loading More Posts ...
Go Top

May i help you?

bot shadow

Our Website is
Best Experienced on
Chrome & Safari

safari icon