Dr Karuna Ramesh, views from a seasoned Pathologist

MBBS, DCP, MD, Ph.D, DML&E (Medical Law and Ethics) FICP

Years of experience:
Teaching 37 years
Service 37 years
Research 30 years
Administrative 30 years

Career Journey:

  • Research & Ethics committee chairperson – St. John’s Medical college ( Oct.2018 to date)
  • Pathologist at Rainbow children’s hospital – DNBE program (February 2019 to date)

Fields of Specialisation:

  • Haematology Anaemia, Thalassemia and Malignancies including myelodysplastic syndromes, Geriatric haematology, 
  • Blood bank, Medical ethics, Gynaec pathology, Medical education


As a head of pathology lab in your experience, what are your thoughts on SigTuple’s technology, Shonit, as a potential product in your lab?

“The product is good! Not only have I seen the demo now, but I’ve seen the product once when they were using at Humain at CARE diagnostics. The team was very comfortable handling the workflow. I saw  the performance of Shonit and it is quite good. One thing I felt is that this AI solution is totally dependent on morphology. But as a pathologist, I also interpret data with some clinical inputs. Hence apart from the AI diagnosis, we would also need to correlate with clinical inputs before diagnostic reports can be issued.”

As a product positioned to assist a pathologist, how confident are you with Shonit?

I have seen and done validations for Shonit in the past as well along with 50 slides we’re currently doing. So I’ve seen around 200 slides so far in various instances. I’m 85% comfortable and confident to allow Shonit to predict the patient results with accuracy, similar to auto approval procedure.

A small green rectangle to divide sections of the document

What would be the instances when you’d like to review an AI result such as from Shonit PBS?

As mentioned, the  15% in my 85% confidence can be built when I see more validation done using pediatric samples. Pediatric population’s normal range is totally different and certain aspects of the morphology is slightly different like nRBCs are part of the normal population, hence the apprehension. Also, the solution is still technician dependent on the smearing procedure. You will always find poor slides where bare nuclei or degenerated cells are seen. In such cases, I use my judgement and count upto 200 cells instead of the regular 100 to ensure accuracy in reporting, But with the case of Shonit, there is no such  judgement involved yet.

Since you’re a certified NABL auditor and head the ethics committee, how do you view AI based solutions like Shonit in terms of ethics and auditing? 

These are two different issues  and we’ll deal with it one by one. First auditing, they accept AI, without any issues. They accept and also look at the limitations when dealing with patient samples. For example, they will check if there is some kind of QC available. Next, if the report or values are only AI based, or if the QC is not available, then they would check the validation done for AI values against a reference and such reports would be checked once a month or bi weekly. In many places and abroad, though I have not seen personally, AI is already implemented and many reports are auto approved. 

Now from the ethics point of view, since this is a patient sample, privacy and confidentiality is key. In analysers, sensitive information is protected. But in AI, such information is a grey zone. Hence there is no easy answer to ethics when it comes to AI. There is a paper on this called “Ethics and AI” where such suggestions have been brought out and a panel of ethics committee members were asked to comment their views on this. 

*It was also clarified that Shonit PBS doesn’t have any such ethics issues since it operates every similar to a reference analyser. 

A small green rectangle to divide sections of the document

How do you think confidence can be built for an AI based product amongst pathologists and technicians?

Technicians are very comfortable with such products which automate their processes. Anything which is manual usually has a lot of errors in terms of transcription etc. Good technicians are used to such changes in the lab, for example Hemat analysers have undergone many changes over the years and people have always adopted better technology. Image based analysers like Shonit and flow cytometry based hemat analysers will inherently have some differences between their values since the methodology is different, but other than that, I don’t think adopting AI based solutions will have any problems. 

Technicians always understand limitations, for example we faced such issues when moving from manual DC and 3 part analyser (first versions of sysmex etc) and then eventually 5 part analysers came about. So until that came, 3 part analysers were used in conjunction with manual DC. So limitations are always understood. 

For Shonit, when 7 part readouts are given, it will have a good advantage over a 5 part analyser, when it performs and picks up IGs, Atypical cells and monocytes correctly. This has to be validated carefully. But the advantage of a 7 part analyser is in huge labs like St John’s which process 2000 samples a day. There patients with malignancies also come, hence the DC on these cells are very important. An accurate 7 part analyser will prove very valuable.

In terms of costs incurred in a lab, how do you see Shonit with AI 100 reduce costs? 

This can be looked at in two ways, from a personnel point of view, there is a change since the smearing and staining can be done by just two technicians in shift. But when you look at the cost of running an analyser, the charges are always calculated per cycle. The reagents and consumables need to be bought and are very expensive. Hence analysers are always used in rental models instead of buying them. So in that sense, Shonit PBS will prove to be cost effective since it doesn’t involve extra consumables, each for detecting WBC, RBC and platelet types. Here the analyser is the only investment. Hemoglobin I understand is still in R&D but it will be critical to have in the future, since a PS report alone doesn’t complete the package. For many patients, anemia detection becomes key in diagnosis.

A small green rectangle to divide sections of the document

What feedback would you give on Shonit when thinking about its implementation pan India? 

I think the major hurdle would be in handling belts with specific health problems. In the north eastern states, detecting Malarial parasites and quantifying hemoglobin is key. The regular analysers are able to flag malarial parasites in the form of a peak and such samples are then manually reviewed under a microscope. So Shonit’s ability to flag malarial parasites especially in malarial belts across the coastal region would be beneficial. 

A small green rectangle to divide sections of the document

What are your thoughts on the tele reporting feature which AI 100 with Shonit enables, especially during a pandemic scenario? 

Shonit that way is  a very well positioned product. Nowadays, only technicians go to the lab. Transfer of patient data happens through the backend channels connected to a doctors personal laptop. So routine reports can be approved without much of a problem but samples which need manual review, or which are dengue positive, (especially during Bangalore’s dengue season) become problematic. Such special cases need Tele review, because analyser results and manual DC don’t match well. So right now they just take pictures of the microscopic images and send via WhatsApp. But with Shonit there is a clear advantage in how this can be done hassle free.

A small green rectangle to divide sections of the document

While validating products like Shonit, what should validations extensively cover? 

As for regulatory and performance perspectives, the AI based solution should always be validated against a known standard. The frequency of these validations should be defined and the metrics should be established. Traceability and troubleshooting of data should be easy and clean. 

In terms of statistics, there is no specific requirement, correlation and RSQ is a very common way of clinical results evaluation, but it should be defined very clearly at the beginning of the validation. Like for example, CV for hemoglobin tests cannot be more than 0.5%, so such products have very low margins but for platelets a wider CV is accepted. 

A small green rectangle to divide sections of the document

Blog by Sigtuple

Problem Statement: Manual Microscopic review is an error-prone, repetitive, inefficient, and constraining task in any clinical laboratory. This is driving up the costs, inefficiencies of the entire laboratory.

How is Sigtuple solving it?

By using AI and Robotics, SigTuple is automating the error prone and inefficient manual microscopic review in clinical laboratories to drive improved patient outcomes, reduce healthcare costs and streamline laboratory operations

What is the Sigtuple’s Solution for the problem?

Our device, AI100, can cater requirements of both hematology and clinical pathology departments with virtue of its applications Shonit (Blood Morphology Analyser) and Shrava (Urine Morphology Analyser).

AI100 analyses morphology of Blood and Urine using Robotics, image processing and Artificial intelligence and gives accurate and reliable results which can be verified and approved by pathologists from anywhere in the world. This enables pathologist to

  1. Focus more on critical cases by reducing the manual work load of error prone, inefficient, repetitive and laborious manual microscopy
  2. Reduce TAT by approving the reports remotely especially during after work hours, Weekends, Holidays etc. 

AI100 is a table top device which only needs a power connection and a Wifi/LAN internet connection. The device does not require any consumable or waste management.

How does the analytical end-to-end workflow function using AI100 and its applications?

AI100 for Blood analysis:

All the Complete Blood Count investigations are run through any hematology analyser. About 15-20% of those investigations will be flagged for any reason like for blood cancer cases, platelet disorders, anemia cases, infections etc. Traditionally, lab technician will prepare a smear of the flagged sample, the smear will be handed over to pathologist and the smear will be reviewed under a microscopy by the pathologist to manually count and detect each and every type of WBCs, RBCs and platelets depending on the flag.

With AI100 in the workflow, Technicians will insert the prepared smear into AI100 for analysis. AI100, using its robotics, high resolution lens and image processing, will detect monolayer cells on the smear. Once the AI analyser captures the images, it will upload the images onto cloud for analysis. 

, which is our cloud based blood analyser application, will detect each and every type of WBCs, RBCs and Platelets and pre classifies them into their respective cell types. Once all the images have been analysed, Shonit will publish the results with all the findings along with images of each and every cell detected. Thus reducing the manual effort of the pathologist and thereby total turn-around time of the investigation. The pathologist can then review and approve the results of shonit in our web platform. As soon the pathologist approves a report, the approved report will be pushed to LIMS of the lab and subsequently to the patient.

AI100 for Urine analysis:

For all urine microscopy investigations, The lab technician will centrifuge the sample and traditionally, prepares a (leak-prone) wet mount. This wet mount will be handed over to the pathologist. Who will analyse the wet mount under the microscope manually. 

With AI100 in the workflow, the technician will use the centrifuged urine sample to prepare a leak proof cartridge specially made to restrict drift of the sample during the analysis. The cartridge is then placed in AI100 for analysis. AI100 then captures relevant images of the sample and uploads them onto cloud for analysis.

, which is our cloud based urine analyser application, will detect each and every type of abnormal cells like epithelial, pus, RBCs, crystals etc. and pre classifies them into predefined Buckets. Once all the images have been analysed, Shrava will publish the results with all the findings along with images of each and every cell detected. Thus reducing the manual effort of the pathologist and thereby total turn-around time of the investigation.The pathologist can then review and approve the results of shonit in our web platform. As soon the pathologist approves a report, the approved report will be pushed to LIMS of the lab and subsequently to the patient.

How do AI100 Applications work?

Our device, AI100, will cater requirements of both hematology and clinical pathology departments with virtue of its applications shonit and shrava respectively.

application is an Artificial Intelligence based on Machine Learning algorithms. This AI analyses blood morphology and identifies blood cells based on the shape, size of the cell and its nucleus. It is able to do that accurately because of the billions and billions of verified data uploaded into the AI.

Once the images of the blood smear are uploaded onto the cloud. AI, then,locates and identifies all the different cells and classifies them into buckets. It classifies WBCs into basophils, neutrophils etc., RBCs into microcytes, macrocytes, etc. and Platelets onto large platelets, plate clumps, etc.

Subsequently, AI produces a report based on the analysis and publishes it in our report reviewing platform. This platform can be accessed through any internet connected device like phone, pad, laptop and computer from anywhere in the world.

Once the pathologist goes through the result of classified cells, will go through them quickly and will be able to change any misclassified cell to its correct class, if necessary.

At this point, pathologists can also request another pathologist to take a look at the report for confirmation/collaboration on the report. As the report can be accessed from anywhere in the world, the second doctor need not be colocated with the first doctor or the AI100(Lab)

The analyser is an AI & ML machine, so, the more data it receives the more accurate it becomes. As the analyser solution is in the cloud, it can be updated with a flick of a finger. 

Shonit has been validated and has been clinically proven to be of the highest industry accuracy.

AI100 + Shonit solution is CE Certified.

application is our urine morphology analyser application based in the cloud. Once AI100 scans the urine sample kept in the device, the images will be uploaded on the cloud for Shrava to analyse the sample.

Shrava will detect all the particles in the sample and identify them and bucket them into different classes of abnormalities like RBCs, Pus cells etc.

Once the analysis of all the uploaded images is done, shrava will upload the results on a report reviewing/approving platform/solution for pathologists to review and approve the result.

Apart from these applications (Shonit and Shrava) we have many more applications to come, which can be performed using the same AI100. Some of upcoming the applications are:

  1. Universal Scanner (Scans any and every sample that can be viewed under a microscope).This feature can be used extensively for telepathology.
  2. Bone marrow analyser
  3. Body fluids analyser
  4. Semen analyser

What is the accuracy of AI100 applications?

In Medical diagnosis, test sensitivity is the ability of a test to correctly identify those with the disease (true positive rate), whereas test specificity is the ability of a test to correctly identify those without the disease (true negative rate).

Shonit accuracy in terms of sensitivity and specificity when compared to manual microscopy results is as follows:


Shrava accuracy in terms of sensitivity and specificity when compared to wet mount manual microscopy results is as follows:

RBCsPus CellsEpithelial cellsBacteriaCrystalsYeast

What went into developing these accurate AI applications?

  • 35 patent applications filed in India and internationally with 12 granted so far.
  • 28 publications in renowned medical and technical journals
  • 16 clinical trials, field trials and clinical studies performed with over 30,000 samples analysed in collaboration with industry’s prominent organizations like Apollo, Narayana hrudayalaya etc.
  • 50+ medical experts trained and validated our AI models

How converting a biological sample on a slide into a digital image helps compared to traditional Manual Microscopy? 

 Once the samples are converted into digital images

  1. The images can be stored forever for any future analysis in chronic cases as opposed to a limited time storage of Smears or wet mounts
  2. The images can be transported to anywhere in the world at, practically, zero cost as opposed to a transportation cost in sending Blood and urine samples to different locations/cities/countries with extra caution to preserve the sample.

How are images and reports shared with a health provider to validate & approve?

Once the images from the slide/cartridge are uploaded, based on its image processing,  the AI application will measure the size and shape of each cell. Then based on that data, AI will determine the type of the cell and bucket them into that class.

Then, once all the images are scanned, AI will generate reports with all types of cells pre-classified. 

These reports can be accessed by any authorized pathologist of the hospital from anywhere by logging in into our server using the credentials, just as easy as logging into your Lab Information system. These pre-classified reports can be approved as is or classification can be changed, wherever required, before approving the report.

How can we use AI100 with LIMS?

The AI100 can be interfaced with LIMS via APIs and support bi-directional communication. Information from a hematology analyser can be pushed from LIMS to AI100, so that pathologists will have all the necessary hematology information on the AI100 report review platform and once the pathologist approves the report, the AI100 results can be pushed to LIMS.

Features & Benefits of Using AI100

AI100 is one magical device with features and applications for multiple departments. 

  1. It can analyse blood using its Blood morphology analyser application called “Shonit”
  2. It can analyse urine using its urine analyser application called “Shrava”

There are multiple other applications in the pipeline which can analyse Semen, Body fluids etc.

Features of Shonit (Blood Analyser) and Shrava (Urine Analyser):

  1. Pre Classification of blood cells: A doctor takes about 5 mins to manually review a smear under microscope. Shonit will do the initial identification and classification and then a pathologist can review Shonit’s report in 1 minute. Thus Shonit will allow pathologists to work on more critical cases than spending time on mundane work.

Also for cases like leukopenia cases, Pathologists will have to spend hours to locate/detect and identify WBCs on the smear. With AI100, the TAT will remain the same for any case.

  1. Remote access to reports: Usually a lab has technicians working for 24Hrs in shifts and has only one pathologist or 2 pathologists covering 8/ 16 hours. If a CBC (hematology) analyser flags a sample just after a pathologist completed his/her shift or when a pathologist is away from office for some official work or on a weekend. The CBC report will be pending till the pathologist comes back to office. 

By virtue of remote access to the PBS reports, the pathologist can approve the report within minutes and reduce the TAT drastically and might save a person’s life in extreme cases.

Same is the case with Urine microscopy investigations

  1. Higher efficiency in detecting abnormal cells: During the manual microscopy, the pathologist usually identifies and counts 100 WBCs and stops the process (unless they are looking from some abnormality that was indicated by some other information). But the AI100 will go through the entire slide and will detect an abnormal cell even in some extreme cases of early symptoms. Especially in the case Leukopenia, Leukemia etc.
  1. AI100 increases collaboration between pathologists: by virtue of its remote access facility multiple doctors can collaborate with either on any special/ rare/ extreme cases without the need of co-locating with each other.
  2. Cloud data storage: As all the reports are stored in secure cloud storage. The past reports of any patient can be easily found and compared with present results for identifying any trend of chronic cases.
  3. Consistent reports: Once the pathologist reviews the smear, they will note down their observations in their own way. The record of these observations depends on the pathologist, each pathologist has their own way of reporting the smear review. This will lead to inconsistent reports between the pathologists. Shonit will ensure a consistent format of the report
  4. Reduced Eye strain and fatigue to pathologist: A manual review of a smear/cartridge under microscope requires a pathologist to view a sample for 3-5 mins with forward bent neck position. This is an ergonomically imbalanced position and will lead to heavy exertion in pathologists and a constantly looking for minor variations in cell structure through microscope leads to eye strain. As The AI100 does most of the work, the pathologist will feel less eye strain and less fatigue.

Benefits of AI100:

How does it reduce cost, efforts and increase revenue?

Reduction in TAT : Turn around time of CBC test with a flag will be any time between 2 hours to 72 Hours depending on the availability of the pathologist in the lab along with the sample. As the AI100 enables pathologists to review and approve reports from anywhere in the world, the TAT of PBS test with AI100 is only 15-25 Mins (based on the internet speed).

Increase in Throughput: Without the AI100, the constraining /least efficient task in the process of PBS testing is the manual review of the smear or slide, which on an average takes around 5 minutes.

With AI100, as the pathologist can review the slide in under 1 minute because of the pre-classification of cells provided by AI100, the constraining/least efficient task in the process will be scanning of the slide by AI100. AI100 takes about 3 mins to finish this task.

Thus the throughput of the PBS testing can be increased by 66%.

Efficient use of Pathologist: With AI100 doing the majority of the work by pre-classifying the cells, the utilization time of pathologist can be reduced by upto 80%. This time of pathologist can be utilized on more critical cases or the lab can increase the number of Peripheral Smear tests and Urine microscopy tests by upto 4 times. 

Reduction in Outsourcing cost: In case if the lab is outsourcing the PS test to a 3rd party lab. The cost per test can be reduced by up to 54% by using AI100 and outsourcing just the pathology services rather than the whole test.

Reduction in Capital investment: While setting up a new lab or peripheral lab, the capital investment can be reduced by up to 50% if a 3-part hematology analyser +AI100 combo is used instead of a costly 5-part/7-part hematology analyser.

The capital cost can be increased upto 58% if an offsite part time pathologist is hired instead of a full time pathologist.