BIONS AI
For Radiology
Diabetic Retinoapthy Analysis Skin Cancer Classification

Our Solutions

AI Analysis Tools for Radiology

Skin cancer (Melanoma Classification)

Skin cancer is the most prevalent type of cancer. Melanoma, specifically, is responsible for 75{69d241dc4d0737a402e70445a02ac74c5e80ae0445e19d8667636fb3de0bfd70} of skin cancer deaths, despite being the least common skin cancer. Here we find the probability (floating point) between 0.0 and 1.0 that the lesion in the image is malignant (the target). The values 0 denotes benign, and 1 indicates malignant.

Cervical Cancer Screening

Cervical cancer is so easy to prevent if caught in its precancerous stage. Here we classify cervix types based on cervical images. These different types of the cervix in our data set are all considered normal (not cancerous), but since the transformation zones aren’t always visible, some of the patients require further testing while some don’t. This decision is very important for the healthcare provider and critical for the patient.

Prostate Cancer (PCa)

Prostate Cancer is the second most common cancer among males worldwide that results in more than 350,000 deaths annually Here we classify the severity of prostate cancer from microscopy scans of prostate biopsy samples.

Lymphoma (Histopathologic Cancer Detection)

Here we Identify metastatic tissue in histopathologic scans of lymph node sections.

Personalized Medicine- Redefining Cancer Treatment

Once sequenced, a cancer tumor can have thousands of genetic mutations. But the challenge is distinguishing the mutations that contribute to tumor growth (drivers) from the neutral mutations (passengers). Currently, this interpretation of genetic mutations is being done manually. This is a very time-consuming task where a clinical pathologist has to manually review and classify every single genetic mutation based on evidence from text-based clinical literature. Here we classify genetic mutations from text-based on clinical evidence

 

Diabetic retinopathy

Diabetic retinopathy is the leading cause of blindness in the working-age population of the developed world. It is estimated to affect over 93 million people. Here we rate the retina image taken using fundus photography under a variety of imaging conditions for the severity of diabetic retinopathy on a scale of 0 to 4. 0 – No DR, 1 – Mild, 2 – Moderate, 3 – Severe, and 4 – Proliferative DR.

Intracranial Hemorrhage Detection

Intracranial hemorrhage, bleeding that occurs inside the cranium, is a serious health problem requiring rapid and often intensive medical treatment. For example, intracranial hemorrhages account for approximately 10{69d241dc4d0737a402e70445a02ac74c5e80ae0445e19d8667636fb3de0bfd70} of strokes in the U.S., where stroke is the fifth-leading cause of death. Identifying the location and type of any hemorrhage present is a critical step in treating the patient. Here we analyze whether a hemorrhage exists in a given CT scan and what type it is.

Detect seizures in intracranial EEG recordings

Here we predict that the clip is within the first 15 seconds of its respective seizure (the technical term for a time into the seizure is “latency”). These early clips are double counted because early detection is critical to successful intervention with a responsive neurostimulation device.

Diagnose Mental Illness Schizophrenia

Schizophrenia is a severe and disabling mental illness which has no well-established, non-invasive diagnosis biomarker. Currently, due to its symptoms overlapping with other mental illnesses (like bipolar disorder), it can only be diagnosed subjectively, by process of elimination. Here we use FNC information (obtained from functional magnetic resonance imaging (fMRI) from a set of schizophrenic patients and healthy controls at rest) to predict 0 = ‘Healthy Control’, 1 = ‘Schizophrenic Patient’

Brain Neuroimaging

Here we predict the age and assessment values from two domains using features derived from brain MRI images as inputs(brain function, structure, and neuron connectivity).

Improve pain management

Accurately identifying nerve structures in ultrasound images of the neck and effectively inserting a patient’s pain management catheter contributes to a more pain-free surgical procedure. So Here we predict the mask of a nerve called Brachial Plexus(BP) in ultrasound images of the neck.

Pneumonia Detection

Here we locate lung opacities on chest x rays.

Pulmonary Embolism Detection in chest CT scans

Identifying Pneumothorax disease in chest x rays.

Detecting Severity of Pulmonary Fibrosis or decline in lung function based on a CT scan of their lungs.

Detect the presence and position of catheters and lines on chest x-rays to save the life

 

Mechanisms of Action (MoA) Prediction

Classify drugs based on their biological activity.

Predict HIV Progression

Predict the likelihood that an HIV patient’s infection will become less severe.

 

Leaf Classification

Leaf Disease Classification

Flower Classification

Plant Seedlings Classification

Identify plant species from herbarium specimens

Wheat heads detection using image analysis

Identify the category of foliar diseases in apple trees

 

Identify wild animals species from their images

Determine the breed of a dog in an image

Bird Species Classification

Identifying a whale by the image of its tail

 

COVID-19 Detection with Lung x-ray, CT scan & historical exams

Pet (Doggy) adoption prediction

About Us

Making a real impact on the radiologists day to day productivity

The BIONS helps radiologists sift through the heaps of data to find what’s truly important, to streamline the workflow.


BIONS uses medical imaging techniques such as

  1. Computed Tomography (CT)
  2. Ultrasound
  3. x-rays
  4. Magnetic Resonance Imaging (MRI)
  5. EEG recording
  6. Fundus photography

50
+

Engineers and Developers

100k
+

Radiologist Using BIONS

35m
+

On-premise Instances Deployed

15m
+

Support answers per month

Process

How does it Work?

fc_ic_1-4

Cloud Compute

Inference model in cloud


Read More

fc_ic_2-4

Block Storage

Storing patient information on cloud


Read More

fc_ic_3-4

Dedicated Cloud

On-premise dedicated cloud


Read More

© BIONS. All rights reserved.