The Deep Learning Based Medical Image Severity Forecasting System provides a comprehensive approach to predicting the severity of medical conditions through image analysis. This report details the layered architecture of the system, including the Presentation Layer for user interaction, the Application Layer for workflow management, and the Deep Learning and Explainability Layer that powers the prediction engine. It also discusses the integration of Grad-CAM heatmaps for visual explanations of predictions, enhancing understanding for healthcare professionals. This report is essential for researchers and developers in the field of medical imaging and AI, aiming to improve diagnostic accuracy and patient outcomes.

Key Points

  • Explains the layered architecture of the medical image forecasting system
  • Describes the integration of Grad-CAM for visualizing prediction results
  • Details the workflow management in the Application Layer
  • Covers the prediction engine's functionality in the Deep Learning Layer
Dileesha A
Author:Akila Victor
66 pages
Language:English
Type:Report
Biology
Dileesha A
Author:Akila Victor
66 pages
Language:English
Type:Report
Biology
213
/ 66
DEEP LEARNING BASED MEDICAL IMAGE SEVERITY FORECASTING SYSTEM
FInal REPORT BOTH NAMES
Akila Victor
Document Details
Submission ID
trn:oid:::3618:136882186
Submission Date
Apr 28, 2026, 12:25 PM GMT+5:30
Download Date
Apr 28, 2026, 12:33 PM GMT+5:30
File Name
FInal REPORT BOTH NAMES.pdf
File Size
5.3 MB
64 Pages
14,056 Words
82,926 Characters
Page 1 of 66 - Cover Page Submission ID trn:oid:::3618:136882186
Page 1 of 66 - Cover Page Submission ID trn:oid:::3618:136882186
57% detected as AI
The percentage indicates the combined amount of likely AI-generated text as
well as likely AI-generated text that was also likely AI-paraphrased.
Caution: Review required.
It is essential to understand the limitations of AI detection before making decisions
about a student’s work. We encourage you to learn more about Turnitin’s AI detection
capabilities before using the tool.
Detection Groups
85 AI-generated only 57%
Likely AI-generated text from a large-language model.
0 AI-generated text that was AI-paraphrased 0%
Likely AI-generated text that was likely revised using an AI-paraphrase tool
or word spinner.
Disclaimer
Our AI writing assessment is designed to help educators identify text that might be prepared by a generative AI tool. Our AI writing assessment may not always be accurate (i.e., our AI models
may produce either false positive results or false negative results), so it should not be used as the sole basis for adverse actions against a student. It takes further scrutiny and human
judgment in conjunction with an organization's application of its specific academic policies to determine whether any academic misconduct has occurred.
Frequently Asked Questions
How should I interpret Turnitin's AI writing percentage and false positives?
The percentage shown in the AI writing report is the amount of qualifying text within the submission that Turnitin’s AI writing
detection model determines was either likely AI-generated text from a large-language model or likely AI-generated text that was
likely revised using an AI paraphrase tool or word spinner.
False positives (incorrectly flagging human-written text as AI-generated) are a possibility in AI models.
AI detection scores under 20%, which we do not surface in new reports, have a higher likelihood of false positives. To reduce the
likelihood of misinterpretation, no score or highlights are attributed and are indicated with an asterisk in the report (*%).
The AI writing percentage should not be the sole basis to determine whether misconduct has occurred. The reviewer/instructor
should use the percentage as a means to start a formative conversation with their student and/or use it to examine the submitted
assignment in accordance with their school's policies.
What does 'qualifying text' mean?
Our model only processes qualifying text in the form of long-form writing. Long-form writing means individual sentences contained in paragraphs that make up a
longer piece of written work, such as an essay, a dissertation, or an article, etc. Qualifying text that has been determined to be likely AI-generated will be
highlighted in cyan in the submission, and likely AI-generated and then likely AI-paraphrased will be highlighted purple.
Non-qualifying text, such as bullet points, annotated bibliographies, etc., will not be processed and can create disparity between the submission highlights and the
percentage shown.
Page 2 of 66 - AI Writing Overview Submission ID trn:oid:::3618:136882186
Page 2 of 66 - AI Writing Overview Submission ID trn:oid:::3618:136882186
BCSE498J Project-II
DEEP LEARNING BASED MEDICAL IMAGE SEVERITY
FORECASTING SYSTEM
Submitted in partial fulfillment of the requirements for the degree of
Bachelor of Technology
in
Computer Science and Engineering
(Information Security)
by
22BCI0131 AVALAMANDA DILEESHA
22BCI0134 GOVERDHAN GAYATRI LAXMIKANT
Under the Supervision of
Dr. Akila Victor
Associate Professor Sr.
School of Computer Science and Engineering (SCOPE)
April 2026
Page 3 of 66 - AI Writing Submission Submission ID trn:oid:::3618:136882186
Page 3 of 66 - AI Writing Submission Submission ID trn:oid:::3618:136882186
/ 66
End of Document
213

You May Also Like

FAQs

What is the purpose of the Deep Learning Based Medical Image Severity Forecasting System?
The purpose of the Deep Learning Based Medical Image Severity Forecasting System is to enhance the diagnostic process by predicting the severity of medical conditions based on image analysis. The system utilizes advanced deep learning techniques to analyze medical images, providing healthcare professionals with insights into the potential severity of ailments. This predictive capability aims to improve patient outcomes by facilitating timely and accurate diagnoses.
How does the Presentation Layer function in this system?
The Presentation Layer serves as the user interface of the Deep Learning Based Medical Image Severity Forecasting System. It allows users to upload medical images, select the type of ailment, and view the predicted outcomes. This layer includes features such as a Grad-CAM heatmap overlay, which visually represents the areas of the image that contribute most to the prediction, along with a numerical severity score to quantify the prediction.
What role does the Application Layer play in the system?
The Application Layer manages the overall workflow of the Deep Learning Based Medical Image Severity Forecasting System. It handles tasks such as image uploads, file storage, and request routing, ensuring smooth communication between the user interface and the prediction modules. The Controller within this layer is responsible for loading the appropriate trained model based on user selections, facilitating efficient processing of requests.
What is Grad-CAM and how is it used in this system?
Grad-CAM, or Gradient-weighted Class Activation Mapping, is a technique used to visualize the regions of an image that are most influential in the model's prediction. In the Deep Learning Based Medical Image Severity Forecasting System, Grad-CAM overlays are utilized to provide healthcare professionals with visual explanations of the model's predictions. This enhances interpretability and trust in the AI system, allowing users to understand which parts of the image contributed to the severity assessment.
What are the key components of the Deep Learning and Explainability Layer?
The Deep Learning and Explainability Layer is crucial for the intelligence of the forecasting system. It includes the Prediction Engine, which processes the uploaded medical images and generates severity predictions based on the trained deep learning models. This layer also incorporates explainability features, such as Grad-CAM, to help users understand the rationale behind the predictions, thereby improving the overall user experience and confidence in the system.
How does the system improve diagnostic accuracy in medical imaging?
The Deep Learning Based Medical Image Severity Forecasting System improves diagnostic accuracy by leveraging advanced deep learning algorithms to analyze medical images. By providing predictions on the severity of conditions, the system aids healthcare professionals in making informed decisions quickly. The integration of visual explanation tools like Grad-CAM further enhances understanding, allowing clinicians to validate the AI's assessments against their clinical expertise.
What is the significance of the numerical severity score provided by the system?
The numerical severity score generated by the Deep Learning Based Medical Image Severity Forecasting System quantifies the predicted severity of a medical condition based on the analysis of the uploaded image. This score is significant as it provides a clear, objective measure that can assist healthcare professionals in prioritizing patient care and determining appropriate treatment plans. By translating complex image data into a numerical format, the system enhances the decision-making process in clinical settings.

Related