Evidence Driven Differential Diagnosis of Malignant Melanoma

Center for Visual Information Technology, IIIT Hyderabad
Medical Image Computing and Computer-Assisted Intervention (MICCAI) - ISIC 2023

Abstract

We present a modular and multi-level framework for the differential diagnosis of malignant melanoma. Our framework integrates contextual information and evidence at the lesion, patient, and population levels, enabling decision-making at each level. We introduce an anatomic-site aware masked transformer, which effectively models the patient context by considering all lesions in a patient, which can be variable in count, and their site of incidence. Additionally, we incorporate patient metadata via learnable demographics embeddings to capture population statistics.

Through extensive experiments, we explore the influence of specific information on the decision-making process and examine the tradeoff in metrics when considering different types of information. Validation results using the publicly available SIIM-ISIC 2020 dataset indicate including the lesion context with location and metadata improves specificity by 17.15% and 7.14%, respectively, while enhancing balanced accuracy.

MelDD Network Architecture

MelDD Network Architecture

Qualitative Results

Examples of malignant melanoma prediction changes with additional context and evidence information

Note: Green and red boxes indicate correct and incorrect predictions, respectively.

  • Patient A: Multiple atypical lesions reduce suspicion of malignancy in an additional atypical lesion, while a morphologically typical lesion distinct in the nevus landscape is considered suspicious.
  • Patient B: Demonstrates how including anatomical location accurately detects an "ugly duckling" suspicious lesion by comparing it to other lesions in the same location to predict malignancy effectively.
  • Patients C and D: Underscore how incorporating location information prevents misclassification of benign lesions as malignant by considering the specific anatomical characteristics that differentiate suspicious lesions in different locations.
  • Patients E and F: Emphasize the importance of patient demographics to help the model correlate lesion characteristics with susceptibility to risk factors, avoiding misdiagnosis of benign lesions as malignant based on a better understanding of patient-specific factors.
Qualitative Prediction Changes

Research Poster

A visual summary of our research findings and methodology presented at RnD Showcase at IIIT Hyderabad

Research Poster