Back close

Interpretable Decision Support Model for Breast Cancer Diagnosis

Thematic Area: Breast Cancer

Project Id: Breast Histopatholohy

Principal Investigator: Sruthi Krishna

Indian Collaborators: Dr. Seethalakshmi, Dr. Jyotsna Yesodharan, Pathology Department, AIMS Hospital

Interpretable Decision Support Model for Breast Cancer Diagnosis

Microscopic examination of biopsy tissue slides is perceived as the gold-standard methodology for the confirmation of presence of cancer cells. Manual analysis of an overwhelming inflow of tissue slides is highly susceptible to misreading of tissue slides by pathologists. A computerized framework for histopathology image analysis is conceived as a diagnostic tool that greatly benefits pathologists, augmenting definitive diagnosis of cancer. Convolutional Neural Network (CNN) turned out to be the most adaptable and effective technique in the detection of abnormal pathologic histology. Despite their high sensitivity and predictive power, clinical translation is constrained by a lack of intelligible insights into the prediction. we introduce a novel interpretable decision-support model using CNN with a trainable attention mechanism using response-based feed-forward visual explanation. A computer-aided system that can offer a definitive diagnosis and interpretability is therefore highly desirable. Conventional visual explanatory techniques, Class Activation Mapping (CAM), combined with CNN models offers interpretable decision making. The major challenge in CAM is, it cannot be optimized to create the best visualization map. CAM also decreases the performance of the CNN models.

To address this challenge, we introduce a novel interpretable decision-support model using CNN with a trainable attention mechanism using response-based feed-forward visual explanation. We introduce a variant of DarkNet19 CNN model for the classification of histopathology images. In order to achieve visual interpretation as well as boost the performance of the DarkNet19 model, an attention branch is integrated with DarkNet19 network forming Attention Branch Network (ABN). The attention branch uses a convolution layer of DarkNet19 and Global Average Pooling (GAP) to model the context of the visual features and generate a heatmap to identify the region of interest. Finally, the perception branch is constituted using a fully connected layer to classify images.

We trained and validated our model using more than 7000 breast cancer biopsy slide images from an openly available dataset and achieved 98.7% accuracy in the binary classification of histopathology images. The observations substantiated the enhanced clinical interpretability of the DarkNet19 CNN model, supervened by the attention branch, besides delivering a 3%–4% performance boost of the baseline model. The cancer regions highlighted by the proposed model correlate well with the findings of an expert pathologist.

The coalesced approach of unifying attention branch with the CNN model capacitates pathologists with augmented diagnostic interpretability of histological images with no detriment to state-of-art performance. The model’s proficiency in pinpointing the region of interest is an added bonus that can lead to accurate clinical translation of deep learning models that underscore clinical decision support.

Publication Details

  • Sruthi Krishna, Suganthi S S, Arnav Bhavsar, Jyotsna Yasodharan, Shivsubramani Krishnamoorthy,”Interpretable Decision Support Model for Breast Cancer Diagnosis Using Histopathology Images”, Journal of Pathology Informatics, Volume 14, 2023, 100319.
  • Alice Divya Nelson, Sruthi Krishna, “An effective approach for the nuclei segmentation from breast histopathological images using star convex polygon”, International Conference on Machine Learning and Data Engineering, 2022
  • Chinnapapakkagari Sreenivasa Vikranth, Bodavula Jagadeesh, Kanna Rakesh, Doriginti Mohammad, Sruthi Krishna,Remya,” Computer Assisted Diagnosis of Breast Cancer Using Histopathology Images and Convolutional Neural Networks”, AISP 2022

Proposed Future Work Details

  • Developing a scalable system for preliminary breast cancer classification

Related Projects

Development of High Volume Flyash Foam Concrete Wall Panel Using Rice Straw as Thermal Insulation Material
Development of High Volume Flyash Foam Concrete Wall Panel Using Rice Straw as Thermal Insulation Material
Synthesis, characterization and liquid Crystalline Studies of Azo and Schiff Base Containing Porphyrin Complex
Synthesis, characterization and liquid Crystalline Studies of Azo and Schiff Base Containing Porphyrin Complex
Development of Light Weight Bullet Proof Material
Development of Light Weight Bullet Proof Material
Sustainability Initiative (Amrita and Deakin University, Australia)
Sustainability Initiative (Amrita and Deakin University, Australia)
Amrita Insulin Pump and Low-cost, Automated Biomedical Devices
Amrita Insulin Pump and Low-cost, Automated Biomedical Devices
Admissions Apply Now