# Towards More Transparent and Accurate Cancer Diagnosis with an Unsupervised CAE Approach

arXiv: https://arxiv.org/abs/2305.11728 · HTML: https://mlsanity.com/paper/2305.11728/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 51 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Training Very Deep Networks](https://mlsanity.com/paper/1507.06228/) (2015)
- [Going Deeper through the Gleason Scoring Scale: An Automatic end-to-end System for Histology Prostate Grading and Cribriform Pattern Detection](https://mlsanity.com/paper/2105.10490/) (2021)
- [DenseNet: Implementing Efficient ConvNet Descriptor Pyramids](https://mlsanity.com/paper/1404.1869/) (2014)
- [Similar Image Search for Histopathology: SMILY](https://mlsanity.com/paper/1901.11112/) (2019)
- [Yottixel -- An Image Search Engine for Large Archives of Histopathology Whole Slide Images](https://mlsanity.com/paper/1911.08748/) (2019)
- [Pan-Cancer Diagnostic Consensus Through Searching Archival Histopathology Images Using Artificial Intelligence](https://mlsanity.com/paper/1911.08736/) (2019)
- [Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Network](https://mlsanity.com/paper/1811.04241/) (2018)
- [Classification and Retrieval of Digital Pathology Scans: A New Dataset](https://mlsanity.com/paper/1705.07522/) (2017)
- [Self-supervised learning of a tailored Convolutional Auto Encoder for histopathological prostate grading](https://mlsanity.com/paper/2303.11837/) (2023)
- [Ranking Loss and Sequestering Learning for Reducing Image Search Bias in Histopathology](https://mlsanity.com/paper/2304.08498/) (2023)
- [Classification of Breast Tumours Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods](https://mlsanity.com/paper/2209.01380/) (2022)

## Built on by (most cited first, 4 of 4)

- [Siamese Content-based Search Engine for a More Transparent Skin and Breast Cancer Diagnosis through Histological Imaging](https://mlsanity.com/paper/2401.08272/) (2024)
- [NMGrad: Advancing Histopathological Bladder Cancer Grading with Weakly Supervised Deep Learning](https://mlsanity.com/paper/2405.15275/) (2024)
- [THIR: Topological Histopathological Image Retrieval](https://mlsanity.com/paper/2511.13170/) (2025)
- [Predicting the risk of colorectal anastomotic leak based on preoperative mapping of the blood supply of the bowel](https://mlsanity.com/paper/2606.02156/) (2026)

## Abstract (arXiv)

Digital pathology has revolutionized cancer diagnosis by leveraging Content-Based Medical Image Retrieval (CBMIR) for analyzing histopathological Whole Slide Images (WSIs). CBMIR enables searching for similar content, enhancing diagnostic reliability and accuracy. In 2020, breast and prostate cancer constituted 11.7% and 14.1% of cases, respectively, as reported by the Global Cancer Observatory (GCO). The proposed Unsupervised CBMIR (UCBMIR) replicates the traditional cancer diagnosis workflow, offering a dependable method to support pathologists in WSI-based diagnostic conclusions. This approach alleviates pathologists' workload, potentially enhancing diagnostic efficiency. To address the challenge of the lack of labeled histopathological images in CBMIR, a customized unsupervised Convolutional Auto Encoder (CAE) was developed, extracting 200 features per image for the search engine component. UCBMIR was evaluated using widely-used numerical techniques in CBMIR, alongside visual evaluation and comparison with a classifier. The validation involved three distinct datasets, with an external evaluation demonstrating its effectiveness. UCBMIR outperformed previous studies, achieving a top 5 recall of 99% and 80% on BreaKHis and SICAPv2, respectively, using the first evaluation technique. Precision rates of 91% and 70% were achieved for BreaKHis and SICAPv2, respectively, using the second evaluation technique. Furthermore, UCBMIR demonstrated the capability to identify various patterns in patches, achieving an 81% accuracy in the top 5 when tested on an external image from Arvaniti.