Constantino Carlos Reyes-Aldasoro’s scientific contributions

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (1)


Fig. 1. Illustration of the main concepts of Persistence Homology: births, death, holes and components. (a) A sequence of six binary images (b) A black bar corresponds to the birth of a component and, a red cross and a grey bar indicates a death. (c) The birth and death of holes. (d) Representation of the components as a simplicial complex: A point corresponds to a component, except if there is a hole, in which case a cycle of 3 points and 3 edges are added. The cycle is filled with a triangle when the hole dies. (e) Step-by-step formation of the persistence diagram.
Fig. 3. Illustration of the datasets with 100 sample patches per class from each set. By class: NCT-CRC-HE-100K images are shown above, normalized CRC-VAL-HE-7K images are shown below. ADI: adipose tissue; BACK: background; CRC: colorectal cancer; DEB: debris; LYM: lymphocytes; MUC: mucus; MUS: smooth muscle; NORM: normal colon mucosa; STR: cancer-associated stroma; TUM: colorectal adenocarcinoma epithelium.
Fig. 5. Illustration of the persistence diagrams of the histological tissues from the 100K-set. One representative patch from each of the classes (ADI, BACK, DEB, LYM, MUC, MUS, NORM, STR, TUM) is converted to greyscale and inverted. Noise is removed on the greyscale image by applying a 5 × 5 median filter. A persistence diagram is calculated from the smoothed greyscale image where blue circles are components and red triangles are holes. The distribution of the scatterplots in the persistence diagram capture differences in the textures of different tissues. ADI: adipose tissue; BACK: background; CRC: colorectal cancer; DEB: debris; LYM: lymphocytes; MUC: mucus; MUS: smooth muscle; NORM: normal colon mucosa; STR: cancer-associated stroma; TUM: colorectal adenocarcinoma epithelium.
Fig. 6. Illustration of Gabor filters. (a) Gabor filters (b) Sample patches converted to greyscales (c) Filtered results.
Persistent Homology and Gabor Features Reveal Inconsistencies Between Widely Used Colorectal Cancer Training and Testing Datasets
  • Preprint
  • File available

April 2025

·

16 Reads

·

·

Ximena Fernandez

·

[...]

·

Constantino Carlos Reyes-Aldasoro

Recent work on computer vision and image processing has relied substantially on open datasets, which allow for an objective comparison of techniques and methodologies. In the area of computational pathology and, more specifically, on colorectal cancer, the dataset NCT-CRC-HE-100K, which consists of 100,000 patches of human tissue stained with Haematoxylin and Eosin has been widely used as a training set for deep learning studies. The patches are grouped into 9 classes of tissue (adipose, background, debris, lymphocytes, mucus, smooth muscle, normal colon mucosa, cancer-associated stroma, colorectal adenocarcinoma epithelium). The set is released with a separate set (CRC-VAL-HE-7K) of 7,180 patches that is commonly used for testing. In this work, features were extracted from both sets first with Persistent Homology, then, with Gabor filters to reveal that the training set presents a rather different distribution from the testing set. Namely, the distribution of features in the 7K-set presents a much higher class overlap than those in the 100K-set, which would imply a much higher separability in the testing set than in the training set.

Download