Restricted mean survival time (RMST), recommended for reporting survival, lacks a tool to analyze multilevel factors. Gini's mean difference of RMSTs, Δ, is proposed and applied to compare a lymph node ratio-based classification (LNRc) versus a number-based classification (ypN) in stage II/III breast cancer patients prospectively enrolled to neoadjuvant chemotherapy who underwent axillary dissection. Number of positive nodes (npos) classified patients into ypN0, npos=0, ypN1, npos=[1,3], ypN2, npos=[4,9], and ypN3, npos≥10.


Breast cancer Neoadjuvant chemotherapy

1 header row.

370 data rows

columns = characteristics, refer to papers for detailed description





In order to load the data, we provide below an example routine working within PyTorch frameworks. We provide two different resolutions, 800 and 7000 um/px.

Within each resolution, we provide .csv files, containing all metadata information for all the included files, comprising:

  • image_id;
  • label (6 classes - HP, NORM, TA.HG, TA.LG, TVA.HG, TVA.LG);
  • type (4 classes - HP, NORM, HG, LG);
  • reference WSI;
  • reference region of interest in WSI (roi);
  • resolution (micron per pixels, mpp);
  • coordinates for the patch (x, y, w, h).

Below you can find the dataloader class of UNITOPatho for PyTorch. More examples can be found here.

import torch

import torchvision

import numpy as np

import cv2

import os


class UNITOPatho(

def __init__(self, df, T, path, target, subsample=-1, gray=False, mock=False):

self.path = path

self.df = df

self.T = T = target

self.subsample = subsample

self.mock = mock

self.gray = gray

allowed_target = ['type', 'grade', 'top_label']

if target not in allowed_target:

print(f'Target must be in {allowed_target}, got {target}')


print(f'Loaded {len(self.df)} images')

def __len__(self):

return len(self.df)

def __getitem__(self, index):

entry = self.df.iloc[index]

image_id = entry.image_id

image_id = os.path.join(self.path, entry.top_label_name, image_id)

img = None

if self.mock:

C = 1 if self.gray else 3

img = np.random.randint(0, 255, (224, 224, C)).astype(np.uint8)


img = cv2.imread(image_id)

if self.subsample != -1:

w = img.shape[0]

while w//2 > self.subsample:

img = cv2.resize(img, (w//2, w//2))

w = w//2

img = cv2.resize(img, (self.subsample, self.subsample))

if self.gray:

img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

img = np.expand_dims(img, axis=2)


img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

if self.T is not None:

img = self.T(img)

return img, entry[]


Microscopic image based analysis plays an important role in histopathological computer based diagnostics. Identification of childhood medulloblastoma and its proper subtype from biopsy tissue specimen of childhood tumor is an integral part for prognosis.The dataset is of Childhood medulloblastoma (CMB) biopsy samples. The images are of 10x and 100x microscopic magnifications, uploaded in separate folders. The images consist of normal brain tissue cell samples and CMB cell samples of different WHO defined subtypes. An excel sheet is also uploaded for ease of data description.


The dataset contains two folder of diffrent magnification images, i.e; 10x and 100x. The type of each image is described in the provided excel file. Each slide has a unique number and the number in bracket denotes that the corresponding image is of the single slide. 


Supplementary materials (Table S2).


Proteome analysis of extracellular vesicles, isolated from murine breast cancer cells or serum of healthy mice.


The migration of cancer cells is highly regulated by the biomechanical properties of their local microenvironment. Using 3D scaffolds of simple composition, several aspects of cancer cell mechanosensing (signal transduction, EMC remodeling, traction forces) have been separately analyzed in the context of cell migration. However, a combined study of these factors in 3D scaffolds that more closely resemble the complex microenvironment of the cancer ECM is still missing.


The datasets is made of a number of zip files. The name of the file identifies the figure (and figure panel) that the data refers to.


Hyperspectral (HS) imaging presents itself as a non-contact, non-ionizing and non-invasive technique, proven to be suitable for medical diagnosis. However, the volume of information contained in these images makes difficult providing the surgeon with information about the boundaries in real-time. To that end, High-Performance-Computing (HPC) platforms become necessary. This paper presents a comparison between the performances provided by five different HPC platforms while processing a spatial-spectral approach to classify HS images, assessing their main benefits and drawbacks.


Dataset description


1) Size of the images


- PD1C1: 1000 samples x 1000 lines x 100 bands

- PD1C2: 1000 samples x 1000 lines x 100 bands

- PD1C3: 1000 samples x 1000 lines x 100 bands


2) Image composition


- The information is stored band by band

- Within each band, the information is stored line by line

- The data type is float


3) Important information


This database only contains the dermatological images. The three brain images, obtained within the context of HELICoiD EU project, are already available in the following repository:


For downloading the brain images used in this research:

- PB1C1: Op12C1

- PB2C1: Op15C1

- PB3C1: Op20C1


Monitoring cell viability and proliferation in real-time provides a more comprehensive picture of the changes cells undergo during their lifecycle than can be achieved using traditional end-point assays. Our lab has developed a CMOS biosensor that monitors cell viability through high-resolution capacitance measurements of cell adhesion quality. The system consists of a 3 × 3 mm2 chip with an array of 16 sensors, on-chip digitization, and serial data output that can be interfaced with inexpensive off-the-shelf components.


The dataset file ( contains capacitance measurements and images. CSV data is provided in the "capData_csv" folder. Images are provided in the "images" folder. The data in MATLAB format is found in "capData.mat". The MATLAB script file, "script_plot_data.m", contains code to parse and plot the data. It can be used as an example to perform data analysis. The spatial locations of the 16 channels can be found in "channel_numbers.jpg".

Please see the attached documentation file for more details.



Malignant pleural effusions (MPEs) are a challenging public health problem, causing significant morbidity and often being the first presenting sign of cancer. Pleural fluid cytology is the most common method used to differentiate malignant from non-malignant effusions. However, its sensitivity reaches 50-70% and depends on the experience of the cytologist, the tumor load, and the amount of fluid tested. Therefore, diagnostic inaccuracy and a high incidence of false negatives may endanger patients with clinical mistreatment and mismanagement.


In this paper, the effects of input power of microwave antenna (MWAN) on liver cancerous tissue at injection of Magnetic Nanoparticles (MNPs) are investigated. At first for base simulation, we validate our results by a comparison with other literature reports. After that, we used a 1.8-cm hepatocellular carcinoma (HCC) tumor that was treated in experiment during a 3-min ablation by using MWAN operating on 2.45 GHz frequency with 90 W power. In the next step of the simulation, the obtained results were compared with experimental results.