Histopathological characterization of colorectal polyps allows to tailor patients' management and follow up with the ultimate aim of avoiding or promptly detecting an invasive carcinoma. Colorectal polyps characterization relies on the histological analysis of tissue samples to determine the polyps malignancy and dysplasia grade. Deep neural networks achieve outstanding accuracy in medical patterns recognition, however they require large sets of annotated training images.


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(torch.utils.data.Dataset):

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

self.path = path

self.df = df

self.T = T

self.target = 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[self.target]


This dataset is in support of my 4 Research papers, initially submitted to different journals

  1. 2
  2. 3
  3. 4
  4. 5
  5. 6

Related Reseach Papers :

  1. Novel ß-Bio Model (Mathematics Foundation)
  2. ß-Model of  (Preprint:      )
  3.           and Humans Body - Part I (Preprint:      )
  4.           and Humans Body - Part II (Preprint:      )

Read Me

(1) This is an open access ,so everything  can be downloaded after login (free signup). You have to click on 'Title'.

(2) Data which was  earlier uploaded in 2021 under this same DOI  'Electro-Magnetic Radiations and Human Body' is explained in ' Experimental Physical Recording’.  That data is as it is. Neither earlier  data is removed nor it is modified, it is as it was earlier submitted. No additions are even done.

(3)  The main paper which has my scientific analysis on 'Electro-Magnetic Radiations and Human Body'  is ‘ and Humans Body’. This paper is used as the foundation because of the accepted facts by WHO, ICNIRP, IARC, NIH,medical doctors, and biomedical engineers. In this paper, I have claimed and proved something.

(4) Zip do not contain any simulation project folder.

(5) Extra Libraries created, modified , other scripts , not shared, as very elementary for any graduate,degree holder, so only results given in research paper.

(6) For  details like model block diagram, parameters, analysis, interpretation, mathematical formulae used to obtain these results etc. please refer "Research Paper".

(7) Radiation patterns - If you expecting the patterns are something easy to understand or decode, but they cannot easily interpreted. For this, pls. refer either textbook or research paper.

(8) The mobile tower installation/distance parameters are also taken according to 'Ministry of Communications, Department of Telecommunications,GoI.

(9) All operating frequency ranges are not mentioned for each 2G,3G,4G,5G,6G. For complete operating frequencies, pls refer your country or search on net. For other details, pls see Research paper.

(10)  This work has undergone complete revisions, loss of data many times,  and many computer crashes. 

(11) This is the last version in those datasets. Only update will be related to ß-Bio models which I

(12)  All work is simple , on basic and elementary concepts, can be easily copied, remade and understood.

(13) The dataset has been checked by the 'Data or Code or model Inspector' before uploading.

(14)  If any problem in creating or copying, pls contact your university professor or board or any of the companies engineer.

(15) As such, No other question or email will be replied. I may have left completely R&D or other reason.


Dataset Files

All the following 25 folders are zipped.

1)  2G

  • 2G_800 is CDMA 800MHz or 0.8 GHz
  • 2G_900 is GSM 900MHZ or 0.9 GHz
  • 2G_1800 is GSM1800MHz or 1.8 GHz

2) 3G 

  • 3G_1900 is 1900  MHz or 1.9 GHz
  • 3G_2100 is 2100 MHz or 2.1 GHz

3)  4G

  • 4G_2300 is 2300 MHz or 2.3 GHz
  • 4G_2400 is 2400 MHz or 2.4 GHz
  • 4G_2600  is 2600 MHz or 2.6 GHz

4) Low/Mid 5G FR1

  • 5G_3300 is 3300 MHz or 3.3 GHz
  • 5G_3500 is 3500 MHz or 3.5 GHz
  • 5G_5200  is 5200 MHz or 5.2 GHz
  • 5G_5900  is 5900 MHz or 5.9 GHz
  • 5G_6000 is 6000 MHz or 6 GHz
  • 5G_6200  is 6200 MHz or 6.2 GHz

Here 5G_3500 is n78 C-Band but 5G_6000, 5G_6200 are TDD, n96, n102  UNII defined by  US FCC. For details, pls refer Research paper.

5) High 5G  FR2

  • 5G_26000  is 26000 MHz or 26 GHz
  • 5G_28000  is 28000 MHz or 28 GHz
  • 5G_39000  is 39000 MHz or 39 GHz
  • 5G_41000  is 41000 MHz or 41 GHz
  • 5G_47000 is 47000 MHz or 47 GHz

6) 6G

  • 6G_90000  is 90,000 MHz or 90 GHz
  • 6G_150000 is 150 GHz
  • 6G_220000 is 220 GHz
  • 6G_500000 is 500 GHz
  • 6G_750000 is  750 GHz
  • 6G_1100000 is 1100 GHz, that is, 1.1 Terahertz (THz)

8) Each of the above zip has following datasets. The plots, images can be seen in IEEE CodeOcean DOI.

9) 3G has addition dataset

10) Following datasets are based on ß-Bio


 Experimental Physical Recording

The folder 'PhysicalRecording_2021.zip ' has recordings of Magnetic fields in the year 2021 measured using  Magnetic Sensor,  mobile app(software) and mobile phone

  •  Recordings.zip     
  •  14.mp4     
  •  327uT at 0:19/00:20   .   At 0:19/0:20 of the recording, 327 uT reading
  •  11uT at 0:04/0:05     .  At 0:04/0:05 of the recording, 11 uT reading
  •  5gproof.zip has screenshots from wifi detection   
  •  479uT at 0:42/0:44  .  At  0:42/0:44  of the recording, 479 uT reading

 Area: Delhi,NCR,India 

  • Physical Magnetic Sensor(hardware)

                  Resolution of the sensor is 0.0976 uT    &   Maximum Range of the sensor : 3000.0044 uT

  • Physical orientation and angular velocity  Sensor  (hardware)

                Resolution of the sensor is 0.0012216975 rad/s  &   Maximum Range of the sensor : 34.90549 rad/s

  •  Physical Proximity Sensor (hardware)

                    Resolution of the sensor : 1.0 cm    &   Maximum Range of the sensor : 5.0 cm

  •  Physical Gravity Sensor (hardware)

                    Resolution of the sensor :  0.01 m/s2  & Maximum Range of the sensor :156.98999 m/s2

Experimental Result   -   Lowest Recorded Reading : 11 uT

Highest Recorded Reading : 479 uT

Around 300 uT was measured anywhere, if nearby has 5G equipment ( fluctuates to 50 uT then 111, then 200 , 286,  ...) .   More details in paper.

Reading of 479 was measured, as few people were feeling unwell and when I checked, it was 420 uT, stationary and fluctuating to it around but that is not recorded.   So after some time, this was recorded.

 But later, this reading went to below 200 uT ? And even from 30 uT to 150 uT ,  how come

Experimental Result   - 24 April 2022, See Corona cases, rising, reading which was 29uT to 150uT is 243.95 uT



For scripts of IEEE Codeocean (Rstudio & Matlab). To see colored plots and images, pls. read details given in ReadMe.txt.

  • Capsule : Plots of EM Fields in 2G              , DOI :
  • Capsule : Plots of EM Fields in 3G            , DOI :
  • Capsule : Plots of EM Fields in 4G             , DOI :
  • Capsule : Plots of EM Fields in 5G             , DOI :
  • Capsule : Plots of EM Fields in 6G             , DOI :

Paper Citing : If want to cite this in paper etc. ,please refer DoI and/or this url.

Funding: There are no funders for this submission. The  author has himself fully self-financed (for his passion).I expect all these papers, would be nice Shroud for the passion and the price paid.

Acknowledgement : The author has generated this on Linux and had even used IEEE partner- Code Ocean - Python,C, Matlab ,Cloud Workstation, Jupyter Notebook,Rstudio,stata,julia,Tensorflow, pandas,trial (evaluation) of many proprietary softwares. No paid research, personal R&D work with no support, wastage of time in self teaching.Few gave trial (evaluation) sw with 2-5 months with even willing for 3-6 months further extension but didnt accepted hire contract request (the names cannot be disclosed & word of acknowledging expired in duration). No industry or academic will use their time only doing this work, even if given free unless financed or top MNC.  The author does not have any special name to be acknowledged.


This dataset is in support of my research paper 'ElectroMagnetic Fields in Wireless Charging of Electric Vehicles '.

Preprint :

This is useful for industries, manufacturers,doctors,environmentalists, who are curious to see and know.


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 (cap_sensor_data.zip) 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.