Machine Learning and How it Can Improve the Detection of Cancer


A research team from Marquette University recently proposed a new machine learning model that could improve cancer diagnosis by analyzing the diffuse reflectance spectroscopy (DRS) better.

Article Highlights

  • Limited access to healthcare resources in rural or poor communities hinders early cancer detection, emphasizing the need for cost-effective and efficient techniques.
  • Diffuse reflectance spectroscopy (DRS) offers a method for discriminating between normal and abnormal tissue based on spectral data, presenting an affordable option for cancer detection.
  • ML holds promise in analyzing DRS data, but faces challenges due to inaccuracies in simulated datasets. A recent study proposes a wavelength-independent regressor (WIR) model to enhance ML accuracy.
  • The WIR model shows promise in improving accuracy and speed compared to traditional methods like inverse Monte Carlo simulations.

Cancer diagnosis is an essential step in saving the lives of patients afflicted with this disease. Early detection of cancer dramatically decreases the mortality rate and increases the survival rate of cancer. However, the early detection of cancer is not always possible for people, especially those who live in rural or poor communities with limited access to healthcare resources (1). As a result, the development of cost-effective, accurate, and efficient techniques that are capable at detecting various types of cancer is critical to meeting the needs of underserved communities.

One spectroscopic technique that has made significant inroads in this field is diffuse reflectance spectroscopy (DRS). DRS is an analytical technique that allows for the discrimination of normal and abnormal tissue based on spectral data, which is helpful for clinicians in observing the presence of cancerous cells (2–5). The benefits of using DRS are that it is relatively inexpensive to perform this type of analysis (1).

Blue folder with Cancer diagnosis | Image Credit: © vchalup -

Blue folder with Cancer diagnosis | Image Credit: © vchalup -

However, DRS data still needs to be analyzed, and that is where scientists and clinicians encounter difficulties and inefficiencies. Although inverse Monte Carlo (MCl) simulations can accurately estimate the optical properties of tissue, they are computationally intensive (1). This is where machine learning (ML) could be effective. However, ML models generally require the use of simulated data sets in the data collection process, and the issue is that these data sets are inaccurate when attempting to model errors caused by instrumentation (user errors) (1).

In a recent study published in the SPIE Journal of Biomedical Optics, associate professor Bing Yu of Marquette University led a research team in exploring how to improve ML models for analyzing DRS data (6). Their study proposed a wavelength-independent regressor (WIR) model to predict the optical properties of the DRS data (6).

Developing and testing the model required using the MCl model to generate the simulated DRS spectra, where where μa= 0.44 to 2.45 cm−1, and μs = 6.53 to 9.58 cm−1 (6). The results were promising, revealing that the WIR model successfully improved accuracy and speed. The researchers reported that the errors for MCl were eight times higher approximately (6). This is because the WIR model used features that were more robust to the use-errors than the MCl model (6).

In summary, the presented WIR algorithm showcases an alternative method that improves upon existing algorithms. It is a reliable algorithm that produces accurate optical property predictions from the DRS data it was given (6). Future studies would be able to further validate the WIR algorithm, enforcing the point that it can (and should) be used for clinical studies moving forward.


  1. EurekAlert, Accurate and Inexpensive Approach for Optical Biopsy. (accessed 2024-02-26).
  2. Nogueira M. S.; Maryam, S.; Amissah, M.; et al. Evaluation of Wavelength Ranges and Tissue Depth Probed by Diffuse Reflectance Spectroscopy for Colorectal Cancer Detection. Sci. Rep. 2021, 11 (1), 798. DOI: 10.1038/s41598-020-79517-2
  3. Akter, S.; Hossain, Md. G.; Nishidate, I.; et al. Medical Applications of Reflectance Spectroscopy in the Diffusive and Sub-diffusive Regimes. J. Near Infrared Spectrosc. 2018, 26 (6), 337–350. DOI: 10.1177/0967033518806637
  4. Baltussen E. J. M.; Snaebjornsson, P.; Brouwer de Koning, S. G.; et al. Diffuse Reflectance Spectroscopy as a Tool for Real-time Tissue Assessment During Colorectal Cancer Surgery. J. Biomed. Opt. 2017, 22 (10), 106014. DOI: 10.1117/1.JBO.22.10.106014
  5. Keller, A.; Bialecki, P.; Wilhelm, T. J.; Vetter, M. K. Diffuse Reflectance Spectroscopy of Human Liver Tumor Specimens–Towards a Tissue Differentiating Optical Biopsy Needle Using Light Emitting Diodes. Biomed. Opt. Express 2018, 9 (3), 1069–1081. DOI: 10.1364/BOE.9.001069
  6. Scarbrough, A.; Chen, K.; Yu, B. J. Biomed. Optics 2024, 29 (1), 015001. DOI: 10.1117/1.JBO.29.1.015001